Compare commits

...
Author SHA1 Message Date
Vitaliy Filippov 0d6eeec6a4 Fix osd_peering_pg_test 2026-04-14 02:44:59 +03:00
Vitaliy Filippov 8ed1e180e0 Clear inode_stats in mon 2026-04-14 02:44:46 +03:00
Vitaliy Filippov 8832fc3b14 Fix print to stdout in client 2026-04-14 02:43:50 +03:00
Vitaliy Filippov 0134934c99 Do not skip garbage entries on start (rollback change from 3.0.4) 2026-04-11 12:05:02 +03:00
Vitaliy Filippov 2e36f292bd Fix buffer alignment during metadata clearing on init 2026-04-10 21:56:12 +03:00
Vitaliy Filippov bcc6419760 Auto-select the only RDMA device/port if there is only one 2026-04-08 15:46:10 +03:00
Vitaliy Filippov dd5941b9a4 Release 3.0.9
- Fix broken garbage collection in the new store leading to very high memory usage
- Make the new store do full garbage collection on OSD startup by default (can be turned off with a new gc_on_start parameter)
- Make startup logging with the new store more informative, allow to log amount of garbage with log_level > 1
- Fix clients reading from snapshots incorrectly on retries (for example when OSDs were restarted during read)
- Fix a possible "send-after-free" in OSD which could probably also affect snapshot reads
- Fix OSD crashing when handling a read_bitmap operation from a deleted object with the new store
2026-04-04 18:38:40 +03:00
Vitaliy Filippov 4005b88865 Do not use node_type 2026-04-04 17:37:47 +03:00
Vitaliy Filippov 280b5cd675 Add gc_on_start docs 2026-04-04 17:19:32 +03:00
30 changed files with 84 additions and 45 deletions
+1 -1
View File
@@ -2,7 +2,7 @@ cmake_minimum_required(VERSION 2.8...3.30)
project(vitastor)
set(VITASTOR_VERSION "3.0.8")
set(VITASTOR_VERSION "3.0.9")
include(CTest)
+1 -1
View File
@@ -1,4 +1,4 @@
VITASTOR_VERSION ?= v3.0.8
VITASTOR_VERSION ?= v3.0.9
all: build push
+1 -1
View File
@@ -49,7 +49,7 @@ spec:
capabilities:
add: ["SYS_ADMIN"]
allowPrivilegeEscalation: true
image: vitalif/vitastor-csi:v3.0.8
image: vitalif/vitastor-csi:v3.0.9
args:
- "--node=$(NODE_ID)"
- "--endpoint=$(CSI_ENDPOINT)"
+1 -1
View File
@@ -121,7 +121,7 @@ spec:
privileged: true
capabilities:
add: ["SYS_ADMIN"]
image: vitalif/vitastor-csi:v3.0.8
image: vitalif/vitastor-csi:v3.0.9
args:
- "--node=$(NODE_ID)"
- "--endpoint=$(CSI_ENDPOINT)"
+1 -1
View File
@@ -5,7 +5,7 @@ package vitastor
const (
vitastorCSIDriverName = "csi.vitastor.io"
vitastorCSIDriverVersion = "3.0.8"
vitastorCSIDriverVersion = "3.0.9"
)
// Config struct fills the parameters of request or user input
+1 -1
View File
@@ -1,4 +1,4 @@
vitastor (3.0.8-1) unstable; urgency=medium
vitastor (3.0.9-1) unstable; urgency=medium
* Bugfixes
+1 -1
View File
@@ -1,4 +1,4 @@
VITASTOR_VERSION ?= v3.0.8
VITASTOR_VERSION ?= v3.0.9
all: build push
+1 -1
View File
@@ -4,7 +4,7 @@
#
# Desired Vitastor version
VITASTOR_VERSION=v3.0.8
VITASTOR_VERSION=v3.0.9
# Additional arguments for all containers
# For example, you may want to specify a custom logging driver here
+7
View File
@@ -70,6 +70,7 @@ with an OSD restart or, for some of them, even without restarting by updating co
- [use_atomic_flag](#use_atomic_flag)
- [pg_reshard_chunk_size](#pg_reshard_chunk_size)
- [pg_reshard_chunk_pause_ms](#pg_reshard_chunk_pause_ms)
- [gc_on_start](#gc_on_start)
## bind_address
@@ -753,3 +754,9 @@ This option sets the maximum number of object is a chunk. Moving 100k objects us
- Default: 100
This option sets the interval between handling two PG count change chunks.
## gc_on_start
- Type: boolean
Forcibly clean all garbage entries in the new store on every OSD restart.
+7
View File
@@ -71,6 +71,7 @@
- [use_atomic_flag](#use_atomic_flag)
- [pg_reshard_chunk_size](#pg_reshard_chunk_size)
- [pg_reshard_chunk_pause_ms](#pg_reshard_chunk_pause_ms)
- [gc_on_start](#gc_on_start)
## bind_address
@@ -793,3 +794,9 @@ pg_minsize OSD во время переключений, что может по
- Значение по умолчанию: 100
Данная опция задаёт интервал между обработкой двух порций изменения числа PG пулов.
## gc_on_start
- Тип: булево (да/нет)
Принудительно очищать все мусорные записи в новом хранилище при каждом запуске OSD.
+4
View File
@@ -938,3 +938,7 @@
This option sets the interval between handling two PG count change chunks.
info_ru: |
Данная опция задаёт интервал между обработкой двух порций изменения числа PG пулов.
- name: gc_on_start
type: bool
info: Forcibly clean all garbage entries in the new store on every OSD restart.
info_ru: Принудительно очищать все мусорные записи в новом хранилище при каждом запуске OSD.
+2 -2
View File
@@ -26,9 +26,9 @@ at Vitastor Kubernetes operator: https://github.com/Antilles7227/vitastor-operat
The instruction is very simple.
1. Download a Docker image of the desired version: \
`docker pull vitalif/vitastor:v3.0.8`
`docker pull vitalif/vitastor:v3.0.9`
2. Install scripts to the host system: \
`docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v3.0.8 install.sh`
`docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v3.0.9 install.sh`
3. Reload udev rules: \
`udevadm control --reload-rules`
4. Enable the vitastor-host service: \
+2 -2
View File
@@ -25,9 +25,9 @@ Vitastor можно установить в Docker/Podman. При этом etcd,
Инструкция по установке максимально простая.
1. Скачайте Docker-образ желаемой версии: \
`docker pull vitalif/vitastor:v3.0.8`
`docker pull vitalif/vitastor:v3.0.9`
2. Установите скрипты в хост-систему командой: \
`docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v3.0.8 install.sh`
`docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v3.0.9 install.sh`
3. Перезагрузите правила udev: \
`udevadm control --reload-rules`
4. Включите сервис vitastor-host: \
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "vitastor-mon",
"version": "3.0.8",
"version": "3.0.9",
"description": "Vitastor SDS monitor service",
"main": "mon-main.js",
"scripts": {
+1
View File
@@ -37,6 +37,7 @@ function derive_osd_stats(st, prev, prev_diff)
const n = c.count - BigInt(pr && pr.count||0);
diff.recovery_stats[op] = { ...c, bps: n > 0 ? b*1000n/timediff : 0n, iops: n > 0 ? n*1000n/timediff : 0n };
}
diff.inode_stats = {};
for (const pool_id in st.inode_stats||{})
{
diff.inode_stats[pool_id] = {};
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "vitastor",
"version": "3.0.8",
"version": "3.0.9",
"description": "Low-level native bindings to Vitastor client library",
"main": "index.js",
"keywords": [
+1 -1
View File
@@ -50,7 +50,7 @@ from cinder.volume import configuration
from cinder.volume import driver
from cinder.volume import volume_utils
VITASTOR_VERSION = '3.0.8'
VITASTOR_VERSION = '3.0.9'
LOG = logging.getLogger(__name__)
+2 -2
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 3.0.8
Version: 3.0.9
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-3.0.8.el10.tar.gz
Source0: vitastor-3.0.9.el10.tar.gz
BuildRequires: gperftools-devel
BuildRequires: gcc-c++
+2 -2
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 3.0.8
Version: 3.0.9
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-3.0.8.el7.tar.gz
Source0: vitastor-3.0.9.el7.tar.gz
BuildRequires: gperftools-devel
BuildRequires: devtoolset-9-gcc-c++
+2 -2
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 3.0.8
Version: 3.0.9
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-3.0.8.el8.tar.gz
Source0: vitastor-3.0.9.el8.tar.gz
BuildRequires: gperftools-devel
BuildRequires: gcc-toolset-9-gcc-c++
+2 -2
View File
@@ -1,11 +1,11 @@
Name: vitastor
Version: 3.0.8
Version: 3.0.9
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-3.0.8.el9.tar.gz
Source0: vitastor-3.0.9.el9.tar.gz
BuildRequires: gperftools-devel
BuildRequires: gcc-c++
+1 -1
View File
@@ -20,7 +20,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
endif()
set(ENABLE_COVERAGE false CACHE BOOL "Enable code coverage")
add_definitions(-DVITASTOR_VERSION="3.0.8")
add_definitions(-DVITASTOR_VERSION="3.0.9")
add_definitions(-D_GNU_SOURCE -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 -fvisibility=hidden -I ${CMAKE_SOURCE_DIR}/src)
add_link_options(-fno-omit-frame-pointer)
if (${WITH_ASAN})
+6 -13
View File
@@ -334,19 +334,12 @@ corrupted_block:
block_num, block_offset, wr->size, sizeof(heap_entry_t));
goto corrupted_block;
}
if (wr->is_garbage())
{
// Garbage collection is only performed when writing new entries into the block
// because it needs a fake LSN and modified blocks require consecutive modified LSNs
// That's why garbage entries may persist on disk
if (log_level > 5)
{
fprintf(stderr, "Notice: skipping garbage entry %jx:%jx v%ju l%ju in metadata block %u at %u\n",
wr->inode, wr->stripe, wr->version, wr->lsn, block_num, block_offset);
}
block_offset += wr->size;
continue;
}
// Garbage collection is only performed when writing new entries into the block
// because it needs a fake LSN and modified blocks require consecutive modified LSNs
// At the same time, further modifications _after_ putting new entries into the block,
// but _before_ writing it, may mark some entries in it as garbage. That's why garbage
// entries may still be present on disk.
wr->entry_type &= ~BS_HEAP_GARBAGE;
if ((wr->entry_type & BS_HEAP_TYPE) < BS_HEAP_BIG_WRITE ||
(wr->entry_type & BS_HEAP_TYPE) > BS_HEAP_ROLLBACK ||
(wr->entry_type & ~(BS_HEAP_TYPE|BS_HEAP_STABLE)) ||
+1 -1
View File
@@ -311,7 +311,7 @@ resume_8:
uint32_t block_num = recheck_mod[i];
uint64_t block_offset = bs->dsk.meta_offset + (uint64_t)(block_num+1) * bs->dsk.meta_block_size;
data = ((ring_data_t*)sqe->user_data);
uint8_t *buf = (uint8_t*)malloc_or_die(bs->dsk.meta_block_size);
uint8_t *buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, bs->dsk.meta_block_size);
bs->heap->get_meta_block(block_num, buf);
data->iov = { buf, bs->dsk.meta_block_size };
data->callback = [this, buf, block_offset](ring_data_t *data)
+1 -1
View File
@@ -877,7 +877,7 @@ uint64_t blockstore_impl_t::get_garbage_entries()
uint64_t blockstore_impl_t::get_garbage_memory()
{
return sizeof(blockstore_dirty_db_t::node_type) * dirty_db.size();
return (sizeof(obj_ver_id) + sizeof(dirty_entry) + 32) * dirty_db.size();
}
} // namespace v1
+1 -1
View File
@@ -590,7 +590,7 @@ void cluster_client_t::on_change_pool_config_hook()
{
if (log_level > 2 && pg_counts[pool_item.first])
{
printf("Pool %u (%s) PG count changed from %lu to %lu\n", pool_item.first, pool_item.second.name.c_str(),
fprintf(stderr, "Pool %u (%s) PG count changed from %lu to %lu\n", pool_item.first, pool_item.second.name.c_str(),
pg_counts[pool_item.first], pool_item.second.real_pg_count);
}
// At this point, all pool operations should have been suspended
+14
View File
@@ -187,6 +187,8 @@ std::vector<msgr_rdma_context_t*> msgr_rdma_context_t::create_all(const std::vec
ibv_device **raw_dev_list = NULL;
ibv_device **dev_list = NULL;
ibv_device *single_list[2] = {};
int up_ports = 0;
int single_port_num = 0;
raw_dev_list = dev_list = ibv_get_device_list(NULL);
if (!dev_list || !*dev_list)
@@ -221,6 +223,7 @@ std::vector<msgr_rdma_context_t*> msgr_rdma_context_t::create_all(const std::vec
dev_list = single_list;
}
retry:
for (int i = 0; dev_list[i]; ++i)
{
auto dev = dev_list[i];
@@ -258,6 +261,9 @@ std::vector<msgr_rdma_context_t*> msgr_rdma_context_t::create_all(const std::vec
fprintf(stderr, "RDMA device %s port %d GID %d does not exist\n", ibv_get_device_name(dev), port_num, sel_gid_index);
continue;
}
up_ports++;
single_port_num = port_num;
single_list[0] = dev;
uint32_t port_mtu = sel_mtu ? sel_mtu : ibv_mtu_to_bytes(portinfo.active_mtu);
#ifdef IBV_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT
if (sel_gid_index < 0)
@@ -298,6 +304,14 @@ cleanup_dev:
ibv_close_device(context);
}
if (!ret.size() && up_ports == 1 && dev_list != single_list)
{
// Auto-select the only available device/port if there is only one
dev_list = single_list;
sel_port_num = single_port_num;
goto retry;
}
cleanup:
if (raw_dev_list)
ibv_free_device_list(raw_dev_list);
+1 -1
View File
@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
Name: Vitastor
Description: Vitastor client library
Version: 3.0.8
Version: 3.0.9
Libs: -L${libdir} -lvitastor_client
Cflags: -I${includedir}
+15 -3
View File
@@ -1,8 +1,6 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 (see README.md for details)
#define _LARGEFILE64_SOURCE
#include "malloc_or_die.h"
#include "osd_peering_pg.h"
#define STRIPE_SHIFT 12
@@ -22,13 +20,20 @@
*/
int main(int argc, char *argv[])
{
setvbuf(stdout, NULL, _IONBF, 0);
setvbuf(stderr, NULL, _IONBF, 0);
pg_t pg = {
.state = PG_PEERING,
.scheme = POOL_SCHEME_EC,
.pg_size = 3,
.pg_minsize = 2,
.pg_data_size = 2,
.pg_num = 1,
.target_set = { 1, 2, 3 },
.cur_set = { 1, 2, 3 },
.peering_state = new pg_peering_state_t(),
};
printf("generating\n");
for (uint64_t osd_num = 1; osd_num <= 3; osd_num++)
{
pg_list_result_t r = {
@@ -48,8 +53,15 @@ int main(int argc, char *argv[])
}
pg.peering_state->list_results[osd_num] = r;
}
printf("calculating states\n");
timespec tv0;
clock_gettime(CLOCK_REALTIME, &tv0);
pg.calc_object_states(0);
printf("deviation variants=%jd clean=%ju\n", pg.state_dict.size(), pg.clean_count);
timespec tv1;
clock_gettime(CLOCK_REALTIME, &tv1);
printf("%.2f deviation variants=%jd clean=%ju\n",
(tv1.tv_sec - tv0.tv_sec + tv1.tv_nsec/1000000000.0 - tv0.tv_nsec/1000000000.0),
pg.state_dict.size(), pg.clean_count);
for (auto it: pg.state_dict)
{
printf("dev: state=%jx\n", it.second.state);
+2 -1
View File
@@ -1893,7 +1893,8 @@ void test_big_intent_csums()
heap.finish_recheck();
auto mod = heap.get_recheck_modified_blocks();
assert(mod.size() == 0);
assert(mod.size() == 1);
assert(mod[0] == 0);
// read object 1 - big_intent should be there
object_id oid = { .inode = INODE_WITH_POOL(1, 1), .stripe = 0 };