The filter arg has been removed in the commit c7ee2fabb8
because it was preventing from caching the number of matching time series per each tf.
Now the cache contains duration for tf execution, so the filter shouldn't break such caching.
The `filter` arg breaks the logic for sorting tag filters by the matching metrics,
which may result in non-optimal performance during time series search.
Production workloads show that indexdb blocks must be cached unconditionally for reducing CPU usage.
This shouldn't increase memory usage too much, since unused blocks are removed from the cache every two minutes.
Remove the code that uses metricIDs caches for the current and the previous hour during metricIDs search,
since this code became unused after implementing per-day inverted index almost a year ago.
While at it, fix a bug, which could prevent from finding time series with names containing dots (aka Graphite-like names
such as `foo.bar.baz`).
Previously the maximum cache lifetime has been limited by 10 seconds. Now it is extended up to a day.
This should reduce CPU usage in the following cases:
* when querying recently added data with small churn rate for time series
* when querying historical data
Previously the time spent on inverted index search could exceed the configured `-search.maxQueryDuration`.
This commit stops searching in inverted index on query timeout.
This is a follow-up commit after 12b16077c4 ,
which didn't reset the `tsidCache` in all the required places.
This could result in indefinite errors like:
missing metricName by metricID ...; this could be the case after unclean shutdown; deleting the metricID, so it could be re-created next time
Fix this by resetting the cache inside deleteMetricIDs function.
Add index for reverse Graphite-like metric names with dots. Use this index during search for filters
like `__name__=~"foo\\.[^.]*\\.bar\\.baz"` which end with non-empty suffix with dots, i.e. `.bar.baz` in this case.
This change may "hide" historical time series during queries. The workaround is to add `[.]*` to the end of regexp label filter,
i.e. "foo\\.[^.]*\\.bar\\.baz" should be substituted with "foo\\.[^.]*\\.bar\\.baz[.]*".
Newly added index entries can be missing after unclean shutdown, since they didn't flush to persistent storage yet.
Log about this and delete the corresponding metricID, so it could be re-created next time.
This should reduce the frequency of the following errors:
cannot find tag filter matching less than N time series; either increase -search.maxUniqueTimeseries or use more specific tag filters
more than N time series found on the time range [...]; either increase -search.maxUniqueTimeseries or shrink the time range
This case is possible when the corresponding metricID->metricName entry didn't propagate to inverted index yet.
This should fix the following error:
error when searching tsids for tfss [...]: cannot find metricName by metricID 1582417212213420669: EOF
- Sort tag filters in the ascending number of matching time series
in order to apply the most specific filters first.
- Fall back to metricName search for filters matching big number of time series
(usually this are negative filters or regexp filters).
The metricID->metricName entry can be missing in the indexdb after unclean shutdown
when only a part of entries for new time series is written into indexdb.
Recover from such a situation by removing the broken metricID. New metricID
will be automatically created for time series with the given metricName
when new data point will arive to it.
The current day could miss entries for already stopped time series before
enabling per-day index.
This fixes the issue when queries return empty results during the first hour after
upgrading to v1.29.*
Production workload shows that the index requires ~4Kb of RAM per active time series.
This is too much for high number of active time series, so let's delete this index.
Now the queries should fall back to the index for the current day instead of the index
for the recent hour. The query performance for the current day index should be good enough
given the 100M rows/sec scan speed per CPU core.
Issues fixed:
- Slow startup times. Now the index is loaded from cache during start.
- High memory usage related to superflouos index copies every 10 seconds.
Production load with >10M active time series showed it could
slow down VictoriaMetrics startup times and could eat
all the memory leading to OOM.
Remove inmemory inverted index for recent hours until thorough
testing on production data shows it works OK.
The origin of the error has been detected and documented in the code,
so it is enough to export a counter for such errors at `vm_index_blocks_with_metric_ids_incorrect_order_total`,
so it could be monitored and alerted on high error rates.
Export also the counter for processed index blocks with metricIDs - `vm_index_blocks_with_metric_ids_processed_total`,
so its' rate could be compared to `rate(vm_index_blocks_with_metric_ids_incorrect_order_total)`.
Slow loops could require seeks and expensive regexp matching, while fast loops just scans
all the metricIDs for the given `tag=value` prefix. So these operations must have separate
max loops multiplier.
The fastest tag filters are non-negative non-regexp, since they are the most specific.
The slowest tag filters are negative regexp, since they require scanning
all the entries for the given label.
This should improve inverted index search performance for filters matching big number of time series,
since `lib/uint64set.Set` is faster than `map[uint64]struct{}` for both `Add` and `Has` calls.
See the corresponding benchmarks in `lib/uint64set`.
