Compare commits

..
34 Commits
Author SHA1 Message Date
Vitaliy Filippov 06f4e0fcce K/V control prints (for debug only) O:-) 2023-12-01 02:33:04 +03:00
Vitaliy Filippov f285cfc483 Fix eviction when random_pos selects the end 2023-12-01 01:43:03 +03:00
Vitaliy Filippov 12b50b421d Implement min/max list_count to make listings during performance test reasonable 2023-12-01 01:17:04 +03:00
Vitaliy Filippov 9f6d09428d Fix and improve parallel allocation
- Do not try to allocate more DB blocks in an inode block until it's "confirmed" and "locked" by the first write
- Do not recheck for new zero DB blocks on first write into an inode block - a CAS failure means someone else is already writing into it
- Throw new allocation blocks away regardless of whether the known_version is 0 on a CAS failure
2023-12-01 01:17:04 +03:00
Vitaliy Filippov 580025cfc9 Implement key_prefix for K/V stress test 2023-12-01 01:17:04 +03:00
Vitaliy Filippov 13e2d3ce7c More fixes
- do not overwrite a block with older version if known version is newer
  (read may start before update and end after update)
- invalidated block versions can't be remembered and trusted
- right boundary for split blocks is right_half when diving down, not key_lt
- restart update also when block is "invalidated", not just on version mismatch
- copy callback in listings to avoid closure destruction bugs too
2023-12-01 01:17:04 +03:00
Vitaliy Filippov c5b00f897a Add logging and one more assert 2023-12-01 01:17:04 +03:00
Vitaliy Filippov e847e26912 Make get_block() wait for updating when unrelated block is found along the path 2023-12-01 01:17:04 +03:00
Vitaliy Filippov 3393463466 Fix a race condition where changed blocks were parsed over existing cached blocks and getting a mix of data 2023-12-01 01:17:04 +03:00
Vitaliy Filippov bd96a6194a Simplify code by removing an unneeded "optimisation" 2023-12-01 01:17:04 +03:00
Vitaliy Filippov 601fe10c28 Add kv_log_level, print warnings on level 1, trace ops on level 10 2023-12-01 01:17:04 +03:00
Vitaliy Filippov 63dbc9ca85 Fix duplicate keys in listings on parallel updates -- do not rewind key "iterator position" 2023-12-01 01:17:04 +03:00
Vitaliy Filippov aa0c363c39 Implement key suffix to avoid collisions of multiple test workers 2023-12-01 01:17:04 +03:00
Vitaliy Filippov ce52c5589e Do not complain on empty first block 2023-12-01 01:17:04 +03:00
Vitaliy Filippov aee20ab1ee Add JSON output for stress-tester 2023-12-01 01:17:04 +03:00
Vitaliy Filippov bb81992fac Print total stats 2023-12-01 01:17:04 +03:00
Vitaliy Filippov a28f401aff Do not send more than op_count operations (fix segfault on finish) 2023-12-01 01:17:04 +03:00
Vitaliy Filippov 4ac7e096fd Add some more resiliency to serialize() 2023-12-01 01:17:04 +03:00
Vitaliy Filippov b6171a4599 Invalidate blocks being updated too 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 28045f230c Change new block allocation method: make each writer choose multiple empty PG blocks and place blocks in them 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 10e867880f Remove blocks from cache on unsuccessful updates 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 012462171a Allow to track multiple updates per block (it should never happen though) 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 904793cdab Do not call stop_updating after failed write_new_block and after clear_block (both delete the item) 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 45c01db2de Track versions of parent blocks and recheck if changed during update 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 8c9206cecd Fix resume_split condition (key_lt can also be "") 2023-12-01 01:17:03 +03:00
Vitaliy Filippov e8c46ededa Experiment: transform offsets for better sharding 2023-12-01 01:17:03 +03:00
Vitaliy Filippov e9b321a0e0 More post-stress-test fixes
- Prevent _split types of new blocks
- Stop updating new blocks only after the whole update, otherwise pointers
  may become invalid
- Use recheck_none for updates initially
- Use UINT64_MAX as initial block version when postponing ops, otherwise the
  check fails when the block is initially empty. This for example leads to
  writing both leaf items & block pointers (which is incorrect) into the root
  block when starting stress-test with --parallelism 32
- Fix -EINTR comparison
2023-12-01 01:17:03 +03:00
Vitaliy Filippov 09a77991ae Print operation statistics 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 29d8c9b6f3 K/V fixes after stress-test :-)
- track block versions correctly - per inode block (128kb) instead of tree block (4kb)
- prevent multiple parallel CAS writes of the same inode block
- add logging for EILSEQ which means invalid data in the tree
- fix get_block updated flag which was true for blocks already in cache and was leading to infinite loops on "unrelated block" errors
- apply changes to blocks in cache only after successful writes (using "virtual changes")
- do not replace cached block with an older version from disk
- recheck "unrelated blocks" (read/update collisions) until data stops changing
- track tree path correctly - do not treat split block as parent of its right half
- correctly move blocks when finding new empty place on disk
- restart updates from the beginning when one of blocks is changed by a parallel update
- fix delete using SET opcode and setting key to the empty value instead
- prevent changing the same key more than 1 time in parallel
- fix listing verification
- resume continue_updates in update_find (required because it uses continue_update itself)
- add allow_old_cached parameter to get()
2023-12-01 01:17:03 +03:00
Vitaliy Filippov 20321aaaef Implement K/V DB stress tester 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 987b005356 Evict blocks based on memory limit & block usage 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 41754b748b Track blocks per level 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 31913256f3 Track block level 2023-12-01 01:17:03 +03:00
Vitaliy Filippov 0ee36baed7 Experimental B-Tree Vitastor embedded K/V database implementation! 2023-12-01 01:17:03 +03:00
220 changed files with 2192 additions and 13519 deletions
+1 -1
View File
@@ -22,7 +22,7 @@ RUN apt-get update
RUN apt-get -y install etcd qemu-system-x86 qemu-block-extra qemu-utils fio libasan5 \
liburing1 liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev
RUN apt-get -y build-dep fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
RUN apt-get -y install jq lp-solve sudo nfs-common
RUN apt-get -y install jq lp-solve sudo
RUN apt-get --download-only source fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
RUN set -ex; \
+1 -37
View File
@@ -395,7 +395,7 @@ jobs:
steps:
- name: Run test
id: test
timeout-minutes: 6
timeout-minutes: 3
run: SCHEME=ec /root/vitastor/tests/test_snapshot_chain.sh
- name: Print logs
if: always() && steps.test.outcome == 'failure'
@@ -532,24 +532,6 @@ jobs:
echo ""
done
test_switch_primary:
runs-on: ubuntu-latest
needs: build
container: ${{env.TEST_IMAGE}}:${{github.sha}}
steps:
- name: Run test
id: test
timeout-minutes: 3
run: /root/vitastor/tests/test_switch_primary.sh
- name: Print logs
if: always() && steps.test.outcome == 'failure'
run: |
for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
echo "-------- $i --------"
cat $i
echo ""
done
test_write:
runs-on: ubuntu-latest
needs: build
@@ -856,21 +838,3 @@ jobs:
echo ""
done
test_nfs:
runs-on: ubuntu-latest
needs: build
container: ${{env.TEST_IMAGE}}:${{github.sha}}
steps:
- name: Run test
id: test
timeout-minutes: 3
run: /root/vitastor/tests/test_nfs.sh
- name: Print logs
if: always() && steps.test.outcome == 'failure'
run: |
for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
echo "-------- $i --------"
cat $i
echo ""
done
-4
View File
@@ -39,10 +39,6 @@ for my $line (<>)
$test_name .= '_'.lc($1).'_'.$2;
}
}
if ($test_name eq 'test_snapshot_chain_ec')
{
$timeout = 6;
}
$line =~ s!\./test_!/root/vitastor/tests/test_!;
# Gitea CI doesn't support artifacts yet, lol
#- name: Upload results
-115
View File
@@ -1,115 +0,0 @@
## Contributor License Agreement
> This Agreement is made in the Russian and English languages. **The English
text of Agreement is for informational purposes only** and is not binding
for the Parties.
>
> In the event of a conflict between the provisions of the Russian and
English versions of this Agreement, the **Russian version shall prevail**.
>
> Russian version is published at https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md
This document represents the offer of Filippov Vitaliy Vladimirovich
("Author"), author and copyright holder of Vitastor software ("Program"),
acknowledged by a certificate of Federal Service for Intellectual
Property of Russian Federation (Rospatent) # 2021617829 dated 20 May 2021,
to "Contributors" to conclude this license agreement as follows
("Agreement" or "Offer").
In accordance with Art. 435, Art. 438 of the Civil Code of the Russian
Federation, this Agreement is an offer and in case of acceptance of the
offer, an agreement is considered concluded on the conditions specified
in the offer.
1. Applicable Terms. \
1.1. "Official Repository" shall mean the computer storage, operated by
the Author, containing all prior and future versions of the Source
Code of the Program, at Internet addresses https://git.yourcmc.ru/vitalif/vitastor/
or https://github.com/vitalif/vitastor/. \
1.2. "Contributions" shall mean results of intellectual activity
(including, but not limited to, source code, libraries, components,
texts, documentation) which can be software or elements of the software
and which are provided by Contributors to the Author for inclusion
in the Program. \
1.3. "Contributor" shall mean a person who provides Contributions to
the Author and agrees with all provisions of this Agreement.
A Сontributor can be: 1) an individual; or 2) a legal entity or an
individual entrepreneur in case when an individual provides Contributions
on behalf of third parties, including on behalf of his employer.
2. Subject of the Agreement. \
2.1. Subject of the Agreement shall be the Contributions sent to the Author by Contributors. \
2.2. The Contributor grants to the Author the right to use Contributions at his own
discretion and without any necessity to get a prior approval from Contributor or
any other third party in any way, under a simple (non-exclusive), royalty-free,
irrevocable license throughout the world by all means not contrary to law, in whole
or as a part of the Program, or other open-source or closed-source computer programs,
products or services (hereinafter -- the "License"), including, but not limited to: \
2.2.1. to execute Contributions and use them for any tasks; \
2.2.2. to publish and distribute Contributions in modified or unmodified form and/or to rent them; \
2.2.3. to modify Contributions, add comments, illustrations or any explanations to Contributions while using them; \
2.2.4. to create other results of intellectual activity based on Contributions, including derivative works and composite works; \
2.2.5. to translate Contributions into other languages, including other programming languages; \
2.2.6. to carry out rental and public display of Contributions; \
2.2.7. to use Contributions under the trade name and/or any trademark or any other label, or without it, as the Author thinks fit; \
2.3. The Contributor grants to the Author the right to sublicense any of the aforementioned
rights to third parties on any terms at the Author's discretion. \
2.4. The License is provided for the entire duration of Contributor's
exclusive intellectual property rights to the Contributions. \
2.5. The Contributor grants to the Author the right to decide how and where to mention,
or to not mention at all, the fact of his authorship, name, nickname and/or company
details when including Contributions into the Program or in any other computer
programs, products or services.
3. Acceptance of the Offer \
3.1. The Contributor may provide Contributions to the Author in the form of
a "Pull Request" in an Official Repository of the Program or by any
other electronic means of communication, including, but not limited to,
E-mail or messenger applications. \
3.2. The acceptance of the Offer shall be the fact of provision of Contributions
to the Author by the Contributor by any means with the following remark:
“I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md”
or “Я принимаю соглашение Vitastor CLA: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md”. \
3.3. Date of acceptance of the Offer shall be the date of such provision.
4. Rights and obligations of the parties. \
4.1. The Contributor reserves the right to use Contributions by any lawful means
not contrary to this Agreement. \
4.2. The Author has the right to refuse to include Contributions into the Program
at any moment with no explanation to the Contributor.
5. Representations and Warranties. \
5.1. The person providing Contributions for the purpose of their inclusion
in the Program represents and warrants that he is the Contributor
or legally acts on the Contributor's behalf. Name or company details
of the Contributor shall be provided with the Contribution at the moment
of their provision to the Author. \
5.2. The Contributor represents and warrants that he legally owns exclusive
intellectual property rights to the Contributions. \
5.3. The Contributor represents and warrants that any further use of
Contributions by the Author as provided by Contributor under the terms
of the Agreement does not infringe on intellectual and other rights and
legitimate interests of third parties. \
5.4. The Contributor represents and warrants that he has all rights and legal
capacity needed to accept this Offer; \
5.5. The Contributor represents and warrants that Contributions don't
contain malware or any information considered illegal under the law
of Russian Federation.
6. Termination of the Agreement \
6.1. The Agreement may be terminated at will of both Author and Contributor,
formalised in the written form or if the Agreement is terminated on
reasons prescribed by the law of Russian Federation.
7. Final Clauses \
7.1. The Contributor may optionally sign the Agreement in the written form. \
7.2. The Agreement is deemed to become effective from the Date of signing of
the Agreement and until the expiration of Contributor's exclusive
intellectual property rights to the Contributions. \
7.3. The Author may unilaterally alter the Agreement without informing Contributors.
The new version of the document shall come into effect 3 (three) days after
being published in the Official Repository of the Program at Internet address
[https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md).
Contributors should keep informed about the actual version of the Agreement themselves. \
7.4. If the Author and the Contributor fail to agree on disputable issues,
disputes shall be referred to the Moscow Arbitration court.
-108
View File
@@ -1,108 +0,0 @@
## Лицензионное соглашение с участником
> Данная Оферта написана в Русской и Английской версиях. **Версия на английском
языке предоставляется в информационных целях** и не связывает стороны договора.
>
> В случае несоответствий между положениями Русской и Английской версий Договора,
**Русская версия имеет приоритет**.
>
> Английская версия опубликована по адресу https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md
Настоящий договор-оферта (далее по тексту – Оферта, Договор) адресована физическим
и юридическим лицам (далее – Участникам) и является официальным публичным предложением
Филиппова Виталия Владимировича (далее – Автора) программного обеспечения Vitastor,
свидетельство Федеральной службы по интеллектуальной собственности (Роспатент) № 2021617829
от 20 мая 2021 г. (далее – Программа) о нижеследующем:
1. Термины и определения \
1.1. Репозиторий – электронное хранилище, содержащее исходный код Программы. \
1.2. Доработка – результат интеллектуальной деятельности Участника, включающий
в себя изменения или дополнения к исходному коду Программы, которые Участник
желает включить в состав Программы для дальнейшего использования и распространения
Автором и для этого направляет их Автору. \
1.3. Участник – физическое или юридическое лицо, вносящее Доработки в код Программы. \
1.4. ГК РФ – Гражданский кодекс Российской Федерации.
2. Предмет оферты \
2.1. Предметом настоящей оферты являются Доработки, отправляемые Участником Автору. \
2.2. Участник предоставляет Автору право использовать Доработки по собственному усмотрению
и без необходимости предварительного согласования с Участником или иным третьим лицом
на условиях простой (неисключительной) безвозмездной безотзывной лицензии, полностью
или фрагментарно, в составе Программы или других программ, продуктов или сервисов
как с открытым, так и с закрытым исходным кодом, любыми способами, не противоречащими
закону, включая, но не ограничиваясь следующими: \
2.2.1. Запускать и использовать Доработки для выполнения любых задач; \
2.2.2. Распространять, импортировать и доводить Доработки до всеобщего сведения; \
2.2.3. Вносить в Доработки изменения, сокращения и дополнения, снабжать Доработки
при их использовании комментариями, иллюстрациями или пояснениями; \
2.2.4. Создавать на основе Доработок иные результаты интеллектуальной деятельности,
в том числе производные и составные произведения; \
2.2.5. Переводить Доработки на другие языки, в том числе на другие языки программирования; \
2.2.6. Осуществлять прокат и публичный показ Доработок; \
2.2.7. Использовать Доработки под любым фирменным наименованием, товарным знаком
(знаком обслуживания) или иным обозначением, или без такового. \
2.3. Участник предоставляет Автору право сублицензировать полученные права на Доработки
третьим лицам на любых условиях на усмотрение Автора. \
2.4. Участник предоставляет Автору права на Доработки на территории всего мира. \
2.5. Участник предоставляет Автору права на весь срок действия исключительного права
Участника на Доработки. \
2.6. Участник предоставляет Автору права на Доработки на безвозмездной основе. \
2.7. Участник разрешает Автору самостоятельно определять порядок, способ и
место указания его имени, реквизитов и/или псевдонима при включении
Доработок в состав Программы или других программ, продуктов или сервисов.
3. Акцепт Оферты \
3.1. Участник может передавать Доработки в адрес Автора через зеркала официального
Репозитория Программы по адресам https://git.yourcmc.ru/vitalif/vitastor/ или
https://github.com/vitalif/vitastor/ в виде “запроса на слияние” (pull request),
либо в письменном виде или с помощью любых других электронных средств коммуникации,
например, электронной почты или мессенджеров. \
3.2. Факт передачи Участником Доработок в адрес Автора любым способом с одной из пометок
“I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md”
или “Я принимаю соглашение Vitastor CLA: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md”
является полным и безоговорочным акцептом (принятием) Участником условий настоящей
Оферты, т.е. Участник считается ознакомившимся с настоящим публичным договором и
в соответствии с ГК РФ признается лицом, вступившим с Автором в договорные отношения
на основании настоящей Оферты. \
3.3. Датой акцептирования настоящей Оферты считается дата такой передачи.
4. Права и обязанности Сторон \
4.1. Участник сохраняет за собой право использовать Доработки любым законным
способом, не противоречащим настоящему Договору. \
4.2. Автор вправе отказать Участнику во включении Доработок в состав
Программы без объяснения причин в любой момент по своему усмотрению.
5. Гарантии и заверения \
5.1. Лицо, направляющее Доработки для целей их включения в состав Программы,
гарантирует, что является Участником или представителем Участника. Имя или реквизиты
Участника должны быть указаны при их передаче в адрес Автора Программы. \
5.2. Участник гарантирует, что является законным обладателем исключительных прав
на Доработки. \
5.3. Участник гарантирует, что на момент акцептирования настоящей Оферты ему
ничего не известно (и не могло быть известно) о правах третьих лиц на
передаваемые Автору Доработки или их часть, которые могут быть нарушены
в связи с передачей Доработок по настоящему Договору. \
5.4. Участник гарантирует, что является дееспособным лицом и обладает всеми
необходимыми правами для заключения Договора. \
5.5. Участник гарантирует, что Доработки не содержат вредоносного ПО, а также
любой другой информации, запрещённой к распространению по законам Российской
Федерации.
6. Прекращение действия оферты \
6.1. Действие настоящего договора может быть прекращено по соглашению сторон,
оформленному в письменном виде, а также вследствие его расторжения по основаниям,
предусмотренным законом.
7. Заключительные положения \
7.1. Участник вправе по желанию подписать настоящий Договор в письменном виде. \
7.2. Настоящий договор действует с момента его заключения и до истечения срока
действия исключительных прав Участника на Доработки. \
7.3. Автор имеет право в одностороннем порядке вносить изменения и дополнения в договор
без специального уведомления об этом Участников. Новая редакция документа вступает
в силу через 3 (Три) календарных дня со дня опубликования в официальном Репозитории
Программы по адресу в сети Интернет
[https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md).
Участники самостоятельно отслеживают действующие условия Оферты. \
7.4. Все споры, возникающие между сторонами в процессе их взаимодействия по настоящему
договору, решаются путём переговоров. В случае невозможности урегулирования споров
переговорным порядком стороны разрешают их в Арбитражном суде г.Москвы.
+1 -1
View File
@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
project(vitastor)
set(VERSION "1.5.0")
set(VERSION "1.2.0")
add_subdirectory(src)
+3 -3
View File
@@ -6,8 +6,8 @@
Вернём былую скорость кластерному блочному хранилищу!
Vitastor - распределённая блочная и файловая SDS (программная СХД), прямой аналог Ceph RBD и CephFS,
а также внутренних СХД популярных облачных провайдеров. Однако, в отличие от них, Vitastor
Vitastor - распределённая блочная SDS (программная СХД), прямой аналог Ceph RBD и
внутренних СХД популярных облачных провайдеров. Однако, в отличие от них, Vitastor
быстрый и при этом простой. Только пока маленький :-).
Vitastor архитектурно похож на Ceph, что означает атомарность и строгую консистентность,
@@ -63,7 +63,7 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
- [fio](docs/usage/fio.ru.md) для тестов производительности
- [NBD](docs/usage/nbd.ru.md) для монтирования ядром
- [QEMU и qemu-img](docs/usage/qemu.ru.md)
- [NFS](docs/usage/nfs.ru.md) кластерная файловая система и псевдо-ФС прокси
- [NFS](docs/usage/nfs.ru.md)-прокси для VMWare и подобных
- Производительность
- [Понимание сути производительности](docs/performance/understanding.ru.md)
- [Теоретический максимум](docs/performance/theoretical.ru.md)
+4 -4
View File
@@ -6,9 +6,9 @@
Make Clustered Block Storage Fast Again.
Vitastor is a distributed block and file SDS, direct replacement of Ceph RBD and CephFS,
and also internal SDS's of public clouds. However, in contrast to them, Vitastor is fast
and simple at the same time. The only thing is it's slightly young :-).
Vitastor is a distributed block SDS, direct replacement of Ceph RBD and internal SDS's
of public clouds. However, in contrast to them, Vitastor is fast and simple at the same time.
The only thing is it's slightly young :-).
Vitastor is architecturally similar to Ceph which means strong consistency,
primary-replication, symmetric clustering and automatic data distribution over any
@@ -63,7 +63,7 @@ Read more details below in the documentation.
- [fio](docs/usage/fio.en.md) for benchmarks
- [NBD](docs/usage/nbd.en.md) for kernel mounts
- [QEMU and qemu-img](docs/usage/qemu.en.md)
- [NFS](docs/usage/nfs.en.md) clustered file system and pseudo-FS proxy
- [NFS](docs/usage/nfs.en.md) emulator for VMWare and similar
- Performance
- [Understanding storage performance](docs/performance/understanding.en.md)
- [Theoretical performance](docs/performance/theoretical.en.md)
+7 -19
View File
@@ -1,15 +1,14 @@
# Compile stage
FROM golang:bookworm AS build
FROM golang:buster AS build
ADD go.sum go.mod /app/
RUN cd /app; CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go mod download -x
ADD . /app
RUN perl -i -e '$/ = undef; while(<>) { s/\n\s*(\{\s*\n)/$1\n/g; s/\}(\s*\n\s*)else\b/$1} else/g; print; }' `find /app -name '*.go'` && \
cd /app && \
CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build -o vitastor-csi
RUN perl -i -e '$/ = undef; while(<>) { s/\n\s*(\{\s*\n)/$1\n/g; s/\}(\s*\n\s*)else\b/$1} else/g; print; }' `find /app -name '*.go'`
RUN cd /app; CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build -o vitastor-csi
# Final stage
FROM debian:bookworm
FROM debian:buster
LABEL maintainers="Vitaliy Filippov <vitalif@yourcmc.ru>"
LABEL description="Vitastor CSI Driver"
@@ -19,30 +18,19 @@ ENV CSI_ENDPOINT=""
RUN apt-get update && \
apt-get install -y wget && \
(echo deb http://deb.debian.org/debian buster-backports main > /etc/apt/sources.list.d/backports.list) && \
(echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
apt-get update && \
apt-get install -y e2fsprogs xfsprogs kmod iproute2 \
# dependencies of qemu-storage-daemon
libnuma1 liburing2 libglib2.0-0 libfuse3-3 libaio1 libzstd1 libnettle8 \
libgmp10 libhogweed6 libp11-kit0 libidn2-0 libunistring2 libtasn1-6 libpcre2-8-0 libffi8 && \
apt-get install -y e2fsprogs xfsprogs kmod && \
apt-get clean && \
(echo options nbd nbds_max=128 > /etc/modprobe.d/nbd.conf)
COPY --from=build /app/vitastor-csi /bin/
RUN (echo deb http://vitastor.io/debian bookworm main > /etc/apt/sources.list.d/vitastor.list) && \
((echo 'Package: *'; echo 'Pin: origin "vitastor.io"'; echo 'Pin-Priority: 1000') > /etc/apt/preferences.d/vitastor.pref) && \
RUN (echo deb http://vitastor.io/debian buster main > /etc/apt/sources.list.d/vitastor.list) && \
wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg && \
apt-get update && \
apt-get install -y vitastor-client && \
wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-utils_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-block-extra_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
dpkg -x qemu-utils*.deb tmp1 && \
dpkg -x qemu-block-extra*.deb tmp1 && \
cp -a tmp1/usr/bin/qemu-storage-daemon /usr/bin/ && \
mkdir -p /usr/lib/x86_64-linux-gnu/qemu && \
cp -a tmp1/usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so /usr/lib/x86_64-linux-gnu/qemu/ && \
rm -rf tmp1 *.deb && \
apt-get clean
ENTRYPOINT ["/bin/vitastor-csi"]
+1 -1
View File
@@ -1,4 +1,4 @@
VERSION ?= v1.5.0
VERSION ?= v1.2.0
all: build push
-1
View File
@@ -2,7 +2,6 @@
apiVersion: v1
kind: ConfigMap
data:
# You can add multiple configuration files here to use a multi-cluster setup
vitastor.conf: |-
{"etcd_address":"http://192.168.7.2:2379","etcd_prefix":"/vitastor"}
metadata:
+1 -6
View File
@@ -49,7 +49,7 @@ spec:
capabilities:
add: ["SYS_ADMIN"]
allowPrivilegeEscalation: true
image: vitalif/vitastor-csi:v1.5.0
image: vitalif/vitastor-csi:v1.2.0
args:
- "--node=$(NODE_ID)"
- "--endpoint=$(CSI_ENDPOINT)"
@@ -82,8 +82,6 @@ spec:
name: host-sys
- mountPath: /run/mount
name: host-mount
- mountPath: /run/vitastor-csi
name: run-vitastor-csi
- mountPath: /lib/modules
name: lib-modules
readOnly: true
@@ -134,9 +132,6 @@ spec:
- name: host-mount
hostPath:
path: /run/mount
- name: run-vitastor-csi
hostPath:
path: /run/vitastor-csi
- name: lib-modules
hostPath:
path: /lib/modules
+1 -1
View File
@@ -121,7 +121,7 @@ spec:
privileged: true
capabilities:
add: ["SYS_ADMIN"]
image: vitalif/vitastor-csi:v1.5.0
image: vitalif/vitastor-csi:v1.2.0
args:
- "--node=$(NODE_ID)"
- "--endpoint=$(CSI_ENDPOINT)"
+4 -1
View File
@@ -12,6 +12,9 @@ parameters:
etcdVolumePrefix: ""
poolId: "1"
# you can choose other configuration file if you have it in the config map
# different etcd URLs and prefixes should also be put in the config
#configPath: "/etc/vitastor/vitastor.conf"
# you can also specify etcdUrl here, maybe to connect to another Vitastor cluster
# multiple etcdUrls may be specified, delimited by comma
#etcdUrl: "http://192.168.7.2:2379"
#etcdPrefix: "/vitastor"
allowVolumeExpansion: true
+1 -1
View File
@@ -5,7 +5,7 @@ package vitastor
const (
vitastorCSIDriverName = "csi.vitastor.io"
vitastorCSIDriverVersion = "1.5.0"
vitastorCSIDriverVersion = "1.2.0"
)
// Config struct fills the parameters of request or user input
+56 -70
View File
@@ -62,7 +62,7 @@ func NewControllerServer(driver *Driver) *ControllerServer
}
}
func GetConnectionParams(params map[string]string) (map[string]string, error)
func GetConnectionParams(params map[string]string) (map[string]string, []string, string)
{
ctxVars := make(map[string]string)
configPath := params["configPath"]
@@ -75,69 +75,71 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
ctxVars["configPath"] = configPath
}
config := make(map[string]interface{})
configFD, err := os.Open(configPath)
if (err != nil)
if configFD, err := os.Open(configPath); err == nil
{
return nil, err
defer configFD.Close()
data, _ := ioutil.ReadAll(configFD)
json.Unmarshal(data, &config)
}
defer configFD.Close()
data, _ := ioutil.ReadAll(configFD)
json.Unmarshal(data, &config)
// Check etcd URL in the config, but do not use the explicit etcdUrl
// parameter for CLI calls, otherwise users won't be able to later
// change them - storage class parameters are saved in volume IDs
// Try to load prefix & etcd URL from the config
var etcdUrl []string
switch config["etcd_address"].(type)
if (params["etcdUrl"] != "")
{
case string:
url := strings.TrimSpace(config["etcd_address"].(string))
if (url != "")
{
etcdUrl = strings.Split(url, ",")
}
case []string:
etcdUrl = config["etcd_address"].([]string)
case []interface{}:
for _, url := range config["etcd_address"].([]interface{})
{
s, ok := url.(string)
if (ok)
{
etcdUrl = append(etcdUrl, s)
}
}
ctxVars["etcdUrl"] = params["etcdUrl"]
etcdUrl = strings.Split(params["etcdUrl"], ",")
}
if (len(etcdUrl) == 0)
{
return nil, status.Error(codes.InvalidArgument, "etcd_address is missing in "+configPath)
switch config["etcd_address"].(type)
{
case string:
etcdUrl = strings.Split(config["etcd_address"].(string), ",")
case []string:
etcdUrl = config["etcd_address"].([]string)
}
}
return ctxVars, nil
}
func system(program string, args ...string) ([]byte, []byte, error)
{
klog.Infof("Running "+program+" "+strings.Join(args, " "))
c := exec.Command(program, args...)
var stdout, stderr bytes.Buffer
c.Stdout, c.Stderr = &stdout, &stderr
err := c.Run()
if (err != nil)
etcdPrefix := params["etcdPrefix"]
if (etcdPrefix == "")
{
stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", stdoutStr+stderrStr, err)
return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
etcdPrefix, _ = config["etcd_prefix"].(string)
if (etcdPrefix == "")
{
etcdPrefix = "/vitastor"
}
}
return stdout.Bytes(), stderr.Bytes(), nil
else
{
ctxVars["etcdPrefix"] = etcdPrefix
}
return ctxVars, etcdUrl, etcdPrefix
}
func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
{
if (ctxVars["etcdUrl"] != "")
{
args = append(args, "--etcd_address", ctxVars["etcdUrl"])
}
if (ctxVars["etcdPrefix"] != "")
{
args = append(args, "--etcd_prefix", ctxVars["etcdPrefix"])
}
if (ctxVars["configPath"] != "")
{
args = append(args, "--config_path", ctxVars["configPath"])
}
stdout, _, err := system("/usr/bin/vitastor-cli", args...)
return stdout, err
c := exec.Command("/usr/bin/vitastor-cli", args...)
var stdout, stderr bytes.Buffer
c.Stdout = &stdout
c.Stderr = &stderr
err := c.Run()
stderrStr := string(stderr.Bytes())
if (err != nil)
{
klog.Errorf("vitastor-cli %s failed: %s, status %s\n", strings.Join(args, " "), stderrStr, err)
return nil, status.Error(codes.Internal, stderrStr+" (status "+err.Error()+")")
}
return stdout.Bytes(), nil
}
// Create the volume
@@ -172,10 +174,10 @@ func (cs *ControllerServer) CreateVolume(ctx context.Context, req *csi.CreateVol
volSize = ((capRange.GetRequiredBytes() + MB - 1) / MB) * MB
}
ctxVars, err := GetConnectionParams(req.Parameters)
if (err != nil)
ctxVars, etcdUrl, _ := GetConnectionParams(req.Parameters)
if (len(etcdUrl) == 0)
{
return nil, err
return nil, status.Error(codes.InvalidArgument, "no etcdUrl in storage class configuration and no etcd_address in vitastor.conf")
}
args := []string{ "create", volName, "-s", fmt.Sprintf("%v", volSize), "--pool", fmt.Sprintf("%v", poolId) }
@@ -205,7 +207,7 @@ func (cs *ControllerServer) CreateVolume(ctx context.Context, req *csi.CreateVol
}
// Create image using vitastor-cli
_, err = invokeCLI(ctxVars, args)
_, err := invokeCLI(ctxVars, args)
if (err != nil)
{
if (strings.Index(err.Error(), "already exists") > 0)
@@ -255,11 +257,7 @@ func (cs *ControllerServer) DeleteVolume(ctx context.Context, req *csi.DeleteVol
}
volName := volVars["name"]
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
ctxVars, _, _ := GetConnectionParams(volVars)
_, err = invokeCLI(ctxVars, []string{ "rm", volName })
if (err != nil)
@@ -471,11 +469,7 @@ func (cs *ControllerServer) DeleteSnapshot(ctx context.Context, req *csi.DeleteS
volName := volVars["name"]
snapName := volVars["snapshot"]
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
ctxVars, _, _ := GetConnectionParams(volVars)
_, err = invokeCLI(ctxVars, []string{ "rm", volName+"@"+snapName })
if (err != nil)
@@ -502,11 +496,7 @@ func (cs *ControllerServer) ListSnapshots(ctx context.Context, req *csi.ListSnap
return nil, status.Error(codes.Internal, "volume ID not in JSON format")
}
volName := volVars["name"]
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
ctxVars, _, _ := GetConnectionParams(volVars)
inodeCfg, err := invokeList(ctxVars, volName+"@*", false)
if (err != nil)
@@ -565,11 +555,7 @@ func (cs *ControllerServer) ControllerExpandVolume(ctx context.Context, req *csi
return nil, status.Error(codes.Internal, "volume ID not in JSON format")
}
volName := volVars["name"]
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
ctxVars, _, _ := GetConnectionParams(volVars)
inodeCfg, err := invokeList(ctxVars, volName, true)
if (err != nil)
+40 -438
View File
@@ -5,16 +5,11 @@ package vitastor
import (
"context"
"errors"
"encoding/json"
"fmt"
"os"
"os/exec"
"path/filepath"
"strconv"
"encoding/json"
"strings"
"syscall"
"time"
"bytes"
"google.golang.org/grpc/codes"
"google.golang.org/grpc/status"
@@ -30,102 +25,16 @@ import (
type NodeServer struct
{
*Driver
useVduse bool
stateDir string
mounter mount.Interface
restartInterval time.Duration
}
type DeviceState struct
{
ConfigPath string `json:"configPath"`
VdpaId string `json:"vdpaId"`
Image string `json:"image"`
Blockdev string `json:"blockdev"`
Readonly bool `json:"readonly"`
PidFile string `json:"pidFile"`
}
// NewNodeServer create new instance node
func NewNodeServer(driver *Driver) *NodeServer
{
stateDir := os.Getenv("STATE_DIR")
if (stateDir == "")
{
stateDir = "/run/vitastor-csi"
}
if (stateDir[len(stateDir)-1] != '/')
{
stateDir += "/"
}
ns := &NodeServer{
return &NodeServer{
Driver: driver,
useVduse: checkVduseSupport(),
stateDir: stateDir,
mounter: mount.New(""),
}
if (ns.useVduse)
{
ns.restoreVduseDaemons()
dur, err := time.ParseDuration(os.Getenv("RESTART_INTERVAL"))
if (err != nil)
{
dur = 10 * time.Second
}
ns.restartInterval = dur
if (ns.restartInterval != time.Duration(0))
{
go ns.restarter()
}
}
return ns
}
func checkVduseSupport() bool
{
// Check VDUSE support (vdpa, vduse, virtio-vdpa kernel modules)
vduse := true
for _, mod := range []string{"vdpa", "vduse", "virtio-vdpa"}
{
_, err := os.Stat("/sys/module/"+mod)
if (err != nil)
{
if (!errors.Is(err, os.ErrNotExist))
{
klog.Errorf("failed to check /sys/module/%s: %v", mod, err)
}
c := exec.Command("/sbin/modprobe", mod)
c.Stdout = os.Stderr
c.Stderr = os.Stderr
err := c.Run()
if (err != nil)
{
klog.Errorf("/sbin/modprobe %s failed: %v", mod, err)
vduse = false
break
}
}
}
// Check that vdpa tool functions
if (vduse)
{
c := exec.Command("/sbin/vdpa", "-j", "dev")
c.Stderr = os.Stderr
err := c.Run()
if (err != nil)
{
klog.Errorf("/sbin/vdpa -j dev failed: %v", err)
vduse = false
}
}
if (!vduse)
{
klog.Errorf(
"Your host apparently has no VDUSE support. VDUSE support disabled, NBD will be used to map devices."+
" For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
)
}
return vduse
}
// NodeStageVolume mounts the volume to a staging path on the node.
@@ -152,318 +61,6 @@ func Contains(list []string, s string) bool
return false
}
func (ns *NodeServer) mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, error)
{
// Map NBD device
// FIXME: Check if already mapped
args := []string{
"map", "--image", volName,
}
if (ctxVars["configPath"] != "")
{
args = append(args, "--config_path", ctxVars["configPath"])
}
if (readonly)
{
args = append(args, "--readonly", "1")
}
stdout, stderr, err := system("/usr/bin/vitastor-nbd", args...)
dev := strings.TrimSpace(string(stdout))
if (dev == "")
{
return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
}
return dev, err
}
func (ns *NodeServer) unmapNbd(devicePath string)
{
// unmap NBD device
unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
if (unmapErr != nil)
{
klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
}
}
func findByPidFile(pidFile string) (*os.Process, error)
{
pidBuf, err := os.ReadFile(pidFile)
if (err != nil)
{
return nil, err
}
pid, err := strconv.ParseInt(strings.TrimSpace(string(pidBuf)), 0, 64)
if (err != nil)
{
return nil, err
}
proc, err := os.FindProcess(int(pid))
if (err != nil)
{
return nil, err
}
return proc, nil
}
func killByPidFile(pidFile string) error
{
klog.Infof("killing process with PID from file %s", pidFile)
proc, err := findByPidFile(pidFile)
if (err != nil)
{
return err
}
return proc.Signal(syscall.SIGTERM)
}
func startStorageDaemon(vdpaId, volName, pidFile, configPath string, readonly bool) error
{
// Start qemu-storage-daemon
blockSpec := map[string]interface{}{
"node-name": "disk1",
"driver": "vitastor",
"image": volName,
"cache": map[string]bool{
"direct": true,
"no-flush": false,
},
"discard": "unmap",
}
if (configPath != "")
{
blockSpec["config-path"] = configPath
}
blockSpecJson, _ := json.Marshal(blockSpec)
writable := "true"
if (readonly)
{
writable = "false"
}
_, _, err := system(
"/usr/bin/qemu-storage-daemon", "--daemonize", "--pidfile", pidFile, "--blockdev", string(blockSpecJson),
"--export", "vduse-blk,id="+vdpaId+",node-name=disk1,name="+vdpaId+",num-queues=16,queue-size=128,writable="+writable,
)
return err
}
func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readonly bool) (string, string, error)
{
// Generate state file
stateFd, err := os.CreateTemp(ns.stateDir, "vitastor-vduse-*.json")
if (err != nil)
{
return "", "", err
}
stateFile := stateFd.Name()
stateFd.Close()
vdpaId := filepath.Base(stateFile)
vdpaId = vdpaId[0:len(vdpaId)-5] // remove ".json"
pidFile := ns.stateDir + vdpaId + ".pid"
// Map VDUSE device via qemu-storage-daemon
err = startStorageDaemon(vdpaId, volName, pidFile, ctxVars["configPath"], readonly)
if (err == nil)
{
// Add device to VDPA bus
_, _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
if (err == nil)
{
// Find block device name
var matches []string
matches, err = filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
if (err == nil && len(matches) == 0)
{
err = errors.New("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/* is not found")
}
if (err == nil)
{
blockdev := "/dev/"+filepath.Base(matches[0])
_, err = os.Stat(blockdev)
if (err == nil)
{
// Generate state file
stateJSON, _ := json.Marshal(&DeviceState{
ConfigPath: ctxVars["configPath"],
VdpaId: vdpaId,
Image: volName,
Blockdev: blockdev,
Readonly: readonly,
PidFile: pidFile,
})
err = os.WriteFile(stateFile, stateJSON, 0600)
if (err == nil)
{
return blockdev, vdpaId, nil
}
}
}
}
killErr := killByPidFile(pidFile)
if (killErr != nil)
{
klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
}
os.Remove(stateFile)
os.Remove(pidFile)
}
return "", "", err
}
func (ns *NodeServer) unmapVduse(devicePath string)
{
if (len(devicePath) < 6 || devicePath[0:6] != "/dev/v")
{
klog.Errorf("%s does not start with /dev/v", devicePath)
return
}
vduseDev, err := os.Readlink("/sys/block/"+devicePath[5:])
if (err != nil)
{
klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx): %v", devicePath, err)
return
}
vdpaId := ""
p := strings.Index(vduseDev, "/vduse/")
if (p >= 0)
{
vduseDev = vduseDev[p+7:]
p = strings.Index(vduseDev, "/")
if (p >= 0)
{
vdpaId = vduseDev[0:p]
}
}
if (vdpaId == "")
{
klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx), but is %v", devicePath, vduseDev)
return
}
ns.unmapVduseById(vdpaId)
}
func (ns *NodeServer) unmapVduseById(vdpaId string)
{
_, err := os.Stat("/sys/bus/vdpa/devices/"+vdpaId)
if (err != nil)
{
klog.Errorf("failed to stat /sys/bus/vdpa/devices/"+vdpaId+": %v", err)
}
else
{
_, _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
}
stateFile := ns.stateDir + vdpaId + ".json"
os.Remove(stateFile)
pidFile := ns.stateDir + vdpaId + ".pid"
_, err = os.Stat(pidFile)
if (os.IsNotExist(err))
{
// ok, already killed
}
else if (err != nil)
{
klog.Errorf("Failed to stat %v: %v", pidFile, err)
return
}
else
{
err = killByPidFile(pidFile)
if (err != nil)
{
klog.Errorf("Failed to kill started qemu-storage-daemon: %v", err)
}
os.Remove(pidFile)
}
}
func (ns *NodeServer) restarter()
{
// Restart dead VDUSE daemons at regular intervals
// Otherwise volume I/O may hang in case of a qemu-storage-daemon crash
// Moreover, it may lead to a kernel panic of the kernel is configured to
// panic on hung tasks
ticker := time.NewTicker(ns.restartInterval)
defer ticker.Stop()
for
{
<-ticker.C
ns.restoreVduseDaemons()
}
}
func (ns *NodeServer) restoreVduseDaemons()
{
pattern := ns.stateDir+"vitastor-vduse-*.json"
matches, err := filepath.Glob(pattern)
if (err != nil)
{
klog.Errorf("failed to list %s: %v", pattern, err)
}
if (len(matches) == 0)
{
return
}
devList := make(map[string]interface{})
// example output: {"dev":{"test1":{"type":"block","mgmtdev":"vduse","vendor_id":0,"max_vqs":16,"max_vq_size":128}}}
devListJSON, _, err := system("/sbin/vdpa", "-j", "dev", "list")
if (err != nil)
{
return
}
err = json.Unmarshal(devListJSON, &devList)
devs, ok := devList["dev"].(map[string]interface{})
if (err != nil || !ok)
{
klog.Errorf("/sbin/vdpa -j dev list returned bad JSON (error %v): %v", err, string(devListJSON))
return
}
for _, stateFile := range matches
{
vdpaId := filepath.Base(stateFile)
vdpaId = vdpaId[0:len(vdpaId)-5]
// Check if VDPA device is still added to the bus
if (devs[vdpaId] != nil)
{
// Check if the storage daemon is still active
pidFile := ns.stateDir + vdpaId + ".pid"
exists := false
proc, err := findByPidFile(pidFile)
if (err == nil)
{
exists = proc.Signal(syscall.Signal(0)) == nil
}
if (!exists)
{
// Restart daemon
stateJSON, err := os.ReadFile(stateFile)
if (err != nil)
{
klog.Warningf("error reading state file %v: %v", stateFile, err)
}
else
{
var state DeviceState
err := json.Unmarshal(stateJSON, &state)
if (err != nil)
{
klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
}
else
{
klog.Warningf("restarting storage daemon for volume %v (VDPA ID %v)", state.Image, vdpaId)
_ = startStorageDaemon(vdpaId, state.Image, pidFile, state.ConfigPath, state.Readonly)
}
}
}
}
else
{
// Unused, clean it up
ns.unmapVduseById(vdpaId)
}
}
}
// NodePublishVolume mounts the volume mounted to the staging path to the target path
func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublishVolumeRequest) (*csi.NodePublishVolumeResponse, error)
{
@@ -484,13 +81,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
if (err != nil)
{
klog.Errorf("failed to create block device mount target %s with error: %v", targetPath, err)
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
err = pathFile.Close()
if (err != nil)
{
klog.Errorf("failed to close %s with error: %v", targetPath, err)
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
}
else
@@ -499,13 +96,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
if (err != nil)
{
klog.Errorf("failed to create fs mount target %s with error: %v", targetPath, err)
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
}
}
else
{
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
}
@@ -517,25 +114,38 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
}
volName := ctxVars["name"]
_, err = GetConnectionParams(ctxVars)
if (err != nil)
_, etcdUrl, etcdPrefix := GetConnectionParams(ctxVars)
if (len(etcdUrl) == 0)
{
return nil, err
return nil, status.Error(codes.InvalidArgument, "no etcdUrl in storage class configuration and no etcd_address in vitastor.conf")
}
var devicePath, vdpaId string
if (!ns.useVduse)
// Map NBD device
// FIXME: Check if already mapped
args := []string{
"map", "--etcd_address", strings.Join(etcdUrl, ","),
"--etcd_prefix", etcdPrefix,
"--image", volName,
};
if (ctxVars["configPath"] != "")
{
devicePath, err = ns.mapNbd(volName, ctxVars, req.GetReadonly())
args = append(args, "--config_path", ctxVars["configPath"])
}
else
if (req.GetReadonly())
{
devicePath, vdpaId, err = ns.mapVduse(volName, ctxVars, req.GetReadonly())
args = append(args, "--readonly", "1")
}
c := exec.Command("/usr/bin/vitastor-nbd", args...)
var stdout, stderr bytes.Buffer
c.Stdout, c.Stderr = &stdout, &stderr
err = c.Run()
stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
if (err != nil)
{
return nil, err
klog.Errorf("vitastor-nbd map failed: %s, status %s\n", stdoutStr+stderrStr, err)
return nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
}
devicePath := strings.TrimSpace(stdoutStr)
diskMounter := &mount.SafeFormatAndMount{Interface: ns.mounter, Exec: utilexec.New()}
if (isBlock)
@@ -617,15 +227,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
return &csi.NodePublishVolumeResponse{}, nil
unmap:
if (!ns.useVduse || len(devicePath) >= 8 && devicePath[0:8] == "/dev/nbd")
// unmap NBD device
unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
if (unmapErr != nil)
{
ns.unmapNbd(devicePath)
klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
}
else
{
ns.unmapVduseById(vdpaId)
}
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
// NodeUnpublishVolume unmounts the volume from the target path
@@ -640,31 +248,25 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
{
return nil, status.Error(codes.NotFound, "Target path not found")
}
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
if (devicePath == "")
{
// volume not mounted
klog.Warningf("%s is not a mountpoint, deleting", targetPath)
os.Remove(targetPath)
return &csi.NodeUnpublishVolumeResponse{}, nil
return nil, status.Error(codes.NotFound, "Volume not mounted")
}
// unmount
err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
if (err != nil)
{
return nil, err
return nil, status.Error(codes.Internal, err.Error())
}
// unmap NBD device
if (refCount == 1)
{
if (!ns.useVduse)
unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
if (unmapErr != nil)
{
ns.unmapNbd(devicePath)
}
else
{
ns.unmapVduse(devicePath)
klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
}
}
return &csi.NodeUnpublishVolumeResponse{}, nil
+1 -1
View File
@@ -3,5 +3,5 @@
cat < vitastor.Dockerfile > ../Dockerfile
cd ..
mkdir -p packages
sudo podman build --build-arg DISTRO=debian --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
sudo podman build --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
rm Dockerfile
+1 -1
View File
@@ -3,5 +3,5 @@
cat < vitastor.Dockerfile > ../Dockerfile
cd ..
mkdir -p packages
sudo podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
sudo podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
rm Dockerfile
+1 -1
View File
@@ -3,5 +3,5 @@
cat < vitastor.Dockerfile > ../Dockerfile
cd ..
mkdir -p packages
sudo podman build --build-arg DISTRO=debian --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
sudo podman build --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
rm Dockerfile
-7
View File
@@ -1,7 +0,0 @@
#!/bin/bash
cat < vitastor.Dockerfile > ../Dockerfile
cd ..
mkdir -p packages
sudo podman build --build-arg DISTRO=ubuntu --build-arg REL=jammy -v `pwd`/packages:/root/packages -f Dockerfile .
rm Dockerfile
+2 -2
View File
@@ -1,10 +1,10 @@
vitastor (1.5.0-1) unstable; urgency=medium
vitastor (1.2.0-1) unstable; urgency=medium
* Bugfixes
-- Vitaliy Filippov <vitalif@yourcmc.ru> Fri, 03 Jun 2022 02:09:44 +0300
vitastor (0.7.0-1) unstable; urgency=medium
vitastor (1.2.0-1) unstable; urgency=medium
* Implement NFS proxy
* Add documentation
+4 -5
View File
@@ -1,14 +1,13 @@
# Build patched libvirt for Debian Buster or Bullseye/Sid inside a container
# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/libvirt.Dockerfile .
# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/libvirt.Dockerfile .
ARG DISTRO=
ARG REL=
FROM $DISTRO:$REL
FROM debian:$REL
ARG REL=
WORKDIR /root
RUN if ([ "${DISTRO}" = "debian" ]) && ( [ "${REL}" = "buster" -o "${REL}" = "bullseye" ] ); then \
RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
echo >> /etc/apt/preferences; \
echo 'Package: *' >> /etc/apt/preferences; \
@@ -24,7 +23,7 @@ RUN apt-get -y build-dep libvirt0
RUN apt-get -y install libglusterfs-dev
RUN apt-get --download-only source libvirt
ADD patches/libvirt-5.0-vitastor.diff patches/libvirt-7.0-vitastor.diff patches/libvirt-7.5-vitastor.diff patches/libvirt-7.6-vitastor.diff patches/libvirt-8.0-vitastor.diff /root
ADD patches/libvirt-5.0-vitastor.diff patches/libvirt-7.0-vitastor.diff patches/libvirt-7.5-vitastor.diff patches/libvirt-7.6-vitastor.diff /root
RUN set -e; \
mkdir -p /root/packages/libvirt-$REL; \
rm -rf /root/packages/libvirt-$REL/*; \
+2 -2
View File
@@ -7,7 +7,7 @@ ARG REL=
WORKDIR /root
RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then \
RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
echo >> /etc/apt/preferences; \
echo 'Package: *' >> /etc/apt/preferences; \
@@ -45,7 +45,7 @@ RUN set -e; \
rm -rf /root/packages/qemu-$REL/*; \
cd /root/packages/qemu-$REL; \
dpkg-source -x /root/qemu*.dsc; \
QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*?(\d+\.\d+).*!$1!'); \
QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*(\d+\.\d+).*!$1!'); \
D=$(ls -d qemu*/); \
cp /root/vitastor/patches/qemu-$QEMU_VER-vitastor.patch ./qemu-*/debian/patches; \
echo qemu-$QEMU_VER-vitastor.patch >> $D/debian/patches/series; \
-2
View File
@@ -3,6 +3,4 @@ usr/bin/vitastor-cli
usr/bin/vitastor-rm
usr/bin/vitastor-nbd
usr/bin/vitastor-nfs
usr/bin/vitastor-kv
usr/bin/vitastor-kv-stress
usr/lib/*/libvitastor*.so*
+6 -8
View File
@@ -1,10 +1,8 @@
# Build Vitastor packages for Debian inside a container
# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
ARG DISTRO=debian
ARG REL=
FROM $DISTRO:$REL
ARG DISTRO=debian
FROM debian:$REL
ARG REL=
WORKDIR /root
@@ -37,8 +35,8 @@ RUN set -e -x; \
mkdir -p /root/packages/vitastor-$REL; \
rm -rf /root/packages/vitastor-$REL/*; \
cd /root/packages/vitastor-$REL; \
cp -r /root/vitastor vitastor-1.5.0; \
cd vitastor-1.5.0; \
cp -r /root/vitastor vitastor-1.2.0; \
cd vitastor-1.2.0; \
ln -s /root/fio-build/fio-*/ ./fio; \
FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -51,8 +49,8 @@ RUN set -e -x; \
rm -rf a b; \
echo "dep:fio=$FIO" > debian/fio_version; \
cd /root/packages/vitastor-$REL; \
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.5.0.orig.tar.xz vitastor-1.5.0; \
cd vitastor-1.5.0; \
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.2.0.orig.tar.xz vitastor-1.2.0; \
cd vitastor-1.2.0; \
V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
+2 -58
View File
@@ -6,40 +6,15 @@
# Client Parameters
These parameters apply only to Vitastor clients (QEMU, fio, NBD and so on) and
affect their interaction with the cluster.
These parameters apply only to clients and affect their interaction with
the cluster.
- [client_retry_interval](#client_retry_interval)
- [client_eio_retry_interval](#client_eio_retry_interval)
- [client_max_dirty_bytes](#client_max_dirty_bytes)
- [client_max_dirty_ops](#client_max_dirty_ops)
- [client_enable_writeback](#client_enable_writeback)
- [client_max_buffered_bytes](#client_max_buffered_bytes)
- [client_max_buffered_ops](#client_max_buffered_ops)
- [client_max_writeback_iodepth](#client_max_writeback_iodepth)
- [nbd_timeout](#nbd_timeout)
- [nbd_max_devices](#nbd_max_devices)
- [nbd_max_part](#nbd_max_part)
## client_retry_interval
- Type: milliseconds
- Default: 50
- Minimum: 10
- Can be changed online: yes
Retry time for I/O requests failed due to inactive PGs or network
connectivity errors.
## client_eio_retry_interval
- Type: milliseconds
- Default: 1000
- Can be changed online: yes
Retry time for I/O requests failed due to data corruption or unfinished
EC object deletions (has_incomplete PG state). 0 disables such retries
and clients are not blocked and just get EIO error code instead.
## client_max_dirty_bytes
@@ -126,34 +101,3 @@ Multiple consecutive modified data regions are counted as 1 write here.
- Can be changed online: yes
Maximum number of parallel writes when flushing buffered data to the server.
## nbd_timeout
- Type: seconds
- Default: 300
Timeout for I/O operations for [NBD](../usage/nbd.en.md). If an operation
executes for longer than this timeout, including when your cluster is just
temporarily down for more than timeout, the NBD device will detach by itself
(and possibly break the mounted file system).
You can set timeout to 0 to never detach, but in that case you won't be
able to remove the kernel device at all if the NBD process dies - you'll have
to reboot the host.
## nbd_max_devices
- Type: integer
- Default: 64
Maximum number of NBD devices in the system. This value is passed as
`nbds_max` parameter for the nbd kernel module when vitastor-nbd autoloads it.
## nbd_max_part
- Type: integer
- Default: 3
Maximum number of partitions per NBD device. This value is passed as
`max_part` parameter for the nbd kernel module when vitastor-nbd autoloads it.
Note that (nbds_max)*(1+max_part) usually can't exceed 256.
+1 -58
View File
@@ -6,41 +6,15 @@
# Параметры клиентского кода
Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD и т.п.) и
Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD) и
затрагивают логику их работы с кластером.
- [client_retry_interval](#client_retry_interval)
- [client_eio_retry_interval](#client_eio_retry_interval)
- [client_max_dirty_bytes](#client_max_dirty_bytes)
- [client_max_dirty_ops](#client_max_dirty_ops)
- [client_enable_writeback](#client_enable_writeback)
- [client_max_buffered_bytes](#client_max_buffered_bytes)
- [client_max_buffered_ops](#client_max_buffered_ops)
- [client_max_writeback_iodepth](#client_max_writeback_iodepth)
- [nbd_timeout](#nbd_timeout)
- [nbd_max_devices](#nbd_max_devices)
- [nbd_max_part](#nbd_max_part)
## client_retry_interval
- Тип: миллисекунды
- Значение по умолчанию: 50
- Минимальное значение: 10
- Можно менять на лету: да
Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
ошибок сети.
## client_eio_retry_interval
- Тип: миллисекунды
- Значение по умолчанию: 1000
- Можно менять на лету: да
Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
или незавершённых удалений EC-объектов (состояния PG has_incomplete).
0 отключает повторы таких запросов и клиенты не блокируются, а вместо
этого просто получают код ошибки EIO.
## client_max_dirty_bytes
@@ -127,34 +101,3 @@
- Можно менять на лету: да
Максимальное число параллельных операций записи при сбросе буферов на сервер.
## nbd_timeout
- Тип: секунды
- Значение по умолчанию: 300
Таймаут для операций чтения/записи через [NBD](../usage/nbd.ru.md). Если
операция выполняется дольше таймаута, включая временную недоступность
кластера на время, большее таймаута, NBD-устройство отключится само собой
(и, возможно, сломает примонтированную ФС).
Вы можете установить таймаут в 0, чтобы никогда не отключать устройство по
таймауту, но в этом случае вы вообще не сможете удалить устройство, если
процесс NBD умрёт - вам придётся перезагружать сервер.
## nbd_max_devices
- Тип: целое число
- Значение по умолчанию: 64
Максимальное число NBD-устройств в системе. Данное значение передаётся
модулю ядра nbd как параметр `nbds_max`, когда его загружает vitastor-nbd.
## nbd_max_part
- Тип: целое число
- Значение по умолчанию: 3
Максимальное число разделов на одном NBD-устройстве. Данное значение передаётся
модулю ядра nbd как параметр `max_part`, когда его загружает vitastor-nbd.
Имейте в виду, что (nbds_max)*(1+max_part) обычно не может превышать 256.
+2 -2
View File
@@ -19,8 +19,8 @@ These parameters only apply to Monitors.
## etcd_mon_ttl
- Type: seconds
- Default: 1
- Minimum: 5
- Default: 30
- Minimum: 10
Monitor etcd lease refresh interval in seconds
+2 -2
View File
@@ -19,8 +19,8 @@
## etcd_mon_ttl
- Тип: секунды
- Значение по умолчанию: 1
- Минимальное значение: 5
- Значение по умолчанию: 30
- Минимальное значение: 10
Интервал обновления etcd резервации (lease) монитором
+12
View File
@@ -25,6 +25,7 @@ between clients, OSDs and etcd.
- [peer_connect_timeout](#peer_connect_timeout)
- [osd_idle_timeout](#osd_idle_timeout)
- [osd_ping_timeout](#osd_ping_timeout)
- [up_wait_retry_interval](#up_wait_retry_interval)
- [max_etcd_attempts](#max_etcd_attempts)
- [etcd_quick_timeout](#etcd_quick_timeout)
- [etcd_slow_timeout](#etcd_slow_timeout)
@@ -211,6 +212,17 @@ Maximum time to wait for OSD keepalive responses. If an OSD doesn't respond
within this time, the connection to it is dropped and a reconnection attempt
is scheduled.
## up_wait_retry_interval
- Type: milliseconds
- Default: 500
- Minimum: 50
- Can be changed online: yes
OSDs respond to clients with a special error code when they receive I/O
requests for a PG that's not synchronized and started. This parameter sets
the time for the clients to wait before re-attempting such I/O requests.
## max_etcd_attempts
- Type: integer
+14
View File
@@ -25,6 +25,7 @@
- [peer_connect_timeout](#peer_connect_timeout)
- [osd_idle_timeout](#osd_idle_timeout)
- [osd_ping_timeout](#osd_ping_timeout)
- [up_wait_retry_interval](#up_wait_retry_interval)
- [max_etcd_attempts](#max_etcd_attempts)
- [etcd_quick_timeout](#etcd_quick_timeout)
- [etcd_slow_timeout](#etcd_slow_timeout)
@@ -220,6 +221,19 @@ OSD в любом случае согласовывают реальное зн
Если OSD не отвечает за это время, соединение отключается и производится
повторная попытка соединения.
## up_wait_retry_interval
- Тип: миллисекунды
- Значение по умолчанию: 500
- Минимальное значение: 50
- Можно менять на лету: да
Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
они отвечают клиентам специальным кодом ошибки, означающим, что клиент
должен некоторое время подождать перед повторением запроса. Именно это время
ожидания задаёт данный параметр.
## max_etcd_attempts
- Тип: целое число
+4 -112
View File
@@ -19,7 +19,6 @@ them, even without restarting by updating configuration in etcd.
- [autosync_interval](#autosync_interval)
- [autosync_writes](#autosync_writes)
- [recovery_queue_depth](#recovery_queue_depth)
- [recovery_sleep_us](#recovery_sleep_us)
- [recovery_pg_switch](#recovery_pg_switch)
- [recovery_sync_batch](#recovery_sync_batch)
- [readonly](#readonly)
@@ -52,14 +51,6 @@ them, even without restarting by updating configuration in etcd.
- [scrub_list_limit](#scrub_list_limit)
- [scrub_find_best](#scrub_find_best)
- [scrub_ec_max_bruteforce](#scrub_ec_max_bruteforce)
- [recovery_tune_interval](#recovery_tune_interval)
- [recovery_tune_util_low](#recovery_tune_util_low)
- [recovery_tune_util_high](#recovery_tune_util_high)
- [recovery_tune_client_util_low](#recovery_tune_client_util_low)
- [recovery_tune_client_util_high](#recovery_tune_client_util_high)
- [recovery_tune_agg_interval](#recovery_tune_agg_interval)
- [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
- [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)
## etcd_report_interval
@@ -144,24 +135,12 @@ operations before issuing an fsync operation internally.
## recovery_queue_depth
- Type: integer
- Default: 1
- Default: 4
- Can be changed online: yes
Maximum recovery and rebalance operations initiated by each OSD in parallel.
Note that each OSD talks to a lot of other OSDs so actual number of parallel
recovery operations per each OSD is greater than just recovery_queue_depth.
Increasing this parameter can speedup recovery if [auto-tuning](#recovery_tune_interval)
allows it or if it is disabled.
## recovery_sleep_us
- Type: microseconds
- Default: 0
- Can be changed online: yes
Delay for all recovery- and rebalance- related operations. If non-zero,
such operations are artificially slowed down to reduce the impact on
client I/O.
Maximum recovery operations per one primary OSD at any given moment of time.
Currently it's the only parameter available to tune the speed or recovery
and rebalancing, but it's planned to implement more.
## recovery_pg_switch
@@ -529,90 +508,3 @@ the variant with most available equal copies is correct. For example, if
you have 3 replicas and 1 of them differs, this one is considered to be
corrupted. But if there is no "best" version with more copies than all
others have then the object is also marked as inconsistent.
## recovery_tune_interval
- Type: seconds
- Default: 1
- Can be changed online: yes
Interval at which OSD re-considers client and recovery load and automatically
adjusts [recovery_sleep_us](#recovery_sleep_us). Recovery auto-tuning is
disabled if recovery_tune_interval is set to 0.
Auto-tuning targets utilization. Utilization is a measure of load and is
equal to the product of iops and average latency (so it may be greater
than 1). You set "low" and "high" client utilization thresholds and two
corresponding target recovery utilization levels. OSD calculates desired
recovery utilization from client utilization using linear interpolation
and auto-tunes recovery operation delay to make actual recovery utilization
match desired.
This allows to reduce recovery/rebalance impact on client operations. It is
of course impossible to remove it completely, but it should become adequate.
In some tests rebalance could earlier drop client write speed from 1.5 GB/s
to 50-100 MB/s, with default auto-tuning settings it now only reduces
to ~1 GB/s.
## recovery_tune_util_low
- Type: number
- Default: 0.1
- Can be changed online: yes
Desired recovery/rebalance utilization when client load is high, i.e. when
it is at or above recovery_tune_client_util_high.
## recovery_tune_util_high
- Type: number
- Default: 1
- Can be changed online: yes
Desired recovery/rebalance utilization when client load is low, i.e. when
it is at or below recovery_tune_client_util_low.
## recovery_tune_client_util_low
- Type: number
- Default: 0
- Can be changed online: yes
Client utilization considered "low".
## recovery_tune_client_util_high
- Type: number
- Default: 0.5
- Can be changed online: yes
Client utilization considered "high".
## recovery_tune_agg_interval
- Type: integer
- Default: 10
- Can be changed online: yes
The number of last auto-tuning iterations to use for calculating the
delay as average. Lower values result in quicker response to client
load change, higher values result in more stable delay. Default value of 10
is usually fine.
## recovery_tune_sleep_min_us
- Type: microseconds
- Default: 10
- Can be changed online: yes
Minimum possible value for auto-tuned recovery_sleep_us. Lower values
are changed to 0.
## recovery_tune_sleep_cutoff_us
- Type: microseconds
- Default: 10000000
- Can be changed online: yes
Maximum possible value for auto-tuned recovery_sleep_us. Higher values
are treated as outliers and ignored in aggregation.
+5 -116
View File
@@ -20,7 +20,6 @@
- [autosync_interval](#autosync_interval)
- [autosync_writes](#autosync_writes)
- [recovery_queue_depth](#recovery_queue_depth)
- [recovery_sleep_us](#recovery_sleep_us)
- [recovery_pg_switch](#recovery_pg_switch)
- [recovery_sync_batch](#recovery_sync_batch)
- [readonly](#readonly)
@@ -53,14 +52,6 @@
- [scrub_list_limit](#scrub_list_limit)
- [scrub_find_best](#scrub_find_best)
- [scrub_ec_max_bruteforce](#scrub_ec_max_bruteforce)
- [recovery_tune_interval](#recovery_tune_interval)
- [recovery_tune_util_low](#recovery_tune_util_low)
- [recovery_tune_util_high](#recovery_tune_util_high)
- [recovery_tune_client_util_low](#recovery_tune_client_util_low)
- [recovery_tune_client_util_high](#recovery_tune_client_util_high)
- [recovery_tune_agg_interval](#recovery_tune_agg_interval)
- [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
- [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)
## etcd_report_interval
@@ -147,25 +138,13 @@ OSD, чтобы успевать очищать журнал - без них OSD
## recovery_queue_depth
- Тип: целое число
- Значение по умолчанию: 1
- Значение по умолчанию: 4
- Можно менять на лету: да
Максимальное число параллельных операций восстановления, инициируемых одним
OSD в любой момент времени. Имейте в виду, что каждый OSD обычно работает с
многими другими OSD, так что на практике параллелизм восстановления больше,
чем просто recovery_queue_depth. Увеличение значения этого параметра может
ускорить восстановление если [автотюнинг скорости](#recovery_tune_interval)
разрешает это или если он отключён.
## recovery_sleep_us
- Тип: микросекунды
- Значение по умолчанию: 0
- Можно менять на лету: да
Delay for all recovery- and rebalance- related operations. If non-zero,
such operations are artificially slowed down to reduce the impact on
client I/O.
Максимальное число операций восстановления на одном первичном OSD в любой
момент времени. На данный момент единственный параметр, который можно менять
для ускорения или замедления восстановления и перебалансировки данных, но
в планах реализация других параметров.
## recovery_pg_switch
@@ -556,93 +535,3 @@ EC (кодов коррекции ошибок) с более, чем 1 диск
считается некорректной. Однако, если "лучшую" версию с числом доступных
копий большим, чем у всех других версий, найти невозможно, то объект тоже
маркируется неконсистентным.
## recovery_tune_interval
- Тип: секунды
- Значение по умолчанию: 1
- Можно менять на лету: да
Интервал, с которым OSD пересматривает клиентскую нагрузку и нагрузку
восстановления и автоматически подстраивает [recovery_sleep_us](#recovery_sleep_us).
Автотюнинг (автоподстройка) отключается, если recovery_tune_interval
устанавливается в значение 0.
Автотюнинг регулирует утилизацию. Утилизация является мерой нагрузки
и равна произведению числа операций в секунду и средней задержки
(то есть, она может быть выше 1). Вы задаёте два уровня клиентской
утилизации - "низкий" и "высокий" (low и high) и два соответствующих
целевых уровня утилизации операциями восстановления. OSD рассчитывает
желаемый уровень утилизации восстановления линейной интерполяцией от
клиентской утилизации и подстраивает задержку операций восстановления
так, чтобы фактическая утилизация восстановления совпадала с желаемой.
Это позволяет снизить влияние восстановления и ребаланса на клиентские
операции. Конечно, невозможно исключить такое влияние полностью, но оно
должно становиться адекватнее. В некоторых тестах перебалансировка могла
снижать клиентскую скорость записи с 1.5 ГБ/с до 50-100 МБ/с, а теперь, с
настройками автотюнинга по умолчанию, она снижается только до ~1 ГБ/с.
## recovery_tune_util_low
- Тип: число
- Значение по умолчанию: 0.1
- Можно менять на лету: да
Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
высокая, то есть, находится на уровне или выше recovery_tune_client_util_high.
## recovery_tune_util_high
- Тип: число
- Значение по умолчанию: 1
- Можно менять на лету: да
Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
низкая, то есть, находится на уровне или ниже recovery_tune_client_util_low.
## recovery_tune_client_util_low
- Тип: число
- Значение по умолчанию: 0
- Можно менять на лету: да
Клиентская утилизация, которая считается "низкой".
## recovery_tune_client_util_high
- Тип: число
- Значение по умолчанию: 0.5
- Можно менять на лету: да
Клиентская утилизация, которая считается "высокой".
## recovery_tune_agg_interval
- Тип: целое число
- Значение по умолчанию: 10
- Можно менять на лету: да
Число последних итераций автоподстройки для расчёта задержки как среднего
значения. Меньшие значения параметра ускоряют отклик на изменение нагрузки,
большие значения делают задержку стабильнее. Значение по умолчанию 10
обычно нормальное и не требует изменений.
## recovery_tune_sleep_min_us
- Тип: микросекунды
- Значение по умолчанию: 10
- Можно менять на лету: да
Минимальное возможное значение авто-подстроенного recovery_sleep_us.
Меньшие значения заменяются на 0.
## recovery_tune_sleep_cutoff_us
- Тип: микросекунды
- Значение по умолчанию: 10000000
- Можно менять на лету: да
Максимальное возможное значение авто-подстроенного recovery_sleep_us.
Большие значения считаются случайными выбросами и игнорируются в
усреднении.
+2 -42
View File
@@ -41,7 +41,6 @@ Parameters:
- [osd_tags](#osd_tags)
- [primary_affinity_tags](#primary_affinity_tags)
- [scrub_interval](#scrub_interval)
- [used_for_fs](#used_for_fs)
Examples:
@@ -155,26 +154,6 @@ That is, if it becomes impossible to place PG data on at least (pg_minsize)
OSDs, PG is deactivated for both read and write. So you know that a fresh
write always goes to at least (pg_minsize) OSDs (disks).
For example, the difference between pg_minsize 2 and 1 in a 3-way replicated
pool (pg_size=3) is:
- If 2 hosts go down with pg_minsize=2, the pool becomes inactive and remains
inactive for [osd_out_time](monitor.en.md#osd_out_time) (10 minutes). After
this timeout, the monitor selects replacement hosts/OSDs and the pool comes
up and starts to heal. Therefore, if you don't have replacement OSDs, i.e.
if you only have 3 hosts with OSDs and 2 of them are down, the pool remains
inactive until you add or return at least 1 host (or change failure_domain
to "osd").
- If 2 hosts go down with pg_minsize=1, the pool only experiences a short
I/O pause until the monitor notices that OSDs are down (5-10 seconds with
the default [etcd_report_interval](osd.en.md#etcd_report_interval)). After
this pause, I/O resumes, but new data is temporarily written in only 1 copy.
Then, after osd_out_time, the monitor also selects replacement OSDs and the
pool starts to heal.
So, pg_minsize regulates the number of failures that a pool can tolerate
without temporary downtime for [osd_out_time](monitor.en.md#osd_out_time),
but at a cost of slightly reduced storage reliability.
FIXME: pg_minsize behaviour may be changed in the future to only make PGs
read-only instead of deactivating them.
@@ -186,8 +165,8 @@ read-only instead of deactivating them.
Number of PGs for this pool. The value should be big enough for the monitor /
LP solver to be able to optimize data placement.
"Enough" is usually around 10-100 PGs per OSD, i.e. you set pg_count for pool
to (total OSD count * 10 / pg_size). You can round it to the closest power of 2,
"Enough" is usually around 64-128 PGs per OSD, i.e. you set pg_count for pool
to (total OSD count * 100 / pg_size). You can round it to the closest power of 2,
because it makes it easier to reduce or increase PG count later by dividing or
multiplying it by 2.
@@ -300,25 +279,6 @@ of the OSDs containing a data chunk for a PG.
Automatic scrubbing interval for this pool. Overrides
[global scrub_interval setting](osd.en.md#scrub_interval).
## used_for_fs
- Type: string
If non-empty, the pool is marked as used for VitastorFS with metadata stored
in block image (regular Vitastor volume) named as the value of this pool parameter.
When a pool is marked as used for VitastorFS, regular block volume creation in it
is disabled (vitastor-cli refuses to create images without --force) to protect
the user from block volume and FS file ID collisions and data loss.
[vitastor-nfs](../usage/nfs.ru.md), in its turn, refuses to use pools not marked
for the corresponding FS when starting. This also implies that you can use one
pool only for one VitastorFS.
The second thing that is disabled for VitastorFS pools is reporting per-inode space
usage statistics in etcd because a FS pool may store a very large number of files
and statistics for them all would take a lot of space in etcd.
# Examples
## Replicated pool
+2 -44
View File
@@ -40,7 +40,6 @@
- [osd_tags](#osd_tags)
- [primary_affinity_tags](#primary_affinity_tags)
- [scrub_interval](#scrub_interval)
- [used_for_fs](#used_for_fs)
Примеры:
@@ -158,26 +157,6 @@
OSD, PG деактивируется на чтение и запись. Иными словами, всегда известно,
что новые блоки данных всегда записываются как минимум на pg_minsize дисков.
Для примера, разница между pg_minsize 2 и 1 в реплицированном пуле с 3 копиями
данных (pg_size=3), проявляется следующим образом:
- Если 2 сервера отключаются при pg_minsize=2, пул становится неактивным и
остаётся неактивным в течение [osd_out_time](monitor.en.md#osd_out_time)
(10 минут), после чего монитор назначает другие OSD/серверы на замену, пул
поднимается и начинает восстанавливать недостающие копии данных. Соответственно,
если OSD на замену нет - то есть, если у вас всего 3 сервера с OSD и 2 из них
недоступны - пул так и остаётся недоступным до тех пор, пока вы не вернёте
или не добавите хотя бы 1 сервер (или не переключите failure_domain на "osd").
- Если 2 сервера отключаются при pg_minsize=1, ввод-вывод лишь приостанавливается
на короткое время, до тех пор, пока монитор не поймёт, что OSD отключены
(что занимает 5-10 секунд при стандартном [etcd_report_interval](osd.en.md#etcd_report_interval)).
После этого ввод-вывод восстанавливается, но новые данные временно пишутся
всего в 1 копии. Когда же проходит osd_out_time, монитор точно так же назначает
другие OSD на замену выбывшим и пул начинает восстанавливать копии данных.
То есть, pg_minsize регулирует число отказов, которые пул может пережить без
временной остановки обслуживания на [osd_out_time](monitor.ru.md#osd_out_time),
но ценой немного пониженных гарантий надёжности.
FIXME: Поведение pg_minsize может быть изменено в будущем с полной деактивации
PG на перевод их в режим только для чтения.
@@ -189,8 +168,8 @@ PG на перевод их в режим только для чтения.
Число PG для данного пула. Число должно быть достаточно большим, чтобы монитор
мог равномерно распределить по ним данные.
Обычно это означает примерно 10-100 PG на 1 OSD, т.е. pg_count можно устанавливать
равным (общему числу OSD * 10 / pg_size). Значение можно округлить до ближайшей
Обычно это означает примерно 64-128 PG на 1 OSD, т.е. pg_count можно устанавливать
равным (общему числу OSD * 100 / pg_size). Значение можно округлить до ближайшей
степени 2, чтобы потом было легче уменьшать или увеличивать число PG, умножая
или деля его на 2.
@@ -307,27 +286,6 @@ OSD с "all".
Интервал скраба, то есть, автоматической фоновой проверки данных для данного пула.
Переопределяет [глобальную настройку scrub_interval](osd.ru.md#scrub_interval).
## used_for_fs
- Type: string
Если непусто, пул помечается как используемый для файловой системы VitastorFS с
метаданными, хранимыми в блочном образе Vitastor с именем, равным значению
этого параметра.
Когда пул помечается как используемый для VitastorFS, создание обычных блочных
образов в нём отключается (vitastor-cli отказывается создавать образы без --force),
чтобы защитить пользователя от коллизий ID файлов и блочных образов и, таким
образом, от потери данных.
[vitastor-nfs](../usage/nfs.ru.md), в свою очередь, при запуске отказывается
использовать для ФС пулы, не выделенные для неё. Это также означает, что один
пул может использоваться только для одной VitastorFS.
Также для ФС-пулов отключается передача статистики в etcd по отдельным инодам,
так как ФС-пул может содержать очень много файлов и статистика по ним всем
заняла бы очень много места в etcd.
# Примеры
## Реплицированный пул
+2 -2
View File
@@ -1,4 +1,4 @@
# Client Parameters
These parameters apply only to Vitastor clients (QEMU, fio, NBD and so on) and
affect their interaction with the cluster.
These parameters apply only to clients and affect their interaction with
the cluster.
+1 -1
View File
@@ -1,4 +1,4 @@
# Параметры клиентского кода
Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD и т.п.) и
Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD) и
затрагивают логику их работы с кластером.
-68
View File
@@ -1,27 +1,3 @@
- name: client_retry_interval
type: ms
min: 10
default: 50
online: true
info: |
Retry time for I/O requests failed due to inactive PGs or network
connectivity errors.
info_ru: |
Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
ошибок сети.
- name: client_eio_retry_interval
type: ms
default: 1000
online: true
info: |
Retry time for I/O requests failed due to data corruption or unfinished
EC object deletions (has_incomplete PG state). 0 disables such retries
and clients are not blocked and just get EIO error code instead.
info_ru: |
Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
или незавершённых удалений EC-объектов (состояния PG has_incomplete).
0 отключает повторы таких запросов и клиенты не блокируются, а вместо
этого просто получают код ошибки EIO.
- name: client_max_dirty_bytes
type: int
default: 33554432
@@ -146,47 +122,3 @@
Maximum number of parallel writes when flushing buffered data to the server.
info_ru: |
Максимальное число параллельных операций записи при сбросе буферов на сервер.
- name: nbd_timeout
type: sec
default: 300
online: false
info: |
Timeout for I/O operations for [NBD](../usage/nbd.en.md). If an operation
executes for longer than this timeout, including when your cluster is just
temporarily down for more than timeout, the NBD device will detach by itself
(and possibly break the mounted file system).
You can set timeout to 0 to never detach, but in that case you won't be
able to remove the kernel device at all if the NBD process dies - you'll have
to reboot the host.
info_ru: |
Таймаут для операций чтения/записи через [NBD](../usage/nbd.ru.md). Если
операция выполняется дольше таймаута, включая временную недоступность
кластера на время, большее таймаута, NBD-устройство отключится само собой
(и, возможно, сломает примонтированную ФС).
Вы можете установить таймаут в 0, чтобы никогда не отключать устройство по
таймауту, но в этом случае вы вообще не сможете удалить устройство, если
процесс NBD умрёт - вам придётся перезагружать сервер.
- name: nbd_max_devices
type: int
default: 64
online: false
info: |
Maximum number of NBD devices in the system. This value is passed as
`nbds_max` parameter for the nbd kernel module when vitastor-nbd autoloads it.
info_ru: |
Максимальное число NBD-устройств в системе. Данное значение передаётся
модулю ядра nbd как параметр `nbds_max`, когда его загружает vitastor-nbd.
- name: nbd_max_part
type: int
default: 3
online: false
info: |
Maximum number of partitions per NBD device. This value is passed as
`max_part` parameter for the nbd kernel module when vitastor-nbd autoloads it.
Note that (nbds_max)*(1+max_part) usually can't exceed 256.
info_ru: |
Максимальное число разделов на одном NBD-устройстве. Данное значение передаётся
модулю ядра nbd как параметр `max_part`, когда его загружает vitastor-nbd.
Имейте в виду, что (nbds_max)*(1+max_part) обычно не может превышать 256.
-2
View File
@@ -38,7 +38,6 @@ const types = {
bool: 'boolean',
int: 'integer',
sec: 'seconds',
float: 'number',
ms: 'milliseconds',
us: 'microseconds',
},
@@ -47,7 +46,6 @@ const types = {
bool: 'булево (да/нет)',
int: 'целое число',
sec: 'секунды',
float: 'число',
ms: 'миллисекунды',
us: 'микросекунды',
},
+2 -2
View File
@@ -1,7 +1,7 @@
- name: etcd_mon_ttl
type: sec
min: 5
default: 1
min: 10
default: 30
info: Monitor etcd lease refresh interval in seconds
info_ru: Интервал обновления etcd резервации (lease) монитором
- name: etcd_mon_timeout
+15
View File
@@ -243,6 +243,21 @@
Максимальное время ожидания ответа на запрос проверки состояния соединения.
Если OSD не отвечает за это время, соединение отключается и производится
повторная попытка соединения.
- name: up_wait_retry_interval
type: ms
min: 50
default: 500
online: true
info: |
OSDs respond to clients with a special error code when they receive I/O
requests for a PG that's not synchronized and started. This parameter sets
the time for the clients to wait before re-attempting such I/O requests.
info_ru: |
Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
они отвечают клиентам специальным кодом ошибки, означающим, что клиент
должен некоторое время подождать перед повторением запроса. Именно это время
ожидания задаёт данный параметр.
- name: max_etcd_attempts
type: int
default: 5
+8 -129
View File
@@ -107,29 +107,17 @@
принудительной отправкой fsync-а.
- name: recovery_queue_depth
type: int
default: 1
default: 4
online: true
info: |
Maximum recovery and rebalance operations initiated by each OSD in parallel.
Note that each OSD talks to a lot of other OSDs so actual number of parallel
recovery operations per each OSD is greater than just recovery_queue_depth.
Increasing this parameter can speedup recovery if [auto-tuning](#recovery_tune_interval)
allows it or if it is disabled.
Maximum recovery operations per one primary OSD at any given moment of time.
Currently it's the only parameter available to tune the speed or recovery
and rebalancing, but it's planned to implement more.
info_ru: |
Максимальное число параллельных операций восстановления, инициируемых одним
OSD в любой момент времени. Имейте в виду, что каждый OSD обычно работает с
многими другими OSD, так что на практике параллелизм восстановления больше,
чем просто recovery_queue_depth. Увеличение значения этого параметра может
ускорить восстановление если [автотюнинг скорости](#recovery_tune_interval)
разрешает это или если он отключён.
- name: recovery_sleep_us
type: us
default: 0
online: true
info: |
Delay for all recovery- and rebalance- related operations. If non-zero,
such operations are artificially slowed down to reduce the impact on
client I/O.
Максимальное число операций восстановления на одном первичном OSD в любой
момент времени. На данный момент единственный параметр, который можно менять
для ускорения или замедления восстановления и перебалансировки данных, но
в планах реализация других параметров.
- name: recovery_pg_switch
type: int
default: 128
@@ -638,112 +626,3 @@
считается некорректной. Однако, если "лучшую" версию с числом доступных
копий большим, чем у всех других версий, найти невозможно, то объект тоже
маркируется неконсистентным.
- name: recovery_tune_interval
type: sec
default: 1
online: true
info: |
Interval at which OSD re-considers client and recovery load and automatically
adjusts [recovery_sleep_us](#recovery_sleep_us). Recovery auto-tuning is
disabled if recovery_tune_interval is set to 0.
Auto-tuning targets utilization. Utilization is a measure of load and is
equal to the product of iops and average latency (so it may be greater
than 1). You set "low" and "high" client utilization thresholds and two
corresponding target recovery utilization levels. OSD calculates desired
recovery utilization from client utilization using linear interpolation
and auto-tunes recovery operation delay to make actual recovery utilization
match desired.
This allows to reduce recovery/rebalance impact on client operations. It is
of course impossible to remove it completely, but it should become adequate.
In some tests rebalance could earlier drop client write speed from 1.5 GB/s
to 50-100 MB/s, with default auto-tuning settings it now only reduces
to ~1 GB/s.
info_ru: |
Интервал, с которым OSD пересматривает клиентскую нагрузку и нагрузку
восстановления и автоматически подстраивает [recovery_sleep_us](#recovery_sleep_us).
Автотюнинг (автоподстройка) отключается, если recovery_tune_interval
устанавливается в значение 0.
Автотюнинг регулирует утилизацию. Утилизация является мерой нагрузки
и равна произведению числа операций в секунду и средней задержки
(то есть, она может быть выше 1). Вы задаёте два уровня клиентской
утилизации - "низкий" и "высокий" (low и high) и два соответствующих
целевых уровня утилизации операциями восстановления. OSD рассчитывает
желаемый уровень утилизации восстановления линейной интерполяцией от
клиентской утилизации и подстраивает задержку операций восстановления
так, чтобы фактическая утилизация восстановления совпадала с желаемой.
Это позволяет снизить влияние восстановления и ребаланса на клиентские
операции. Конечно, невозможно исключить такое влияние полностью, но оно
должно становиться адекватнее. В некоторых тестах перебалансировка могла
снижать клиентскую скорость записи с 1.5 ГБ/с до 50-100 МБ/с, а теперь, с
настройками автотюнинга по умолчанию, она снижается только до ~1 ГБ/с.
- name: recovery_tune_util_low
type: float
default: 0.1
online: true
info: |
Desired recovery/rebalance utilization when client load is high, i.e. when
it is at or above recovery_tune_client_util_high.
info_ru: |
Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
высокая, то есть, находится на уровне или выше recovery_tune_client_util_high.
- name: recovery_tune_util_high
type: float
default: 1
online: true
info: |
Desired recovery/rebalance utilization when client load is low, i.e. when
it is at or below recovery_tune_client_util_low.
info_ru: |
Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
низкая, то есть, находится на уровне или ниже recovery_tune_client_util_low.
- name: recovery_tune_client_util_low
type: float
default: 0
online: true
info: Client utilization considered "low".
info_ru: Клиентская утилизация, которая считается "низкой".
- name: recovery_tune_client_util_high
type: float
default: 0.5
online: true
info: Client utilization considered "high".
info_ru: Клиентская утилизация, которая считается "высокой".
- name: recovery_tune_agg_interval
type: int
default: 10
online: true
info: |
The number of last auto-tuning iterations to use for calculating the
delay as average. Lower values result in quicker response to client
load change, higher values result in more stable delay. Default value of 10
is usually fine.
info_ru: |
Число последних итераций автоподстройки для расчёта задержки как среднего
значения. Меньшие значения параметра ускоряют отклик на изменение нагрузки,
большие значения делают задержку стабильнее. Значение по умолчанию 10
обычно нормальное и не требует изменений.
- name: recovery_tune_sleep_min_us
type: us
default: 10
online: true
info: |
Minimum possible value for auto-tuned recovery_sleep_us. Lower values
are changed to 0.
info_ru: |
Минимальное возможное значение авто-подстроенного recovery_sleep_us.
Меньшие значения заменяются на 0.
- name: recovery_tune_sleep_cutoff_us
type: us
default: 10000000
online: true
info: |
Maximum possible value for auto-tuned recovery_sleep_us. Higher values
are treated as outliers and ignored in aggregation.
info_ru: |
Максимальное возможное значение авто-подстроенного recovery_sleep_us.
Большие значения считаются случайными выбросами и игнорируются в
усреднении.
-12
View File
@@ -19,14 +19,6 @@ for i in ./???-*.yaml; do kubectl apply -f $i; done
After that you'll be able to create PersistentVolumes.
**Important:** For best experience, use Linux kernel at least 5.15 with [VDUSE](../usage/qemu.en.md#vduse)
kernel modules enabled (vdpa, vduse, virtio-vdpa). If your distribution doesn't
have them pre-built - build them yourself ([instructions](../usage/qemu.en.md#vduse)),
I promise it's worth it :-). When VDUSE is unavailable, CSI driver uses [NBD](../usage/nbd.en.md)
to map Vitastor devices. NBD is slower and prone to timeout issues: if Vitastor
cluster becomes unresponsible for more than [nbd_timeout](../config/client.en.md#nbd_timeout),
the NBD device detaches and breaks pods using it.
## Features
Vitastor CSI supports:
@@ -35,9 +27,5 @@ Vitastor CSI supports:
- Raw block RWX (ReadWriteMany) volumes. Example: [PVC](../../csi/deploy/example-pvc-block.yaml), [pod](../../csi/deploy/example-test-pod-block.yaml)
- Volume expansion
- Volume snapshots. Example: [snapshot class](../../csi/deploy/example-snapshot-class.yaml), [snapshot](../../csi/deploy/example-snapshot.yaml), [clone](../../csi/deploy/example-snapshot-clone.yaml)
- [VDUSE](../usage/qemu.en.md#vduse) (preferred) and [NBD](../usage/nbd.en.md) device mapping methods
- Upgrades with VDUSE - new handler processes are restarted when CSI pods are restarted themselves
- VDUSE daemon auto-restart - handler processes are automatically restarted if they crash due to a bug in Vitastor client code
- Multiple clusters by using multiple configuration files in ConfigMap.
Remember that to use snapshots with CSI you also have to install [Snapshot Controller and CRDs](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).
-12
View File
@@ -19,14 +19,6 @@ for i in ./???-*.yaml; do kubectl apply -f $i; done
После этого вы сможете создавать PersistentVolume.
**Важно:** Лучше всего использовать ядро Linux версии не менее 5.15 с включёнными модулями
[VDUSE](../usage/qemu.ru.md#vduse) (vdpa, vduse, virtio-vdpa). Если в вашем дистрибутиве
они не собраны из коробки - соберите их сами, обещаю, что это стоит того ([инструкция](../usage/qemu.ru.md#vduse)) :-).
Когда VDUSE недоступно, CSI-плагин использует [NBD](../usage/nbd.ru.md) для подключения
дисков, а NBD медленнее и имеет проблему таймаута - если кластер остаётся недоступным
дольше, чем [nbd_timeout](../config/client.ru.md#nbd_timeout), NBD-устройство отключается
и ломает поды, использующие его.
## Возможности
CSI-плагин Vitastor поддерживает:
@@ -35,9 +27,5 @@ CSI-плагин Vitastor поддерживает:
- Сырые блочные RWX (ReadWriteMany) тома. Пример: [PVC](../../csi/deploy/example-pvc-block.yaml), [под](../../csi/deploy/example-test-pod-block.yaml)
- Расширение размера томов
- Снимки томов. Пример: [класс снимков](../../csi/deploy/example-snapshot-class.yaml), [снимок](../../csi/deploy/example-snapshot.yaml), [клон снимка](../../csi/deploy/example-snapshot-clone.yaml)
- Способы подключения устройств [VDUSE](../usage/qemu.ru.md#vduse) (предпочитаемый) и [NBD](../usage/nbd.ru.md)
- Обновление при использовании VDUSE - новые процессы-обработчики устройств успешно перезапускаются вместе с самими подами CSI
- Автоперезауск демонов VDUSE - процесс-обработчик автоматически перезапустится, если он внезапно упадёт из-за бага в коде клиента Vitastor
- Несколько кластеров через задание нескольких файлов конфигурации в ConfigMap.
Не забывайте, что для использования снимков нужно сначала установить [контроллер снимков и CRD](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).
+1 -1
View File
@@ -18,7 +18,7 @@
stable version from 0.9.x branch instead of 1.x
- For Debian 10 (Buster) also enable backports repository:
`deb http://deb.debian.org/debian buster-backports main`
- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
## CentOS
+1 -1
View File
@@ -18,7 +18,7 @@
установить последнюю стабильную версию из ветки 0.9.x вместо 1.x
- Для Debian 10 (Buster) также включите репозиторий backports:
`deb http://deb.debian.org/debian buster-backports main`
- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
## CentOS
+3 -3
View File
@@ -6,10 +6,10 @@
# Proxmox VE
To enable Vitastor support in Proxmox Virtual Environment (6.4-8.1 are supported):
To enable Vitastor support in Proxmox Virtual Environment (6.4-8.0 are supported):
- Add the corresponding Vitastor Debian repository into sources.list on Proxmox hosts:
bookworm for 8.1, pve8.0 for 8.0, bullseye for 7.4, pve7.3 for 7.3, pve7.2 for 7.2, pve7.1 for 7.1, buster for 6.4
bookworm for 8.0, bullseye for 7.4, pve7.3 for 7.3, pve7.2 for 7.2, pve7.1 for 7.1, buster for 6.4
- Install vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* or see note) packages from Vitastor repository
- Define storage in `/etc/pve/storage.cfg` (see below)
- Block network access from VMs to Vitastor network (to OSDs and etcd),
@@ -25,7 +25,7 @@ vitastor: vitastor
vitastor_pool testpool
# path to the configuration file
vitastor_config_path /etc/vitastor/vitastor.conf
# etcd address(es), OPTIONAL, required only if missing in the configuration file
# etcd address(es), required only if missing in the configuration file
vitastor_etcd_address 192.168.7.2:2379/v3
# prefix for keys in etcd
vitastor_etcd_prefix /vitastor
+3 -3
View File
@@ -6,10 +6,10 @@
# Proxmox VE
Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.1):
Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.0):
- Добавьте соответствующий Debian-репозиторий Vitastor в sources.list на хостах Proxmox:
bookworm для 8.1, pve8.0 для 8.0, bullseye для 7.4, pve7.3 для 7.3, pve7.2 для 7.2, pve7.1 для 7.1, buster для 6.4
bookworm для 8.0, bullseye для 7.4, pve7.3 для 7.3, pve7.2 для 7.2, pve7.1 для 7.1, buster для 6.4
- Установите пакеты vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* или см. сноску) из репозитория Vitastor
- Определите тип хранилища в `/etc/pve/storage.cfg` (см. ниже)
- Обязательно заблокируйте доступ от виртуальных машин к сети Vitastor (OSD и etcd), т.к. Vitastor (пока) не поддерживает аутентификацию
@@ -24,7 +24,7 @@ vitastor: vitastor
vitastor_pool testpool
# Путь к файлу конфигурации
vitastor_config_path /etc/vitastor/vitastor.conf
# Адрес(а) etcd, ОПЦИОНАЛЬНЫ, нужны, только если не указаны в vitastor.conf
# Адрес(а) etcd, нужны, только если не указаны в vitastor.conf
vitastor_etcd_address 192.168.7.2:2379/v3
# Префикс ключей метаданных в etcd
vitastor_etcd_prefix /vitastor
+1 -2
View File
@@ -54,8 +54,7 @@
виртуальные диски, их снимки и клоны.
- **Драйвер QEMU** — подключаемый модуль QEMU, позволяющий QEMU/KVM виртуальным машинам работать
с виртуальными дисками Vitastor напрямую из пространства пользователя с помощью клиентской
библиотеки, без необходимости отображения дисков в виде блочных устройств. Тот же драйвер
позволяет подключать диски в систему через [VDUSE](../usage/qemu.ru.md#vduse).
библиотеки, без необходимости отображения дисков в виде блочных устройств.
- **vitastor-nbd** — утилита, позволяющая монтировать образы Vitastor в виде блочных устройств
с помощью NBD (Network Block Device), на самом деле скорее работающего как "BUSE"
(Block Device In Userspace). Модуля ядра Linux для выполнения той же задачи в Vitastor нет
+2 -3
View File
@@ -32,8 +32,6 @@
- [Scrubbing](../config/osd.en.md#auto_scrub) (verification of copies)
- [Checksums](../config/layout-osd.en.md#data_csum_type)
- [Client write-back cache](../config/client.en.md#client_enable_writeback)
- [Intelligent recovery auto-tuning](../config/osd.en.md#recovery_tune_interval)
- [Clustered file system](../usage/nfs.en.md#vitastorfs)
## Plugins and tools
@@ -47,12 +45,13 @@
- [CSI plugin for Kubernetes](../installation/kubernetes.en.md)
- [OpenStack support: Cinder driver, Nova and libvirt patches](../installation/openstack.en.md)
- [Proxmox storage plugin and packages](../installation/proxmox.en.md)
- [Simplified NFS proxy for file-based image access emulation (suitable for VMWare)](../usage/nfs.en.md#pseudo-fs)
- [Simplified NFS proxy for file-based image access emulation (suitable for VMWare)](../usage/nfs.en.md)
## Roadmap
The following features are planned for the future:
- File system
- Control plane optimisation
- Other administrative tools
- Web GUI
+2 -3
View File
@@ -34,8 +34,6 @@
- [Фоновая проверка целостности](../config/osd.ru.md#auto_scrub) (сверка копий)
- [Контрольные суммы](../config/layout-osd.ru.md#data_csum_type)
- [Буферизация записи на стороне клиента](../config/client.ru.md#client_enable_writeback)
- [Интеллектуальная автоподстройка скорости восстановления](../config/osd.ru.md#recovery_tune_interval)
- [Кластерная файловая система](../usage/nfs.ru.md#vitastorfs)
## Драйверы и инструменты
@@ -49,10 +47,11 @@
- [CSI-плагин для Kubernetes](../installation/kubernetes.ru.md)
- [Базовая поддержка OpenStack: драйвер Cinder, патчи для Nova и libvirt](../installation/openstack.ru.md)
- [Плагин для Proxmox](../installation/proxmox.ru.md)
- [Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)](../usage/nfs.ru.md#псевдо-фс)
- [Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)](../usage/nfs.ru.md)
## Планы развития
- Файловая система
- Оптимизация слоя управления
- Другие инструменты администрирования
- Web-интерфейс
+5 -10
View File
@@ -14,7 +14,6 @@
- [Check cluster status](#check-cluster-status)
- [Create an image](#create-an-image)
- [Install plugins](#install-plugins)
- [Create VitastorFS](#create-vitastorfs)
## Preparation
@@ -76,16 +75,18 @@ On the monitor hosts:
## Create a pool
Create a pool using vitastor-cli:
Create pool configuration in etcd:
```
vitastor-cli create-pool testpool --pg_size 2 --pg_count 256
etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
"scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
```
For EC pools the configuration should look like the following:
```
vitastor-cli create-pool testpool --ec 2+2 --pg_count 256
etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
"scheme":"ec","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}}'
```
After you do this, one of the monitors will configure PGs and OSDs will start them.
@@ -115,9 +116,3 @@ After that, you can [run benchmarks](../usage/fio.en.md) or [start QEMU manually
- [Proxmox](../installation/proxmox.en.md)
- [OpenStack](../installation/openstack.en.md)
- [Kubernetes CSI](../installation/kubernetes.en.md)
## Create VitastorFS
If you want to use clustered file system in addition to VM or container images:
- [Follow the instructions here](../usage/nfs.en.md#vitastorfs)
+5 -11
View File
@@ -14,7 +14,6 @@
- [Проверьте состояние кластера](#проверьте-состояние-кластера)
- [Создайте образ](#создайте-образ)
- [Установите плагины](#установите-плагины)
- [Создайте VitastorFS](#создайте-vitastorfs)
## Подготовка
@@ -78,16 +77,18 @@
## Создайте пул
Создайте пул с помощью vitastor-cli:
Создайте конфигурацию пула с помощью etcdctl:
```
vitastor-cli create-pool testpool --pg_size 2 --pg_count 256
etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
"scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
```
Для пулов с кодами коррекции ошибок конфигурация должна выглядеть примерно так:
```
vitastor-cli create-pool testpool --ec 2+2 --pg_count 256
etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
"scheme":"ec","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}}'
```
После этого один из мониторов должен сконфигурировать PG, а OSD должны запустить их.
@@ -117,10 +118,3 @@ vitastor-cli create -s 10G testimg
- [Proxmox](../installation/proxmox.ru.md)
- [OpenStack](../installation/openstack.ru.md)
- [Kubernetes CSI](../installation/kubernetes.ru.md)
## Создайте VitastorFS
Если вы хотите использовать не только блочные образы виртуальных машин или контейнеров,
а также кластерную файловую систему, то:
- [Следуйте инструкциям](../usage/nfs.en.md#vitastorfs)
+7 -14
View File
@@ -11,26 +11,19 @@ Replicated setups:
- Single-threaded write+fsync latency:
- With immediate commit: 2 network roundtrips + 1 disk write.
- With lazy commit: 4 network roundtrips + 1 disk write + 1 disk flush.
- Linear read: `min(total network bandwidth, sum(disk read MB/s))`.
- Linear write: `min(total network bandwidth, sum(disk write MB/s / number of replicas))`.
- Saturated parallel read iops: `min(total network bandwidth, sum(disk read iops))`.
- Saturated parallel write iops: `min(total network bandwidth / number of replicas, sum(disk write iops / number of replicas / (write amplification = 4)))`.
- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
- Saturated parallel write iops: min(network bandwidth, sum(disk write iops / number of replicas / write amplification)).
EC/XOR setups (EC N+K):
EC/XOR setups:
- Single-threaded (T1Q1) read latency: 1.5 network roundtrips + 1 disk read.
- Single-threaded write+fsync latency:
- With immediate commit: 3.5 network roundtrips + 1 disk read + 2 disk writes.
- With lazy commit: 5.5 network roundtrips + 1 disk read + 2 disk writes + 2 disk fsyncs.
- 0.5 in actually `(N-1)/N` which means that an additional roundtrip doesn't happen when
- 0.5 in actually (k-1)/k which means that an additional roundtrip doesn't happen when
the read sub-operation can be served locally.
- Linear read: `min(total network bandwidth, sum(disk read MB/s))`.
- Linear write: `min(total network bandwidth, sum(disk write MB/s * N/(N+K)))`.
- Saturated parallel read iops: `min(total network bandwidth, sum(disk read iops))`.
- Saturated parallel write iops: roughly `total iops / (N+K) / WA`. More exactly,
`min(total network bandwidth * N/(N+K), sum(disk randrw iops / (N*4 + K*5 + 1)))` with
random read/write mix corresponding to `(N-1)/(N*4 + K*5 + 1)*100 % reads`.
- For example, with EC 2+1 it is: `(7% randrw iops) / 14`.
- With EC 6+3 it is: `(12.5% randrw iops) / 40`.
- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
- Saturated parallel write iops: min(network bandwidth, sum(disk write iops * number of data drives / (number of data + parity drives) / write amplification)).
In fact, you should put disk write iops under the condition of ~10% reads / ~90% writes in this formula.
Write amplification for 4 KB blocks is usually 3-5 in Vitastor:
1. Journal block write
+7 -14
View File
@@ -11,27 +11,20 @@
- Запись+fsync в 1 поток:
- С мгновенным сбросом: 2 RTT + 1 запись.
- С отложенным ("ленивым") сбросом: 4 RTT + 1 запись + 1 fsync.
- Линейное чтение: сумма МБ/с чтения всех дисков, либо общая производительность сети (сумма пропускной способности сети всех нод), если в сеть упрётся раньше.
- Линейная запись: сумма МБ/с записи всех дисков / число реплик, либо производительность сети / число реплик, если в сеть упрётся раньше.
- Параллельное случайное мелкое чтение: сумма IOPS чтения всех дисков, либо производительность сети, если в сеть упрётся раньше.
- Параллельная случайная мелкая запись: сумма IOPS записи всех дисков / число реплик / WA, либо производительность сети / число реплик, если в сеть упрётся раньше.
- Параллельное чтение: сумма IOPS всех дисков либо производительность сети, если в сеть упрётся раньше.
- Параллельная запись: сумма IOPS всех дисков / число реплик / WA либо производительность сети, если в сеть упрётся раньше.
При использовании кодов коррекции ошибок (EC N+K):
При использовании кодов коррекции ошибок (EC):
- Задержка чтения в 1 поток (T1Q1): 1.5 RTT + 1 чтение.
- Запись+fsync в 1 поток:
- С мгновенным сбросом: 3.5 RTT + 1 чтение + 2 записи.
- С отложенным ("ленивым") сбросом: 5.5 RTT + 1 чтение + 2 записи + 2 fsync.
- Под 0.5 на самом деле подразумевается (N-1)/N, где N - число дисков данных,
- Под 0.5 на самом деле подразумевается (k-1)/k, где k - число дисков данных,
что означает, что дополнительное обращение по сети не нужно, когда операция
чтения обслуживается локально.
- Линейное чтение: сумма МБ/с чтения всех дисков, либо общая производительность сети, если в сеть упрётся раньше.
- Линейная запись: сумма МБ/с записи всех дисков * N/(N+K), либо производительность сети * N / (N+K), если в сеть упрётся раньше.
- Параллельное случайное мелкое чтение: сумма IOPS чтения всех дисков либо производительность сети, если в сеть упрётся раньше.
- Параллельная случайная мелкая запись: грубо `(сумма IOPS / (N+K) / WA)`. Если точнее, то:
сумма смешанного IOPS всех дисков при `(N-1)/(N*4 + K*5 + 1)*100 %` чтения, делённая на `(N*4 + K*5 + 1)`.
Либо, производительность сети * N/(N+K), если в сеть упрётся раньше.
- Например, при EC 2+1 это: `(сумма IOPS при 7% чтения) / 14`.
- При EC 6+3 это: `(сумма IOPS при 12.5% чтения) / 40`.
- Параллельное чтение: сумма IOPS всех дисков либо производительность сети, если в сеть упрётся раньше.
- Параллельная запись: сумма IOPS всех дисков / общее число дисков данных и чётности / WA либо производительность сети, если в сеть упрётся раньше.
Примечание: IOPS дисков в данном случае надо брать в смешанном режиме чтения/записи в пропорции, аналогичной формулам выше.
WA (мультипликатор записи) для 4 КБ блоков в Vitastor обычно составляет 3-5:
1. Запись метаданных в журнал
+6 -102
View File
@@ -24,16 +24,11 @@ It supports the following commands:
- [fix](#fix)
- [alloc-osd](#alloc-osd)
- [rm-osd](#rm-osd)
- [create-pool](#create-pool)
- [modify-pool](#modify-pool)
- [ls-pools](#ls-pools)
- [rm-pool](#rm-pool)
Global options:
```
--config_file FILE Path to Vitastor configuration file
--etcd_address URL Etcd connection address
--etcd_address ADDR Etcd connection address
--iodepth N Send N operations in parallel to each OSD when possible (default 32)
--parallel_osds M Work with M osds in parallel when possible (default 4)
--progress 1|0 Report progress (default 1)
@@ -135,18 +130,19 @@ See also about [how to export snapshots](qemu.en.md#exporting-snapshots).
## modify
`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
Rename, resize image or change its readonly status. Images with children can't be made read-write.
If the new size is smaller than the old size, extra data will be purged.
You should resize file system in the image, if present, before shrinking it.
* `-f|--force` - Proceed with shrinking or setting readwrite flag even if the image has children.
* `--down-ok` - Proceed with shrinking even if some data will be left on unavailable OSDs.
```
-f|--force Proceed with shrinking or setting readwrite flag even if the image has children.
```
## rm
`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
`vitastor-cli rm <from> [<to>] [--writers-stopped]`
Remove `<from>` or all layers between `<from>` and `<to>` (`<to>` must be a child of `<from>`),
rebasing all their children accordingly. --writers-stopped allows merging to be a bit
@@ -154,10 +150,6 @@ more effective in case of a single 'slim' read-write child and 'fat' removed par
the child is merged into parent and parent is renamed to child in that case.
In other cases parent layers are always merged into children.
Other options:
* `--down-ok` - Continue deletion/merging even if some data will be left on unavailable OSDs.
## flatten
`vitastor-cli flatten <layer>`
@@ -245,91 +237,3 @@ Refuses to remove OSDs with data without `--force` and `--allow-data-loss`.
With `--dry-run` only checks if deletion is possible without data loss and
redundancy degradation.
## create-pool
`vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]`
Create a pool. Required parameters:
| <!-- --> | <!-- --> |
|--------------------------|---------------------------------------------------------------------------------------|
| `-s R` or `--pg_size R` | Number of replicas for replicated pools |
| `--ec N+K` | Number of data (N) and parity (K) chunks for erasure-coded pools |
| `-n N` or `--pg_count N` | PG count for the new pool (start with 10*<OSD count>/pg_size rounded to a power of 2) |
Optional parameters:
| <!-- --> | <!-- --> |
|--------------------------------|----------------------------------------------------------------------------|
| `--pg_minsize <number>` | R or N+K minus number of failures to tolerate without downtime ([details](../config/pool.en.md#pg_minsize)) |
| `--failure_domain host` | Failure domain: host, osd or a level from placement_levels. Default: host |
| `--root_node <node>` | Put pool only on child OSDs of this placement tree node |
| `--osd_tags <tag>[,<tag>]...` | Put pool only on OSDs tagged with all specified tags |
| `--block_size 128k` | Put pool only on OSDs with this data block size |
| `--bitmap_granularity 4k` | Put pool only on OSDs with this logical sector size |
| `--immediate_commit none` | Put pool only on OSDs with this or larger immediate_commit (none < small < all) |
| `--primary_affinity_tags tags` | Prefer to put primary copies on OSDs with all specified tags |
| `--scrub_interval <time>` | Enable regular scrubbing for this pool. Format: number + unit s/m/h/d/M/y |
| `--used_for_fs <name>` | Mark pool as used for VitastorFS with metadata in image <name> |
| `--pg_stripe_size <number>` | Increase object grouping stripe |
| `--max_osd_combinations 10000` | Maximum number of random combinations for LP solver input |
| `--wait` | Wait for the new pool to come online |
| `-f` or `--force` | Do not check that cluster has enough OSDs to create the pool |
See also [Pool configuration](../config/pool.en.md) for detailed parameter descriptions.
Examples:
`vitastor-cli create-pool test_x4 -s 4 -n 32`
`vitastor-cli create-pool test_ec42 --ec 4+2 -n 32`
## modify-pool
`vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]`
Modify an existing pool. Modifiable parameters:
```
[-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]
[--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>] [--no_inode_stats 0|1]
[--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]
```
Non-modifiable parameters (changing them WILL lead to data loss):
```
[--block_size <size>] [--bitmap_granularity <size>]
[--immediate_commit <all|small|none>] [--pg_stripe_size <size>]
```
These, however, can still be modified with -f|--force.
See [create-pool](#create-pool) for parameter descriptions.
Examples:
`vitastor-cli modify-pool pool_A --name pool_B`
`vitastor-cli modify-pool 2 --pg_size 4 -n 128`
## rm-pool
`vitastor-cli rm-pool|pool-rm [--force] <id|name>`
Remove a pool. Refuses to remove pools with images without `--force`.
## ls-pools
`vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]`
List pools (only matching <glob> patterns if passed).
| <!-- --> | <!-- --> |
|----------------------|-------------------------------------------------------|
| `-l` or `--long` | Also report I/O statistics |
| `--detail` | Use list format (not table), show all details |
| `--sort FIELD` | Sort by specified field (see fields in --json output) |
| `-r` or `--reverse` | Sort in descending order |
| `-n` or `--count N` | Only list first N items |
+8 -104
View File
@@ -23,16 +23,11 @@ vitastor-cli - интерфейс командной строки для адм
- [merge-data](#merge-data)
- [alloc-osd](#alloc-osd)
- [rm-osd](#rm-osd)
- [create-pool](#create-pool)
- [modify-pool](#modify-pool)
- [ls-pools](#ls-pools)
- [rm-pool](#rm-pool)
Глобальные опции:
```
--config_file FILE Путь к файлу конфигурации Vitastor
--etcd_address URL Адрес соединения с etcd
--etcd_address ADDR Адрес соединения с etcd
--iodepth N Отправлять параллельно N операций на каждый OSD (по умолчанию 32)
--parallel_osds M Работать параллельно с M OSD (по умолчанию 4)
--progress 1|0 Печатать прогресс выполнения (по умолчанию 1)
@@ -89,8 +84,8 @@ kaveri 2/1 32 0 B 10 G 0 B 100% 0%
`vitastor-cli ls [-l] [-p POOL] [--sort FIELD] [-r] [-n N] [<glob> ...]`
Показать список образов, если передан(ы) шаблон(ы) `<glob>`, то только с именами,
соответствующими одному из шаблонов (стандартные ФС-шаблоны с * и ?).
Показать список образов, если переданы шаблоны `<glob>`, то только с именами,
соответствующими этим шаблонам (стандартные ФС-шаблоны с * и ?).
Опции:
@@ -136,7 +131,7 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
## modify
`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
Изменить размер, имя образа или флаг "только для чтения". Снимать флаг "только для чтения"
и уменьшать размер образов, у которых есть дочерние клоны, без `--force` нельзя.
@@ -144,12 +139,13 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
Если новый размер меньше старого, "лишние" данные будут удалены, поэтому перед уменьшением
образа сначала уменьшите файловую систему в нём.
* `-f|--force` - Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
* `--down-ok` - Разрешить уменьшение, даже если часть данных останется неудалённой на недоступных OSD.
```
-f|--force Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
```
## rm
`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
`vitastor-cli rm <from> [<to>] [--writers-stopped]`
Удалить образ `<from>` или все слои от `<from>` до `<to>` (`<to>` должен быть дочерним
образом `<from>`), одновременно меняя родительские образы их клонов (если таковые есть).
@@ -161,10 +157,6 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
В других случаях родительские слои вливаются в дочерние.
Другие опции:
* `--down-ok` - Продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD.
## flatten
`vitastor-cli flatten <layer>`
@@ -262,91 +254,3 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
С опцией `--dry-run` только проверяет, возможно ли удаление без потери данных и деградации
избыточности.
## create-pool
`vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]`
Создать пул. Обязательные параметры:
| <!-- --> | <!-- --> |
|---------------------------|---------------------------------------------------------------------------------------------|
| `-s R` или `--pg_size R` | Число копий данных для реплицированных пулов |
| `--ec N+K` | Число частей данных (N) и чётности (K) для пулов с кодами коррекции ошибок |
| `-n N` или `--pg_count N` | Число PG для нового пула (начните с 10*<число OSD>/pg_size, округлённого до степени двойки) |
Необязательные параметры:
| <!-- --> | <!-- --> |
|--------------------------------|----------------------------------------------------------------------------|
| `--pg_minsize <number>` | (R или N+K) минус число разрешённых отказов без остановки пула ([подробнее](../config/pool.ru.md#pg_minsize)) |
| `--failure_domain host` | Домен отказа: host, osd или другой из placement_levels. По умолчанию: host |
| `--root_node <node>` | Использовать для пула только дочерние OSD этого узла дерева размещения |
| `--osd_tags <tag>[,<tag>]...` | ...только OSD со всеми заданными тегами |
| `--block_size 128k` | ...только OSD с данным размером блока |
| `--bitmap_granularity 4k` | ...только OSD с данным размером логического сектора |
| `--immediate_commit none` | ...только OSD с этим или большим immediate_commit (none < small < all) |
| `--primary_affinity_tags tags` | Предпочитать OSD со всеми данными тегами для роли первичных |
| `--scrub_interval <time>` | Включить скрабы с заданным интервалом времени (число + единица s/m/h/d/M/y) |
| `--pg_stripe_size <number>` | Увеличить блок группировки объектов по PG |
| `--max_osd_combinations 10000` | Максимальное число случайных комбинаций OSD для ЛП-солвера |
| `--wait` | Подождать, пока новый пул будет активирован |
| `-f` или `--force` | Не проверять, что в кластере достаточно доменов отказа для создания пула |
Подробно о параметрах см. [Конфигурация пулов](../config/pool.ru.md).
Примеры:
`vitastor-cli create-pool test_x4 -s 4 -n 32`
`vitastor-cli create-pool test_ec42 --ec 4+2 -n 32`
## modify-pool
`vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]`
Изменить настройки существующего пула. Изменяемые параметры:
```
[-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]
[--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>]
[--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]
```
Неизменяемые параметры (их изменение ПРИВЕДЁТ к потере данных):
```
[--block_size <size>] [--bitmap_granularity <size>]
[--immediate_commit <all|small|none>] [--pg_stripe_size <size>]
```
Эти параметры можно изменить, только если явно передать опцию -f или --force.
Описания параметров смотрите в [create-pool](#create-pool).
Примеры:
`vitastor-cli modify-pool pool_A --name pool_B`
`vitastor-cli modify-pool 2 --pg_size 4 -n 128`
## rm-pool
`vitastor-cli rm-pool|pool-rm [--force] <id|name>`
Удалить пул. Отказывается удалять пул, в котором ещё есть образы, без `--force`.
## ls-pools
`vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]`
Показать список пулов. Если передан(ы) шаблон(ы) `<glob>`, то только с именами,
соответствующими одному из шаблонов (стандартные ФС-шаблоны с * и ?).
| <!-- --> | <!-- --> |
|-----------------------|------------------------------------------------------------|
| `-l` или `--long` | Вывести также статистику ввода-вывода |
| `--detail` | Максимально подробный вывод в виде списка (а не таблицы) |
| `--sort FIELD` | Сортировать по заданному полю (поля см. в выводе с --json) |
| `-r` или `--reverse` | Сортировать в обратном порядке |
| `-n` или `--count N` | Выводить только первые N записей |
+1 -10
View File
@@ -17,7 +17,6 @@ It supports the following commands:
- [purge](#purge)
- [read-sb](#read-sb)
- [write-sb](#write-sb)
- [update-sb](#update-sb)
- [udev](#udev)
- [exec-osd](#exec-osd)
- [pre-exec](#pre-exec)
@@ -183,14 +182,6 @@ Try to read Vitastor OSD superblock from `<device>` and print it in JSON format.
Read JSON from STDIN and write it into Vitastor OSD superblock on `<device>`.
## update-sb
`vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]`
Read Vitastor OSD superblock from <device>, update parameters in it and write it back.
`--force` allows to ignore validation errors.
## udev
`vitastor-disk udev <device>`
@@ -261,7 +252,7 @@ Options (see also [Cluster-Wide Disk Layout Parameters](../config/layout-cluster
```
--object_size 128k Set blockstore block size
--bitmap_granularity 4k Set bitmap granularity
--journal_size 32M Set journal size
--journal_size 16M Set journal size
--data_csum_type none Set data checksum type (crc32c or none)
--csum_block_size 4k Set data checksum block size
--device_block_size 4k Set device block size
+1 -11
View File
@@ -17,7 +17,6 @@ vitastor-disk - инструмент командной строки для уп
- [purge](#purge)
- [read-sb](#read-sb)
- [write-sb](#write-sb)
- [update-sb](#update-sb)
- [udev](#udev)
- [exec-osd](#exec-osd)
- [pre-exec](#pre-exec)
@@ -188,15 +187,6 @@ throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
Прочитать JSON со стандартного ввода и записать его в суперблок OSD на диск `<device>`.
## update-sb
`vitastor-disk update-sb <device> [--force] [--<параметр> <значение>] [...]`
Прочитать суперблок OSD с диска `<device>`, изменить в нём заданные параметры и записать обратно.
Опция `--force` позволяет читать суперблок, даже если он считается некорректным
из-за ошибок валидации.
## udev
`vitastor-disk udev <device>`
@@ -267,7 +257,7 @@ OSD отключены fsync-и.
```
--object_size 128k Размер блока хранилища
--bitmap_granularity 4k Гранулярность битовых карт
--journal_size 32M Размер журнала
--journal_size 16M Размер журнала
--data_csum_type none Задать тип контрольных сумм (crc32c или none)
--csum_block_size 4k Задать размер блока расчёта контрольных сумм
--device_block_size 4k Размер блока устройства
+2 -5
View File
@@ -14,13 +14,10 @@ Vitastor has a fio driver which can be installed from the package vitastor-fio.
Use the following command as an example to run tests with fio against a Vitastor cluster:
```
fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -image=testimg
fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -etcd=10.115.0.10:2379/v3 -image=testimg
```
If you don't want to access your image by name, you can specify pool number, inode number and size
(`-pool=1 -inode=1 -size=400G`) instead of the image name (`-image=testimg`).
You can also specify etcd address(es) explicitly by adding `-etcd=10.115.0.10:2379/v3`, or you
can override configuration file path by adding `-conf=/etc/vitastor/vitastor.conf`.
See exact fio commands to use for benchmarking [here](../performance/understanding.en.md#fio-commands).
See exact fio commands to use for benchmarking [here](../performance/understanding.en.md#команды-fio).
+1 -4
View File
@@ -14,13 +14,10 @@
Используйте следующую команду как пример для запуска тестов кластера Vitastor через fio:
```
fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -image=testimg
fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -etcd=10.115.0.10:2379/v3 -image=testimg
```
Вместо обращения к образу по имени (`-image=testimg`) можно указать номер пула, номер инода и размер:
`-pool=1 -inode=1 -size=400G`.
Вы также можете задать адрес(а) подключения к etcd явно, добавив `-etcd=10.115.0.10:2379/v3`,
или переопределить путь к файлу конфигурации, добавив `-conf=/etc/vitastor/vitastor.conf`.
Конкретные команды fio для тестирования производительности можно посмотреть [здесь](../performance/understanding.ru.md#команды-fio).
+5 -8
View File
@@ -11,25 +11,25 @@ NBD stands for "Network Block Device", but in fact it also functions as "BUSE"
NBD slighly lowers the performance due to additional overhead, but performance still
remains decent (see an example [here](../performance/comparison1.en.md#vitastor-0-4-0-nbd)).
See also [VDUSE](qemu.en.md#vduse) as a better alternative to NBD.
Vitastor Kubernetes CSI driver is based on NBD.
Vitastor Kubernetes CSI driver uses NBD when VDUSE is unavailable.
See also [VDUSE](qemu.en.md#vduse).
## Map image
To create a local block device for a Vitastor image run:
```
vitastor-nbd map --image testimg
vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
```
It will output a block device name like /dev/nbd0 which you can then use as a normal disk.
You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
vitastor-nbd supports all usual Vitastor configuration options like `--config_file <path_to_config>` plus NBD-specific:
Additional options for map command:
* `--nbd_timeout 300` \
* `--nbd_timeout 30` \
Timeout for I/O operations in seconds after exceeding which the kernel stops
the device. You can set it to 0 to disable the timeout, but beware that you
won't be able to stop the device at all if vitastor-nbd process dies.
@@ -44,9 +44,6 @@ vitastor-nbd supports all usual Vitastor configuration options like `--config_fi
* `--foreground 1` \
Stay in foreground, do not daemonize.
Note that `nbd_timeout`, `nbd_max_devices` and `nbd_max_part` options may also be specified
in `/etc/vitastor/vitastor.conf` or in other configuration file specified with `--config_file`.
## Unmap image
To unmap the device run:
+4 -9
View File
@@ -14,16 +14,16 @@ NBD на данный момент необходимо, чтобы монтир
NBD немного снижает производительность из-за дополнительных копирований памяти,
но она всё равно остаётся на неплохом уровне (см. для примера [тест](../performance/comparison1.ru.md#vitastor-0-4-0-nbd)).
Смотрите также [VDUSE](qemu.ru.md#vduse), как лучшую альтернативу NBD.
CSI-драйвер Kubernetes Vitastor основан на NBD.
CSI-драйвер Kubernetes Vitastor использует NBD, когда VDUSE недоступен.
Смотрите также [VDUSE](qemu.ru.md#vduse).
## Подключить устройство
Чтобы создать локальное блочное устройство для образа, выполните команду:
```
vitastor-nbd map --image testimg
vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
```
Команда напечатает название блочного устройства вида /dev/nbd0, которое потом можно
@@ -32,8 +32,7 @@ vitastor-nbd map --image testimg
Для обращения по номеру инода, аналогично другим командам, можно использовать опции
`--pool <POOL> --inode <INODE> --size <SIZE>` вместо `--image testimg`.
vitastor-nbd поддерживает все обычные опции Vitastor, например, `--config_file <path_to_config>`,
плюс специфичные для NBD:
Дополнительные опции для команды подключения NBD-устройства:
* `--nbd_timeout 30` \
Максимальное время выполнения любой операции чтения/записи в секундах, при
@@ -54,10 +53,6 @@ vitastor-nbd поддерживает все обычные опции Vitastor,
* `--foreground 1` \
Не уводить процесс в фоновый режим.
Обратите внимание, что опции `nbd_timeout`, `nbd_max_devices` и `nbd_max_part` можно
также задавать в `/etc/vitastor/vitastor.conf` или в другом файле конфигурации,
заданном опцией `--config_file`.
## Отключить устройство
Для отключения устройства выполните:
+27 -135
View File
@@ -4,150 +4,42 @@
[Читать на русском](nfs.ru.md)
# VitastorFS and pseudo-FS
# NFS
Vitastor has two file system implementations. Both can be used via `vitastor-nfs`.
Vitastor has a simplified NFS 3.0 proxy for file-based image access emulation. It's not
suitable as a full-featured file system, at least because all file/image metadata is stored
in etcd and kept in memory all the time - thus you can't put a lot of files in it.
Commands:
- [mount](#mount)
- [start](#start)
However, NFS proxy is totally fine as a method to provide VM image access and allows to
plug Vitastor into, for example, VMWare. It's important to note that for VMWare it's a much
better access method than iSCSI, because with iSCSI we'd have to put all VM images into one
Vitastor image exported as a LUN to VMWare and formatted with VMFS. VMWare doesn't use VMFS
over NFS.
## Pseudo-FS
NFS proxy is stateless if you use immediate_commit=all mode (for SSD with capacitors or
HDDs with disabled cache), so you can run multiple NFS proxies and use a network load
balancer or any failover method you want to in that case.
Simplified pseudo-FS proxy is used for file-based image access emulation. It's not
suitable as a full-featured file system: it lacks a lot of FS features, it stores
all file/image metadata in memory and in etcd. So it's fine for hundreds or thousands
of large files/images, but not for millions.
Pseudo-FS proxy is intended for environments where other block volume access methods
can't be used or impose additional restrictions - for example, VMWare. NFS is better
for VMWare than, for example, iSCSI, because with iSCSI, VMWare puts all VM images
into one large shared block image in its own VMFS file system, and with NFS, VMWare
doesn't use VMFS and puts each VM disk in a regular file which is equal to one
Vitastor block image, just as originally intended.
To use Vitastor pseudo-FS locally, run `vitastor-nfs mount --block /mnt/vita`.
Also you can start the network server:
vitastor-nfs usage:
```
vitastor-nfs start --block --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
vitastor-nfs [--etcd_address ADDR] [OTHER OPTIONS]
--subdir <DIR> export images prefixed <DIR>/ (default empty - export all images)
--portmap 0 do not listen on port 111 (portmap/rpcbind, requires root)
--bind <IP> bind service to <IP> address (default 0.0.0.0)
--nfspath <PATH> set NFS export path to <PATH> (default is /)
--port <PORT> use port <PORT> for NFS services (default is 2049)
--pool <POOL> use <POOL> as default pool for new files (images)
--foreground 1 stay in foreground, do not daemonize
```
To mount the FS exported by this server, run:
Example start and mount commands:
```
mount server:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
```
## VitastorFS
VitastorFS is a full-featured clustered (Read-Write-Many) file system. It supports most POSIX
features like hierarchical organization, symbolic links, hard links, quick renames and so on.
VitastorFS metadata is stored in a Parallel Optimistic B-Tree key-value database,
implemented over a regular Vitastor block volume. Directory entries and inodes
are stored in a simple human-readable JSON format in the B-Tree. `vitastor-kv` tool
can be used to inspect the database.
To use VitastorFS:
1. Create a pool or choose an existing empty pool for FS data
2. Create an image for FS metadata, preferably in a faster (SSD or replica-HDD) pool,
but you can create it in the data pool too if you want (image size doesn't matter):
`vitastor-cli create -s 10G -p fastpool testfs`
3. Mark data pool as an FS pool: `vitastor-cli modify-pool --used-for-fs testfs data-pool`
4. Either mount the FS: `vitastor-nfs mount --fs testfs --pool data-pool /mnt/vita`
5. Or start the NFS server: `vitastor-nfs start --fs testfs --pool data-pool`
### Supported POSIX features
- Read-after-write semantics (read returns new data immediately after write)
- Linear and random read and write
- Writing outside current file size
- Hierarchical structure, immediate rename of files and directories
- File size change support (truncate)
- Permissions (chmod/chown)
- Flushing data to stable storage (if required) (fsync)
- Symbolic links
- Hard links
- Special files (devices, sockets, named pipes)
- File modification and attribute change time tracking (mtime and ctime)
- Modification time (mtime) and last access time (atime) change support (utimes)
- Correct handling of directory listing during file creation/deletion
### Limitations
POSIX features currently not implemented in VitastorFS:
- File locking is not supported
- Actually used space is not counted, so `du` always reports apparent file sizes
instead of actually allocated space
- Access times (`atime`) are not tracked (like `-o noatime`)
- Modification time (`mtime`) is updated lazily every second (like `-o lazytime`)
Other notable missing features which should be addressed in the future:
- Defragmentation of "shared" inodes. Files smaller than pool object size (block_size
multiplied by data part count if pool is EC) are internally stored in large block
volumes sequentially, one after another, and leave garbage after deleting or resizing.
Defragmentator will be implemented to collect this garbage.
- Inode ID reuse. Currently inode IDs always grow, the limit is 2^48 inodes, so
in theory you may hit it if you create and delete a very large number of files
- Compaction of the key-value B-Tree. Current implementation never merges or deletes
B-Tree blocks, so B-Tree may become bloated over time. Currently you can
use `vitastor-kv dumpjson` & `loadjson` commands to recreate the index in such
situations.
- Filesystem check tool. VitastorFS doesn't have journal because it would impose a
severe performance hit, optimistic CAS-based transactions are used instead of it.
So, again, in theory an abnormal shutdown of the FS server may leave some garbage
in the DB. The FS is implemented is such way that this garbage doesn't affect its
function, but having a tool to clean it up still seems a right thing to do.
## Horizontal scaling
Linux NFS 3.0 client doesn't support built-in scaling or failover, i.e. you can't
specify multiple server addresses when mounting the FS.
However, you can use any regular TCP load balancing over multiple NFS servers.
It's absolutely safe with `immediate_commit=all` and `client_enable_writeback=false`
settings, because Vitastor NFS proxy doesn't keep uncommitted data in memory
with these settings. But it may even work without `immediate_commit=all` because
the Linux NFS client repeats all uncommitted writes if it loses the connection.
## Commands
### mount
`vitastor-nfs (--fs <NAME> | --block) [-o <OPT>] mount <MOUNTPOINT>`
Start local filesystem server and mount file system to <MOUNTPOINT>.
Use regular `umount <MOUNTPOINT>` to unmount the FS.
The server will be automatically stopped when the FS is unmounted.
- `-o|--options <OPT>` - Pass additional NFS mount options (ex.: -o async).
### start
`vitastor-nfs (--fs <NAME> | --block) start`
Start network NFS server. Options:
| <!-- --> | <!-- --> |
|-----------------|------------------------------------------------------------|
| `--bind <IP>` | bind service to \<IP> address (default 0.0.0.0) |
| `--port <PORT>` | use port \<PORT> for NFS services (default is 2049) |
| `--portmap 0` | do not listen on port 111 (portmap/rpcbind, requires root) |
## Common options
| <!-- --> | <!-- --> |
|--------------------|----------------------------------------------------------|
| `--fs <NAME>` | use VitastorFS with metadata in image \<NAME> |
| `--block` | use pseudo-FS presenting images as files |
| `--pool <POOL>` | use \<POOL> as default pool for new files |
| `--subdir <DIR>` | export \<DIR> instead of root directory (pseudo-FS only) |
| `--nfspath <PATH>` | set NFS export path to \<PATH> (default is /) |
| `--pidfile <FILE>` | write process ID to the specified file |
| `--logfile <FILE>` | log to the specified file |
| `--foreground 1` | stay in foreground, do not daemonize |
```
mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
```
+26 -141
View File
@@ -4,156 +4,41 @@
[Read in English](nfs.en.md)
# VitastorFS и псевдо-ФС
# NFS
В Vitastor есть две реализации файловой системы. Обе используются через `vitastor-nfs`.
В Vitastor реализована упрощённая NFS 3.0 прокси для эмуляции файлового доступа к образам.
Это не полноценная файловая система, т.к. метаданные всех файлов (образов) сохраняются
в etcd и всё время хранятся в оперативной памяти - то есть, положить туда много файлов
не получится.
Команды:
- [mount](#mount)
- [start](#start)
Однако в качестве способа доступа к образам виртуальных машин NFS прокси прекрасно подходит
и позволяет подключить Vitastor, например, к VMWare.
## Псевдо-ФС
При этом, если вы используете режим immediate_commit=all (для SSD с конденсаторами или HDD
с отключённым кэшем), то NFS-сервер не имеет состояния и вы можете свободно поднять
его в нескольких экземплярах и использовать поверх них сетевой балансировщик нагрузки или
схему с отказоустойчивостью.
Упрощённая реализация псевдо-ФС используется для эмуляции файлового доступа к блочным
образам Vitastor. Это не полноценная файловая система - в ней отсутствуют многие функции
POSIX ФС, а метаданные всех файлов (образов) сохраняются в etcd и всё время хранятся в
оперативной памяти - то есть, псевдо-ФС подходит для сотен или тысяч файлов, но не миллионов.
Псевдо-ФС предназначена для доступа к образам виртуальных машин в средах, где другие
способы невозможны или неудобны - например, в VMWare. Для VMWare это лучшая опция, чем
iSCSI, так как при использовании iSCSI VMWare размещает все виртуальные машины в одном
большом блочном образе внутри собственной ФС VMFS, а с NFS VMFS не используется и каждый
диск ВМ представляется в виде одного файла, то есть, соответствует одному блочному образу
Vitastor, как это и задумано изначально.
Чтобы подключить псевдо-ФС Vitastor, выполните команду `vitastor-nfs mount --block /mnt/vita`.
Либо же запустите сетевой вариант сервера:
Использование vitastor-nfs:
```
vitastor-nfs start --block --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
vitastor-nfs [--etcd_address ADDR] [ДРУГИЕ ОПЦИИ]
--subdir <DIR> экспортировать "поддиректорию" - образы с префиксом имени <DIR>/ (по умолчанию пусто - экспортировать все образы)
--portmap 0 отключить сервис portmap/rpcbind на порту 111 (по умолчанию включён и требует root привилегий)
--bind <IP> принимать соединения по адресу <IP> (по умолчанию 0.0.0.0 - на всех)
--nfspath <PATH> установить путь NFS-экспорта в <PATH> (по умолчанию /)
--port <PORT> использовать порт <PORT> для NFS-сервисов (по умолчанию 2049)
--pool <POOL> использовать пул <POOL> для новых образов (обязательно, если пул в кластере не один)
--foreground 1 не уходить в фон после запуска
```
Примонтировать ФС, запущенную с такими опциями, можно следующей командой:
Пример монтирования Vitastor через NFS:
```
mount server:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
```
## VitastorFS
VitastorFS - полноценная кластерная (Read-Write-Many) файловая система. Она поддерживает
большую часть функций POSIX - иерархическую организацию, символические ссылки, жёсткие
ссылки, быстрые переименования и так далее.
Метаданные VitastorFS хранятся в собственной реализации БД формата ключ-значения,
основанной на Параллельном Оптимистичном Б-дереве поверх обычного блочного образа Vitastor.
И записи каталогов, и иноды, как обычно в Vitastor, хранятся в простом человекочитаемом
JSON-формате :-). Для инспекции содержимого БД можно использовать инструмент `vitastor-kv`.
Чтобы использовать VitastorFS:
1. Создайте пул для данных ФС или выберите существующий пустой пул
2. Создайте блочный образ для метаданных ФС, желательно, в более быстром пуле (на SSD
или по крайней мере на HDD, но без EC), но можно и в том же пуле, что данные
(размер образа значения не имеет):
`vitastor-cli create -s 10G -p fastpool testfs`
3. Пометьте пул данных как ФС-пул: `vitastor-cli modify-pool --used-for-fs testfs data-pool`
4. Либо примонтируйте ФС: `vitastor-nfs mount --fs testfs --pool data-pool /mnt/vita`
5. Либо запустите сетевой NFS-сервер: `vitastor-nfs start --fs testfs --pool data-pool`
### Поддерживаемые функции POSIX
- Чтение актуальной версии данных сразу после записи
- Последовательное и произвольное чтение и запись
- Запись за пределами текущего размера файла
- Иерархическая организация, мгновенное переименование файлов и каталогов
- Изменение размера файла (truncate)
- Права на файлы (chmod/chown)
- Фиксация данных на диски (когда необходимо) (fsync)
- Символические ссылки
- Жёсткие ссылки
- Специальные файлы (устройства, сокеты, каналы)
- Отслеживание времён модификации (mtime), изменения атрибутов (ctime)
- Ручное изменение времён модификации (mtime), последнего доступа (atime)
- Корректная обработка изменений списка файлов во время листинга
### Ограничения
Отсутствующие на данный момент в VitastorFS функции POSIX:
- Блокировки файлов не поддерживаются
- Фактически занятое файлами место не подсчитывается и не возвращается вызовами
stat(2), так что `du` всегда показывает сумму размеров файлов, а не фактически занятое место
- Времена доступа (`atime`) не отслеживаются (как будто ФС смонтирована с `-o noatime`)
- Времена модификации (`mtime`) отслеживаются асинхронно (как будто ФС смонтирована с `-o lazytime`)
Другие недостающие функции, которые нужно добавить в будущем:
- Дефрагментация "общих инодов". На уровне реализации ФС файлы, меньшие, чем размер
объекта пула (block_size умножить на число частей данных, если пул EC),
упаковываются друг за другом в большие "общие" иноды/тома. Если такие файлы удалять
или увеличивать, они перемещаются и оставляют за собой "мусор", вот тут-то и нужен
дефрагментатор.
- Переиспользование номеров инодов. В текущей реализации номера инодов всё время
увеличиваются, так что в теории вы можете упереться в лимит, если насоздаёте
и наудаляете больше, чем 2^48 файлов.
- Очистка места в Б-дереве метаданных. Текущая реализация никогда не сливает и не
удаляет блоки Б-дерева, так что в теории дерево может разростись и стать неоптимальным.
Если вы столкнётесь с такой ситуацией сейчас, вы можете решить её с помощью
команд `vitastor-kv dumpjson` и `loadjson` (т.е. пересоздав и загрузив обратно все метаданные ФС).
- Инструмент проверки метаданных файловой системы. У VitastorFS нет журнала, так как
журнал бы сильно замедлил реализацию, вместо него используются оптимистичные
транзакции на основе CAS (сравнить-и-записать), и теоретически при нештатном
завершении сервера ФС в БД также могут оставаться неконсистентные "мусорные"
записи. ФС устроена так, что на работу они не влияют, но для порядка и их стоит
уметь подчищать.
## Горизонтальное масштабирование
Клиент Linux NFS 3.0 не поддерживает встроенное масштабирование или отказоустойчивость.
То есть, вы не можете задать несколько адресов серверов при монтировании ФС.
Однако вы можете использовать любые стандартные сетевые балансировщики нагрузки
или схемы с отказоустойчивостью. Это точно безопасно при настройках `immediate_commit=all` и
`client_enable_writeback=false`, так как с ними NFS-сервер Vitastor вообще не хранит
в памяти ещё не зафиксированные на дисках данные; и вполне вероятно безопасно
даже без `immediate_commit=all`, потому что NFS-клиент ядра Linux повторяет все
незафиксированные запросы при потере соединения.
## Команды
### mount
`vitastor-nfs (--fs <NAME> | --block) mount [-o <OPT>] <MOUNTPOINT>`
Запустить локальный сервер и примонтировать ФС в директорию <MOUNTPOINT>.
Чтобы отмонтировать ФС, используйте обычную команду `umount <MOUNTPOINT>`.
Сервер автоматически останавливается при отмонтировании ФС.
- `-o|--options <OPT>` - Передать дополнительные опции монтирования NFS (пример: -o async).
### start
`vitastor-nfs (--fs <NAME> | --block) start`
Запустить сетевой NFS-сервер. Опции:
| <!-- --> | <!-- --> |
|-----------------|-----------------------------------------------------------------------|
| `--bind <IP>` | принимать соединения по адресу \<IP> (по умолчанию 0.0.0.0 - на всех) |
| `--port <PORT>` | использовать порт \<PORT> для NFS-сервисов (по умолчанию 2049) |
| `--portmap 0` | отключить сервис portmap/rpcbind на порту 111 (по умолчанию включён и требует root привилегий) |
## Общие опции
| <!-- --> | <!-- --> |
|--------------------|---------------------------------------------------------|
| `--fs <NAME>` | использовать VitastorFS с метаданными в образе \<NAME> |
| `--block` | использовать псевдо-ФС для доступа к блочным образам |
| `--pool <POOL>` | использовать пул \<POOL> для новых файлов (обязательно, если пул в кластере не один) |
| `--subdir <DIR>` | экспортировать подкаталог \<DIR>, а не корень (только для псевдо-ФС) |
| `--nfspath <PATH>` | установить путь NFS-экспорта в \<PATH> (по умолчанию /) |
| `--pidfile <FILE>` | записать ID процесса в заданный файл |
| `--logfile <FILE>` | записывать логи в заданный файл |
| `--foreground 1` | не уходить в фон после запуска |
```
mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
```
+6 -9
View File
@@ -16,16 +16,13 @@ Old syntax (-drive):
```
qemu-system-x86_64 -enable-kvm -m 1024 \
-drive 'file=vitastor:image=debian9',
-drive 'file=vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian9',
format=raw,if=none,id=drive-virtio-disk0,cache=none \
-device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
id=virtio-disk0,bootindex=1,write-cache=off' \
-vnc 0.0.0.0:0
```
Etcd address may be specified explicitly by adding `:etcd_host=192.168.7.2\:2379/v3` to `file=`.
Configuration file path may be overriden by adding `:config_path=/etc/vitastor/vitastor.conf`.
New syntax (-blockdev):
```
@@ -53,12 +50,12 @@ You can also specify inode ID, pool and size manually instead of `:image=<IMAGE>
## qemu-img
For qemu-img, you should use `vitastor:image=<IMAGE>[:etcd_host=<HOST>]` as filename.
For qemu-img, you should use `vitastor:etcd_host=<HOST>:image=<IMAGE>` as filename.
For example, to upload a VM image into Vitastor, run:
```
qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:image=debian10'
qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian10'
```
You can also specify `:pool=<POOL>:inode=<INODE>:size=<SIZE>` instead of `:image=<IMAGE>`
@@ -75,10 +72,10 @@ the snapshot separately using the following commands (key points are using `skip
`-B backing_file` option):
```
qemu-img convert -f raw 'vitastor:image=testimg@0' \
qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg@0' \
-O qcow2 testimg_0.qcow2
qemu-img convert -f raw 'vitastor:image=testimg:skip-parents=1' \
qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg:skip-parents=1' \
-O qcow2 -o 'cluster_size=4k' -B testimg_0.qcow2 testimg.qcow2
```
@@ -149,7 +146,7 @@ Example performance comparison:
| 4k random read Q1 | 9600 iops | 7640 iops | 7780 iops |
To try VDUSE you need at least Linux 5.15, built with VDUSE support
(CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
(CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
Debian Linux kernels have these options disabled by now, so if you want to try it on Debian,
use a kernel from Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/), Proxmox,
+6 -9
View File
@@ -18,16 +18,13 @@
```
qemu-system-x86_64 -enable-kvm -m 1024 \
-drive 'file=vitastor:image=debian9',
-drive 'file=vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian9',
format=raw,if=none,id=drive-virtio-disk0,cache=none \
-device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
id=virtio-disk0,bootindex=1,write-cache=off' \
-vnc 0.0.0.0:0
```
Адрес подключения etcd можно задать явно, если добавить `:etcd_host=192.168.7.2\:2379/v3` к `file=`.
Путь к файлу конфигурации можно переопределить, добавив `:config_path=/etc/vitastor/vitastor.conf`.
Новый синтаксис (-blockdev):
```
@@ -55,12 +52,12 @@ qemu-system-x86_64 -enable-kvm -m 1024 \
## qemu-img
Для qemu-img используйте строку `vitastor:image=<IMAGE>[:etcd_host=<HOST>]` в качестве имени файла диска.
Для qemu-img используйте строку `vitastor:etcd_host=<HOST>:image=<IMAGE>` в качестве имени файла диска.
Например, чтобы загрузить образ диска в Vitastor:
```
qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:image=testimg'
qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=10.115.0.10\:2379/v3:image=testimg'
```
Если вы не хотите обращаться к образу по имени, вместо `:image=<IMAGE>` можно указать номер пула, номер инода и размер:
@@ -76,10 +73,10 @@ qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:image=testimg'
с помощью следующих команд (ключевые моменты - использование `skip-parents=1` и опции `-B backing_file.qcow2`):
```
qemu-img convert -f raw 'vitastor:image=testimg@0' \
qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg@0' \
-O qcow2 testimg_0.qcow2
qemu-img convert -f raw 'vitastor:image=testimg:skip-parents=1' \
qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg:skip-parents=1' \
-O qcow2 -o 'cluster_size=4k' -B testimg_0.qcow2 testimg.qcow2
```
@@ -152,7 +149,7 @@ VDUSE - на данный момент лучший интерфейс для п
| 4k случайное чтение Q1 | 9600 iops | 7640 iops | 7780 iops |
Чтобы попробовать VDUSE, вам нужно ядро Linux как минимум версии 5.15, собранное с поддержкой
VDUSE (CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
VDUSE (CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
В ядрах в Debian Linux поддержка пока отключена по умолчанию, так что чтобы попробовать VDUSE
на Debian, поставьте ядро из Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/),
+5 -14
View File
@@ -3,7 +3,6 @@
module.exports = {
scale_pg_count,
scale_pg_history,
};
function add_pg_history(new_pg_history, new_pg, prev_pgs, prev_pg_history, old_pg)
@@ -44,18 +43,16 @@ function finish_pg_history(merged_history)
merged_history.all_peers = Object.values(merged_history.all_peers);
}
function scale_pg_history(prev_pg_history, prev_pgs, new_pgs)
function scale_pg_count(prev_pgs, real_prev_pgs, prev_pg_history, new_pg_history, new_pg_count)
{
const new_pg_history = [];
const old_pg_count = prev_pgs.length;
const new_pg_count = new_pgs.length;
const old_pg_count = real_prev_pgs.length;
// Add all possibly intersecting PGs to the history of new PGs
if (!(new_pg_count % old_pg_count))
{
// New PG count is a multiple of old PG count
for (let i = 0; i < new_pg_count; i++)
{
add_pg_history(new_pg_history, i, prev_pgs, prev_pg_history, i % old_pg_count);
add_pg_history(new_pg_history, i, real_prev_pgs, prev_pg_history, i % old_pg_count);
finish_pg_history(new_pg_history[i]);
}
}
@@ -67,7 +64,7 @@ function scale_pg_history(prev_pg_history, prev_pgs, new_pgs)
{
for (let j = 0; j < mul; j++)
{
add_pg_history(new_pg_history, i, prev_pgs, prev_pg_history, i+j*new_pg_count);
add_pg_history(new_pg_history, i, real_prev_pgs, prev_pg_history, i+j*new_pg_count);
}
finish_pg_history(new_pg_history[i]);
}
@@ -79,7 +76,7 @@ function scale_pg_history(prev_pg_history, prev_pgs, new_pgs)
let merged_history = {};
for (let i = 0; i < old_pg_count; i++)
{
add_pg_history(merged_history, 1, prev_pgs, prev_pg_history, i);
add_pg_history(merged_history, 1, real_prev_pgs, prev_pg_history, i);
}
finish_pg_history(merged_history[1]);
for (let i = 0; i < new_pg_count; i++)
@@ -92,12 +89,6 @@ function scale_pg_history(prev_pg_history, prev_pgs, new_pgs)
{
new_pg_history[i] = null;
}
return new_pg_history;
}
function scale_pg_count(prev_pgs, new_pg_count)
{
const old_pg_count = prev_pgs.length;
// Just for the lp_solve optimizer - pick a "previous" PG for each "new" one
if (prev_pgs.length < new_pg_count)
{
+174 -262
View File
@@ -37,7 +37,7 @@ const etcd_allow = new RegExp('^'+[
'pg/history/[1-9]\\d*/[1-9]\\d*',
'pool/stats/[1-9]\\d*',
'history/last_clean_pgs',
'inode/stats/[1-9]\\d*/\\d+',
'inode/stats/[1-9]\\d*/[1-9]\\d*',
'pool/stats/[1-9]\\d*',
'stats',
'index/image/.*',
@@ -55,11 +55,10 @@ const etcd_tree = {
// etcd connection - configurable online
etcd_address: "10.0.115.10:2379/v3",
// mon
etcd_mon_ttl: 5, // min: 1
etcd_mon_ttl: 30, // min: 10
etcd_mon_timeout: 1000, // ms. min: 0
etcd_mon_retries: 5, // min: 0
mon_change_timeout: 1000, // ms. min: 100
mon_retry_change_timeout: 50, // ms. min: 10
mon_stats_timeout: 1000, // ms. min: 100
osd_out_time: 600, // seconds. min: 0
placement_levels: { datacenter: 1, rack: 2, host: 3, osd: 4, ... },
@@ -86,14 +85,13 @@ const etcd_tree = {
client_max_buffered_bytes: 33554432,
client_max_buffered_ops: 1024,
client_max_writeback_iodepth: 256,
client_retry_interval: 50, // ms. min: 10
client_eio_retry_interval: 1000, // ms
// client and osd - configurable online
log_level: 0,
peer_connect_interval: 5, // seconds. min: 1
peer_connect_timeout: 5, // seconds. min: 1
osd_idle_timeout: 5, // seconds. min: 1
osd_ping_timeout: 5, // seconds. min: 1
up_wait_retry_interval: 500, // ms. min: 50
max_etcd_attempts: 5,
etcd_quick_timeout: 1000, // ms
etcd_slow_timeout: 5000, // ms
@@ -112,15 +110,7 @@ const etcd_tree = {
autosync_interval: 5,
autosync_writes: 128,
client_queue_depth: 128, // unused
recovery_queue_depth: 1,
recovery_sleep_us: 0,
recovery_tune_util_low: 0.1,
recovery_tune_client_util_low: 0,
recovery_tune_util_high: 1.0,
recovery_tune_client_util_high: 0.5,
recovery_tune_interval: 1,
recovery_tune_agg_interval: 10, // 10 times recovery_tune_interval
recovery_tune_sleep_min_us: 10, // 10 microseconds
recovery_queue_depth: 4,
recovery_pg_switch: 128,
recovery_sync_batch: 16,
no_recovery: false,
@@ -391,8 +381,7 @@ class Mon
{
constructor(config)
{
this.failconnect = (e) => this._die(e, 2);
this.die = (e) => this._die(e, 1);
this.die = (e) => this._die(e);
if (fs.existsSync(config.config_path||'/etc/vitastor/vitastor.conf'))
{
config = {
@@ -403,7 +392,7 @@ class Mon
this.parse_etcd_addresses(config.etcd_address||config.etcd_url);
this.verbose = config.verbose || 0;
this.initConfig = config;
this.config = { ...config };
this.config = {};
this.etcd_prefix = config.etcd_prefix || '/vitastor';
this.etcd_prefix = this.etcd_prefix.replace(/\/\/+/g, '/').replace(/^\/?(.*[^\/])\/?$/, '/$1');
this.etcd_start_timeout = (config.etcd_start_timeout || 5) * 1000;
@@ -481,10 +470,10 @@ class Mon
check_config()
{
this.config.etcd_mon_ttl = Number(this.config.etcd_mon_ttl) || 5;
if (this.config.etcd_mon_ttl < 1)
this.config.etcd_mon_ttl = Number(this.config.etcd_mon_ttl) || 30;
if (this.config.etcd_mon_ttl < 10)
{
this.config.etcd_mon_ttl = 1;
this.config.etcd_mon_ttl = 10;
}
this.config.etcd_mon_timeout = Number(this.config.etcd_mon_timeout) || 0;
if (this.config.etcd_mon_timeout <= 0)
@@ -501,11 +490,6 @@ class Mon
{
this.config.mon_change_timeout = 100;
}
this.config.mon_retry_change_timeout = Number(this.config.mon_retry_change_timeout) || 50;
if (this.config.mon_retry_change_timeout < 50)
{
this.config.mon_retry_change_timeout = 50;
}
this.config.mon_stats_timeout = Number(this.config.mon_stats_timeout) || 1000;
if (this.config.mon_stats_timeout < 100)
{
@@ -606,7 +590,7 @@ class Mon
}
if (!this.ws)
{
this.failconnect('Failed to open etcd watch websocket');
this.die('Failed to open etcd watch websocket');
}
const cur_addr = this.selected_etcd_url;
this.ws_alive = true;
@@ -622,7 +606,7 @@ class Mon
console.log('etcd websocket timed out, restarting it');
this.restart_watcher(cur_addr);
}
}, (Number(this.config.etcd_ws_keepalive_interval) || 30)*1000);
}, (Number(this.config.etcd_keepalive_interval) || 30)*1000);
this.ws.on('error', () => this.restart_watcher(cur_addr));
this.ws.send(JSON.stringify({
create_request: {
@@ -676,12 +660,7 @@ class Mon
{
this.parse_kv(e.kv);
const key = e.kv.key.substr(this.etcd_prefix.length);
if (key.substr(0, 11) == '/osd/state/')
{
stats_changed = true;
changed = true;
}
else if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 10) == '/pg/stats/' || key.substr(0, 16) == '/osd/inodestats/')
if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 10) == '/pg/stats/' || key.substr(0, 16) == '/osd/inodestats/')
{
stats_changed = true;
}
@@ -798,9 +777,9 @@ class Mon
const res = await this.etcd_call('/lease/keepalive', { ID: this.etcd_lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
if (!res.result.TTL)
{
this.failconnect('Lease expired');
this.die('Lease expired');
}
}, this.config.etcd_mon_ttl*1000);
}, this.config.etcd_mon_timeout);
if (!this.signals_set)
{
process.on('SIGINT', this.on_stop_cb);
@@ -1243,89 +1222,6 @@ class Mon
return aff_osds;
}
async generate_pool_pgs(pool_id, osd_tree, levels)
{
const pool_cfg = this.state.config.pools[pool_id];
if (!this.validate_pool_cfg(pool_id, pool_cfg, false))
{
return null;
}
let pool_tree = osd_tree[pool_cfg.root_node || ''];
pool_tree = pool_tree ? pool_tree.children : [];
pool_tree = LPOptimizer.flatten_tree(pool_tree, levels, pool_cfg.failure_domain, 'osd');
this.filter_osds_by_tags(osd_tree, pool_tree, pool_cfg.osd_tags);
this.filter_osds_by_block_layout(
pool_tree,
pool_cfg.block_size || this.config.block_size || 131072,
pool_cfg.bitmap_granularity || this.config.bitmap_granularity || 4096,
pool_cfg.immediate_commit || this.config.immediate_commit || 'none'
);
// First try last_clean_pgs to minimize data movement
let prev_pgs = [];
for (const pg in ((this.state.history.last_clean_pgs.items||{})[pool_id]||{}))
{
prev_pgs[pg-1] = [ ...this.state.history.last_clean_pgs.items[pool_id][pg].osd_set ];
}
if (!prev_pgs.length)
{
// Fall back to config/pgs if it's empty
for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
{
prev_pgs[pg-1] = [ ...this.state.config.pgs.items[pool_id][pg].osd_set ];
}
}
const old_pg_count = prev_pgs.length;
const optimize_cfg = {
osd_tree: pool_tree,
pg_count: pool_cfg.pg_count,
pg_size: pool_cfg.pg_size,
pg_minsize: pool_cfg.pg_minsize,
max_combinations: pool_cfg.max_osd_combinations,
ordered: pool_cfg.scheme != 'replicated',
};
let optimize_result;
// Re-shuffle PGs if config/pgs.hash is empty
if (old_pg_count > 0 && this.state.config.pgs.hash)
{
if (prev_pgs.length != pool_cfg.pg_count)
{
// Scale PG count
// Do it even if old_pg_count is already equal to pool_cfg.pg_count,
// because last_clean_pgs may still contain the old number of PGs
PGUtil.scale_pg_count(prev_pgs, pool_cfg.pg_count);
}
for (const pg of prev_pgs)
{
while (pg.length < pool_cfg.pg_size)
{
pg.push(0);
}
}
optimize_result = await LPOptimizer.optimize_change({
prev_pgs,
...optimize_cfg,
});
}
else
{
optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
}
console.log(`Pool ${pool_id} (${pool_cfg.name || 'unnamed'}):`);
LPOptimizer.print_change_stats(optimize_result);
const pg_effsize = Math.min(pool_cfg.pg_size, Object.keys(pool_tree).length);
return {
pool_id,
pgs: optimize_result.int_pgs,
stats: {
total_raw_tb: optimize_result.space,
pg_real_size: pg_effsize || pool_cfg.pg_size,
raw_to_usable: (pg_effsize || pool_cfg.pg_size) / (pool_cfg.scheme === 'replicated'
? 1 : (pool_cfg.pg_size - (pool_cfg.parity_chunks||0))),
space_efficiency: optimize_result.space/(optimize_result.total_space||1),
},
};
}
async recheck_pgs()
{
if (this.recheck_pgs_active)
@@ -1340,47 +1236,158 @@ class Mon
const { up_osds, levels, osd_tree } = this.get_osd_tree();
const tree_cfg = {
osd_tree,
levels,
pools: this.state.config.pools,
};
const tree_hash = sha1hex(stableStringify(tree_cfg));
if (this.state.config.pgs.hash != tree_hash)
{
// Something has changed
console.log('Pool configuration or OSD tree changed, re-optimizing');
// First re-optimize PGs, but don't look at history yet
const optimize_results = await Promise.all(Object.keys(this.state.config.pools)
.map(pool_id => this.generate_pool_pgs(pool_id, osd_tree, levels)));
// Then apply the modification in the form of an optimistic transaction,
// each time considering new pg/history modifications (OSDs modify it during rebalance)
while (!await this.apply_pool_pgs(optimize_results, up_osds, osd_tree, tree_hash))
const new_config_pgs = JSON.parse(JSON.stringify(this.state.config.pgs));
const etcd_request = { compare: [], success: [] };
for (const pool_id in (this.state.config.pgs||{}).items||{})
{
console.log(
'Someone changed PG configuration while we also tried to change it.'+
' Retrying in '+this.config.mon_retry_change_timeout+' ms'
);
// Failed to apply - parallel change detected. Wait a bit and retry
const old_rev = this.etcd_watch_revision;
while (this.etcd_watch_revision === old_rev)
if (!this.state.config.pools[pool_id])
{
await new Promise(ok => setTimeout(ok, this.config.mon_retry_change_timeout));
// Pool deleted. Delete all PGs, but first stop them.
if (!await this.stop_all_pgs(pool_id))
{
this.recheck_pgs_active = false;
this.schedule_recheck();
return;
}
const prev_pgs = [];
for (const pg in this.state.config.pgs.items[pool_id]||{})
{
prev_pgs[pg-1] = this.state.config.pgs.items[pool_id][pg].osd_set;
}
// Also delete pool statistics
etcd_request.success.push({ requestDeleteRange: {
key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
} });
this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, prev_pgs, [], []);
}
const new_ot = this.get_osd_tree();
const new_tcfg = {
osd_tree: new_ot.osd_tree,
levels: new_ot.levels,
pools: this.state.config.pools,
};
if (sha1hex(stableStringify(new_tcfg)) !== tree_hash)
{
// Configuration actually changed, restart from the beginning
this.recheck_pgs_active = false;
setImmediate(() => this.recheck_pgs().catch(this.die));
return;
}
// Configuration didn't change, PG history probably changed, so just retry
}
console.log('PG configuration successfully changed');
for (const pool_id in this.state.config.pools)
{
const pool_cfg = this.state.config.pools[pool_id];
if (!this.validate_pool_cfg(pool_id, pool_cfg, false))
{
continue;
}
let pool_tree = osd_tree[pool_cfg.root_node || ''];
pool_tree = pool_tree ? pool_tree.children : [];
pool_tree = LPOptimizer.flatten_tree(pool_tree, levels, pool_cfg.failure_domain, 'osd');
this.filter_osds_by_tags(osd_tree, pool_tree, pool_cfg.osd_tags);
this.filter_osds_by_block_layout(
pool_tree,
pool_cfg.block_size || this.config.block_size || 131072,
pool_cfg.bitmap_granularity || this.config.bitmap_granularity || 4096,
pool_cfg.immediate_commit || this.config.immediate_commit || 'none'
);
// These are for the purpose of building history.osd_sets
const real_prev_pgs = [];
let pg_history = [];
for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
{
real_prev_pgs[pg-1] = this.state.config.pgs.items[pool_id][pg].osd_set;
if (this.state.pg.history[pool_id] &&
this.state.pg.history[pool_id][pg])
{
pg_history[pg-1] = this.state.pg.history[pool_id][pg];
}
}
// And these are for the purpose of minimizing data movement
let prev_pgs = [];
for (const pg in ((this.state.history.last_clean_pgs.items||{})[pool_id]||{}))
{
prev_pgs[pg-1] = this.state.history.last_clean_pgs.items[pool_id][pg].osd_set;
}
prev_pgs = JSON.parse(JSON.stringify(prev_pgs.length ? prev_pgs : real_prev_pgs));
const old_pg_count = real_prev_pgs.length;
const optimize_cfg = {
osd_tree: pool_tree,
pg_count: pool_cfg.pg_count,
pg_size: pool_cfg.pg_size,
pg_minsize: pool_cfg.pg_minsize,
max_combinations: pool_cfg.max_osd_combinations,
ordered: pool_cfg.scheme != 'replicated',
};
let optimize_result;
if (old_pg_count > 0)
{
if (old_pg_count != pool_cfg.pg_count)
{
// PG count changed. Need to bring all PGs down.
if (!await this.stop_all_pgs(pool_id))
{
this.recheck_pgs_active = false;
this.schedule_recheck();
return;
}
}
if (prev_pgs.length != pool_cfg.pg_count)
{
// Scale PG count
// Do it even if old_pg_count is already equal to pool_cfg.pg_count,
// because last_clean_pgs may still contain the old number of PGs
const new_pg_history = [];
PGUtil.scale_pg_count(prev_pgs, real_prev_pgs, pg_history, new_pg_history, pool_cfg.pg_count);
pg_history = new_pg_history;
}
for (const pg of prev_pgs)
{
while (pg.length < pool_cfg.pg_size)
{
pg.push(0);
}
}
if (!this.state.config.pgs.hash)
{
// Re-shuffle PGs
optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
}
else
{
optimize_result = await LPOptimizer.optimize_change({
prev_pgs,
...optimize_cfg,
});
}
}
else
{
optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
}
if (old_pg_count != optimize_result.int_pgs.length)
{
console.log(
`PG count for pool ${pool_id} (${pool_cfg.name || 'unnamed'})`+
` changed from: ${old_pg_count} to ${optimize_result.int_pgs.length}`
);
// Drop stats
etcd_request.success.push({ requestDeleteRange: {
key: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'/'),
range_end: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'0'),
} });
}
LPOptimizer.print_change_stats(optimize_result);
const pg_effsize = Math.min(pool_cfg.pg_size, Object.keys(pool_tree).length);
this.state.pool.stats[pool_id] = {
used_raw_tb: (this.state.pool.stats[pool_id]||{}).used_raw_tb || 0,
total_raw_tb: optimize_result.space,
pg_real_size: pg_effsize || pool_cfg.pg_size,
raw_to_usable: (pg_effsize || pool_cfg.pg_size) / (pool_cfg.scheme === 'replicated'
? 1 : (pool_cfg.pg_size - (pool_cfg.parity_chunks||0))),
space_efficiency: optimize_result.space/(optimize_result.total_space||1),
};
etcd_request.success.push({ requestPut: {
key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
value: b64(JSON.stringify(this.state.pool.stats[pool_id])),
} });
this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, optimize_result.int_pgs, pg_history);
}
new_config_pgs.hash = tree_hash;
await this.save_pg_config(new_config_pgs, etcd_request);
}
else
{
@@ -1421,97 +1428,12 @@ class Mon
}
if (changed)
{
const ok = await this.save_pg_config(new_config_pgs);
if (ok)
console.log('PG configuration successfully changed');
else
{
console.log('Someone changed PG configuration while we also tried to change it. Retrying in '+this.config.mon_change_timeout+' ms');
this.schedule_recheck();
}
await this.save_pg_config(new_config_pgs);
}
}
this.recheck_pgs_active = false;
}
async apply_pool_pgs(results, up_osds, osd_tree, tree_hash)
{
for (const pool_id in (this.state.config.pgs||{}).items||{})
{
// We should stop all PGs when deleting a pool or changing its PG count
if (!this.state.config.pools[pool_id] ||
this.state.config.pgs.items[pool_id] && this.state.config.pools[pool_id].pg_count !=
Object.keys(this.state.config.pgs.items[pool_id]).reduce((a, c) => (a < (0|c) ? (0|c) : a), 0))
{
if (!await this.stop_all_pgs(pool_id))
{
return false;
}
}
}
const new_config_pgs = JSON.parse(JSON.stringify(this.state.config.pgs));
const etcd_request = { compare: [], success: [] };
for (const pool_id in (new_config_pgs||{}).items||{})
{
if (!this.state.config.pools[pool_id])
{
const prev_pgs = [];
for (const pg in new_config_pgs.items[pool_id]||{})
{
prev_pgs[pg-1] = new_config_pgs.items[pool_id][pg].osd_set;
}
// Also delete pool statistics
etcd_request.success.push({ requestDeleteRange: {
key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
} });
this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, prev_pgs, [], []);
}
}
for (const pool_res of results)
{
const pool_id = pool_res.pool_id;
const pool_cfg = this.state.config.pools[pool_id];
let pg_history = [];
for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
{
if (this.state.pg.history[pool_id] &&
this.state.pg.history[pool_id][pg])
{
pg_history[pg-1] = this.state.pg.history[pool_id][pg];
}
}
const real_prev_pgs = [];
for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
{
real_prev_pgs[pg-1] = [ ...this.state.config.pgs.items[pool_id][pg].osd_set ];
}
if (real_prev_pgs.length > 0 && real_prev_pgs.length != pool_res.pgs.length)
{
console.log(
`Changing PG count for pool ${pool_id} (${pool_cfg.name || 'unnamed'})`+
` from: ${real_prev_pgs.length} to ${pool_res.pgs.length}`
);
pg_history = PGUtil.scale_pg_history(pg_history, real_prev_pgs, pool_res.pgs);
// Drop stats
etcd_request.success.push({ requestDeleteRange: {
key: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'/'),
range_end: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'0'),
} });
}
const stats = {
used_raw_tb: (this.state.pool.stats[pool_id]||{}).used_raw_tb || 0,
...pool_res.stats,
};
etcd_request.success.push({ requestPut: {
key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
value: b64(JSON.stringify(stats)),
} });
this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, pool_res.pgs, pg_history);
}
new_config_pgs.hash = tree_hash;
return await this.save_pg_config(new_config_pgs, etcd_request);
}
async save_pg_config(new_config_pgs, etcd_request = { compare: [], success: [] })
{
etcd_request.compare.push(
@@ -1521,8 +1443,14 @@ class Mon
etcd_request.success.push(
{ requestPut: { key: b64(this.etcd_prefix+'/config/pgs'), value: b64(JSON.stringify(new_config_pgs)) } },
);
const txn_res = await this.etcd_call('/kv/txn', etcd_request, this.config.etcd_mon_timeout, 0);
return txn_res.succeeded;
const res = await this.etcd_call('/kv/txn', etcd_request, this.config.etcd_mon_timeout, 0);
if (!res.succeeded)
{
console.log('Someone changed PG configuration while we also tried to change it. Retrying in '+this.config.mon_change_timeout+' ms');
this.schedule_recheck();
return;
}
console.log('PG configuration successfully changed');
}
// Schedule next recheck at least at <unixtime>
@@ -1641,13 +1569,9 @@ class Mon
}
const sum_diff = { op_stats: {}, subop_stats: {}, recovery_stats: {} };
// Sum derived values instead of deriving summed
for (const osd in this.state.osd.state)
for (const osd in this.state.osd.stats)
{
const derived = this.prev_stats.osd_diff[osd];
if (!this.state.osd.state[osd] || !derived)
{
continue;
}
for (const type in sum_diff)
{
for (const op in derived[type]||{})
@@ -1737,11 +1661,8 @@ class Mon
for (const inode_num in this.state.osd.space[osd_num][pool_id])
{
const u = BigInt(this.state.osd.space[osd_num][pool_id][inode_num]||0);
if (inode_num)
{
inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
inode_stats[pool_id][inode_num].raw_used += u;
}
inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
inode_stats[pool_id][inode_num].raw_used += u;
this.state.pool.stats[pool_id].used_raw_tb += u;
}
}
@@ -1751,13 +1672,9 @@ class Mon
const used = this.state.pool.stats[pool_id].used_raw_tb;
this.state.pool.stats[pool_id].used_raw_tb = Number(used)/1024/1024/1024/1024;
}
for (const osd_num in this.state.osd.state)
for (const osd_num in this.state.osd.inodestats)
{
const ist = this.state.osd.inodestats[osd_num];
if (!ist || !this.state.osd.state[osd_num])
{
continue;
}
for (const pool_id in ist)
{
inode_stats[pool_id] = inode_stats[pool_id] || {};
@@ -1773,14 +1690,9 @@ class Mon
}
}
}
for (const osd in this.state.osd.state)
for (const osd in this.prev_stats.osd_diff)
{
const osd_diff = this.prev_stats.osd_diff[osd];
if (!osd_diff || !this.state.osd.state[osd])
{
continue;
}
for (const pool_id in osd_diff.inode_stats)
for (const pool_id in this.prev_stats.osd_diff[osd].inode_stats)
{
for (const inode_num in this.prev_stats.osd_diff[osd].inode_stats[pool_id])
{
@@ -2020,14 +1932,14 @@ class Mon
return res.json;
}
}
this.failconnect();
this.die();
}
_die(err, code)
_die(err)
{
// In fact we can just try to rejoin
console.error(new Error(err || 'Cluster connection failed'));
process.exit(code || 2);
process.exit(1);
}
local_ips(all)
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "vitastor-mon",
"version": "1.5.0",
"version": "1.2.0",
"description": "Vitastor SDS monitor service",
"main": "mon-main.js",
"scripts": {
+1 -3
View File
@@ -8,9 +8,7 @@ PartOf=vitastor.target
LimitNOFILE=1048576
LimitNPROC=1048576
LimitMEMLOCK=infinity
# Use the following for direct logs to files
#ExecStart=bash -c 'exec vitastor-disk exec-osd /dev/vitastor/osd%i-data >>/var/log/vitastor/osd%i.log 2>&1'
ExecStart=vitastor-disk exec-osd /dev/vitastor/osd%i-data
ExecStart=bash -c 'exec vitastor-disk exec-osd /dev/vitastor/osd%i-data >>/var/log/vitastor/osd%i.log 2>&1'
ExecStartPre=+vitastor-disk pre-exec /dev/vitastor/osd%i-data
WorkingDirectory=/
User=vitastor
+1
View File
@@ -110,6 +110,7 @@ sub properties
vitastor_etcd_address => {
description => 'IP address(es) of etcd.',
type => 'string',
format => 'pve-storage-portal-dns-list',
},
vitastor_etcd_prefix => {
description => 'Prefix for Vitastor etcd metadata',
+1 -1
View File
@@ -50,7 +50,7 @@ from cinder.volume import configuration
from cinder.volume import driver
from cinder.volume import volume_utils
VERSION = '1.5.0'
VERSION = '1.2.0'
LOG = logging.getLogger(__name__)
-692
View File
@@ -1,692 +0,0 @@
commit d85024bd803b3b91f15578ed22de4ce31856626f
Author: Vitaliy Filippov <vitalif@yourcmc.ru>
Date: Wed Jan 24 18:07:43 2024 +0300
Add Vitastor support
diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng
index 7fa5c2b8b5..2d77f391e7 100644
--- a/docs/schemas/domaincommon.rng
+++ b/docs/schemas/domaincommon.rng
@@ -1898,6 +1898,35 @@
</element>
</define>
+ <define name="diskSourceNetworkProtocolVitastor">
+ <element name="source">
+ <interleave>
+ <attribute name="protocol">
+ <value>vitastor</value>
+ </attribute>
+ <ref name="diskSourceCommon"/>
+ <optional>
+ <attribute name="name"/>
+ </optional>
+ <optional>
+ <attribute name="query"/>
+ </optional>
+ <zeroOrMore>
+ <ref name="diskSourceNetworkHost"/>
+ </zeroOrMore>
+ <optional>
+ <element name="config">
+ <attribute name="file">
+ <ref name="absFilePath"/>
+ </attribute>
+ <empty/>
+ </element>
+ </optional>
+ <empty/>
+ </interleave>
+ </element>
+ </define>
+
<define name="diskSourceNetworkProtocolISCSI">
<element name="source">
<attribute name="protocol">
@@ -2154,6 +2183,7 @@
<ref name="diskSourceNetworkProtocolSimple"/>
<ref name="diskSourceNetworkProtocolVxHS"/>
<ref name="diskSourceNetworkProtocolNFS"/>
+ <ref name="diskSourceNetworkProtocolVitastor"/>
</choice>
</define>
diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
index f89856b93e..a8cb9387e2 100644
--- a/include/libvirt/libvirt-storage.h
+++ b/include/libvirt/libvirt-storage.h
@@ -246,6 +246,7 @@ typedef enum {
VIR_CONNECT_LIST_STORAGE_POOLS_ZFS = 1 << 17,
VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE = 1 << 18,
VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT = 1 << 19,
+ VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR = 1 << 20,
} virConnectListAllStoragePoolsFlags;
int virConnectListAllStoragePools(virConnectPtr conn,
diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
index 5691b8d2d5..6669e8451d 100644
--- a/src/conf/domain_conf.c
+++ b/src/conf/domain_conf.c
@@ -8293,7 +8293,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
src->configFile = virXPathString("string(./config/@file)", ctxt);
if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
- src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS)
+ src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS ||
+ src->protocol == VIR_STORAGE_NET_PROTOCOL_VITASTOR)
src->query = virXMLPropString(node, "query");
if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
@@ -31267,6 +31268,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSource *src,
case VIR_STORAGE_POOL_MPATH:
case VIR_STORAGE_POOL_RBD:
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_SHEEPDOG:
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_LAST:
diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c
index a4271f1247..621c1b7b31 100644
--- a/src/conf/domain_validate.c
+++ b/src/conf/domain_validate.c
@@ -508,7 +508,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
}
}
- /* internal snapshots and config files are currently supported only with rbd: */
+ /* internal snapshots are currently supported only with rbd: */
if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
if (src->snapshot) {
@@ -517,11 +517,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
"only with 'rbd' disks"));
return -1;
}
-
+ }
+ /* config files are currently supported only with rbd and vitastor: */
+ if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
if (src->configFile) {
virReportError(VIR_ERR_XML_ERROR, "%s",
_("<config> element is currently supported "
- "only with 'rbd' disks"));
+ "only with 'rbd' and 'vitastor' disks"));
return -1;
}
}
diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
index 6690d26ffd..2255df9d28 100644
--- a/src/conf/storage_conf.c
+++ b/src/conf/storage_conf.c
@@ -60,7 +60,7 @@ VIR_ENUM_IMPL(virStoragePool,
"logical", "disk", "iscsi",
"iscsi-direct", "scsi", "mpath",
"rbd", "sheepdog", "gluster",
- "zfs", "vstorage",
+ "zfs", "vstorage", "vitastor",
);
VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
@@ -246,6 +246,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
.formatToString = virStorageFileFormatTypeToString,
}
},
+ {.poolType = VIR_STORAGE_POOL_VITASTOR,
+ .poolOptions = {
+ .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
+ VIR_STORAGE_POOL_SOURCE_NETWORK |
+ VIR_STORAGE_POOL_SOURCE_NAME),
+ },
+ .volOptions = {
+ .defaultFormat = VIR_STORAGE_FILE_RAW,
+ .formatFromString = virStorageVolumeFormatFromString,
+ .formatToString = virStorageFileFormatTypeToString,
+ }
+ },
{.poolType = VIR_STORAGE_POOL_SHEEPDOG,
.poolOptions = {
.flags = (VIR_STORAGE_POOL_SOURCE_HOST |
@@ -546,6 +558,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
_("element 'name' is mandatory for RBD pool"));
return -1;
}
+ if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
+ virReportError(VIR_ERR_XML_ERROR, "%s",
+ _("element 'name' is mandatory for Vitastor pool"));
+ return -1;
+ }
if (options->formatFromString) {
g_autofree char *format = NULL;
@@ -1176,6 +1193,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
/* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
* files, so they don't have a target */
if (def->type != VIR_STORAGE_POOL_RBD &&
+ def->type != VIR_STORAGE_POOL_VITASTOR &&
def->type != VIR_STORAGE_POOL_SHEEPDOG &&
def->type != VIR_STORAGE_POOL_GLUSTER &&
def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
index aaecf138d6..97172db38b 100644
--- a/src/conf/storage_conf.h
+++ b/src/conf/storage_conf.h
@@ -106,6 +106,7 @@ typedef enum {
VIR_STORAGE_POOL_GLUSTER, /* Gluster device */
VIR_STORAGE_POOL_ZFS, /* ZFS */
VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
+ VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
VIR_STORAGE_POOL_LAST,
} virStoragePoolType;
@@ -466,6 +467,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
VIR_CONNECT_LIST_STORAGE_POOLS_SCSI | \
VIR_CONNECT_LIST_STORAGE_POOLS_MPATH | \
VIR_CONNECT_LIST_STORAGE_POOLS_RBD | \
+ VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER | \
VIR_CONNECT_LIST_STORAGE_POOLS_ZFS | \
diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
index d42f715f26..29d8da3d10 100644
--- a/src/conf/storage_source_conf.c
+++ b/src/conf/storage_source_conf.c
@@ -86,6 +86,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
"ssh",
"vxhs",
"nfs",
+ "vitastor",
);
@@ -1265,6 +1266,7 @@ virStorageSourceNetworkDefaultPort(virStorageNetProtocol protocol)
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
return 24007;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_RBD:
/* we don't provide a default for RBD */
return 0;
diff --git a/src/conf/storage_source_conf.h b/src/conf/storage_source_conf.h
index c4a026881c..67568e9181 100644
--- a/src/conf/storage_source_conf.h
+++ b/src/conf/storage_source_conf.h
@@ -128,6 +128,7 @@ typedef enum {
VIR_STORAGE_NET_PROTOCOL_SSH,
VIR_STORAGE_NET_PROTOCOL_VXHS,
VIR_STORAGE_NET_PROTOCOL_NFS,
+ VIR_STORAGE_NET_PROTOCOL_VITASTOR,
VIR_STORAGE_NET_PROTOCOL_LAST
} virStorageNetProtocol;
diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
index 02903ac487..504df599fb 100644
--- a/src/conf/virstorageobj.c
+++ b/src/conf/virstorageobj.c
@@ -1481,6 +1481,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
return 1;
break;
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_RBD:
case VIR_STORAGE_POOL_LAST:
break;
@@ -1978,6 +1979,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
(obj->def->type == VIR_STORAGE_POOL_MPATH)) ||
(MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
(obj->def->type == VIR_STORAGE_POOL_RBD)) ||
+ (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
+ (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
(MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
(obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
(MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
index cbc522b300..b4760fa58d 100644
--- a/src/libvirt-storage.c
+++ b/src/libvirt-storage.c
@@ -92,6 +92,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
* VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
* VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
* VIR_CONNECT_LIST_STORAGE_POOLS_RBD
+ * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
* VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
* VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
* VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
index 1ac6253ad7..abe4587f94 100644
--- a/src/libxl/libxl_conf.c
+++ b/src/libxl/libxl_conf.c
@@ -962,6 +962,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSource *src,
case VIR_STORAGE_NET_PROTOCOL_SSH:
case VIR_STORAGE_NET_PROTOCOL_VXHS:
case VIR_STORAGE_NET_PROTOCOL_NFS:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_LAST:
case VIR_STORAGE_NET_PROTOCOL_NONE:
virReportError(VIR_ERR_NO_SUPPORT,
diff --git a/src/libxl/xen_xl.c b/src/libxl/xen_xl.c
index 7604e3d534..6453bb9776 100644
--- a/src/libxl/xen_xl.c
+++ b/src/libxl/xen_xl.c
@@ -1506,6 +1506,7 @@ xenFormatXLDiskSrcNet(virStorageSource *src)
case VIR_STORAGE_NET_PROTOCOL_SSH:
case VIR_STORAGE_NET_PROTOCOL_VXHS:
case VIR_STORAGE_NET_PROTOCOL_NFS:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_LAST:
case VIR_STORAGE_NET_PROTOCOL_NONE:
virReportError(VIR_ERR_NO_SUPPORT,
diff --git a/src/qemu/qemu_block.c b/src/qemu/qemu_block.c
index e5ff653a60..884ecc79ea 100644
--- a/src/qemu/qemu_block.c
+++ b/src/qemu/qemu_block.c
@@ -943,6 +943,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
}
+static virJSONValue *
+qemuBlockStorageSourceGetVitastorProps(virStorageSource *src)
+{
+ virJSONValue *ret = NULL;
+ virStorageNetHostDef *host;
+ size_t i;
+ g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER;
+ g_autofree char *etcd = NULL;
+
+ for (i = 0; i < src->nhosts; i++) {
+ host = src->hosts + i;
+ if ((virStorageNetHostTransport)host->transport != VIR_STORAGE_NET_HOST_TRANS_TCP) {
+ return NULL;
+ }
+ virBufferAsprintf(&buf, i > 0 ? ",%s:%u" : "%s:%u", host->name, host->port);
+ }
+ if (src->nhosts > 0) {
+ etcd = virBufferContentAndReset(&buf);
+ }
+
+ if (virJSONValueObjectCreate(&ret,
+ "S:etcd-host", etcd,
+ "S:etcd-prefix", src->query,
+ "S:config-path", src->configFile,
+ "s:image", src->path,
+ NULL) < 0)
+ return NULL;
+
+ return ret;
+}
+
+
static virJSONValue *
qemuBlockStorageSourceGetSheepdogProps(virStorageSource *src)
{
@@ -1233,6 +1265,12 @@ qemuBlockStorageSourceGetBackendProps(virStorageSource *src,
return NULL;
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ driver = "vitastor";
+ if (!(fileprops = qemuBlockStorageSourceGetVitastorProps(src)))
+ return NULL;
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
driver = "sheepdog";
if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
@@ -2244,6 +2282,7 @@ qemuBlockGetBackingStoreString(virStorageSource *src,
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_VXHS:
case VIR_STORAGE_NET_PROTOCOL_NFS:
case VIR_STORAGE_NET_PROTOCOL_SSH:
@@ -2626,6 +2665,12 @@ qemuBlockStorageSourceCreateGetStorageProps(virStorageSource *src,
return -1;
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ driver = "vitastor";
+ if (!(location = qemuBlockStorageSourceGetVitastorProps(src)))
+ return -1;
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
driver = "sheepdog";
if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
index d822533ccb..afe2087303 100644
--- a/src/qemu/qemu_command.c
+++ b/src/qemu/qemu_command.c
@@ -1723,6 +1723,43 @@ qemuBuildNetworkDriveStr(virStorageSource *src,
ret = virBufferContentAndReset(&buf);
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ if (strchr(src->path, ':')) {
+ virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
+ _("':' not allowed in Vitastor source volume name '%s'"),
+ src->path);
+ return NULL;
+ }
+
+ virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
+
+ if (src->nhosts > 0) {
+ virBufferAddLit(&buf, ":etcd-host=");
+ for (i = 0; i < src->nhosts; i++) {
+ if (i)
+ virBufferAddLit(&buf, ",");
+
+ /* assume host containing : is ipv6 */
+ if (strchr(src->hosts[i].name, ':'))
+ virBufferEscape(&buf, '\\', ":", "[%s]",
+ src->hosts[i].name);
+ else
+ virBufferAsprintf(&buf, "%s", src->hosts[i].name);
+
+ if (src->hosts[i].port)
+ virBufferAsprintf(&buf, "\\:%u", src->hosts[i].port);
+ }
+ }
+
+ if (src->configFile)
+ virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
+
+ if (src->query)
+ virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->query);
+
+ ret = virBufferContentAndReset(&buf);
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_VXHS:
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("VxHS protocol does not support URI syntax"));
diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
index a8401bac30..3dc1fe6db0 100644
--- a/src/qemu/qemu_domain.c
+++ b/src/qemu/qemu_domain.c
@@ -4731,7 +4731,8 @@ qemuDomainValidateStorageSource(virStorageSource *src,
if (src->query &&
(actualType != VIR_STORAGE_TYPE_NETWORK ||
(src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTPS &&
- src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP))) {
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP &&
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR))) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("query is supported only with HTTP(S) protocols"));
return -1;
@@ -9919,6 +9920,7 @@ qemuDomainPrepareStorageSourceTLS(virStorageSource *src,
break;
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
diff --git a/src/qemu/qemu_snapshot.c b/src/qemu/qemu_snapshot.c
index f92e00f9c0..854a3fbc90 100644
--- a/src/qemu/qemu_snapshot.c
+++ b/src/qemu/qemu_snapshot.c
@@ -393,6 +393,7 @@ qemuSnapshotPrepareDiskExternalInactive(virDomainSnapshotDiskDef *snapdisk,
case VIR_STORAGE_NET_PROTOCOL_NONE:
case VIR_STORAGE_NET_PROTOCOL_NBD:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
@@ -485,6 +486,7 @@ qemuSnapshotPrepareDiskExternalActive(virDomainObj *vm,
case VIR_STORAGE_NET_PROTOCOL_NONE:
case VIR_STORAGE_NET_PROTOCOL_NBD:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
case VIR_STORAGE_NET_PROTOCOL_HTTP:
@@ -638,6 +640,7 @@ qemuSnapshotPrepareDiskInternal(virDomainDiskDef *disk,
case VIR_STORAGE_NET_PROTOCOL_NONE:
case VIR_STORAGE_NET_PROTOCOL_NBD:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
index 4df2c75a2b..5a5e48ef71 100644
--- a/src/storage/storage_driver.c
+++ b/src/storage/storage_driver.c
@@ -1643,6 +1643,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_RBD:
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_SHEEPDOG:
case VIR_STORAGE_POOL_ZFS:
case VIR_STORAGE_POOL_LAST:
diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
index e48ae725ab..2017ccc88c 100644
--- a/src/storage_file/storage_source_backingstore.c
+++ b/src/storage_file/storage_source_backingstore.c
@@ -284,6 +284,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
}
+static int
+virStorageSourceParseVitastorColonString(const char *colonstr,
+ virStorageSource *src)
+{
+ char *p, *e, *next;
+ g_autofree char *options = NULL;
+
+ /* optionally skip the "vitastor:" prefix if provided */
+ if (STRPREFIX(colonstr, "vitastor:"))
+ colonstr += strlen("vitastor:");
+
+ options = g_strdup(colonstr);
+
+ p = options;
+ while (*p) {
+ /* find : delimiter or end of string */
+ for (e = p; *e && *e != ':'; ++e) {
+ if (*e == '\\') {
+ e++;
+ if (*e == '\0')
+ break;
+ }
+ }
+ if (*e == '\0') {
+ next = e; /* last kv pair */
+ } else {
+ next = e + 1;
+ *e = '\0';
+ }
+
+ if (STRPREFIX(p, "image=")) {
+ src->path = g_strdup(p + strlen("image="));
+ } else if (STRPREFIX(p, "etcd-prefix=")) {
+ src->query = g_strdup(p + strlen("etcd-prefix="));
+ } else if (STRPREFIX(p, "config-path=")) {
+ src->configFile = g_strdup(p + strlen("config-path="));
+ } else if (STRPREFIX(p, "etcd-host=")) {
+ char *h, *sep;
+
+ h = p + strlen("etcd-host=");
+ while (h < e) {
+ for (sep = h; sep < e; ++sep) {
+ if (*sep == '\\' && (sep[1] == ',' ||
+ sep[1] == ';' ||
+ sep[1] == ' ')) {
+ *sep = '\0';
+ sep += 2;
+ break;
+ }
+ }
+
+ if (virStorageSourceRBDAddHost(src, h) < 0)
+ return -1;
+
+ h = sep;
+ }
+ }
+
+ p = next;
+ }
+
+ if (!src->path) {
+ return -1;
+ }
+
+ return 0;
+}
+
+
static int
virStorageSourceParseNBDColonString(const char *nbdstr,
virStorageSource *src)
@@ -396,6 +465,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
return -1;
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ if (virStorageSourceParseVitastorColonString(path, src) < 0)
+ return -1;
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_LAST:
case VIR_STORAGE_NET_PROTOCOL_NONE:
@@ -984,6 +1058,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
return 0;
}
+static int
+virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
+ virJSONValue *json,
+ const char *jsonstr G_GNUC_UNUSED,
+ int opaque G_GNUC_UNUSED)
+{
+ const char *filename;
+ const char *image = virJSONValueObjectGetString(json, "image");
+ const char *conf = virJSONValueObjectGetString(json, "config-path");
+ const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
+ virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
+ size_t nservers;
+ size_t i;
+
+ src->type = VIR_STORAGE_TYPE_NETWORK;
+ src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
+
+ /* legacy syntax passed via 'filename' option */
+ if ((filename = virJSONValueObjectGetString(json, "filename")))
+ return virStorageSourceParseVitastorColonString(filename, src);
+
+ if (!image) {
+ virReportError(VIR_ERR_INVALID_ARG, "%s",
+ _("missing image name in Vitastor backing volume "
+ "JSON specification"));
+ return -1;
+ }
+
+ src->path = g_strdup(image);
+ src->configFile = g_strdup(conf);
+ src->query = g_strdup(etcd_prefix);
+
+ if (servers) {
+ nservers = virJSONValueArraySize(servers);
+
+ src->hosts = g_new0(virStorageNetHostDef, nservers);
+ src->nhosts = nservers;
+
+ for (i = 0; i < nservers; i++) {
+ if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
+ virJSONValueArrayGet(servers, i)) < 0)
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
static int
virStorageSourceParseBackingJSONRaw(virStorageSource *src,
virJSONValue *json,
@@ -1162,6 +1284,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
{"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
{"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
{"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
+ {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
{"raw", true, virStorageSourceParseBackingJSONRaw, 0},
{"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
{"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
diff --git a/src/test/test_driver.c b/src/test/test_driver.c
index 0e93b79922..b4d33f5f56 100644
--- a/src/test/test_driver.c
+++ b/src/test/test_driver.c
@@ -7367,6 +7367,7 @@ testStorageVolumeTypeForPool(int pooltype)
case VIR_STORAGE_POOL_ISCSI_DIRECT:
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_RBD:
+ case VIR_STORAGE_POOL_VITASTOR:
return VIR_STORAGE_VOL_NETWORK;
case VIR_STORAGE_POOL_LOGICAL:
case VIR_STORAGE_POOL_DISK:
diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
index eee75af746..8bd0a57bdd 100644
--- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
@@ -204,4 +204,11 @@
</enum>
</volOptions>
</pool>
+ <pool type='vitastor' supported='no'>
+ <volOptions>
+ <defaultFormat type='raw'/>
+ <enum name='targetFormatType'>
+ </enum>
+ </volOptions>
+ </pool>
</storagepoolCapabilities>
diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
index 805950a937..852df0de16 100644
--- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
+++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
@@ -204,4 +204,11 @@
</enum>
</volOptions>
</pool>
+ <pool type='vitastor' supported='yes'>
+ <volOptions>
+ <defaultFormat type='raw'/>
+ <enum name='targetFormatType'>
+ </enum>
+ </volOptions>
+ </pool>
</storagepoolCapabilities>
diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
index 449b745519..7f95cc8e08 100644
--- a/tests/storagepoolxml2argvtest.c
+++ b/tests/storagepoolxml2argvtest.c
@@ -68,6 +68,7 @@ testCompareXMLToArgvFiles(bool shouldFail,
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_ZFS:
case VIR_STORAGE_POOL_VSTORAGE:
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_LAST:
default:
VIR_TEST_DEBUG("pool type '%s' has no xml2argv test", defTypeStr);
diff --git a/tools/virsh-pool.c b/tools/virsh-pool.c
index d391257f6e..46799c4a90 100644
--- a/tools/virsh-pool.c
+++ b/tools/virsh-pool.c
@@ -1213,6 +1213,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
case VIR_STORAGE_POOL_VSTORAGE:
flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
break;
+ case VIR_STORAGE_POOL_VITASTOR:
+ flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
+ break;
case VIR_STORAGE_POOL_LAST:
break;
}
-643
View File
@@ -1,643 +0,0 @@
commit c1cd026e211e94b120028e7c98a6e4ce5afe9846
Author: Vitaliy Filippov <vitalif@yourcmc.ru>
Date: Wed Jan 24 22:04:50 2024 +0300
Add Vitastor support
diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
index aaad4a3da1..5f5daa8341 100644
--- a/include/libvirt/libvirt-storage.h
+++ b/include/libvirt/libvirt-storage.h
@@ -326,6 +326,7 @@ typedef enum {
VIR_CONNECT_LIST_STORAGE_POOLS_ZFS = 1 << 17, /* (Since: 1.2.8) */
VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE = 1 << 18, /* (Since: 3.1.0) */
VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT = 1 << 19, /* (Since: 5.6.0) */
+ VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR = 1 << 20, /* (Since: 5.0.0) */
} virConnectListAllStoragePoolsFlags;
int virConnectListAllStoragePools(virConnectPtr conn,
diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
index 22ad43e1d7..56c81d6852 100644
--- a/src/conf/domain_conf.c
+++ b/src/conf/domain_conf.c
@@ -7185,7 +7185,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
src->configFile = virXPathString("string(./config/@file)", ctxt);
if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
- src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS)
+ src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS ||
+ src->protocol == VIR_STORAGE_NET_PROTOCOL_VITASTOR)
src->query = virXMLPropString(node, "query");
if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
@@ -30618,6 +30619,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSource *src,
case VIR_STORAGE_POOL_MPATH:
case VIR_STORAGE_POOL_RBD:
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_SHEEPDOG:
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_LAST:
diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c
index c72108886e..c739ed6c43 100644
--- a/src/conf/domain_validate.c
+++ b/src/conf/domain_validate.c
@@ -495,6 +495,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
case VIR_STORAGE_NET_PROTOCOL_RBD:
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_NBD:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
@@ -541,7 +542,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
}
}
- /* internal snapshots and config files are currently supported only with rbd: */
+ /* internal snapshots are currently supported only with rbd: */
if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
if (src->snapshot) {
@@ -549,10 +550,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
_("<snapshot> element is currently supported only with 'rbd' disks"));
return -1;
}
+ }
+ /* config files are currently supported only with rbd and vitastor: */
+ if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
if (src->configFile) {
virReportError(VIR_ERR_XML_ERROR, "%s",
- _("<config> element is currently supported only with 'rbd' disks"));
+ _("<config> element is currently supported only with 'rbd' and 'vitastor' disks"));
return -1;
}
}
diff --git a/src/conf/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng
index b98a2ae602..7d7a872e01 100644
--- a/src/conf/schemas/domaincommon.rng
+++ b/src/conf/schemas/domaincommon.rng
@@ -1997,6 +1997,35 @@
</element>
</define>
+ <define name="diskSourceNetworkProtocolVitastor">
+ <element name="source">
+ <interleave>
+ <attribute name="protocol">
+ <value>vitastor</value>
+ </attribute>
+ <ref name="diskSourceCommon"/>
+ <optional>
+ <attribute name="name"/>
+ </optional>
+ <optional>
+ <attribute name="query"/>
+ </optional>
+ <zeroOrMore>
+ <ref name="diskSourceNetworkHost"/>
+ </zeroOrMore>
+ <optional>
+ <element name="config">
+ <attribute name="file">
+ <ref name="absFilePath"/>
+ </attribute>
+ <empty/>
+ </element>
+ </optional>
+ <empty/>
+ </interleave>
+ </element>
+ </define>
+
<define name="diskSourceNetworkProtocolISCSI">
<element name="source">
<attribute name="protocol">
@@ -2347,6 +2376,7 @@
<ref name="diskSourceNetworkProtocolSimple"/>
<ref name="diskSourceNetworkProtocolVxHS"/>
<ref name="diskSourceNetworkProtocolNFS"/>
+ <ref name="diskSourceNetworkProtocolVitastor"/>
</choice>
</define>
diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
index 68842004b7..1d69a788b6 100644
--- a/src/conf/storage_conf.c
+++ b/src/conf/storage_conf.c
@@ -56,7 +56,7 @@ VIR_ENUM_IMPL(virStoragePool,
"logical", "disk", "iscsi",
"iscsi-direct", "scsi", "mpath",
"rbd", "sheepdog", "gluster",
- "zfs", "vstorage",
+ "zfs", "vstorage", "vitastor",
);
VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
@@ -242,6 +242,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
.formatToString = virStorageFileFormatTypeToString,
}
},
+ {.poolType = VIR_STORAGE_POOL_VITASTOR,
+ .poolOptions = {
+ .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
+ VIR_STORAGE_POOL_SOURCE_NETWORK |
+ VIR_STORAGE_POOL_SOURCE_NAME),
+ },
+ .volOptions = {
+ .defaultFormat = VIR_STORAGE_FILE_RAW,
+ .formatFromString = virStorageVolumeFormatFromString,
+ .formatToString = virStorageFileFormatTypeToString,
+ }
+ },
{.poolType = VIR_STORAGE_POOL_SHEEPDOG,
.poolOptions = {
.flags = (VIR_STORAGE_POOL_SOURCE_HOST |
@@ -538,6 +550,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
_("element 'name' is mandatory for RBD pool"));
return -1;
}
+ if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
+ virReportError(VIR_ERR_XML_ERROR, "%s",
+ _("element 'name' is mandatory for Vitastor pool"));
+ return -1;
+ }
if (options->formatFromString) {
g_autofree char *format = NULL;
@@ -1127,6 +1144,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
/* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
* files, so they don't have a target */
if (def->type != VIR_STORAGE_POOL_RBD &&
+ def->type != VIR_STORAGE_POOL_VITASTOR &&
def->type != VIR_STORAGE_POOL_SHEEPDOG &&
def->type != VIR_STORAGE_POOL_GLUSTER &&
def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
index fc67957cfe..720c07ef74 100644
--- a/src/conf/storage_conf.h
+++ b/src/conf/storage_conf.h
@@ -103,6 +103,7 @@ typedef enum {
VIR_STORAGE_POOL_GLUSTER, /* Gluster device */
VIR_STORAGE_POOL_ZFS, /* ZFS */
VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
+ VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
VIR_STORAGE_POOL_LAST,
} virStoragePoolType;
@@ -454,6 +455,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
VIR_CONNECT_LIST_STORAGE_POOLS_SCSI | \
VIR_CONNECT_LIST_STORAGE_POOLS_MPATH | \
VIR_CONNECT_LIST_STORAGE_POOLS_RBD | \
+ VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER | \
VIR_CONNECT_LIST_STORAGE_POOLS_ZFS | \
diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
index f974a521b1..cd394d0a9f 100644
--- a/src/conf/storage_source_conf.c
+++ b/src/conf/storage_source_conf.c
@@ -88,6 +88,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
"ssh",
"vxhs",
"nfs",
+ "vitastor",
);
@@ -1301,6 +1302,7 @@ virStorageSourceNetworkDefaultPort(virStorageNetProtocol protocol)
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
return 24007;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_RBD:
/* we don't provide a default for RBD */
return 0;
diff --git a/src/conf/storage_source_conf.h b/src/conf/storage_source_conf.h
index 5e7d127453..283709eeb3 100644
--- a/src/conf/storage_source_conf.h
+++ b/src/conf/storage_source_conf.h
@@ -129,6 +129,7 @@ typedef enum {
VIR_STORAGE_NET_PROTOCOL_SSH,
VIR_STORAGE_NET_PROTOCOL_VXHS,
VIR_STORAGE_NET_PROTOCOL_NFS,
+ VIR_STORAGE_NET_PROTOCOL_VITASTOR,
VIR_STORAGE_NET_PROTOCOL_LAST
} virStorageNetProtocol;
diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
index 59fa5da372..4739167f5f 100644
--- a/src/conf/virstorageobj.c
+++ b/src/conf/virstorageobj.c
@@ -1438,6 +1438,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
return 1;
break;
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_ISCSI_DIRECT:
case VIR_STORAGE_POOL_RBD:
case VIR_STORAGE_POOL_LAST:
@@ -1921,6 +1922,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
(obj->def->type == VIR_STORAGE_POOL_MPATH)) ||
(MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
(obj->def->type == VIR_STORAGE_POOL_RBD)) ||
+ (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
+ (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
(MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
(obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
(MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
index db7660aac4..561df34709 100644
--- a/src/libvirt-storage.c
+++ b/src/libvirt-storage.c
@@ -94,6 +94,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
* VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
* VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
* VIR_CONNECT_LIST_STORAGE_POOLS_RBD
+ * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
* VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
* VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
* VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
index 62e1be6672..71a1d42896 100644
--- a/src/libxl/libxl_conf.c
+++ b/src/libxl/libxl_conf.c
@@ -979,6 +979,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSource *src,
case VIR_STORAGE_NET_PROTOCOL_SSH:
case VIR_STORAGE_NET_PROTOCOL_VXHS:
case VIR_STORAGE_NET_PROTOCOL_NFS:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_LAST:
case VIR_STORAGE_NET_PROTOCOL_NONE:
virReportError(VIR_ERR_NO_SUPPORT,
diff --git a/src/libxl/xen_xl.c b/src/libxl/xen_xl.c
index f175359307..8efcf4c329 100644
--- a/src/libxl/xen_xl.c
+++ b/src/libxl/xen_xl.c
@@ -1456,6 +1456,7 @@ xenFormatXLDiskSrcNet(virStorageSource *src)
case VIR_STORAGE_NET_PROTOCOL_SSH:
case VIR_STORAGE_NET_PROTOCOL_VXHS:
case VIR_STORAGE_NET_PROTOCOL_NFS:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_LAST:
case VIR_STORAGE_NET_PROTOCOL_NONE:
virReportError(VIR_ERR_NO_SUPPORT,
diff --git a/src/qemu/qemu_block.c b/src/qemu/qemu_block.c
index 7e9daf0bdc..825b4a3006 100644
--- a/src/qemu/qemu_block.c
+++ b/src/qemu/qemu_block.c
@@ -758,6 +758,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
}
+static virJSONValue *
+qemuBlockStorageSourceGetVitastorProps(virStorageSource *src)
+{
+ virJSONValue *ret = NULL;
+ virStorageNetHostDef *host;
+ size_t i;
+ g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER;
+ g_autofree char *etcd = NULL;
+
+ for (i = 0; i < src->nhosts; i++) {
+ host = src->hosts + i;
+ if ((virStorageNetHostTransport)host->transport != VIR_STORAGE_NET_HOST_TRANS_TCP) {
+ return NULL;
+ }
+ virBufferAsprintf(&buf, i > 0 ? ",%s:%u" : "%s:%u", host->name, host->port);
+ }
+ if (src->nhosts > 0) {
+ etcd = virBufferContentAndReset(&buf);
+ }
+
+ if (virJSONValueObjectAdd(&ret,
+ "S:etcd-host", etcd,
+ "S:etcd-prefix", src->query,
+ "S:config-path", src->configFile,
+ "s:image", src->path,
+ NULL) < 0)
+ return NULL;
+
+ return ret;
+}
+
+
static virJSONValue *
qemuBlockStorageSourceGetSheepdogProps(virStorageSource *src)
{
@@ -1140,6 +1172,12 @@ qemuBlockStorageSourceGetBackendProps(virStorageSource *src,
return NULL;
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ driver = "vitastor";
+ if (!(fileprops = qemuBlockStorageSourceGetVitastorProps(src)))
+ return NULL;
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
driver = "sheepdog";
if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
@@ -2032,6 +2070,7 @@ qemuBlockGetBackingStoreString(virStorageSource *src,
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_VXHS:
case VIR_STORAGE_NET_PROTOCOL_NFS:
case VIR_STORAGE_NET_PROTOCOL_SSH:
@@ -2415,6 +2454,12 @@ qemuBlockStorageSourceCreateGetStorageProps(virStorageSource *src,
return -1;
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ driver = "vitastor";
+ if (!(location = qemuBlockStorageSourceGetVitastorProps(src)))
+ return -1;
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
driver = "sheepdog";
if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
index 953808fcfe..62860283d8 100644
--- a/src/qemu/qemu_domain.c
+++ b/src/qemu/qemu_domain.c
@@ -5215,7 +5215,8 @@ qemuDomainValidateStorageSource(virStorageSource *src,
if (src->query &&
(actualType != VIR_STORAGE_TYPE_NETWORK ||
(src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTPS &&
- src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP))) {
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP &&
+ src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR))) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("query is supported only with HTTP(S) protocols"));
return -1;
@@ -10340,6 +10341,7 @@ qemuDomainPrepareStorageSourceTLS(virStorageSource *src,
break;
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
diff --git a/src/qemu/qemu_snapshot.c b/src/qemu/qemu_snapshot.c
index 73ff533827..e9c799ca8f 100644
--- a/src/qemu/qemu_snapshot.c
+++ b/src/qemu/qemu_snapshot.c
@@ -423,6 +423,7 @@ qemuSnapshotPrepareDiskExternalInactive(virDomainSnapshotDiskDef *snapdisk,
case VIR_STORAGE_NET_PROTOCOL_NONE:
case VIR_STORAGE_NET_PROTOCOL_NBD:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
@@ -648,6 +649,7 @@ qemuSnapshotPrepareDiskInternal(virDomainDiskDef *disk,
case VIR_STORAGE_NET_PROTOCOL_NONE:
case VIR_STORAGE_NET_PROTOCOL_NBD:
case VIR_STORAGE_NET_PROTOCOL_RBD:
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
case VIR_STORAGE_NET_PROTOCOL_ISCSI:
diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
index 314fe930e0..fb615a8b4e 100644
--- a/src/storage/storage_driver.c
+++ b/src/storage/storage_driver.c
@@ -1626,6 +1626,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_RBD:
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_SHEEPDOG:
case VIR_STORAGE_POOL_ZFS:
case VIR_STORAGE_POOL_LAST:
diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
index 80681924ea..8a3ade9ec0 100644
--- a/src/storage_file/storage_source_backingstore.c
+++ b/src/storage_file/storage_source_backingstore.c
@@ -287,6 +287,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
}
+static int
+virStorageSourceParseVitastorColonString(const char *colonstr,
+ virStorageSource *src)
+{
+ char *p, *e, *next;
+ g_autofree char *options = NULL;
+
+ /* optionally skip the "vitastor:" prefix if provided */
+ if (STRPREFIX(colonstr, "vitastor:"))
+ colonstr += strlen("vitastor:");
+
+ options = g_strdup(colonstr);
+
+ p = options;
+ while (*p) {
+ /* find : delimiter or end of string */
+ for (e = p; *e && *e != ':'; ++e) {
+ if (*e == '\\') {
+ e++;
+ if (*e == '\0')
+ break;
+ }
+ }
+ if (*e == '\0') {
+ next = e; /* last kv pair */
+ } else {
+ next = e + 1;
+ *e = '\0';
+ }
+
+ if (STRPREFIX(p, "image=")) {
+ src->path = g_strdup(p + strlen("image="));
+ } else if (STRPREFIX(p, "etcd-prefix=")) {
+ src->query = g_strdup(p + strlen("etcd-prefix="));
+ } else if (STRPREFIX(p, "config-path=")) {
+ src->configFile = g_strdup(p + strlen("config-path="));
+ } else if (STRPREFIX(p, "etcd-host=")) {
+ char *h, *sep;
+
+ h = p + strlen("etcd-host=");
+ while (h < e) {
+ for (sep = h; sep < e; ++sep) {
+ if (*sep == '\\' && (sep[1] == ',' ||
+ sep[1] == ';' ||
+ sep[1] == ' ')) {
+ *sep = '\0';
+ sep += 2;
+ break;
+ }
+ }
+
+ if (virStorageSourceRBDAddHost(src, h) < 0)
+ return -1;
+
+ h = sep;
+ }
+ }
+
+ p = next;
+ }
+
+ if (!src->path) {
+ return -1;
+ }
+
+ return 0;
+}
+
+
static int
virStorageSourceParseNBDColonString(const char *nbdstr,
virStorageSource *src)
@@ -399,6 +468,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
return -1;
break;
+ case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+ if (virStorageSourceParseVitastorColonString(path, src) < 0)
+ return -1;
+ break;
+
case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
case VIR_STORAGE_NET_PROTOCOL_LAST:
case VIR_STORAGE_NET_PROTOCOL_NONE:
@@ -975,6 +1049,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
return 0;
}
+static int
+virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
+ virJSONValue *json,
+ const char *jsonstr G_GNUC_UNUSED,
+ int opaque G_GNUC_UNUSED)
+{
+ const char *filename;
+ const char *image = virJSONValueObjectGetString(json, "image");
+ const char *conf = virJSONValueObjectGetString(json, "config-path");
+ const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
+ virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
+ size_t nservers;
+ size_t i;
+
+ src->type = VIR_STORAGE_TYPE_NETWORK;
+ src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
+
+ /* legacy syntax passed via 'filename' option */
+ if ((filename = virJSONValueObjectGetString(json, "filename")))
+ return virStorageSourceParseVitastorColonString(filename, src);
+
+ if (!image) {
+ virReportError(VIR_ERR_INVALID_ARG, "%s",
+ _("missing image name in Vitastor backing volume "
+ "JSON specification"));
+ return -1;
+ }
+
+ src->path = g_strdup(image);
+ src->configFile = g_strdup(conf);
+ src->query = g_strdup(etcd_prefix);
+
+ if (servers) {
+ nservers = virJSONValueArraySize(servers);
+
+ src->hosts = g_new0(virStorageNetHostDef, nservers);
+ src->nhosts = nservers;
+
+ for (i = 0; i < nservers; i++) {
+ if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
+ virJSONValueArrayGet(servers, i)) < 0)
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
static int
virStorageSourceParseBackingJSONRaw(virStorageSource *src,
virJSONValue *json,
@@ -1152,6 +1274,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
{"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
{"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
{"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
+ {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
{"raw", true, virStorageSourceParseBackingJSONRaw, 0},
{"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
{"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
diff --git a/src/test/test_driver.c b/src/test/test_driver.c
index e87d7cfd44..ccc05d7aae 100644
--- a/src/test/test_driver.c
+++ b/src/test/test_driver.c
@@ -7335,6 +7335,7 @@ testStorageVolumeTypeForPool(int pooltype)
case VIR_STORAGE_POOL_ISCSI_DIRECT:
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_RBD:
+ case VIR_STORAGE_POOL_VITASTOR:
return VIR_STORAGE_VOL_NETWORK;
case VIR_STORAGE_POOL_LOGICAL:
case VIR_STORAGE_POOL_DISK:
diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
index eee75af746..8bd0a57bdd 100644
--- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
@@ -204,4 +204,11 @@
</enum>
</volOptions>
</pool>
+ <pool type='vitastor' supported='no'>
+ <volOptions>
+ <defaultFormat type='raw'/>
+ <enum name='targetFormatType'>
+ </enum>
+ </volOptions>
+ </pool>
</storagepoolCapabilities>
diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
index 805950a937..852df0de16 100644
--- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
+++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
@@ -204,4 +204,11 @@
</enum>
</volOptions>
</pool>
+ <pool type='vitastor' supported='yes'>
+ <volOptions>
+ <defaultFormat type='raw'/>
+ <enum name='targetFormatType'>
+ </enum>
+ </volOptions>
+ </pool>
</storagepoolCapabilities>
diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
index e8e40d695e..db55fe5f3a 100644
--- a/tests/storagepoolxml2argvtest.c
+++ b/tests/storagepoolxml2argvtest.c
@@ -65,6 +65,7 @@ testCompareXMLToArgvFiles(bool shouldFail,
case VIR_STORAGE_POOL_GLUSTER:
case VIR_STORAGE_POOL_ZFS:
case VIR_STORAGE_POOL_VSTORAGE:
+ case VIR_STORAGE_POOL_VITASTOR:
case VIR_STORAGE_POOL_LAST:
default:
VIR_TEST_DEBUG("pool type '%s' has no xml2argv test", defTypeStr);
diff --git a/tools/virsh-pool.c b/tools/virsh-pool.c
index 36f00cf643..5f5bd3464e 100644
--- a/tools/virsh-pool.c
+++ b/tools/virsh-pool.c
@@ -1223,6 +1223,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
case VIR_STORAGE_POOL_VSTORAGE:
flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
break;
+ case VIR_STORAGE_POOL_VITASTOR:
+ flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
+ break;
case VIR_STORAGE_POOL_LAST:
break;
}
-190
View File
@@ -1,190 +0,0 @@
Index: pve-qemu-kvm-8.1.2/block/meson.build
===================================================================
--- pve-qemu-kvm-8.1.2.orig/block/meson.build
+++ pve-qemu-kvm-8.1.2/block/meson.build
@@ -123,6 +123,7 @@ foreach m : [
[libnfs, 'nfs', files('nfs.c')],
[libssh, 'ssh', files('ssh.c')],
[rbd, 'rbd', files('rbd.c')],
+ [vitastor, 'vitastor', files('vitastor.c')],
]
if m[0].found()
module_ss = ss.source_set()
Index: pve-qemu-kvm-8.1.2/meson.build
===================================================================
--- pve-qemu-kvm-8.1.2.orig/meson.build
+++ pve-qemu-kvm-8.1.2/meson.build
@@ -1303,6 +1303,26 @@ if not get_option('rbd').auto() or have_
endif
endif
+vitastor = not_found
+if not get_option('vitastor').auto() or have_block
+ libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
+ required: get_option('vitastor'))
+ if libvitastor_client.found()
+ if cc.links('''
+ #include <vitastor_c.h>
+ int main(void) {
+ vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+ return 0;
+ }''', dependencies: libvitastor_client)
+ vitastor = declare_dependency(dependencies: libvitastor_client)
+ elif get_option('vitastor').enabled()
+ error('could not link libvitastor_client')
+ else
+ warning('could not link libvitastor_client, disabling')
+ endif
+ endif
+endif
+
glusterfs = not_found
glusterfs_ftruncate_has_stat = false
glusterfs_iocb_has_stat = false
@@ -2123,6 +2143,7 @@ if numa.found()
endif
config_host_data.set('CONFIG_OPENGL', opengl.found())
config_host_data.set('CONFIG_RBD', rbd.found())
+config_host_data.set('CONFIG_VITASTOR', vitastor.found())
config_host_data.set('CONFIG_RDMA', rdma.found())
config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
config_host_data.set('CONFIG_SDL', sdl.found())
@@ -4298,6 +4319,7 @@ summary_info += {'fdt support': fd
summary_info += {'libcap-ng support': libcap_ng}
summary_info += {'bpf support': libbpf}
summary_info += {'rbd support': rbd}
+summary_info += {'vitastor support': vitastor}
summary_info += {'smartcard support': cacard}
summary_info += {'U2F support': u2f}
summary_info += {'libusb': libusb}
Index: pve-qemu-kvm-8.1.2/meson_options.txt
===================================================================
--- pve-qemu-kvm-8.1.2.orig/meson_options.txt
+++ pve-qemu-kvm-8.1.2/meson_options.txt
@@ -186,6 +186,8 @@ option('lzo', type : 'feature', value :
description: 'lzo compression support')
option('rbd', type : 'feature', value : 'auto',
description: 'Ceph block device driver')
+option('vitastor', type : 'feature', value : 'auto',
+ description: 'Vitastor block device driver')
option('opengl', type : 'feature', value : 'auto',
description: 'OpenGL support')
option('rdma', type : 'feature', value : 'auto',
Index: pve-qemu-kvm-8.1.2/qapi/block-core.json
===================================================================
--- pve-qemu-kvm-8.1.2.orig/qapi/block-core.json
+++ pve-qemu-kvm-8.1.2/qapi/block-core.json
@@ -3403,7 +3403,7 @@
'raw', 'rbd',
{ 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
'pbs',
- 'ssh', 'throttle', 'vdi', 'vhdx',
+ 'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
{ 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
@@ -4465,6 +4465,28 @@
'*server': ['InetSocketAddressBase'] } }
##
+# @BlockdevOptionsVitastor:
+#
+# Driver specific block device options for vitastor
+#
+# @image: Image name
+# @inode: Inode number
+# @pool: Pool ID
+# @size: Desired image size in bytes
+# @config-path: Path to Vitastor configuration
+# @etcd-host: etcd connection address(es)
+# @etcd-prefix: etcd key/value prefix
+##
+{ 'struct': 'BlockdevOptionsVitastor',
+ 'data': { '*inode': 'uint64',
+ '*pool': 'uint64',
+ '*size': 'uint64',
+ '*image': 'str',
+ '*config-path': 'str',
+ '*etcd-host': 'str',
+ '*etcd-prefix': 'str' } }
+
+##
# @ReplicationMode:
#
# An enumeration of replication modes.
@@ -4923,6 +4945,7 @@
'throttle': 'BlockdevOptionsThrottle',
'vdi': 'BlockdevOptionsGenericFormat',
'vhdx': 'BlockdevOptionsGenericFormat',
+ 'vitastor': 'BlockdevOptionsVitastor',
'virtio-blk-vfio-pci':
{ 'type': 'BlockdevOptionsVirtioBlkVfioPci',
'if': 'CONFIG_BLKIO' },
@@ -5360,6 +5383,17 @@
'*encrypt' : 'RbdEncryptionCreateOptions' } }
##
+# @BlockdevCreateOptionsVitastor:
+#
+# Driver specific image creation options for Vitastor.
+#
+# @size: Size of the virtual disk in bytes
+##
+{ 'struct': 'BlockdevCreateOptionsVitastor',
+ 'data': { 'location': 'BlockdevOptionsVitastor',
+ 'size': 'size' } }
+
+##
# @BlockdevVmdkSubformat:
#
# Subformat options for VMDK images
@@ -5581,6 +5615,7 @@
'ssh': 'BlockdevCreateOptionsSsh',
'vdi': 'BlockdevCreateOptionsVdi',
'vhdx': 'BlockdevCreateOptionsVhdx',
+ 'vitastor': 'BlockdevCreateOptionsVitastor',
'vmdk': 'BlockdevCreateOptionsVmdk',
'vpc': 'BlockdevCreateOptionsVpc'
} }
Index: pve-qemu-kvm-8.1.2/scripts/ci/org.centos/stream/8/x86_64/configure
===================================================================
--- pve-qemu-kvm-8.1.2.orig/scripts/ci/org.centos/stream/8/x86_64/configure
+++ pve-qemu-kvm-8.1.2/scripts/ci/org.centos/stream/8/x86_64/configure
@@ -30,7 +30,7 @@
--with-suffix="qemu-kvm" \
--firmwarepath=/usr/share/qemu-firmware \
--target-list="x86_64-softmmu" \
---block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
+--block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,vitastor,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
--audio-drv-list="" \
--block-drv-ro-whitelist="vmdk,vhdx,vpc,https,ssh" \
--with-coroutine=ucontext \
@@ -176,6 +176,7 @@
--enable-opengl \
--enable-pie \
--enable-rbd \
+--enable-vitastor \
--enable-rdma \
--enable-seccomp \
--enable-snappy \
Index: pve-qemu-kvm-8.1.2/scripts/meson-buildoptions.sh
===================================================================
--- pve-qemu-kvm-8.1.2.orig/scripts/meson-buildoptions.sh
+++ pve-qemu-kvm-8.1.2/scripts/meson-buildoptions.sh
@@ -153,6 +153,7 @@ meson_options_help() {
printf "%s\n" ' qed qed image format support'
printf "%s\n" ' qga-vss build QGA VSS support (broken with MinGW)'
printf "%s\n" ' rbd Ceph block device driver'
+ printf "%s\n" ' vitastor Vitastor block device driver'
printf "%s\n" ' rdma Enable RDMA-based migration'
printf "%s\n" ' replication replication support'
printf "%s\n" ' sdl SDL user interface'
@@ -416,6 +417,8 @@ _meson_option_parse() {
--disable-qom-cast-debug) printf "%s" -Dqom_cast_debug=false ;;
--enable-rbd) printf "%s" -Drbd=enabled ;;
--disable-rbd) printf "%s" -Drbd=disabled ;;
+ --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
+ --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
--enable-rdma) printf "%s" -Drdma=enabled ;;
--disable-rdma) printf "%s" -Drdma=disabled ;;
--enable-replication) printf "%s" -Dreplication=enabled ;;
-190
View File
@@ -1,190 +0,0 @@
diff --git a/block/meson.build b/block/meson.build
index 529fc172c6..d542dc0609 100644
--- a/block/meson.build
+++ b/block/meson.build
@@ -110,6 +110,7 @@ foreach m : [
[libnfs, 'nfs', files('nfs.c')],
[libssh, 'ssh', files('ssh.c')],
[rbd, 'rbd', files('rbd.c')],
+ [vitastor, 'vitastor', files('vitastor.c')],
]
if m[0].found()
module_ss = ss.source_set()
diff --git a/meson.build b/meson.build
index a9c4f28247..8496cf13f1 100644
--- a/meson.build
+++ b/meson.build
@@ -1303,6 +1303,26 @@ if not get_option('rbd').auto() or have_block
endif
endif
+vitastor = not_found
+if not get_option('vitastor').auto() or have_block
+ libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
+ required: get_option('vitastor'))
+ if libvitastor_client.found()
+ if cc.links('''
+ #include <vitastor_c.h>
+ int main(void) {
+ vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+ return 0;
+ }''', dependencies: libvitastor_client)
+ vitastor = declare_dependency(dependencies: libvitastor_client)
+ elif get_option('vitastor').enabled()
+ error('could not link libvitastor_client')
+ else
+ warning('could not link libvitastor_client, disabling')
+ endif
+ endif
+endif
+
glusterfs = not_found
glusterfs_ftruncate_has_stat = false
glusterfs_iocb_has_stat = false
@@ -2119,6 +2139,7 @@ if numa.found()
endif
config_host_data.set('CONFIG_OPENGL', opengl.found())
config_host_data.set('CONFIG_RBD', rbd.found())
+config_host_data.set('CONFIG_VITASTOR', vitastor.found())
config_host_data.set('CONFIG_RDMA', rdma.found())
config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
config_host_data.set('CONFIG_SDL', sdl.found())
@@ -4286,6 +4307,7 @@ summary_info += {'fdt support': fdt_opt == 'disabled' ? false : fdt_opt}
summary_info += {'libcap-ng support': libcap_ng}
summary_info += {'bpf support': libbpf}
summary_info += {'rbd support': rbd}
+summary_info += {'vitastor support': vitastor}
summary_info += {'smartcard support': cacard}
summary_info += {'U2F support': u2f}
summary_info += {'libusb': libusb}
diff --git a/meson_options.txt b/meson_options.txt
index ae6d8f469d..e3d9f8404d 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -186,6 +186,8 @@ option('lzo', type : 'feature', value : 'auto',
description: 'lzo compression support')
option('rbd', type : 'feature', value : 'auto',
description: 'Ceph block device driver')
+option('vitastor', type : 'feature', value : 'auto',
+ description: 'Vitastor block device driver')
option('opengl', type : 'feature', value : 'auto',
description: 'OpenGL support')
option('rdma', type : 'feature', value : 'auto',
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 2b1d493d6e..90673fdbdc 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -3146,7 +3146,7 @@
'parallels', 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum',
'raw', 'rbd',
{ 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
- 'ssh', 'throttle', 'vdi', 'vhdx',
+ 'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
{ 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
@@ -4196,6 +4196,28 @@
'*key-secret': 'str',
'*server': ['InetSocketAddressBase'] } }
+##
+# @BlockdevOptionsVitastor:
+#
+# Driver specific block device options for vitastor
+#
+# @image: Image name
+# @inode: Inode number
+# @pool: Pool ID
+# @size: Desired image size in bytes
+# @config-path: Path to Vitastor configuration
+# @etcd-host: etcd connection address(es)
+# @etcd-prefix: etcd key/value prefix
+##
+{ 'struct': 'BlockdevOptionsVitastor',
+ 'data': { '*inode': 'uint64',
+ '*pool': 'uint64',
+ '*size': 'uint64',
+ '*image': 'str',
+ '*config-path': 'str',
+ '*etcd-host': 'str',
+ '*etcd-prefix': 'str' } }
+
##
# @ReplicationMode:
#
@@ -4654,6 +4676,7 @@
'throttle': 'BlockdevOptionsThrottle',
'vdi': 'BlockdevOptionsGenericFormat',
'vhdx': 'BlockdevOptionsGenericFormat',
+ 'vitastor': 'BlockdevOptionsVitastor',
'virtio-blk-vfio-pci':
{ 'type': 'BlockdevOptionsVirtioBlkVfioPci',
'if': 'CONFIG_BLKIO' },
@@ -5089,6 +5112,17 @@
'*cluster-size' : 'size',
'*encrypt' : 'RbdEncryptionCreateOptions' } }
+##
+# @BlockdevCreateOptionsVitastor:
+#
+# Driver specific image creation options for Vitastor.
+#
+# @size: Size of the virtual disk in bytes
+##
+{ 'struct': 'BlockdevCreateOptionsVitastor',
+ 'data': { 'location': 'BlockdevOptionsVitastor',
+ 'size': 'size' } }
+
##
# @BlockdevVmdkSubformat:
#
@@ -5311,6 +5345,7 @@
'ssh': 'BlockdevCreateOptionsSsh',
'vdi': 'BlockdevCreateOptionsVdi',
'vhdx': 'BlockdevCreateOptionsVhdx',
+ 'vitastor': 'BlockdevCreateOptionsVitastor',
'vmdk': 'BlockdevCreateOptionsVmdk',
'vpc': 'BlockdevCreateOptionsVpc'
} }
diff --git a/scripts/ci/org.centos/stream/8/x86_64/configure b/scripts/ci/org.centos/stream/8/x86_64/configure
index d02b09a4b9..f0b5fbfef3 100755
--- a/scripts/ci/org.centos/stream/8/x86_64/configure
+++ b/scripts/ci/org.centos/stream/8/x86_64/configure
@@ -30,7 +30,7 @@
--with-suffix="qemu-kvm" \
--firmwarepath=/usr/share/qemu-firmware \
--target-list="x86_64-softmmu" \
---block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
+--block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,vitastor,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
--audio-drv-list="" \
--block-drv-ro-whitelist="vmdk,vhdx,vpc,https,ssh" \
--with-coroutine=ucontext \
@@ -176,6 +176,7 @@
--enable-opengl \
--enable-pie \
--enable-rbd \
+--enable-vitastor \
--enable-rdma \
--enable-seccomp \
--enable-snappy \
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index d7020af175..94958eb6fa 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -153,6 +153,7 @@ meson_options_help() {
printf "%s\n" ' qed qed image format support'
printf "%s\n" ' qga-vss build QGA VSS support (broken with MinGW)'
printf "%s\n" ' rbd Ceph block device driver'
+ printf "%s\n" ' vitastor Vitastor block device driver'
printf "%s\n" ' rdma Enable RDMA-based migration'
printf "%s\n" ' replication replication support'
printf "%s\n" ' sdl SDL user interface'
@@ -416,6 +417,8 @@ _meson_option_parse() {
--disable-qom-cast-debug) printf "%s" -Dqom_cast_debug=false ;;
--enable-rbd) printf "%s" -Drbd=enabled ;;
--disable-rbd) printf "%s" -Drbd=disabled ;;
+ --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
+ --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
--enable-rdma) printf "%s" -Drdma=enabled ;;
--disable-rdma) printf "%s" -Drdma=disabled ;;
--enable-replication) printf "%s" -Dreplication=enabled ;;
-28
View File
@@ -1,28 +0,0 @@
name: Pull Request
about: Submit a pull request
body:
- type: textarea
id: description
attributes:
label: Description
description: Describe your pull request
placeholder: ""
value: ""
validations:
required: true
- type: input
id: author
attributes:
label: Contributor Name
description: Contributor Name or Company Details if the Contributor is a company
placeholder: ""
validations:
required: false
- type: checkboxes
id: terms
attributes:
label: CLA
description: By submitting this pull request, I accept [Vitastor CLA](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md)
options:
- label: "I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md"
required: true
+1 -1
View File
@@ -24,4 +24,4 @@ rm fio
mv fio-copy fio
FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
tar --transform 's#^#vitastor-1.5.0/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.5.0$(rpm --eval '%dist').tar.gz *
tar --transform 's#^#vitastor-1.2.0/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.2.0$(rpm --eval '%dist').tar.gz *
+1 -2
View File
@@ -15,7 +15,6 @@ RUN yumdownloader --disablerepo=centos-sclo-rh --source fio
RUN rpm --nomd5 -i fio*.src.rpm
RUN rm -f /etc/yum.repos.d/CentOS-Media.repo
RUN cd ~/rpmbuild/SPECS && yum-builddep -y fio.spec
RUN yum -y install cmake3
ADD https://vitastor.io/rpms/liburing-el7/liburing-0.7-2.el7.src.rpm /root
@@ -36,7 +35,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-1.5.0.el7.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-1.2.0.el7.tar.gz ~/rpmbuild/SOURCES; \
cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
cd ~/rpmbuild/SPECS/; \
rpmbuild -ba vitastor.spec; \
+4 -7
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 1.5.0
Version: 1.2.0
Release: 1%{?dist}
Summary: Vitastor, a fast software-defined clustered block storage
License: Vitastor Network Public License 1.1
URL: https://vitastor.io/
Source0: vitastor-1.5.0.el7.tar.gz
Source0: vitastor-1.2.0.el7.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel
@@ -16,7 +16,7 @@ BuildRequires: jerasure-devel
BuildRequires: libisa-l-devel
BuildRequires: gf-complete-devel
BuildRequires: libibverbs-devel
BuildRequires: cmake3
BuildRequires: cmake
Requires: vitastor-osd = %{version}-%{release}
Requires: vitastor-mon = %{version}-%{release}
Requires: vitastor-client = %{version}-%{release}
@@ -94,7 +94,7 @@ Vitastor fio drivers for benchmarking.
%build
. /opt/rh/devtoolset-9/enable
%cmake3 .
%cmake .
%make_build
@@ -149,12 +149,9 @@ mkdir -p /etc/vitastor
%_bindir/vitastor-nfs
%_bindir/vitastor-cli
%_bindir/vitastor-rm
%_bindir/vitastor-kv
%_bindir/vitastor-kv-stress
%_bindir/vita
%_libdir/libvitastor_blk.so*
%_libdir/libvitastor_client.so*
%_libdir/libvitastor_kv.so*
%files -n vitastor-client-devel
+1 -1
View File
@@ -35,7 +35,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-1.5.0.el8.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-1.2.0.el8.tar.gz ~/rpmbuild/SOURCES; \
cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
cd ~/rpmbuild/SPECS/; \
rpmbuild -ba vitastor.spec; \
+2 -5
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 1.5.0
Version: 1.2.0
Release: 1%{?dist}
Summary: Vitastor, a fast software-defined clustered block storage
License: Vitastor Network Public License 1.1
URL: https://vitastor.io/
Source0: vitastor-1.5.0.el8.tar.gz
Source0: vitastor-1.2.0.el8.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel
@@ -146,12 +146,9 @@ mkdir -p /etc/vitastor
%_bindir/vitastor-nfs
%_bindir/vitastor-cli
%_bindir/vitastor-rm
%_bindir/vitastor-kv
%_bindir/vitastor-kv-stress
%_bindir/vita
%_libdir/libvitastor_blk.so*
%_libdir/libvitastor_client.so*
%_libdir/libvitastor_kv.so*
%files -n vitastor-client-devel
+1 -1
View File
@@ -18,7 +18,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-1.5.0.el9.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-1.2.0.el9.tar.gz ~/rpmbuild/SOURCES; \
cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
cd ~/rpmbuild/SPECS/; \
rpmbuild -ba vitastor.spec; \
+2 -5
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 1.5.0
Version: 1.2.0
Release: 1%{?dist}
Summary: Vitastor, a fast software-defined clustered block storage
License: Vitastor Network Public License 1.1
URL: https://vitastor.io/
Source0: vitastor-1.5.0.el9.tar.gz
Source0: vitastor-1.2.0.el9.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel
@@ -139,12 +139,9 @@ mkdir -p /etc/vitastor
%_bindir/vitastor-nfs
%_bindir/vitastor-cli
%_bindir/vitastor-rm
%_bindir/vitastor-kv
%_bindir/vitastor-kv-stress
%_bindir/vita
%_libdir/libvitastor_blk.so*
%_libdir/libvitastor_client.so*
%_libdir/libvitastor_kv.so*
%files -n vitastor-client-devel
+12 -36
View File
@@ -16,8 +16,8 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
endif()
add_definitions(-DVERSION="1.5.0")
add_definitions(-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
add_definitions(-DVERSION="1.2.0")
add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
add_link_options(-fno-omit-frame-pointer)
if (${WITH_ASAN})
add_definitions(-fsanitize=address)
@@ -145,6 +145,7 @@ add_library(vitastor_client SHARED
cli_status.cpp
cli_describe.cpp
cli_fix.cpp
cli_df.cpp
cli_ls.cpp
cli_create.cpp
cli_modify.cpp
@@ -153,11 +154,6 @@ add_library(vitastor_client SHARED
cli_rm_data.cpp
cli_rm.cpp
cli_rm_osd.cpp
cli_pool_cfg.cpp
cli_pool_create.cpp
cli_pool_ls.cpp
cli_pool_modify.cpp
cli_pool_rm.cpp
)
set_target_properties(vitastor_client PROPERTIES PUBLIC_HEADER "vitastor_c.h")
target_link_libraries(vitastor_client
@@ -185,48 +181,29 @@ target_link_libraries(vitastor-nbd
vitastor_client
)
# libvitastor_kv.so
add_library(vitastor_kv SHARED
kv_db.cpp
kv_db.h
)
target_link_libraries(vitastor_kv
vitastor_client
)
set_target_properties(vitastor_kv PROPERTIES VERSION ${VERSION} SOVERSION 0)
# vitastor-kv
add_executable(vitastor-kv
kv_cli.cpp
kv_db.cpp
kv_db.h
)
target_link_libraries(vitastor-kv
vitastor_kv
vitastor_client
)
add_executable(vitastor-kv-stress
kv_stress.cpp
kv_db.cpp
kv_db.h
)
target_link_libraries(vitastor-kv-stress
vitastor_kv
vitastor_client
)
# vitastor-nfs
add_executable(vitastor-nfs
nfs_proxy.cpp
nfs_block.cpp
nfs_kv.cpp
nfs_kv_create.cpp
nfs_kv_getattr.cpp
nfs_kv_link.cpp
nfs_kv_lookup.cpp
nfs_kv_read.cpp
nfs_kv_readdir.cpp
nfs_kv_remove.cpp
nfs_kv_rename.cpp
nfs_kv_setattr.cpp
nfs_kv_write.cpp
nfs_fsstat.cpp
nfs_mount.cpp
nfs_conn.cpp
nfs_portmap.cpp
sha256.c
nfs/xdr_impl.cpp
@@ -236,7 +213,6 @@ add_executable(vitastor-nfs
)
target_link_libraries(vitastor-nfs
vitastor_client
vitastor_kv
)
# vitastor-cli
@@ -361,12 +337,12 @@ add_test(NAME test_cluster_client COMMAND test_cluster_client)
### Install
install(TARGETS vitastor-osd vitastor-disk vitastor-nbd vitastor-nfs vitastor-cli vitastor-kv vitastor-kv-stress RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
install(TARGETS vitastor-osd vitastor-disk vitastor-nbd vitastor-nfs vitastor-cli RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
install_symlink(vitastor-disk ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vitastor-dump-journal)
install_symlink(vitastor-cli ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vitastor-rm)
install_symlink(vitastor-cli ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vita)
install(
TARGETS vitastor_blk vitastor_client vitastor_kv
TARGETS vitastor_blk vitastor_client
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
)
+4 -6
View File
@@ -8,7 +8,6 @@
#include <stdio.h>
#include <stdexcept>
#include <set>
#include "addr_util.h"
@@ -136,7 +135,7 @@ std::vector<std::string> getifaddr_list(std::vector<std::string> mask_cfg, bool
throw std::runtime_error((include_v6 ? "Invalid IPv4 address mask: " : "Invalid IP address mask: ") + mask);
}
}
std::set<std::string> addresses;
std::vector<std::string> addresses;
ifaddrs *list, *ifa;
if (getifaddrs(&list) == -1)
{
@@ -150,8 +149,7 @@ std::vector<std::string> getifaddr_list(std::vector<std::string> mask_cfg, bool
}
int family = ifa->ifa_addr->sa_family;
if ((family == AF_INET || family == AF_INET6 && include_v6) &&
// Do not skip loopback addresses if the address filter is specified
(ifa->ifa_flags & (IFF_UP | IFF_RUNNING | (masks.size() ? 0 : IFF_LOOPBACK))) == (IFF_UP | IFF_RUNNING))
(ifa->ifa_flags & (IFF_UP | IFF_RUNNING | IFF_LOOPBACK)) == (IFF_UP | IFF_RUNNING))
{
void *addr_ptr;
if (family == AF_INET)
@@ -184,11 +182,11 @@ std::vector<std::string> getifaddr_list(std::vector<std::string> mask_cfg, bool
{
throw std::runtime_error(std::string("inet_ntop: ") + strerror(errno));
}
addresses.insert(std::string(addr));
addresses.push_back(std::string(addr));
}
}
freeifaddrs(list);
return std::vector<std::string>(addresses.begin(), addresses.end());
return addresses;
}
int create_and_bind_socket(std::string bind_address, int bind_port, int listen_backlog, int *listening_port)
-5
View File
@@ -82,8 +82,3 @@ uint32_t blockstore_t::get_bitmap_granularity()
{
return impl->get_bitmap_granularity();
}
void blockstore_t::set_no_inode_stats(const std::vector<uint64_t> & pool_ids)
{
impl->set_no_inode_stats(pool_ids);
}
-3
View File
@@ -216,9 +216,6 @@ public:
// Get per-inode space usage statistics
std::map<uint64_t, uint64_t> & get_inode_space_stats();
// Set per-pool no_inode_stats
void set_no_inode_stats(const std::vector<uint64_t> & pool_ids);
// Print diagnostics to stdout
void dump_diagnostics();
-8
View File
@@ -108,10 +108,6 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
{
throw std::runtime_error("journal_block_size must be a multiple of "+std::to_string(DIRECT_IO_ALIGNMENT));
}
else if (journal_block_size > MAX_DATA_BLOCK_SIZE)
{
throw std::runtime_error("journal_block_size must not exceed "+std::to_string(MAX_DATA_BLOCK_SIZE));
}
if (!meta_block_size)
{
meta_block_size = 4096;
@@ -120,10 +116,6 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
{
throw std::runtime_error("meta_block_size must be a multiple of "+std::to_string(DIRECT_IO_ALIGNMENT));
}
else if (meta_block_size > MAX_DATA_BLOCK_SIZE)
{
throw std::runtime_error("meta_block_size must not exceed "+std::to_string(MAX_DATA_BLOCK_SIZE));
}
if (data_offset % disk_alignment)
{
throw std::runtime_error("data_offset must be a multiple of disk_alignment = "+std::to_string(disk_alignment));
+33 -34
View File
@@ -19,6 +19,7 @@ journal_flusher_t::journal_flusher_t(blockstore_impl_t *bs)
syncing_flushers = 0;
// FIXME: allow to configure flusher_start_threshold and journal_trim_interval
flusher_start_threshold = bs->dsk.journal_block_size / sizeof(journal_entry_stable);
journal_trim_interval = 512;
journal_trim_counter = bs->journal.flush_journal ? 1 : 0;
trim_wanted = bs->journal.flush_journal ? 1 : 0;
journal_superblock = bs->journal.inmemory ? bs->journal.buffer : memalign_or_die(MEM_ALIGNMENT, bs->dsk.journal_block_size);
@@ -93,7 +94,7 @@ void journal_flusher_t::loop()
void journal_flusher_t::enqueue_flush(obj_ver_id ov)
{
#ifdef BLOCKSTORE_DEBUG
printf("enqueue_flush %jx:%jx v%ju\n", ov.oid.inode, ov.oid.stripe, ov.version);
printf("enqueue_flush %lx:%lx v%lu\n", ov.oid.inode, ov.oid.stripe, ov.version);
#endif
auto it = flush_versions.find(ov.oid);
if (it != flush_versions.end())
@@ -116,7 +117,7 @@ void journal_flusher_t::enqueue_flush(obj_ver_id ov)
void journal_flusher_t::unshift_flush(obj_ver_id ov, bool force)
{
#ifdef BLOCKSTORE_DEBUG
printf("unshift_flush %jx:%jx v%ju\n", ov.oid.inode, ov.oid.stripe, ov.version);
printf("unshift_flush %lx:%lx v%lu\n", ov.oid.inode, ov.oid.stripe, ov.version);
#endif
auto it = flush_versions.find(ov.oid);
if (it != flush_versions.end())
@@ -142,7 +143,7 @@ void journal_flusher_t::unshift_flush(obj_ver_id ov, bool force)
void journal_flusher_t::remove_flush(object_id oid)
{
#ifdef BLOCKSTORE_DEBUG
printf("undo_flush %jx:%jx\n", oid.inode, oid.stripe);
printf("undo_flush %lx:%lx\n", oid.inode, oid.stripe);
#endif
auto v_it = flush_versions.find(oid);
if (v_it != flush_versions.end())
@@ -183,7 +184,8 @@ void journal_flusher_t::mark_trim_possible()
if (trim_wanted > 0)
{
dequeuing = true;
journal_trim_counter = 0;
if (!journal_trim_counter)
journal_trim_counter = journal_trim_interval;
bs->ringloop->wakeup();
}
}
@@ -233,7 +235,7 @@ void journal_flusher_t::dump_diagnostics()
break;
}
printf(
"Flusher: queued=%zd first=%s%jx:%jx trim_wanted=%d dequeuing=%d trimming=%d cur=%d target=%d active=%d syncing=%d\n",
"Flusher: queued=%ld first=%s%lx:%lx trim_wanted=%d dequeuing=%d trimming=%d cur=%d target=%d active=%d syncing=%d\n",
flush_queue.size(), unflushable_type, unflushable.oid.inode, unflushable.oid.stripe,
trim_wanted, dequeuing, trimming, cur_flusher_count, target_flusher_count,
active_flushers, syncing_flushers
@@ -266,7 +268,7 @@ bool journal_flusher_t::try_find_other(std::map<obj_ver_id, dirty_entry>::iterat
{
int search_left = flush_queue.size() - 1;
#ifdef BLOCKSTORE_DEBUG
printf("Flusher overran writers (%jx:%jx v%ju, dirty_start=%08jx) - searching for older flushes (%d left)\n",
printf("Flusher overran writers (%lx:%lx v%lu, dirty_start=%08lx) - searching for older flushes (%d left)\n",
cur.oid.inode, cur.oid.stripe, cur.version, bs->journal.dirty_start, search_left);
#endif
while (search_left > 0)
@@ -283,7 +285,7 @@ bool journal_flusher_t::try_find_other(std::map<obj_ver_id, dirty_entry>::iterat
dirty_end->second.journal_sector < bs->journal.used_start))
{
#ifdef BLOCKSTORE_DEBUG
printf("Write %jx:%jx v%ju is too new: offset=%08jx\n", cur.oid.inode, cur.oid.stripe, cur.version, dirty_end->second.journal_sector);
printf("Write %lx:%lx v%lu is too new: offset=%08lx\n", cur.oid.inode, cur.oid.stripe, cur.version, dirty_end->second.journal_sector);
#endif
enqueue_flush(cur);
}
@@ -364,10 +366,9 @@ resume_0:
!flusher->flush_queue.size() || !flusher->dequeuing)
{
stop_flusher:
if (flusher->trim_wanted > 0 && cur.oid.inode != 0)
if (flusher->trim_wanted > 0 && flusher->journal_trim_counter > 0)
{
// Attempt forced trim
cur.oid = {};
flusher->active_flushers++;
goto trim_journal;
}
@@ -386,7 +387,7 @@ stop_flusher:
if (repeat_it != flusher->sync_to_repeat.end())
{
#ifdef BLOCKSTORE_DEBUG
printf("Postpone %jx:%jx v%ju\n", cur.oid.inode, cur.oid.stripe, cur.version);
printf("Postpone %lx:%lx v%lu\n", cur.oid.inode, cur.oid.stripe, cur.version);
#endif
// We don't flush different parts of history of the same object in parallel
// So we check if someone is already flushing this object
@@ -415,13 +416,12 @@ stop_flusher:
flusher->sync_to_repeat.erase(cur.oid);
if (!flusher->try_find_other(dirty_end, cur))
{
cur.oid = {};
goto stop_flusher;
}
}
}
#ifdef BLOCKSTORE_DEBUG
printf("Flushing %jx:%jx v%ju\n", cur.oid.inode, cur.oid.stripe, cur.version);
printf("Flushing %lx:%lx v%lu\n", cur.oid.inode, cur.oid.stripe, cur.version);
#endif
flusher->active_flushers++;
// Find it in clean_db
@@ -448,7 +448,7 @@ stop_flusher:
// Object not allocated. This is a bug.
char err[1024];
snprintf(
err, 1024, "BUG: Object %jx:%jx v%ju that we are trying to flush is not allocated on the data device",
err, 1024, "BUG: Object %lx:%lx v%lu that we are trying to flush is not allocated on the data device",
cur.oid.inode, cur.oid.stripe, cur.version
);
throw std::runtime_error(err);
@@ -538,7 +538,7 @@ resume_2:
clean_disk_entry *old_entry = (clean_disk_entry*)((uint8_t*)meta_old.buf + meta_old.pos*bs->dsk.clean_entry_size);
if (old_entry->oid.inode != 0 && old_entry->oid != cur.oid)
{
printf("Fatal error (metadata corruption or bug): tried to wipe metadata entry %ju (%jx:%jx v%ju) as old location of %jx:%jx\n",
printf("Fatal error (metadata corruption or bug): tried to wipe metadata entry %lu (%lx:%lx v%lu) as old location of %lx:%lx\n",
old_clean_loc >> bs->dsk.block_order, old_entry->oid.inode, old_entry->oid.stripe,
old_entry->version, cur.oid.inode, cur.oid.stripe);
exit(1);
@@ -571,7 +571,7 @@ resume_2:
// Erase dirty_db entries
bs->erase_dirty(dirty_start, std::next(dirty_end), clean_loc);
#ifdef BLOCKSTORE_DEBUG
printf("Flushed %jx:%jx v%ju (%d copies, wr:%d, del:%d), %jd left\n", cur.oid.inode, cur.oid.stripe, cur.version,
printf("Flushed %lx:%lx v%lu (%d copies, wr:%d, del:%d), %ld left\n", cur.oid.inode, cur.oid.stripe, cur.version,
copy_count, has_writes, has_delete, flusher->flush_queue.size());
#endif
release_oid:
@@ -584,8 +584,7 @@ resume_2:
flusher->sync_to_repeat.erase(repeat_it);
trim_journal:
// Clear unused part of the journal every <journal_trim_interval> flushes
if (bs->journal_trim_interval && !((++flusher->journal_trim_counter) % bs->journal_trim_interval) ||
flusher->trim_wanted > 0)
if (!((++flusher->journal_trim_counter) % flusher->journal_trim_interval) || flusher->trim_wanted > 0)
{
resume_26:
resume_27:
@@ -610,8 +609,8 @@ void journal_flusher_co::update_metadata_entry()
{
printf(
has_delete
? "Fatal error (metadata corruption or bug): tried to delete metadata entry %ju (%jx:%jx v%ju) while deleting %jx:%jx v%ju\n"
: "Fatal error (metadata corruption or bug): tried to overwrite non-zero metadata entry %ju (%jx:%jx v%ju) with %jx:%jx v%ju\n",
? "Fatal error (metadata corruption or bug): tried to delete metadata entry %lu (%lx:%lx v%lu) while deleting %lx:%lx v%lu\n"
: "Fatal error (metadata corruption or bug): tried to overwrite non-zero metadata entry %lu (%lx:%lx v%lu) with %lx:%lx v%lu\n",
clean_loc >> bs->dsk.block_order, new_entry->oid.inode, new_entry->oid.stripe,
new_entry->version, cur.oid.inode, cur.oid.stripe, cur.version
);
@@ -711,7 +710,7 @@ bool journal_flusher_co::write_meta_block(flusher_meta_write_t & meta_block, int
if (wait_state == wait_base)
goto resume_0;
await_sqe(0);
data->iov = (struct iovec){ meta_block.buf, (size_t)bs->dsk.meta_block_size };
data->iov = (struct iovec){ meta_block.buf, bs->dsk.meta_block_size };
data->callback = simple_callback_w;
my_uring_prep_writev(
sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bs->dsk.meta_block_size + meta_block.sector
@@ -761,7 +760,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
{
// If we encounter bad checksums during flush, we still update the bad block,
// but intentionally mangle checksums to avoid hiding the corruption.
iovec iov = { .iov_base = v[i].buf, .iov_len = (size_t)v[i].len };
iovec iov = { .iov_base = v[i].buf, .iov_len = v[i].len };
if (!(v[i].copy_flags & COPY_BUF_JOURNAL))
{
assert(!(v[i].offset % bs->dsk.csum_block_size));
@@ -769,7 +768,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
bs->verify_padded_checksums(new_clean_bitmap, new_clean_bitmap + 2*bs->dsk.clean_entry_bitmap_size,
v[i].offset, &iov, 1, [&](uint32_t bad_block, uint32_t calc_csum, uint32_t stored_csum)
{
printf("Checksum mismatch in object %jx:%jx v%ju in data area at offset 0x%jx+0x%x: got %08x, expected %08x\n",
printf("Checksum mismatch in object %lx:%lx v%lu in data area at offset 0x%lx+0x%x: got %08x, expected %08x\n",
cur.oid.inode, cur.oid.stripe, old_clean_ver, old_clean_loc, bad_block, calc_csum, stored_csum);
for (uint32_t j = 0; j < bs->dsk.csum_block_size; j += bs->dsk.bitmap_granularity)
{
@@ -782,7 +781,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
{
bs->verify_journal_checksums(v[i].csum_buf, v[i].offset, &iov, 1, [&](uint32_t bad_block, uint32_t calc_csum, uint32_t stored_csum)
{
printf("Checksum mismatch in object %jx:%jx v%ju in journal at offset 0x%jx+0x%x (block offset 0x%jx): got %08x, expected %08x\n",
printf("Checksum mismatch in object %lx:%lx v%lu in journal at offset 0x%lx+0x%x (block offset 0x%lx): got %08x, expected %08x\n",
cur.oid.inode, cur.oid.stripe, old_clean_ver,
v[i].disk_offset, bad_block, v[i].offset, calc_csum, stored_csum);
bad_block += (v[i].offset/bs->dsk.csum_block_size) * bs->dsk.csum_block_size;
@@ -806,7 +805,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
if (new_entry->oid != cur.oid)
{
printf(
"Fatal error (metadata corruption or bug): tried to make holes in %ju (%jx:%jx v%ju) with %jx:%jx v%ju\n",
"Fatal error (metadata corruption or bug): tried to make holes in %lu (%lx:%lx v%lu) with %lx:%lx v%lu\n",
clean_loc >> bs->dsk.block_order, new_entry->oid.inode, new_entry->oid.stripe,
new_entry->version, cur.oid.inode, cur.oid.stripe, cur.version
);
@@ -926,7 +925,7 @@ void journal_flusher_co::scan_dirty()
{
char err[1024];
snprintf(
err, 1024, "BUG: Unexpected dirty_entry %jx:%jx v%ju unstable state during flush: 0x%x",
err, 1024, "BUG: Unexpected dirty_entry %lx:%lx v%lu unstable state during flush: 0x%x",
dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version, dirty_it->second.state
);
throw std::runtime_error(err);
@@ -1022,7 +1021,7 @@ void journal_flusher_co::scan_dirty()
// May happen if the metadata entry is corrupt, but journal isn't
// FIXME: Report corrupted object to the upper layer (OSD)
printf(
"Warning: object %jx:%jx has overwrites, but doesn't have a clean version."
"Warning: object %lx:%lx has overwrites, but doesn't have a clean version."
" Metadata is likely corrupted. Dropping object from the DB.\n",
cur.oid.inode, cur.oid.stripe
);
@@ -1057,7 +1056,7 @@ void journal_flusher_co::scan_dirty()
flusher->enqueue_flush(cur);
cur.version = dirty_end->first.version;
#ifdef BLOCKSTORE_DEBUG
printf("Partial checksum block overwrites found - rewinding flush back to %jx:%jx v%ju\n", cur.oid.inode, cur.oid.stripe, cur.version);
printf("Partial checksum block overwrites found - rewinding flush back to %lx:%lx v%lu\n", cur.oid.inode, cur.oid.stripe, cur.version);
#endif
v.clear();
copy_count = 0;
@@ -1085,7 +1084,7 @@ bool journal_flusher_co::read_dirty(int wait_base)
auto & vi = v[v.size()-i];
assert(vi.len != 0);
vi.buf = memalign_or_die(MEM_ALIGNMENT, vi.len);
data->iov = (struct iovec){ vi.buf, (size_t)vi.len };
data->iov = (struct iovec){ vi.buf, vi.len };
data->callback = simple_callback_r;
my_uring_prep_readv(
sqe, bs->dsk.data_fd, &data->iov, 1, bs->dsk.data_offset + old_clean_loc + vi.offset
@@ -1209,7 +1208,7 @@ bool journal_flusher_co::modify_meta_read(uint64_t meta_loc, flusher_meta_write_
.usage_count = 1,
}).first;
await_sqe(0);
data->iov = (struct iovec){ wr.it->second.buf, (size_t)bs->dsk.meta_block_size };
data->iov = (struct iovec){ wr.it->second.buf, bs->dsk.meta_block_size };
data->callback = simple_callback_r;
wr.submitted = true;
my_uring_prep_readv(
@@ -1248,7 +1247,7 @@ void journal_flusher_co::free_data_blocks()
auto uo_it = bs->used_clean_objects.find(old_clean_loc);
bool used = uo_it != bs->used_clean_objects.end();
#ifdef BLOCKSTORE_DEBUG
printf("%s block %ju from %jx:%jx v%ju (new location is %ju)\n",
printf("%s block %lu from %lx:%lx v%lu (new location is %lu)\n",
used ? "Postpone free" : "Free",
old_clean_loc >> bs->dsk.block_order,
cur.oid.inode, cur.oid.stripe, cur.version,
@@ -1265,7 +1264,7 @@ void journal_flusher_co::free_data_blocks()
auto uo_it = bs->used_clean_objects.find(old_clean_loc);
bool used = uo_it != bs->used_clean_objects.end();
#ifdef BLOCKSTORE_DEBUG
printf("%s block %ju from %jx:%jx v%ju (delete)\n",
printf("%s block %lu from %lx:%lx v%lu (delete)\n",
used ? "Postpone free" : "Free",
old_clean_loc >> bs->dsk.block_order,
cur.oid.inode, cur.oid.stripe, cur.version);
@@ -1347,6 +1346,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
else if (wait_state == wait_base+2) goto resume_2;
else if (wait_state == wait_base+3) goto resume_3;
else if (wait_state == wait_base+4) goto resume_4;
flusher->journal_trim_counter = 0;
new_trim_pos = bs->journal.get_trim_pos();
if (new_trim_pos != bs->journal.used_start)
{
@@ -1378,7 +1378,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
.csum_block_size = bs->dsk.csum_block_size,
};
((journal_entry_start*)flusher->journal_superblock)->crc32 = je_crc32((journal_entry*)flusher->journal_superblock);
data->iov = (struct iovec){ flusher->journal_superblock, (size_t)bs->dsk.journal_block_size };
data->iov = (struct iovec){ flusher->journal_superblock, bs->dsk.journal_block_size };
data->callback = simple_callback_w;
my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
wait_count++;
@@ -1410,7 +1410,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
}
bs->journal.used_start = new_trim_pos;
#ifdef BLOCKSTORE_DEBUG
printf("Journal trimmed to %08jx (next_free=%08jx dirty_start=%08jx)\n", bs->journal.used_start, bs->journal.next_free, bs->journal.dirty_start);
printf("Journal trimmed to %08lx (next_free=%08lx dirty_start=%08lx)\n", bs->journal.used_start, bs->journal.next_free, bs->journal.dirty_start);
#endif
if (bs->journal.flush_journal && !flusher->flush_queue.size())
{
@@ -1419,7 +1419,6 @@ bool journal_flusher_co::trim_journal(int wait_base)
exit(0);
}
}
flusher->journal_trim_counter = 0;
flusher->trimming = false;
}
return true;
+1 -1
View File
@@ -107,7 +107,7 @@ class journal_flusher_t
blockstore_impl_t *bs;
friend class journal_flusher_co;
int journal_trim_counter;
int journal_trim_counter, journal_trim_interval;
bool trimming;
void* journal_superblock;
+22 -104
View File
@@ -163,10 +163,20 @@ void blockstore_impl_t::loop()
}
else if (op->opcode == BS_OP_SYNC)
{
// sync only completed writes?
// wait for all small writes to be submitted
// wait for all big writes to complete, submit data device fsync
// wait for the data device fsync to complete, then submit journal writes for big writes
// then submit an fsync operation
if (has_writes)
{
// Can't submit SYNC before previous writes
continue;
}
wr_st = continue_sync(op);
if (wr_st != 2)
{
has_writes = wr_st > 0 ? 1 : 2;
}
}
else if (op->opcode == BS_OP_STABLE)
{
@@ -195,10 +205,6 @@ void blockstore_impl_t::loop()
// ring is full, stop submission
break;
}
else if (PRIV(op)->wait_for == WAIT_JOURNAL)
{
PRIV(op)->wait_detail2 = (unstable_writes.size()+unstable_unsynced);
}
}
}
if (op_idx != new_idx)
@@ -269,7 +275,7 @@ void blockstore_impl_t::check_wait(blockstore_op_t *op)
{
// stop submission if there's still no free space
#ifdef BLOCKSTORE_DEBUG
printf("Still waiting for %ju SQE(s)\n", PRIV(op)->wait_detail);
printf("Still waiting for %lu SQE(s)\n", PRIV(op)->wait_detail);
#endif
return;
}
@@ -277,12 +283,11 @@ void blockstore_impl_t::check_wait(blockstore_op_t *op)
}
else if (PRIV(op)->wait_for == WAIT_JOURNAL)
{
if (journal.used_start == PRIV(op)->wait_detail &&
(unstable_writes.size()+unstable_unsynced) == PRIV(op)->wait_detail2)
if (journal.used_start == PRIV(op)->wait_detail)
{
// do not submit
#ifdef BLOCKSTORE_DEBUG
printf("Still waiting to flush journal offset %08jx\n", PRIV(op)->wait_detail);
printf("Still waiting to flush journal offset %08lx\n", PRIV(op)->wait_detail);
#endif
return;
}
@@ -553,14 +558,13 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
if (stable_count >= stable_alloc)
{
stable_alloc *= 2;
obj_ver_id* nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
if (!nst)
stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
if (!stable)
{
op->retval = -ENOMEM;
FINISH_OP(op);
return;
}
stable = nst;
}
stable[stable_count++] = {
.oid = clean_it->first,
@@ -638,8 +642,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
if (stable_count >= stable_alloc)
{
stable_alloc += 32768;
obj_ver_id *nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
if (!nst)
stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
if (!stable)
{
if (unstable)
free(unstable);
@@ -647,7 +651,6 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
FINISH_OP(op);
return;
}
stable = nst;
}
stable[stable_count++] = dirty_it->first;
}
@@ -663,8 +666,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
if (unstable_count >= unstable_alloc)
{
unstable_alloc += 32768;
obj_ver_id *nst = (obj_ver_id*)realloc(unstable, sizeof(obj_ver_id) * unstable_alloc);
if (!nst)
unstable = (obj_ver_id*)realloc(unstable, sizeof(obj_ver_id) * unstable_alloc);
if (!unstable)
{
if (stable)
free(stable);
@@ -672,7 +675,6 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
FINISH_OP(op);
return;
}
unstable = nst;
}
unstable[unstable_count++] = dirty_it->first;
}
@@ -692,8 +694,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
if (stable_count+unstable_count > stable_alloc)
{
stable_alloc = stable_count+unstable_count;
obj_ver_id *nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
if (!nst)
stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
if (!stable)
{
if (unstable)
free(unstable);
@@ -701,7 +703,6 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
FINISH_OP(op);
return;
}
stable = nst;
}
// Copy unstable entries
for (int i = 0; i < unstable_count; i++)
@@ -733,86 +734,3 @@ void blockstore_impl_t::disk_error_abort(const char *op, int retval, int expecte
fprintf(stderr, "Disk %s failed: result is %d, expected %d. Can't continue, sorry :-(\n", op, retval, expected);
exit(1);
}
void blockstore_impl_t::set_no_inode_stats(const std::vector<uint64_t> & pool_ids)
{
for (auto & np: no_inode_stats)
{
np.second = 2;
}
for (auto pool_id: pool_ids)
{
if (!no_inode_stats[pool_id])
recalc_inode_space_stats(pool_id, false);
no_inode_stats[pool_id] = 1;
}
for (auto np_it = no_inode_stats.begin(); np_it != no_inode_stats.end(); )
{
if (np_it->second == 2)
{
recalc_inode_space_stats(np_it->first, true);
no_inode_stats.erase(np_it++);
}
else
np_it++;
}
}
void blockstore_impl_t::recalc_inode_space_stats(uint64_t pool_id, bool per_inode)
{
auto sp_begin = inode_space_stats.lower_bound((pool_id << (64-POOL_ID_BITS)));
auto sp_end = inode_space_stats.lower_bound(((pool_id+1) << (64-POOL_ID_BITS)));
inode_space_stats.erase(sp_begin, sp_end);
auto sh_it = clean_db_shards.lower_bound((pool_id << (64-POOL_ID_BITS)));
while (sh_it != clean_db_shards.end() &&
(sh_it->first >> (64-POOL_ID_BITS)) == pool_id)
{
for (auto & pair: sh_it->second)
{
uint64_t space_id = per_inode ? pair.first.inode : (pool_id << (64-POOL_ID_BITS));
inode_space_stats[space_id] += dsk.data_block_size;
}
sh_it++;
}
object_id last_oid = {};
bool last_exists = false;
auto dirty_it = dirty_db.lower_bound((obj_ver_id){ .oid = { .inode = (pool_id << (64-POOL_ID_BITS)) } });
while (dirty_it != dirty_db.end() && (dirty_it->first.oid.inode >> (64-POOL_ID_BITS)) == pool_id)
{
if (IS_STABLE(dirty_it->second.state) && (IS_BIG_WRITE(dirty_it->second.state) || IS_DELETE(dirty_it->second.state)))
{
bool exists = false;
if (last_oid == dirty_it->first.oid)
{
exists = last_exists;
}
else
{
auto & clean_db = clean_db_shard(dirty_it->first.oid);
auto clean_it = clean_db.find(dirty_it->first.oid);
exists = clean_it != clean_db.end();
}
uint64_t space_id = per_inode ? dirty_it->first.oid.inode : (pool_id << (64-POOL_ID_BITS));
if (IS_BIG_WRITE(dirty_it->second.state))
{
if (!exists)
inode_space_stats[space_id] += dsk.data_block_size;
last_exists = true;
}
else
{
if (exists)
{
auto & sp = inode_space_stats[space_id];
if (sp > dsk.data_block_size)
sp -= dsk.data_block_size;
else
inode_space_stats.erase(space_id);
}
last_exists = false;
}
last_oid = dirty_it->first.oid;
}
dirty_it++;
}
}
+3 -11
View File
@@ -55,7 +55,6 @@
#define IS_JOURNAL(st) (((st) & 0x0F) == BS_ST_SMALL_WRITE)
#define IS_BIG_WRITE(st) (((st) & 0x0F) == BS_ST_BIG_WRITE)
#define IS_DELETE(st) (((st) & 0x0F) == BS_ST_DELETE)
#define IS_INSTANT(st) (((st) & BS_ST_TYPE_MASK) == BS_ST_DELETE || ((st) & BS_ST_INSTANT))
#define BS_SUBMIT_CHECK_SQES(n) \
if (ringloop->sqes_left() < (n))\
@@ -202,7 +201,7 @@ struct blockstore_op_private_t
{
// Wait status
int wait_for;
uint64_t wait_detail, wait_detail2;
uint64_t wait_detail;
int pending_ops;
int op_state;
@@ -253,7 +252,6 @@ class blockstore_impl_t
bool inmemory_meta = false;
// Maximum and minimum flusher count
unsigned max_flusher_count, min_flusher_count;
unsigned journal_trim_interval;
// Maximum queue depth
unsigned max_write_iodepth = 128;
// Enable small (journaled) write throttling, useful for the SSD+HDD case
@@ -272,7 +270,6 @@ class blockstore_impl_t
std::map<pool_id_t, pool_shard_settings_t> clean_db_settings;
std::map<pool_pg_id_t, blockstore_clean_db_t> clean_db_shards;
std::map<uint64_t, int> no_inode_stats;
uint8_t *clean_bitmaps = NULL;
blockstore_dirty_db_t dirty_db;
std::vector<blockstore_op_t*> submit_queue;
@@ -280,7 +277,6 @@ class blockstore_impl_t
int unsynced_big_write_count = 0, unstable_unsynced = 0;
int unsynced_queued_ops = 0;
allocator *data_alloc = NULL;
uint64_t used_blocks = 0;
uint8_t *zero_object;
void *metadata_buffer = NULL;
@@ -319,7 +315,6 @@ class blockstore_impl_t
blockstore_clean_db_t& clean_db_shard(object_id oid);
void reshard_clean_db(pool_id_t pool_id, uint32_t pg_count, uint32_t pg_stripe_size);
void recalc_inode_space_stats(uint64_t pool_id, bool per_inode);
// Journaling
void prepare_journal_sector_write(int sector, blockstore_op_t *op);
@@ -381,7 +376,7 @@ class blockstore_impl_t
// Stabilize
int dequeue_stable(blockstore_op_t *op);
int continue_stable(blockstore_op_t *op);
void mark_stable(obj_ver_id ov, bool forget_dirty = false);
void mark_stable(const obj_ver_id & ov, bool forget_dirty = false);
void stabilize_object(object_id oid, uint64_t max_ver);
blockstore_op_t* selective_sync(blockstore_op_t *op);
int split_stab_op(blockstore_op_t *op, std::function<int(obj_ver_id v)> decider);
@@ -430,15 +425,12 @@ public:
// Space usage statistics
std::map<uint64_t, uint64_t> inode_space_stats;
// Set per-pool no_inode_stats
void set_no_inode_stats(const std::vector<uint64_t> & pool_ids);
// Print diagnostics to stdout
void dump_diagnostics();
inline uint32_t get_block_size() { return dsk.data_block_size; }
inline uint64_t get_block_count() { return dsk.block_count; }
inline uint64_t get_free_block_count() { return dsk.block_count - used_blocks; }
inline uint64_t get_free_block_count() { return data_alloc->get_free_count(); }
inline uint32_t get_bitmap_granularity() { return dsk.disk_alignment; }
inline uint64_t get_journal_size() { return dsk.journal_len; }
};
+36 -48
View File
@@ -32,7 +32,7 @@ void blockstore_init_meta::handle_event(ring_data_t *data, int buf_num)
if (data->res < 0)
{
throw std::runtime_error(
std::string("read metadata failed at offset ") + std::to_string(buf_num >= 0 ? bufs[buf_num].offset : last_read_offset) +
std::string("read metadata failed at offset ") + std::to_string(bufs[buf_num].offset) +
std::string(": ") + strerror(-data->res)
);
}
@@ -63,8 +63,7 @@ int blockstore_init_meta::loop()
throw std::runtime_error("Failed to allocate metadata read buffer");
// Read superblock
GET_SQE();
last_read_offset = 0;
data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
data->iov = { metadata_buffer, bs->dsk.meta_block_size };
data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
bs->ringloop->submit();
@@ -101,8 +100,7 @@ resume_1:
{
printf("Initializing metadata area\n");
GET_SQE();
last_read_offset = 0;
data->iov = (struct iovec){ metadata_buffer, (size_t)bs->dsk.meta_block_size };
data->iov = (struct iovec){ metadata_buffer, bs->dsk.meta_block_size };
data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
bs->ringloop->submit();
@@ -155,7 +153,7 @@ resume_1:
else if (hdr->version > BLOCKSTORE_META_FORMAT_V2)
{
printf(
"Metadata format is too new for me (stored version is %ju, max supported %u).\n",
"Metadata format is too new for me (stored version is %lu, max supported %u).\n",
hdr->version, BLOCKSTORE_META_FORMAT_V2
);
exit(1);
@@ -169,7 +167,7 @@ resume_1:
printf(
"Configuration stored in metadata superblock"
" (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u, data_csum_type=%u, csum_block_size=%u)"
" differs from OSD configuration (%ju/%u/%ju, %u/%u).\n",
" differs from OSD configuration (%lu/%u/%lu, %u/%u).\n",
hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
hdr->data_csum_type, hdr->csum_block_size,
bs->dsk.meta_block_size, bs->dsk.data_block_size, bs->dsk.bitmap_granularity,
@@ -201,8 +199,7 @@ resume_2:
submitted++;
next_offset += bufs[i].size;
GET_SQE();
assert(bufs[i].size <= 0x7fffffff);
data->iov = { bufs[i].buf, (size_t)bufs[i].size };
data->iov = { bufs[i].buf, bufs[i].size };
data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
if (!zero_on_init)
my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
@@ -234,11 +231,9 @@ resume_2:
{
// write the modified buffer back
GET_SQE();
assert(bufs[i].size <= 0x7fffffff);
data->iov = { bufs[i].buf, (size_t)bufs[i].size };
data->iov = { bufs[i].buf, bufs[i].size };
data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
bs->ringloop->submit();
bufs[i].state = INIT_META_WRITING;
submitted++;
}
@@ -262,11 +257,9 @@ resume_2:
next_offset = entries_to_zero[i]/entries_per_block;
for (j = i; j < entries_to_zero.size() && entries_to_zero[j]/entries_per_block == next_offset; j++) {}
GET_SQE();
last_read_offset = (1+next_offset)*bs->dsk.meta_block_size;
data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
data->iov = { metadata_buffer, bs->dsk.meta_block_size };
data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
bs->ringloop->submit();
submitted++;
resume_5:
if (submitted > 0)
@@ -280,10 +273,9 @@ resume_5:
memset((uint8_t*)metadata_buffer + pos*bs->dsk.clean_entry_size, 0, bs->dsk.clean_entry_size);
}
GET_SQE();
data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
data->iov = { metadata_buffer, bs->dsk.meta_block_size };
data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
bs->ringloop->submit();
submitted++;
resume_6:
if (submitted > 0)
@@ -295,7 +287,7 @@ resume_6:
entries_to_zero.clear();
}
// metadata read finished
printf("Metadata entries loaded: %ju, free blocks: %ju / %ju\n", entries_loaded, bs->data_alloc->get_free_count(), bs->dsk.block_count);
printf("Metadata entries loaded: %lu, free blocks: %lu / %lu\n", entries_loaded, bs->data_alloc->get_free_count(), bs->dsk.block_count);
if (!bs->inmemory_meta)
{
free(metadata_buffer);
@@ -305,7 +297,6 @@ resume_6:
{
GET_SQE();
my_uring_prep_fsync(sqe, bs->dsk.meta_fd, IORING_FSYNC_DATASYNC);
last_read_offset = 0;
data->iov = { 0 };
data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
submitted++;
@@ -337,7 +328,7 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
uint32_t *entry_csum = (uint32_t*)((uint8_t*)entry + bs->dsk.clean_entry_size - 4);
if (*entry_csum != crc32c(0, entry, bs->dsk.clean_entry_size - 4))
{
printf("Metadata entry %ju is corrupt (checksum mismatch), skipping\n", done_cnt+i);
printf("Metadata entry %lu is corrupt (checksum mismatch), skipping\n", done_cnt+i);
continue;
}
}
@@ -375,7 +366,7 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
entries_to_zero.push_back(clean_it->second.location >> bs->dsk.block_order);
}
#ifdef BLOCKSTORE_DEBUG
printf("Free block %ju from %jx:%jx v%ju (new location is %ju)\n",
printf("Free block %lu from %lx:%lx v%lu (new location is %lu)\n",
old_clean_loc,
clean_it->first.inode, clean_it->first.stripe, clean_it->second.version,
done_cnt+i);
@@ -385,11 +376,10 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
else
{
bs->inode_space_stats[entry->oid.inode] += bs->dsk.data_block_size;
bs->used_blocks++;
}
entries_loaded++;
#ifdef BLOCKSTORE_DEBUG
printf("Allocate block (clean entry) %ju: %jx:%jx v%ju\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
printf("Allocate block (clean entry) %lu: %lx:%lx v%lu\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
#endif
bs->data_alloc->set(done_cnt+i, true);
clean_db[entry->oid] = (struct clean_entry){
@@ -403,7 +393,7 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
updated = true;
memset(entry, 0, bs->dsk.clean_entry_size);
#ifdef BLOCKSTORE_DEBUG
printf("Old clean entry %ju: %jx:%jx v%ju\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
printf("Old clean entry %lu: %lx:%lx v%lu\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
#endif
}
}
@@ -475,7 +465,7 @@ int blockstore_init_journal::loop()
if (!sqe)
throw std::runtime_error("io_uring is full while trying to read journal");
data = ((ring_data_t*)sqe->user_data);
data->iov = { submitted_buf, (size_t)bs->journal.block_size };
data->iov = { submitted_buf, bs->journal.block_size };
data->callback = simple_callback;
my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
bs->ringloop->submit();
@@ -516,7 +506,7 @@ resume_1:
// FIXME: Randomize initial crc32. Track crc32 when trimming.
printf("Resetting journal\n");
GET_SQE();
data->iov = (struct iovec){ submitted_buf, (size_t)(2*bs->journal.block_size) };
data->iov = (struct iovec){ submitted_buf, 2*bs->journal.block_size };
data->callback = simple_callback;
my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
wait_count++;
@@ -566,7 +556,7 @@ resume_1:
(je_start->version != JOURNAL_VERSION_V2 || je_start->size != JE_START_V2_SIZE && je_start->size != JE_START_V1_SIZE))
{
fprintf(
stderr, "The code only supports journal versions 2 and 1, but it is %ju on disk."
stderr, "The code only supports journal versions 2 and 1, but it is %lu on disk."
" Please use vitastor-disk to rewrite the journal\n",
je_start->size == JE_START_V0_SIZE ? 0 : je_start->version
);
@@ -615,7 +605,7 @@ resume_1:
submitted_buf = (uint8_t*)bs->journal.buffer + journal_pos;
data->iov = {
submitted_buf,
(size_t)(end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE),
end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE,
};
data->callback = [this](ring_data_t *data1) { handle_event(data1); };
my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
@@ -631,7 +621,7 @@ resume_1:
if (init_write_buf && !bs->readonly)
{
GET_SQE();
data->iov = { init_write_buf, (size_t)bs->journal.block_size };
data->iov = { init_write_buf, bs->journal.block_size };
data->callback = simple_callback;
my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + init_write_sector);
wait_count++;
@@ -700,7 +690,7 @@ resume_1:
IS_BIG_WRITE(dirty_it->second.state) &&
dirty_it->second.location == UINT64_MAX)
{
printf("Fatal error (bug): %jx:%jx v%ju big_write journal_entry was allocated over another object\n",
printf("Fatal error (bug): %lx:%lx v%lu big_write journal_entry was allocated over another object\n",
dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version);
exit(1);
}
@@ -708,7 +698,7 @@ resume_1:
bs->flusher->mark_trim_possible();
bs->journal.dirty_start = bs->journal.next_free;
printf(
"Journal entries loaded: %ju, free journal space: %ju bytes (%08jx..%08jx is used), free blocks: %ju / %ju\n",
"Journal entries loaded: %lu, free journal space: %lu bytes (%08lx..%08lx is used), free blocks: %lu / %lu\n",
entries_loaded,
(bs->journal.next_free >= bs->journal.used_start
? bs->journal.len-bs->journal.block_size - (bs->journal.next_free-bs->journal.used_start)
@@ -742,9 +732,8 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
resume:
while (pos < bs->journal.block_size)
{
auto buf_pos = proc_pos - done_pos + pos;
journal_entry *je = (journal_entry*)((uint8_t*)buf + buf_pos);
if (je->magic != JOURNAL_MAGIC || buf_pos+je->size > len || je_crc32(je) != je->crc32 ||
journal_entry *je = (journal_entry*)((uint8_t*)buf + proc_pos - done_pos + pos);
if (je->magic != JOURNAL_MAGIC || je_crc32(je) != je->crc32 ||
je->type < JE_MIN || je->type > JE_MAX || started && je->crc32_prev != crc32_last)
{
if (pos == 0)
@@ -763,7 +752,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
{
#ifdef BLOCKSTORE_DEBUG
printf(
"je_small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u\n",
"je_small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u\n",
je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
je->small_write.offset, je->small_write.len
@@ -785,7 +774,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
if (location != je->small_write.data_offset)
{
char err[1024];
snprintf(err, 1024, "BUG: calculated journal data offset (%08jx) != stored journal data offset (%08jx)", location, je->small_write.data_offset);
snprintf(err, 1024, "BUG: calculated journal data offset (%08lx) != stored journal data offset (%08lx)", location, je->small_write.data_offset);
throw std::runtime_error(err);
}
small_write_data.clear();
@@ -812,7 +801,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
covered += part_end - part_begin;
small_write_data.push_back((iovec){
.iov_base = (uint8_t*)done[i].buf + part_begin - done[i].pos,
.iov_len = (size_t)(part_end - part_begin),
.iov_len = part_end - part_begin,
});
}
}
@@ -835,7 +824,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
if (!data_csum_valid)
{
printf(
"Journal entry data is corrupt for small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u - data crc32 %x != %x\n",
"Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - data crc32 %x != %x\n",
je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
je->small_write.offset, je->small_write.len,
@@ -854,7 +843,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
if (je->size != required_size)
{
printf(
"Journal entry data has invalid size for small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u - should be %u bytes but is %u bytes\n",
"Journal entry data has invalid size for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - should be %u bytes but is %u bytes\n",
je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
je->small_write.offset, je->small_write.len,
@@ -902,7 +891,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
if (block_crc32 != *block_csums)
{
printf(
"Journal entry data is corrupt for small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u - block %u crc32 %x != %x\n",
"Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - block %u crc32 %x != %x\n",
je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
je->small_write.offset, je->small_write.len,
@@ -965,7 +954,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
bs->journal.used_sectors[proc_pos]++;
#ifdef BLOCKSTORE_DEBUG
printf(
"journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
"journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
proc_pos, ov.oid.inode, ov.oid.stripe, ov.version, bs->journal.used_sectors[proc_pos]
);
#endif
@@ -981,7 +970,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
{
#ifdef BLOCKSTORE_DEBUG
printf(
"je_big_write%s oid=%jx:%jx ver=%ju loc=%ju\n",
"je_big_write%s oid=%lx:%lx ver=%lu loc=%lu\n",
je->type == JE_BIG_WRITE_INSTANT ? "_instant" : "",
je->big_write.oid.inode, je->big_write.oid.stripe, je->big_write.version, je->big_write.location >> bs->dsk.block_order
);
@@ -1058,7 +1047,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
{
#ifdef BLOCKSTORE_DEBUG
printf(
"Allocate block (journal) %ju: %jx:%jx v%ju\n",
"Allocate block (journal) %lu: %lx:%lx v%lu\n",
je->big_write.location >> bs->dsk.block_order,
ov.oid.inode, ov.oid.stripe, ov.version
);
@@ -1068,7 +1057,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
bs->journal.used_sectors[proc_pos]++;
#ifdef BLOCKSTORE_DEBUG
printf(
"journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
"journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
proc_pos, ov.oid.inode, ov.oid.stripe, ov.version, bs->journal.used_sectors[proc_pos]
);
#endif
@@ -1083,7 +1072,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
else if (je->type == JE_STABLE)
{
#ifdef BLOCKSTORE_DEBUG
printf("je_stable oid=%jx:%jx ver=%ju\n", je->stable.oid.inode, je->stable.oid.stripe, je->stable.version);
printf("je_stable oid=%lx:%lx ver=%lu\n", je->stable.oid.inode, je->stable.oid.stripe, je->stable.version);
#endif
// oid, version
obj_ver_id ov = {
@@ -1095,7 +1084,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
else if (je->type == JE_ROLLBACK)
{
#ifdef BLOCKSTORE_DEBUG
printf("je_rollback oid=%jx:%jx ver=%ju\n", je->rollback.oid.inode, je->rollback.oid.stripe, je->rollback.version);
printf("je_rollback oid=%lx:%lx ver=%lu\n", je->rollback.oid.inode, je->rollback.oid.stripe, je->rollback.version);
#endif
// rollback dirty writes of <oid> up to <version>
obj_ver_id ov = {
@@ -1107,7 +1096,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
else if (je->type == JE_DELETE)
{
#ifdef BLOCKSTORE_DEBUG
printf("je_delete oid=%jx:%jx ver=%ju\n", je->del.oid.inode, je->del.oid.stripe, je->del.version);
printf("je_delete oid=%lx:%lx ver=%lu\n", je->del.oid.inode, je->del.oid.stripe, je->del.version);
#endif
bool dirty_exists = false;
auto dirty_it = bs->dirty_db.upper_bound((obj_ver_id){
@@ -1191,7 +1180,6 @@ void blockstore_init_journal::erase_dirty_object(blockstore_dirty_db_t::iterator
sp -= bs->dsk.data_block_size;
else
bs->inode_space_stats.erase(oid.inode);
bs->used_blocks--;
}
bs->erase_dirty(dirty_it, dirty_end, clean_loc);
// Remove it from the flusher's queue, too
-1
View File
@@ -23,7 +23,6 @@ class blockstore_init_meta
struct ring_data_t *data;
uint64_t md_offset = 0;
uint64_t next_offset = 0;
uint64_t last_read_offset = 0;
uint64_t entries_loaded = 0;
unsigned entries_per_block = 0;
int i = 0, j = 0;
+10 -12
View File
@@ -90,8 +90,8 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
}
// In fact, it's even more rare than "ran out of journal space", so print a warning
printf(
"Ran out of journal sector buffers: %d/%ju buffers used (%d dirty), next buffer (%jd)"
" is %s and flushed %ju times. Consider increasing \'journal_sector_buffer_count\'\n",
"Ran out of journal sector buffers: %d/%lu buffers used (%d dirty), next buffer (%ld)"
" is %s and flushed %lu times. Consider increasing \'journal_sector_buffer_count\'\n",
used, bs->journal.sector_count, dirty, next_sector,
bs->journal.sector_info[next_sector].dirty ? "dirty" : "not dirty",
bs->journal.sector_info[next_sector].flush_count
@@ -103,7 +103,7 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
if (data_after > 0)
{
next_pos = next_pos + data_after;
if (next_pos >= bs->journal.len)
if (next_pos > bs->journal.len)
{
if (right_dir)
next_pos = bs->journal.block_size + data_after;
@@ -114,7 +114,7 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
{
// No space in the journal. Wait until used_start changes.
printf(
"Ran out of journal space (used_start=%08jx, next_free=%08jx, dirty_start=%08jx)\n",
"Ran out of journal space (used_start=%08lx, next_free=%08lx, dirty_start=%08lx)\n",
bs->journal.used_start, bs->journal.next_free, bs->journal.dirty_start
);
PRIV(op)->wait_for = WAIT_JOURNAL;
@@ -144,10 +144,8 @@ journal_entry* prefill_single_journal_entry(journal_t & journal, uint16_t type,
journal.sector_info[journal.cur_sector].written = false;
journal.sector_info[journal.cur_sector].offset = journal.next_free;
journal.in_sector_pos = 0;
auto next_next_free = (journal.next_free+journal.block_size) < journal.len ? journal.next_free + journal.block_size : journal.block_size;
// double check that next_free doesn't cross used_start from the left
assert(journal.next_free >= journal.used_start && next_next_free >= journal.next_free || next_next_free < journal.used_start);
journal.next_free = next_next_free;
journal.next_free = (journal.next_free+journal.block_size) < journal.len ? journal.next_free + journal.block_size : journal.block_size;
assert(journal.next_free != journal.used_start);
memset(journal.inmemory
? (uint8_t*)journal.buffer + journal.sector_info[journal.cur_sector].offset
: (uint8_t*)journal.sector_buf + journal.block_size*journal.cur_sector, 0, journal.block_size);
@@ -183,7 +181,7 @@ void blockstore_impl_t::prepare_journal_sector_write(int cur_sector, blockstore_
(journal.inmemory
? (uint8_t*)journal.buffer + journal.sector_info[cur_sector].offset
: (uint8_t*)journal.sector_buf + journal.block_size*cur_sector),
(size_t)journal.block_size
journal.block_size
};
data->callback = [this, flush_id = journal.submit_id](ring_data_t *data) { handle_journal_write(data, flush_id); };
my_uring_prep_writev(
@@ -263,7 +261,7 @@ uint64_t journal_t::get_trim_pos()
// next_free does not need updating during trim
#ifdef BLOCKSTORE_DEBUG
printf(
"Trimming journal (used_start=%08jx, next_free=%08jx, dirty_start=%08jx, new_start=%08jx, new_refcount=%jd)\n",
"Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
used_start, next_free, dirty_start,
journal_used_it->first, journal_used_it->second
);
@@ -276,7 +274,7 @@ uint64_t journal_t::get_trim_pos()
// Journal is cleared up to <journal_used_it>
#ifdef BLOCKSTORE_DEBUG
printf(
"Trimming journal (used_start=%08jx, next_free=%08jx, dirty_start=%08jx, new_start=%08jx, new_refcount=%jd)\n",
"Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
used_start, next_free, dirty_start,
journal_used_it->first, journal_used_it->second
);
@@ -296,7 +294,7 @@ void journal_t::dump_diagnostics()
journal_used_it = used_sectors.begin();
}
printf(
"Journal: used_start=%08jx next_free=%08jx dirty_start=%08jx trim_to=%08jx trim_to_refs=%jd\n",
"Journal: used_start=%08lx next_free=%08lx dirty_start=%08lx trim_to=%08lx trim_to_refs=%ld\n",
used_start, next_free, dirty_start,
journal_used_it == used_sectors.end() ? 0 : journal_used_it->first,
journal_used_it == used_sectors.end() ? 0 : journal_used_it->second
+1 -6
View File
@@ -13,14 +13,13 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config, bool init)
max_flusher_count = strtoull(config["flusher_count"].c_str(), NULL, 10);
}
min_flusher_count = strtoull(config["min_flusher_count"].c_str(), NULL, 10);
journal_trim_interval = strtoull(config["journal_trim_interval"].c_str(), NULL, 10);
max_write_iodepth = strtoull(config["max_write_iodepth"].c_str(), NULL, 10);
throttle_small_writes = config["throttle_small_writes"] == "true" || config["throttle_small_writes"] == "1" || config["throttle_small_writes"] == "yes";
throttle_target_iops = strtoull(config["throttle_target_iops"].c_str(), NULL, 10);
throttle_target_mbs = strtoull(config["throttle_target_mbs"].c_str(), NULL, 10);
throttle_target_parallelism = strtoull(config["throttle_target_parallelism"].c_str(), NULL, 10);
throttle_threshold_us = strtoull(config["throttle_threshold_us"].c_str(), NULL, 10);
if (config["autosync_writes"] != "")
if (config.find("autosync_writes") != config.end())
{
autosync_writes = strtoull(config["autosync_writes"].c_str(), NULL, 10);
}
@@ -32,10 +31,6 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config, bool init)
{
min_flusher_count = 1;
}
if (!journal_trim_interval)
{
journal_trim_interval = 512;
}
if (!max_write_iodepth)
{
max_write_iodepth = 128;

Some files were not shown because too many files have changed in this diff Show More