thebestvibedev/tromcho.net
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'rel-1.4'

Browse Source
This commit is contained in:
Vitaliy Filippov
2024-02-29 09:59:01 +03:00
parent 4eab26f968 38b8963330
commit 4cf6dceed7
35 changed files with 217 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/CMakeLists.txt
+1 -1
View File
@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
endif()
add_definitions(-DVERSION="1.4.7")
add_definitions(-DVERSION="1.4.8")
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 ${CMAKE_SOURCE_DIR}/src)
add_link_options(-fno-omit-frame-pointer)
if (${WITH_ASAN})
src/cli.cpp
+7 -3
View File
@@ -46,18 +46,21 @@ static const char* help_text =
"vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>\n"
" Create a snapshot of image <name>. May be used live if only a single writer is active.\n"
"\n"
"vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]\n"
"vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]\n"
" Rename, resize image or change its readonly status. Images with children can't be made read-write.\n"
" If the new size is smaller than the old size, extra data will be purged.\n"
" You should resize file system in the image, if present, before shrinking it.\n"
" -f|--force Proceed with shrinking or setting readwrite flag even if the image has children.\n"
" --down-ok Proceed with shrinking even if some data will be left on unavailable OSDs.\n"
"\n"
"vitastor-cli rm <from> [<to>] [--writers-stopped]\n"
"vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]\n"
" Remove <from> or all layers between <from> and <to> (<to> must be a child of <from>),\n"
" rebasing all their children accordingly. --writers-stopped allows merging to be a bit\n"
" more effective in case of a single 'slim' read-write child and 'fat' removed parent:\n"
" the child is merged into parent and parent is renamed to child in that case.\n"
" In other cases parent layers are always merged into children.\n"
" Other options:\n"
" --down-ok Continue deletion/merging even if some data will be left on unavailable OSDs.\n"
"\n"
"vitastor-cli flatten <layer>\n"
" Flatten a layer, i.e. merge data and detach it from parents.\n"
@@ -170,7 +173,7 @@ static const char* help_text =
" --parallel_osds M Work with M osds in parallel when possible (default 4)\n"
" --progress 1|0 Report progress (default 1)\n"
" --cas 1|0 Use CAS writes for flatten, merge, rm (default is decide automatically)\n"
" --no-color Disable colored output\n"
" --color 1|0 Enable/disable colored output and CR symbols (default 1 if stdout is a terminal)\n"
" --json JSON output\n"
;
@@ -221,6 +224,7 @@ static json11::Json::object parse_args(int narg, const char *args[])
!strcmp(opt, "readonly") || !strcmp(opt, "readwrite") ||
!strcmp(opt, "force") || !strcmp(opt, "reverse") ||
!strcmp(opt, "allow-data-loss") || !strcmp(opt, "allow_data_loss") ||
!strcmp(opt, "down-ok") || !strcmp(opt, "down_ok") ||
!strcmp(opt, "dry-run") || !strcmp(opt, "dry_run") ||
!strcmp(opt, "help") || !strcmp(opt, "all") ||
!strcmp(opt, "writers-stopped") || !strcmp(opt, "writers_stopped"))
src/cli_common.cpp
+7 -1
View File
@@ -1,6 +1,7 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 (see README.md for details)
#include <unistd.h>
#include "str_util.h"
#include "cluster_client.h"
#include "cli.h"
@@ -113,7 +114,12 @@ void cli_tool_t::parse_config(json11::Json::object & cfg)
else
kv_it++;
}
color = !cfg["no_color"].bool_value();
if (cfg.find("no_color") != cfg.end())
color = !cfg["no_color"].bool_value();
else if (cfg.find("color") != cfg.end())
color = cfg["color"].bool_value();
else
color = isatty(1);
json_output = cfg["json"].bool_value();
iodepth = cfg["iodepth"].uint64_value();
if (!iodepth)
src/cli_merge.cpp
+12 -4
View File
@@ -275,7 +275,9 @@ struct snap_merger_t
processed++;
if (parent->progress && !(processed % 128))
{
printf("\rFiltering target blocks: %ju/%ju", processed, to_process);
fprintf(stderr, parent->color
? "\rFiltering target blocks: %ju/%ju"
: "Filtering target blocks: %ju/%ju\n", processed, to_process);
}
}
if (in_flight > 0 || oit != merge_offsets.end())
@@ -285,7 +287,9 @@ struct snap_merger_t
}
if (parent->progress)
{
printf("\r%ju full blocks of target filtered out\n", to_process-merge_offsets.size());
fprintf(stderr, parent->color
? "\r%ju full blocks of target filtered out\n"
: "%ju full blocks of target filtered out\n", to_process-merge_offsets.size());
}
}
state = 3;
@@ -320,7 +324,9 @@ struct snap_merger_t
processed++;
if (parent->progress && !(processed % 128))
{
printf("\rOverwriting blocks: %ju/%ju", processed, to_process);
fprintf(stderr, parent->color
? "\rOverwriting blocks: %ju/%ju"
: "Overwriting blocks: %ju/%ju\n", processed, to_process);
}
}
if (in_flight == 0 && rwo_error.size())
@@ -339,7 +345,9 @@ struct snap_merger_t
}
if (parent->progress)
{
printf("\rOverwriting blocks: %ju/%ju\n", to_process, to_process);
fprintf(stderr, parent->color
? "\rOverwriting blocks: %ju/%ju\n"
: "Overwriting blocks: %ju/%ju\n", to_process, to_process);
}
// Done
result = (cli_result_t){ .text = "Done, layers from "+from_name+" to "+to_name+" merged into "+target_name, .data = json11::Json::object {
src/cli_modify.cpp
+3
View File
@@ -15,6 +15,7 @@ struct image_changer_t
uint64_t new_size = 0;
bool force_size = false, inc_size = false;
bool set_readonly = false, set_readwrite = false, force = false;
bool down_ok = false;
// interval between fsyncs
int fsync_interval = 128;
@@ -108,6 +109,7 @@ struct image_changer_t
{ "pool", (uint64_t)INODE_POOL(inode_num) },
{ "fsync-interval", fsync_interval },
{ "min-offset", ((new_size+4095)/4096)*4096 },
{ "down-ok", down_ok },
});
resume_1:
while (!cb(result))
@@ -252,6 +254,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_modify(json11::Json cfg)
changer->fsync_interval = cfg["fsync_interval"].uint64_value();
if (!changer->fsync_interval)
changer->fsync_interval = 128;
changer->down_ok = cfg["down_ok"].bool_value();
// FIXME Check that the image doesn't have children when shrinking
return [changer](cli_result_t & result)
{
src/cli_rm.cpp
+4
View File
@@ -53,6 +53,8 @@ struct snap_remover_t
int use_cas = 1;
// interval between fsyncs
int fsync_interval = 128;
// ignore deletion errors
bool down_ok = false;
std::map<inode_t,int> sources;
std::map<inode_t,uint64_t> inode_used;
@@ -680,6 +682,7 @@ resume_100:
{ "inode", inode },
{ "pool", (uint64_t)INODE_POOL(inode) },
{ "fsync-interval", fsync_interval },
{ "down-ok", down_ok },
});
}
};
@@ -691,6 +694,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm(json11::Json cfg)
snap_remover->from_name = cfg["from"].string_value();
snap_remover->to_name = cfg["to"].string_value();
snap_remover->fsync_interval = cfg["fsync_interval"].uint64_value();
snap_remover->down_ok = cfg["down_ok"].bool_value();
if (!snap_remover->fsync_interval)
snap_remover->fsync_interval = 128;
if (!cfg["cas"].is_null())
src/cli_rm_data.cpp
+10 -5
View File
@@ -25,6 +25,7 @@ struct rm_inode_t
uint64_t inode = 0;
pool_id_t pool_id = 0;
uint64_t min_offset = 0;
bool down_ok = false;
cli_tool_t *parent = NULL;
inode_list_t *lister = NULL;
@@ -212,7 +213,9 @@ struct rm_inode_t
}
if (parent->progress && total_count > 0 && total_done*1000/total_count != total_prev_pct)
{
fprintf(stderr, "\rRemoved %ju/%ju objects, %ju more PGs to list...", total_done, total_count, pgs_to_list);
fprintf(stderr, parent->color
? "\rRemoved %ju/%ju objects, %ju more PGs to list..."
: "Removed %ju/%ju objects, %ju more PGs to list...\n", total_done, total_count, pgs_to_list);
total_prev_pct = total_done*1000/total_count;
}
if (lists_done && !lists.size())
@@ -221,17 +224,18 @@ struct rm_inode_t
{
fprintf(stderr, "\n");
}
if (parent->progress && (total_done < total_count || inactive_osds.size() > 0 || error_count > 0))
bool is_error = (total_done < total_count || inactive_osds.size() > 0 || error_count > 0);
if (parent->progress && is_error)
{
fprintf(
stderr, "Warning: Pool:%u,ID:%ju inode data may not have been fully removed.\n"
" Use `vitastor-cli rm-data --pool %u --inode %ju` if you encounter it in listings.\n",
"Use `vitastor-cli rm-data --pool %u --inode %ju` if you encounter it in listings.\n",
pool_id, INODE_NO_POOL(inode), pool_id, INODE_NO_POOL(inode)
);
}
result = (cli_result_t){
.err = error_count > 0 ? EIO : 0,
.text = error_count > 0 ? "Some blocks were not removed" : (
.err = is_error && !down_ok ? EIO : 0,
.text = is_error ? "Some blocks were not removed" : (
"Done, inode "+std::to_string(INODE_NO_POOL(inode))+" from pool "+
std::to_string(pool_id)+" removed"),
.data = json11::Json::object {
@@ -280,6 +284,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm_data(json11::Json cfg)
{
remover->inode = (remover->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (((uint64_t)remover->pool_id) << (64-POOL_ID_BITS));
}
remover->down_ok = cfg["down_ok"].bool_value();
remover->pool_id = INODE_POOL(remover->inode);
remover->min_offset = cfg["min_offset"].uint64_value();
return [remover](cli_result_t & result)
src/cluster_client.cpp
+57 -33
View File
@@ -265,7 +265,7 @@ void cluster_client_t::erase_op(cluster_op_t *op)
}
}
void cluster_client_t::continue_ops(bool up_retry)
void cluster_client_t::continue_ops(int time_passed)
{
if (!pgs_loaded)
{
@@ -277,22 +277,27 @@ void cluster_client_t::continue_ops(bool up_retry)
// Attempt to reenter the function
return;
}
int reset_duration = 0;
restart:
continuing_ops = 1;
for (auto op = op_queue_head; op; )
{
cluster_op_t *next_op = op->next;
if (!op->up_wait || up_retry)
if (op->retry_after && time_passed)
{
op->up_wait = false;
if (!op->prev_wait)
op->retry_after = op->retry_after > time_passed ? op->retry_after-time_passed : 0;
if (op->retry_after && (!reset_duration || op->retry_after < reset_duration))
{
if (op->opcode == OSD_OP_SYNC)
continue_sync(op);
else
continue_rw(op);
reset_duration = op->retry_after;
}
}
if (!op->retry_after && !op->prev_wait)
{
if (op->opcode == OSD_OP_SYNC)
continue_sync(op);
else
continue_rw(op);
}
op = next_op;
if (continuing_ops == 2)
{
@@ -300,6 +305,27 @@ restart:
}
}
continuing_ops = 0;
reset_retry_timer(reset_duration);
}
void cluster_client_t::reset_retry_timer(int new_duration)
{
if (retry_timeout_duration && retry_timeout_duration <= new_duration || !new_duration)
{
return;
}
if (retry_timeout_id)
{
tfd->clear_timer(retry_timeout_id);
}
retry_timeout_duration = new_duration;
retry_timeout_id = tfd->set_timer(retry_timeout_duration, false, [this](int)
{
int time_passed = retry_timeout_duration;
retry_timeout_id = 0;
retry_timeout_duration = 0;
continue_ops(time_passed);
});
}
void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_config)
@@ -349,15 +375,25 @@ void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_co
{
client_max_writeback_iodepth = DEFAULT_CLIENT_MAX_WRITEBACK_IODEPTH;
}
// up_wait_retry_interval
up_wait_retry_interval = config["up_wait_retry_interval"].uint64_value();
if (!up_wait_retry_interval)
// client_retry_interval
client_retry_interval = config["client_retry_interval"].uint64_value();
if (!client_retry_interval)
{
up_wait_retry_interval = 50;
client_retry_interval = 50;
}
else if (up_wait_retry_interval < 10)
else if (client_retry_interval < 10)
{
up_wait_retry_interval = 10;
client_retry_interval = 10;
}
// client_eio_retry_interval
client_eio_retry_interval = 1000;
if (!config["client_eio_retry_interval"].is_null())
{
client_eio_retry_interval = config["client_eio_retry_interval"].uint64_value();
if (client_eio_retry_interval && client_eio_retry_interval < 10)
{
client_eio_retry_interval = 10;
}
}
// log_level
log_level = config["log_level"].uint64_value();
@@ -716,15 +752,8 @@ resume_1:
// We'll need to retry again
if (op->parts[i].flags & PART_RETRY)
{
op->up_wait = true;
if (!retry_timeout_id)
{
retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
{
retry_timeout_id = 0;
continue_ops(true);
});
}
op->retry_after = client_retry_interval;
reset_retry_timer(client_retry_interval);
}
op->state = 1;
}
@@ -780,10 +809,9 @@ resume_2:
return 1;
}
else if (op->retval != 0 && !(op->flags & OP_FLUSH_BUFFER) &&
op->retval != -EPIPE && op->retval != -EIO && op->retval != -ENOSPC)
op->retval != -EPIPE && (op->retval != -EIO || !client_eio_retry_interval) && op->retval != -ENOSPC)
{
// Fatal error (neither -EPIPE, -EIO nor -ENOSPC)
// FIXME: Add a parameter to allow to not wait for EIOs (incomplete or corrupted objects) to heal
erase_op(op);
return 1;
}
@@ -1171,16 +1199,12 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
// All next things like timer, continue_sync/rw and stop_client may affect the operation again
// So do all these things after modifying operation state, otherwise we may hit reenterability bugs
// FIXME postpone such things to set_immediate here to avoid bugs
// Mark op->up_wait = true to retry operation after a short pause (not immediately)
op->up_wait = true;
if (!retry_timeout_id)
// Set op->retry_after to retry operation after a short pause (not immediately)
if (!op->retry_after)
{
retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
{
retry_timeout_id = 0;
continue_ops(true);
});
op->retry_after = op->retval == -EIO ? client_eio_retry_interval : client_retry_interval;
}
reset_retry_timer(op->retry_after);
if (op->inflight_count == 0)
{
if (op->opcode == OSD_OP_SYNC)
src/cluster_client.h
+6 -3
View File
@@ -59,7 +59,7 @@ protected:
void *buf = NULL;
cluster_op_t *orig_op = NULL;
bool needs_reslice = false;
bool up_wait = false;
int retry_after = 0;
int inflight_count = 0, done_count = 0;
std::vector<cluster_op_part_t> parts;
void *part_bitmaps = NULL;
@@ -92,9 +92,11 @@ class cluster_client_t
uint64_t client_max_writeback_iodepth = 0;
int log_level = 0;
int up_wait_retry_interval = 500; // ms
int client_retry_interval = 50; // ms
int client_eio_retry_interval = 1000; // ms
int retry_timeout_id = 0;
int retry_timeout_duration = 0;
std::vector<cluster_op_t*> offline_ops;
cluster_op_t *op_queue_head = NULL, *op_queue_tail = NULL;
writeback_cache_t *wb = NULL;
@@ -131,7 +133,7 @@ public:
bool get_immediate_commit(uint64_t inode);
void continue_ops(bool up_retry = false);
void continue_ops(int time_passed = 0);
inode_list_t *list_inode_start(inode_t inode,
std::function<void(inode_list_t* lst, std::set<object_id>&& objects, pg_num_t pg_num, osd_num_t primary_osd, int status)> callback);
int list_pg_count(inode_list_t *lst);
@@ -152,6 +154,7 @@ protected:
int continue_rw(cluster_op_t *op);
bool check_rw(cluster_op_t *op);
void slice_rw(cluster_op_t *op);
void reset_retry_timer(int new_duration);
bool try_send(cluster_op_t *op, int i);
int continue_sync(cluster_op_t *op);
void send_sync(cluster_op_t *op, cluster_op_part_t *part);
src/vitastor.pc.in
+1 -1
View File
@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
Name: Vitastor
Description: Vitastor client library
Version: 1.4.7
Version: 1.4.8
Libs: -L${libdir} -lvitastor_client
Cflags: -I${includedir}