Commit Graph

7971 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
482560a1f3
lib/streamaggr: do not flush dedup shards in parallel
This significantly increases CPU usage on systems with many CPU cores, while doesn't reduce flush latency too much
2024-03-04 17:01:42 +02:00
Aliaksandr Valialkin
d7252fce79
lib/streamaggr: reduce memory allocations when registering new series in deduplication and aggregation structs 2024-03-04 17:01:41 +02:00
Aliaksandr Valialkin
402dc14ec0
lib/streamaggr: make aggregate.runFlusher() more roubst and clear 2024-03-04 17:01:41 +02:00
Aliaksandr Valialkin
2ffef39bb3
lib/streamaggr: properly drop samples on the first incomplete interval
Previously samples were dropped on the first incomplete interval and the next complete interval.
Also make sure that the de-duplication is performed just before flushing the aggregate state.
This should help the case then dedup_interval = interval.
2024-03-04 17:01:40 +02:00
hagen1778
51745ec5ff
dashboards: update links in various panels
* use docs.victoriametrics.com instead of github docs
* add links to common terms used in VictoriaMetrics

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-03-04 17:00:54 +02:00
Aliaksandr Valialkin
c2dae136b3
lib/streamaggr: explicitly call resetSeries after flushSeries
This makes the code less fragile
2024-03-04 06:23:36 +02:00
Aliaksandr Valialkin
48a425898a
lib/streamaggr: enable time alignment for aggregate flushed to multiples of interval
For example, if `interval: 1m`, then data flush occurs at the end of every minute,
while `interval: 1h` leads to data flush at the end of every hour.

Add `no_align_flush_to_interval` option, which can be used for disabling the alignment.
2024-03-04 06:23:35 +02:00
Aliaksandr Valialkin
3ba9b2225e
docs/stream-aggregation.md: add troubleshooting section with solutions for common problems in streaming aggregation 2024-03-04 03:04:59 +02:00
Aliaksandr Valialkin
d80deaeaf4
lib/streamaggr: ignore the first sample in new time series during staleness_interval seconds after the stream aggregation start for total and increase outputs 2024-03-04 03:04:58 +02:00
Aliaksandr Valialkin
5e9cbfd4db
lib/streamaggr: flush dedup state and aggregation state in parallel on all the available CPU cores
This should reduce the time needed for aggregation state flush on systems with many CPU cores
2024-03-04 01:22:41 +02:00
Aliaksandr Valialkin
1e741ed6db
lib/streamaggr: add a benchmark for flushing dedup state 2024-03-04 01:22:40 +02:00
Aliaksandr Valialkin
5205972b83
lib/streamaggr: add a benchmark for measuring the performance of aggregator.flush 2024-03-04 01:22:40 +02:00
Aliaksandr Valialkin
8daf7a3f43
lib/streamaggr: add a benchmark for de-duplicating of 1M samples 2024-03-04 01:22:39 +02:00
Aliaksandr Valialkin
d4a425af87
lib/prompbmarshal: use clear() instead of a loop for clearing tss inside ResetTimeSeries() 2024-03-03 23:40:47 +02:00
Aliaksandr Valialkin
b958135677
lib/promutils: optimize LabelsCompressor.Decompress by using a specialized labelsMap struct instead of sync.Map
The labelsMap struct employs the fact that label indexes are condensed around 0,
so it stores the referred labels in a slice instead of map and uses slice index as label key.
This allows increasing the LabelsCompressor.Decompress performance by up to 3x.
This also reduces the latency of data flush in stream aggregation.
2024-03-03 23:25:27 +02:00
Aliaksandr Valialkin
492c6c3ff5
docs/CHANGELOG.md: typo fix 2024-03-02 04:52:41 +02:00
Aliaksandr Valialkin
d0e6541f35
docs/stream-aggregation.md: typo fixes 2024-03-02 04:35:37 +02:00
Aliaksandr Valialkin
b912a45220
docs/stream-aggregation.md: remove superflouous output_relabel_configs from the config example for histogram aggregation 2024-03-02 03:36:08 +02:00
Aliaksandr Valialkin
0d5d46f9db
lib/streamaggr: huge pile of changes
- Reduce memory usage by up to 5x when de-duplicating samples across big number of time series.
- Reduce memory usage by up to 5x when aggregating across big number of output time series.
- Add lib/promutils.LabelsCompressor, which is going to be used by other VictoriaMetrics components
  for reducing memory usage for marshaled []prompbmarshal.Label.
- Add `dedup_interval` option at aggregation config, which allows setting individual
  deduplication intervals per each aggregation.
- Add `keep_metric_names` option at aggregation config, which allows keeping the original
  metric names in the output samples.
- Add `unique_samples` output, which counts the number of unique sample values.
- Add `increase_prometheus` and `total_prometheus` outputs, which ignore the first sample
  per each newly encountered time series.
- Use 64-bit hashes instead of marshaled labels as map keys when calculating `count_series` output.
  This makes obsolete https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5579
- Expose various metrics, which may help debugging stream aggregation:
  - vm_streamaggr_dedup_state_size_bytes - the size of data structures responsible for deduplication
  - vm_streamaggr_dedup_state_items_count - the number of items in the deduplication data structures
  - vm_streamaggr_labels_compressor_size_bytes - the size of labels compressor data structures
  - vm_streamaggr_labels_compressor_items_count - the number of entries in the labels compressor
  - vm_streamaggr_flush_duration_seconds - a histogram, which shows the duration of stream aggregation flushes
  - vm_streamaggr_dedup_flush_duration_seconds - a histogram, which shows the duration of deduplication flushes
  - vm_streamaggr_flush_timeouts_total - counter for timed out stream aggregation flushes,
    which took longer than the configured interval
  - vm_streamaggr_dedup_flush_timeouts_total - counter for timed out deduplication flushes,
    which took longer than the configured dedup_interval
- Actualize docs/stream-aggregation.md

The memory usage reduction increases CPU usage during stream aggregation by up to 30%.

This commit is based on https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5850
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5898
2024-03-02 03:15:43 +02:00
Aliaksandr Valialkin
31f0dc4b97
lib/streamaggr: allow one second aggregation interval 2024-03-01 21:35:43 +02:00
Aliaksandr Valialkin
7533070a52
lib/promrelabel: use clear() function inside CleanLabels() 2024-03-01 21:34:47 +02:00
hagen1778
8ce65e93d0
docs: mention docs link for VictoriaLogs docker env
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2024-03-01 21:34:15 +02:00
Aliaksandr Valialkin
7559b6eb97
docs: update -help output after recent changes in VictoriaMetrics components 2024-03-01 05:31:13 +02:00
Aliaksandr Valialkin
0dbcc07d04
docs/CHANGELOG.md: typo fix 2024-03-01 04:41:39 +02:00
Aliaksandr Valialkin
5f0dd8743c
docs: bump the latest VictoriaMetrics release from v1.98.0 to v1.99.0
See https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.99.0
2024-03-01 04:24:11 +02:00
Aliaksandr Valialkin
be1446f720
docs/LTS-releases.md: update latest LTS release to v1.97.3 and v1.93.13
See https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.97.3
and https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.93.13
2024-03-01 04:21:25 +02:00
Aliaksandr Valialkin
2540b8fdf8
deployment: update VictoriaLogs docker image from v0.4.2-victorialogs to v0.5.0-victorialogs
See https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v0.5.0-victorialogs
2024-03-01 04:18:59 +02:00
Aliaksandr Valialkin
4543f86827
deployment: update VictoriaMetrics docker image from v1.98.0 to v1.99.0 2024-03-01 04:15:17 +02:00
Aliaksandr Valialkin
d66680fc47
docs/CHANGELOG.md: cut v1.99.0 release 2024-03-01 03:33:44 +02:00
Aliaksandr Valialkin
dc91c07384
docs/CHANGELOG.md: document v1.97.3 LTS release 2024-03-01 03:31:19 +02:00
Aliaksandr Valialkin
e4a1d6774e
docs: consistently use https://docs.victoriametrics.com/lts-releases/ link for LTS releases 2024-03-01 02:52:41 +02:00
Aliaksandr Valialkin
0fac8d6e87
docs/CHANGELOG.md: document v1.93.13 LTS release
See https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.93.13
2024-03-01 02:41:05 +02:00
Aliaksandr Valialkin
bde2de3298
docs/VictoriaLogs/CHANGELOG.md: typo fix: bufix -> bugfix 2024-03-01 02:41:04 +02:00
Aliaksandr Valialkin
052f2177a4
lib/fs: fix GOOS=windows build after f8baf29b6e 2024-03-01 01:46:44 +02:00
Aliaksandr Valialkin
9a470239cf
docs/VictoriaLogs/CHANGELOG.md: cut v0.5.0-victorialogs 2024-03-01 01:43:35 +02:00
Aliaksandr Valialkin
334b90598e
app/vlselect/vmui: run make vmui-logs-update after c51031dd70
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5674
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5799
2024-03-01 01:33:37 +02:00
Yury Molodov
e00d313333
vmui: add field for log entries limit (#5799)
* vmui: add field for log entries limit (#5674)

* vmui: refactor useFetchLogs

* vmui: fix log query encoding

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2024-03-01 01:33:35 +02:00
Aliaksandr Valialkin
7675bc8f27
vendor: run make vendor-update 2024-03-01 00:55:54 +02:00
Aliaksandr Valialkin
d84cdf98da
app/{vmselect,vlselect}/vmui: run make vmui-update vmui-logs-update after e130f29659
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5862
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5152
2024-03-01 00:51:49 +02:00
Yury Molodov
c71c2b37c5
vmui: add gap display option for charts #5152 (#5862) 2024-03-01 00:51:48 +02:00
Aliaksandr Valialkin
816202bca7
lib/protoparser/opentelemetry/firehose: verify that the full response is parsed properly in ProcessRequestBody
This is a follow-up for bf9cb84575
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5899
2024-03-01 00:39:47 +02:00
Andrii Chubatiuk
e575fb1aeb
opentelemetry: fix firehose message parsing (#5899)
Co-authored-by: Andrii Chubatiuk <wachy@Andriis-MBP-2.lan>
2024-03-01 00:24:14 +02:00
Aliaksandr Valialkin
728fb59e0d
docs: update docs after 0b7a23a91d 2024-03-01 00:18:46 +02:00
Aliaksandr Valialkin
46d92fae3d
app/vmselect/prometheus: ignore match[] additionally to extra_filters[] and extra_label if -search.ignoreExtraFiltersAtLabelsAPI command-line flag is set
The match[] at /api/v1/labels and /api/v1/label/.../values also may lead to slow requests and
high resource usage if it matches big number of time series. So it must be igrnored if -search.ignoreExtraFiltersAtLabelsAPI
command-line flag is set.

This is a follow-up for fab02faa3f
2024-03-01 00:18:08 +02:00
Aliaksandr Valialkin
6aea1e5093
app/{vmagent,vminsert}: follow-up for 434a5803e7
Document the /opentelemetry/v1/metrics endpoint instead of /opentelemetry/api/v1/push,
since the /v1/metrics suffix is hardcoded in OpenTelemetry protocol specification.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5871
2024-02-29 18:05:12 +02:00
Nikolay
abb773120d
app/{vmagent,vminsert}: adds /v1/metrics suffix for opentelemetry route path (#5871)
* app/{vmagent,vminsert}: adds /v1/metrics suffix for opentelemetry route path
it must fix compatibility with opentemetry-collector [spec](https://opentelemetry.io/docs/specs/otlp/\#otlphttp-request)
this suffix is hard-coded and cannot be changed with collector configuration

* Apply suggestions from code review

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2024-02-29 17:59:57 +02:00
Github Actions
5e20be845f
Automatic update operator docs from VictoriaMetrics/operator@7e8f811 (#5902) 2024-02-29 17:53:11 +02:00
Aliaksandr Valialkin
fed04e7f25
app/vmselect/promql: use unsafe.Slice instead of deprecated reflect.SliceHeader 2024-02-29 17:51:16 +02:00
Aliaksandr Valialkin
319d21eddf
app/vmselect/netstorage: usae unsafe.SliceData instead of deprecated reflect.SliceHeader 2024-02-29 17:38:14 +02:00
Aliaksandr Valialkin
01d8bee14c
lib/mergeset: use unsafe.Slice and unsafe.String instead of deprecated reflect.SliceHeader with unsafe conversion from slice header to string header 2024-02-29 17:29:40 +02:00