* Optimize the performance of data merge: decimal.CalibrateScale() from 49633 ns/op to 9146 ns/op
* Optimize the performance of data merge: decimal.CalibrateScale()
Sending unfinished aggregate states tend to produce unexpected anomalies with lower values than expected.
The old behavior can be restored by specifying `flush_on_shutdown: true` setting in streaming aggregation config
Signed-off-by: hagen1778 <roman@victoriametrics.com>
- Maintain a separate worker pool per each part type (in-memory, file, big and small).
Previously a shared pool was used for merging all the part types.
A single merge worker could merge parts with mixed types at once. For example,
it could merge simultaneously an in-memory part plus a big file part.
Such a merge could take hours for big file part. During the duration of this merge
the in-memory part was pinned in memory and couldn't be persisted to disk
under the configured -inmemoryDataFlushInterval .
Another common issue, which could happen when parts with mixed types are merged,
is uncontrolled growth of in-memory parts or small parts when all the merge workers
were busy with merging big files. Such growth could lead to significant performance
degradataion for queries, since every query needs to check ever growing list of parts.
This could also slow down the registration of new time series, since VictoriaMetrics
searches for the internal series_id in the indexdb for every new time series.
The third issue is graceful shutdown duration, which could be very long when a background
merge is running on in-memory parts plus big file parts. This merge couldn't be interrupted,
since it merges in-memory parts.
A separate pool of merge workers per every part type elegantly resolves both issues:
- In-memory parts are merged to file-based parts in a timely manner, since the maximum
size of in-memory parts is limited.
- Long-running merges for big parts do not block merges for in-memory parts and small parts.
- Graceful shutdown duration is now limited by the time needed for flushing in-memory parts to files.
Merging for file parts is instantly canceled on graceful shutdown now.
- Deprecate -smallMergeConcurrency command-line flag, since the new background merge algorithm
should automatically self-tune according to the number of available CPU cores.
- Deprecate -finalMergeDelay command-line flag, since it wasn't working correctly.
It is better to run forced merge when needed - https://docs.victoriametrics.com/#forced-merge
- Tune the number of shards for pending rows and items before the data goes to in-memory parts
and becomes visible for search. This improves the maximum data ingestion rate and the maximum rate
for registration of new time series. This should reduce the duration of data ingestion slowdown
in VictoriaMetrics cluster on e.g. re-routing events, when some of vmstorage nodes become temporarily
unavailable.
- Prevent from possible "sync: WaitGroup misuse" panic on graceful shutdown.
This is a follow-up for fa566c68a6 .
Thanks @misutoth to for the inspiration at https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5212
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5190
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3790
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3551
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3337
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3425
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3647
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3641
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/291
The maxFileParts usage has been accidentally removed in fa566c68a6
While at it, add Count suffix to *AssistedMerges counter names in order to make them less misleading.
Previously their names were falsely suggesting that these are gauges, which show the number of concurrently
executed assisted merges.
It has been appeared that the registration of new time series slows down linearly
with the number of indexdb parts, since VictoriaMetrics needs to check every indexdb part
when it searches for TSID by newly ingested metric name.
The number of in-memory parts grows when new time series are registered
at high rate. The number of in-memory parts grows faster on systems with big number
of CPU cores, because the mergeset maintains per-CPU buffers with newly added entries
for the indexdb, and every such entry is transformed eventually into a separate in-memory part.
The solution has been suggested in https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5212
by @misutoth - to limit the number of in-memory parts with buffered channel.
This solution is implemented in this commit. Additionally, this commit merges per-CPU parts
into a single part before adding it to the list of in-memory parts. This reduces CPU load
when searching for TSID by newly ingested metric name.
The https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5212 recommends setting the limit on the number
of in-memory parts to 100, but my internal testing shows that much lower limit 15 works with the same efficiency
on a system with 16 CPU cores while reducing memory usage for `indexdb/dataBlocks` cache by up to 50%.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5190
This allows reducing the indexdb/tagFiltersToMetricIDs cache size by 8 on average.
The cache size can be checked via vm_cache_size_bytes{type="indexdb/tagFiltersToMetricIDs"} metric exposed at /metrics page.
Measuring read / write duration from / to in-memory buffers has little sense,
since it will be always fast. It is better to measure read / write duration from / to
real files at vm_filestream_write_duration_seconds_total and vm_filestream_read_duration_seconds_total metrics.
This also reduces overhead on time.Now() and Histogram.UpdateDuration() calls
per each filestream.Reader.Read() and filestream.Writer.Write() call when the data is read / written from / to in-memory buffers.
This is a follow-up for 2f63dec2e3
* lib/promscrape: respect `0` value for `series_limit` param
Respect `0` value for `series_limit` param in `scrape_config`
even if global limit was set via `-promscrape.seriesLimitPerTarget`.
Previously, `0` value will be ignored in favor of `-promscrape.seriesLimitPerTarget`.
This behavior aligns with possibility to override `series_limit` value via
relabeling with `__series_limit__` label.
Signed-off-by: hagen1778 <roman@victoriametrics.com>
* Update docs/CHANGELOG.md
---------
Signed-off-by: hagen1778 <roman@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
This should smooth CPU and RAM usage spikes related to these periodic tasks,
by reducing the probability that multiple concurrent periodic tasks are performed at the same time.
The dateMetricIDCache puts recently registered (date, metricID) entries into mutable cache protected by the mutex.
The dateMetricIDCache.Has() checks for the entry in the mutable cache when it isn't found in the immutable cache.
Access to the mutable cache is protected by the mutex. This means this access is slow on systems with many CPU cores.
The mutabe cache was merged into immutable cache every 10 seconds in order to avoid slow access to mutable cache.
This means that ingestion of new time series to VictoriaMetrics could result in significant slowdown for up to 10 seconds
because of bottleneck at the mutex.
Fix this by merging the mutable cache into immutable cache after len(cacheItems) / 2
cache hits under the mutex, e.g. when the entry is found in the mutable cache.
This should automatically adjust intervals between merges depending on the addition rate
for new time series (aka churn rate):
- The interval will be much smaller than 10 seconds under high churn rate.
This should reduce the mutex contention for mutable cache.
- The interval will be bigger than 10 seconds under low churn rate.
This should reduce the uneeded work on merging of mutable cache into immutable cache.
* lib/promscrape/discovery/kubernetes: fix watcher start order for roles endpoints and endpointslice
Previously the groupWatcher could be mistakenly stopped when requests for pod or services resources take too long.
* remove mislead comment
* docs/sd_configs.md: mention -promscrape.kubernetes.attachNodeMetadataAll flag in the description for attach_metadata section
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4640
* wip
* lib/promscrape/kubernetes: prevent from stopping groupWatcher when there are in-flight apiWatcher.mustStart() calls
groupWatcher is stopped if it has zero registered apiWatchers during 14 seconds.
But such a groupWatcher can be still in use if apiWatcher for `role: endpoints` or `role: endpointslice`
is being registered and the discovery of the associated `pod` and/or `service` objects takes longer
than 14 seconds - see the beginning of groupWatcher.startWatchersForRole() function for details.
Track the number of in-flight calls to apiWatcher.mustStart() and prevent from stopping the associated groupWatcher
if the number of in-flight calls is non-zero.
P.S. postponing the discovery of `pod` and/or `service` objects associated with `endpoints` or `endpointslice` roles
isn't the best solution, since it slows down initial discovery of `endpoints` and `endpointslice` targets.
* typo fix
---------
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
Examples:
1) -metricsAuthKey=file:///abs/path/to/file - reads flag value from the given absolute filepath
2) -metricsAuthKey=file://./relative/path/to/file - reads flag value from the given relative filepath
3) -metricsAuthKey=http://some-host/some/path?query_arg=abc - reads flag value from the given url
The flag value is automatically updated when the file contents changes.
- docs/sd_configs.md: moved hetzner_sd_configs docs to the correct place according to alphabetical order of SD names,
document missing __meta_hetzner_role label.
- lib/promscrape/config.go: added missing MustStop() call for Hetzner SD,
and moved the code to the correct place according to alphabetical order of SD names.
- lib/promscrape/discovery/hetzner: properly handle pagination for hloud API responses,
populate missing __meta_hetzner_role label like Prometheus does.
- Properly populate __meta_hetzner_public_ipv6_network label like Prometheus does.
- Remove unused SDConfig.Token.
- Remove "omitempty" annotation from SDConfig.Role field, since this field is mandatory.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5550
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3154
- Clarify the bugfix description at docs/CHANGELOG.md
- Simplify the code by accessing prefetchedMetricIDs struct under the lock
instead of using lockless access to immutable struct.
This shouldn't worsen code scalability too much on busy systems with many CPU cores,
since the code executed under the lock is quite small and fast.
This allows removing cloning of prefetchedMetricIDs struct every time
new metric names are pre-fetched. This should reduce load on Go GC,
since the cloning of uin64set.Set struct allocates many new objects.
Before, this cache was limited only by size.
Cache invalidation by time happens with jitter to prevent thundering herd problem.
Signed-off-by: hagen1778 <roman@victoriametrics.com>
