Hint allows to choose type of cache to be used for index search:
- in-memory parts are storing recently ingested samples and should use
main cache. This improves ingestion speed and cache hit ration for
queries accessing recently ingested samples.
- merges of file parts is performed in background, using a separate
cache allows avoiding pollution of the main cache with irrelevant
entries.
Related issue:
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7182
---------
Signed-off-by: f41gh7 <nik@victoriametrics.com>
(cherry picked from commit e9f86af7f5)
Related issue:
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7182
- add a separate index cache for searches which might read through large
amounts of random entries. Primary use-case for this is retention and
downsampling filters, when applying filters background merge needs to
fetch large amount of random entries which pollutes an index cache.
Using different caches allows to reduce effect on memory usage and cache
efficiency of the main cache while still having high cache hit rate. A
separate cache size is 5% of allowed memory.
- reduce size of indexdb/dataBlocks cache in order to free memory for
new sparse cache. Reduced size by 5% and moved this to a separate cache.
- add a separate metricName search which does not cache metric names -
this is needed in order to allow disabling metric name caching when
applying downsampling/retention filters. Applying filters during
background merge accesses random entries, this fills up cache and does
not provide an actual improvement due to random access nature.
Merge performance and memory usage stats before and after the change:
- before

- after

---------
Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
(cherry picked from commit 837d0d136d)
Callers of InitFromFilePart log the error and exit.
It is better to log the error with the path to the part and the call stack
directly inside the MustInitFromFilePart() function.
This simplifies the code at callers' side while leaving the same level of debuggability.
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.
This should improve lookup performance if the same `label=value` pair exists
in big number of time series.
This should also reduce memory usage for mergeset data cache, since `tag->metricIDs` rows
occupy less space than the original `tag->metricID` rows.