Previously the time spent on inverted index search could exceed the configured `-search.maxQueryDuration`.
This commit stops searching in inverted index on query timeout.
Heavy queries could result in the lack of CPU resources for processing the current data ingestion stream.
Prevent this by delaying queries' execution until free resources are available for data ingestion.
Expose `vm_search_delays_total` metric, which may be used in for alerting when there is no enough CPU resources
for data ingestion and/or for executing heavy queries.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/291
Previously it was possible that the connection is served after the server is closed if the following
steps are performed:
1) Server accepts new connection.
2) Server.MustClose() is called and successfully finished.
3) Server starts processing the connection accepted at step 1. There could be various crashes
like in https://github.com/VictoriaMetrics/VictoriaMetrics/issues/534 since the storage may be already closed.
Now the server closes the connection at step 3 without processing it.
Previously the duration for graceful shutdown for http server could take more than a minute
because of imporperly set timeouts in setNetworkTimeout.
Now typical duration for graceful shutdown should be reduced to less than 5 seconds.
This should protect from possible data loss when `vmstorage` is stopped while the packet is sent from `vminsert`.
This commit switches to new protocol between vminsert and vmstorage, which is incompatible
with the previous protocol. So it is required that both vminsert and vmstorage nodes are updated.
This eliminates the need for storing block data into temporary files on a single-node VictoriaMetrics
during heavy queries, which touch big number of time series over long time ranges.
This improves single-node VM performance on heavy queries by up to 2x.
Such filters must match all the time series with `label="foo"` plus all the time series without `label`
Previously only time series with `label="foo"` were matched.
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.
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.
Continue trying to remove NFS directory on temporary errors for up to a minute.
The previous async removal process breaks in the following case during VictoriaMetrics start
- VictoriaMetrics opens index, finds incomplete merge transactions and starts replaying them.
- The transaction instructs removing old directories for parts, which were already merged into bigger part.
- VictoriaMetrics removes these directories, but their removal is delayed due to NFS errors.
- VictoriaMetrics scans partition directory after all the incomplete merge transactions are finished
and finds directories, which should be removed, but weren't still removed due to NFS errors.
- VictoriaMetrics panics when it finds unexpected empty directory.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/162
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)`.
