Commit Graph

8083 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
4617dc8bbe
lib/logstorage: consistently use atomic.* types instead of atomic.* functions on regular types
See ea9e2b19a5
2024-02-23 23:46:13 +02:00
Aliaksandr Valialkin
f81b480905
lib/mergeset: consistently use atomic.* types instead of atomic.* function calls on ordinary types
See ea9e2b19a5
2024-02-23 23:29:35 +02:00
Aliaksandr Valialkin
275335c181
lib/logstorage: consistently use atomic.* type for refCount and mustDrop fields in datadb and storage structs in the same way as it is used in lib/storage
See ea9e2b19a5 and a204fd69f1
2024-02-23 23:04:42 +02:00
Aliaksandr Valialkin
5c89150fc9
lib/mergeset: consistently use atomic.* type for refCount and mustDrop fields in table struct in the same way as it is used in lib/storage
See ea9e2b19a5 and a204fd69f1
2024-02-23 22:59:23 +02:00
Aliaksandr Valialkin
a204fd69f1
lib/storage: consistently use atomic.* type for refCount and mustDrop fields in indexDB, table and partition structs
See ea9e2b19a5
2024-02-23 22:54:59 +02:00
Aliaksandr Valialkin
0f1ea36dc8
lib/storage: convert dedupsDuringMerge from uint64 to atomic.Uint64
This should simplify code maintenance by gradually converting to atomic.* types instead of calling atomic.* functions
on int and bool types.

See ea9e2b19a5
2024-02-23 22:52:00 +02:00
Aliaksandr Valialkin
ea9e2b19a5
lib/{storage,mergeset}: properly fix 'unaligned 64-bit atomic operation' panic on 32-bit architectures
The issue has been introduced in bace9a2501
The improper fix was in the d4c0615dcd ,
since it fixed the issue just by an accident, because Go comiler aligned the rawRowsShards field
by 4-byte boundary inside partition struct.

The proper fix is to use atomic.Int64 field - this guarantees that the access to this field
won't result in unaligned 64-bit atomic operation. See https://github.com/golang/go/issues/50860
and https://github.com/golang/go/issues/19057
2024-02-23 22:27:06 +02:00
Aliaksandr Valialkin
cf94522389
lib/httpserver: return back the default value for -http.connTimeout to 2 minutes
It has been appeared that there are VictoriaMetrics users, who rely on the fact that
VictoriaMetrics components were closing incoming connections to -httpListenAddr every 2 minutes
by default. So let's return back this value by default in order to fix the breaking change
made at d8c1db7953 .

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1304#issuecomment-1961891450 .
2024-02-23 22:03:37 +02:00
Aliaksandr Valialkin
ea858b6e72
docs/Troubleshooting.md: add Too much disk space used chapter` 2024-02-23 22:03:36 +02:00
hagen1778
6390b54c4d
docs: mention missing change 521f9ffb430edf6aea7720a966b5b079cf15e34e
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-02-23 19:55:06 +01:00
hagen1778
c8d1d2ab72
lib/storage: cleanup after d4c0615dcd
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-02-23 18:53:55 +01:00
Dmytro Kozlov
d4c0615dcd
lib/storage: fix aligning (#5860) 2024-02-23 16:37:21 +01:00
Roman Khavronenko
840ab60111
deployment: add topology visualizations (#5858)
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-02-23 12:20:32 +01:00
Aliaksandr Valialkin
340638d4b0
app/vmstorage: cleanup after 9bad52b687 2024-02-23 04:55:17 +02:00
Aliaksandr Valialkin
9bad52b687
app/vmstorage: deprecate -snapshotCreateTimeout command-line flag
Creating snapshot shouldn't time out under normal conditions.
The timeout was related to the bug, which has been fixed in 6460475e3b .

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3551
2024-02-23 04:49:23 +02:00
Aliaksandr Valialkin
f79944532b
lib/storage: do not drop (date, metricID) entries for the date older than 2 days if samples are ingested at this date
Previously the (date, metricID) entries for dates older than the last 2 days were removed.
This could lead to slow check for the (date, metricID) entry in the indexdb during ingesting historical data (aka backfilling).

The issue has been introduced in 431aa16c8d
2024-02-23 04:06:19 +02:00
Aliaksandr Valialkin
f46eaf92eb
app/vmselect: add -search.maxLabelsAPIDuration and -search.maxLabelsAPISeries options for fine-tuning CPU and RAM usage for /api/v1/series , /api/v1/labels and /api/v1/label/.../values
This commit returns back limits for these endpoints, which have been removed at 5d66ee88bd ,
since it has been appeared that missing limits result in high CPU usage, while the introduced concurrency limiter
results in failed lightweight requests to these endpoints because of timeout when heavyweight requests are executed.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5055
2024-02-23 02:57:16 +02:00
Aliaksandr Valialkin
8995b04886
app/{vmselect,vlselect}/vmui: run make vmui-update vmui-logs-update after recent changes to app/vmui 2024-02-23 01:40:48 +02:00
Yury Molodov
abf82c3657
vmui: add a time picker to the "Logs Explorer" page (#5808)
* vmui: add a time picker to the "Logs Explorer" page #5673

* Update app/vmui/packages/vmui/src/pages/ExploreLogs/hooks/useFetchLogs.ts

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2024-02-23 01:38:30 +02:00
Yury Molodov
9e44870d5c
vmui: fix display Popper.tsx (#5842)
* vmui: fix display Popper.tsx

* vmui/docs: fix display Popper.tsx

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2024-02-23 01:32:48 +02:00
Aliaksandr Valialkin
348eec39ba
docs/Single-server-VictoriaMetrics.md: sync with docs/README.md after 79b57f625c 2024-02-23 01:09:53 +02:00
Aliaksandr Valialkin
3997319f45
docs/CHANGELOG.md: document d68bb658ce
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5833
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5834
2024-02-23 01:03:48 +02:00
Anton L
d68bb658ce
#5833 Fix Deadlock when using shardByURL of VMAgent (#5834) 2024-02-23 00:59:47 +02:00
Aliaksandr Valialkin
df7d3c55ed
lib/promutils: hide the math.Round() logic inside ParseTimeMsec() function
This should prevent from bugs similar to https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5801 in the future

This is a follow-up for ce3ec3ff2e
2024-02-23 00:55:32 +02:00
Aliaksandr Valialkin
5934002b57
lib/mergeset: run go fmt after bace9a2501 2024-02-23 00:53:28 +02:00
Aliaksandr Valialkin
bace9a2501
lib/{mergeset,storage}: convert bufferred items to searchable parts more optimally
Do not convert shard items to part when a shard becomes full. Instead, collect multiple
full shards and then convert them to a searchable part at once. This reduces
the number of searchable parts, which, in turn, should increase query performance,
since queries need to scan smaller number of parts.
2024-02-23 00:16:34 +02:00
hagen1778
3bec0549dc
docs: re-classify change of default http timeout to bugfix
The change introduced in d8c1db7953 (diff-2bfab3db5cc1baf4c6d3ff6b19901926e3bdf4411ec685dac973e5fcff1c723b)
was backported to v1.97.2. Therefore, it is a `bugfix` and should be explicitly
mentioned in the changelog of v1.97.2

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-02-22 21:57:39 +01:00
Nikolay
07855de142
app/vmselect: change export/csv timestamp format for rfc3339 to respect milliseconds (#5853)
* app/vmselect: adds milliseconds to the csv export response for rfc3339
* milliseconds is a standard prescion for VictoriaMetrics query request responses
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5837

* app/victoria-metrics: adds tests for csv export/import
follow-up after 3541a8d0cf96dd4f8563624c4aab6816615d0756


---------

Signed-off-by: hagen1778 <roman@victoriametrics.com>
Co-authored-by: hagen1778 <roman@victoriametrics.com>
2024-02-22 20:31:22 +01:00
Aliaksandr Valialkin
e8b3045062
lib/storage: handle common case when the number of rows passed to flushRowsToInmemoryParts() doesnt exceed maxRawRowsPerShard 2024-02-22 20:44:11 +02:00
Aliaksandr Valialkin
73f0a805e2
lib/{storage,mergeset}: convert beffered items into searchable in-memory parts exactly once per the given flush interval
Previously the interval between item addition and its conversion to searchable in-memory part
could vary significantly because of too coarse per-second precision. Switch from fasttime.UnixTimestamp()
to time.Now().UnixMilli() for millisecond precision. It is OK to use time.Now() for tracking
the time when buffered items must be converted to searchable in-memory parts, since time.Now()
calls aren't located in hot paths.

Increase the flush interval for converting buffered samples to searchable in-memory parts
from one second to two seconds. This should reduce the number of blocks, which are needed
to be processed during high-frequency alerting queries. This, in turn, should reduce CPU usage.

While at it, hardcode the maximum size of rawRows shard to 8Mb, since this size gives the optimal
data ingestion pefromance according to load tests. This reduces memory usage and CPU usage on systems
with big amounts of RAM under high data ingestion rate.
2024-02-22 20:21:14 +02:00
Aliaksandr Valialkin
463bc27312
lib/storage: avoid superflouos copy of block header data 2024-02-22 20:21:14 +02:00
Fred Navruzov
34aa25d681
- v1.11 doc updates (#5852)
- fix dead links
2024-02-22 18:48:54 +01:00
Dan Dascalescu
79b57f625c
docs: CSV RFC3339 format uses server timezone (#5839) 2024-02-22 18:13:41 +01:00
Aliaksandr Valialkin
8d9d7a8a12
app/vmstorage: expose vm_snapshots metric, which shows the current number of snapshots
While at it, refresh docs about snapshots - https://docs.victoriametrics.com/#how-to-work-with-snapshots
2024-02-22 18:32:57 +02:00
Aliaksandr Valialkin
cd34142a14
README.md: sync with docs/Single-server-VictoriaMetrics.md after 5b652bccad 2024-02-22 18:32:11 +02:00
Aliaksandr Valialkin
aec9cd4316
lib/storage: do not pool rawRowsBlock when flushing rawRows to in-memory blocks
The pooled rawRowsBlock objects occupies big amounts of memory between flushes,
and the flushes are relatively rare. So it is better to don't use the pool
and to allocate rawRow blocks on demand. This should reduce the average
memory usage between flushes.
2024-02-22 17:37:48 +02:00
Aliaksandr Valialkin
b7dfe9894c
lib/storage: do not keep rawRows buffer across flush() calls
The buffer can be quite big under high ingestion rate (e.g. more than 100MB).
This leads to increased memory usage between buffer flushes.
So it is better to re-create the buffer on every flush in order to reduce memory usage
between buffer flushes.
2024-02-22 17:22:26 +02:00
Aliaksandr Valialkin
fa19daf3bd
docs/MetricsQL.md: improve text formatting for better readability 2024-02-22 14:00:47 +02:00
Aliaksandr Valialkin
f7c3dee1c3
app/vmselect/promql: add count_values_over_time() MetricsQL function
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5847
2024-02-22 13:39:29 +02:00
Aliaksandr Valialkin
a6eacfdb11
app/vmselect/promql: move needSilenceIntervalForRollupFunc from eval.go to rollup.go
This should improve maintainability of the code related to rollup functions,
since it is located in rollup.go

While at it, properly return empty results from holt_winters(), rate_over_sum(),
sum2_over_time(), geomean_over_time() and distinct_over_time() when there are no real samples
on the selected lookbehind window. Previously the previous sample value was mistakenly
returned from these functions.
2024-02-22 13:39:28 +02:00
Alexander Marshalov
ce3ec3ff2e
[lib/httputils] fixed floating-point error when parsing time in RFC3339 format (#5814)
* [lib/promutils, lib/httputils] fixed floating-point error when parsing time in RFC3339 format (#5801)

* fixed tests

* fixed test

* Revert "fixed test"

This reverts commit 8a29764806.

* Revert "fixed tests"

This reverts commit 9ce13d1042.

* Revert "[lib/promutils, lib/httputils] fixed floating-point error when parsing time in RFC3339 format (#5801)"

This reverts commit a7a04bd4

* [lib/httputils] fixed floating-point error when parsing time in RFC3339 format (#5801)

---------

Co-authored-by: Nikolay <nik@victoriametrics.com>
2024-02-22 10:20:54 +01:00
Artem Navoiev
7332431b90
docs: change header from h1 to h2 1.97.2. The markdown requires the proper structure in hierachy of title so h1 can not be a child of h1,h2... only be a separate item, in our structure title is the parent h1
Signed-off-by: Artem Navoiev <tenmozes@gmail.com>
2024-02-21 16:15:41 +01:00
Github Actions
2c98e8712c
Automatic update operator docs from VictoriaMetrics/operator@d88157b (#5845) 2024-02-21 16:13:34 +01:00
Github Actions
c35c1b007c
Automatic update operator docs from VictoriaMetrics/operator@c393852 (#5844) 2024-02-21 13:28:05 +01:00
Github Actions
0af5f88744
Automatic update operator docs from VictoriaMetrics/operator@4791fd1 (#5843) 2024-02-21 12:52:32 +01:00
hagen1778
7ee131de8b
deployment/docker: add comments to components in docker-compose manifests
This should help readers to understand interconnectivity between components.

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-02-20 18:31:45 +01:00
Dan Dascalescu
17cf031fa1
app/vmselect: simplify wording for too many samples error (#5827) 2024-02-20 16:26:38 +01:00
Roman Khavronenko
bb1279bfc4
vmctl : Provide TLS config options for Open TSDB datasource #5797 (#5832)
Originally implemented here https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5797

---------

Signed-off-by: hagen1778 <roman@victoriametrics.com>
Co-authored-by: khushijain21 <khushij393@gmail.com>
2024-02-20 16:22:58 +01:00
Daria Karavaieva
4034d081f4
Vmanomaly Quickstart Fix absolute links (#5831)
* links fix

* typo fix
2024-02-20 16:19:18 +01:00
Daria Karavaieva
b2baf7d472
Vmanomaly QuickStart (#5800)
* first edit

* typo 1

* typo 2

* fixes 3

* fixes 4

* fixes 5

* fixes, cross links

* v1.10 config

* models why, self-monitoring fix

* config next steps

* fixes

* minor fix
2024-02-20 15:20:57 +01:00