VictoriaMetrics/app/vmagent/remotewrite/streamaggr.go

251 lines
13 KiB
Go
Raw Normal View History

package remotewrite
import (
"flag"
"fmt"
"strings"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/streamaggr"
"github.com/VictoriaMetrics/metrics"
)
var (
// Global config
streamAggrGlobalConfig = flag.String("streamAggr.config", "", "Optional path to file with stream aggregation config. "+
"See https://docs.victoriametrics.com/stream-aggregation/ . "+
"See also -streamAggr.keepInput, -streamAggr.dropInput and -streamAggr.dedupInterval")
streamAggrGlobalKeepInput = flag.Bool("streamAggr.keepInput", false, "Whether to keep all the input samples after the aggregation "+
"with -streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to remote storages write. See also -streamAggr.dropInput and https://docs.victoriametrics.com/stream-aggregation/")
streamAggrGlobalDropInput = flag.Bool("streamAggr.dropInput", false, "Whether to drop all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to remote storages write. See also -streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation/")
streamAggrGlobalDedupInterval = flagutil.NewDuration("streamAggr.dedupInterval", "0s", "Input samples are de-duplicated with this interval on "+
"aggregator before optional aggregation with -streamAggr.config . "+
"See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation/#deduplication")
streamAggrGlobalIgnoreOldSamples = flag.Bool("streamAggr.ignoreOldSamples", false, "Whether to ignore input samples with old timestamps outside the "+
"current aggregation interval for aggregator. "+
"See https://docs.victoriametrics.com/stream-aggregation/#ignoring-old-samples")
streamAggrGlobalIgnoreFirstIntervals = flag.Int("streamAggr.ignoreFirstIntervals", 0, "Number of aggregation intervals to skip after the start for "+
"aggregator. Increase this value if you observe incorrect aggregation results after vmagent restarts. It could be caused by receiving unordered delayed data from "+
"clients pushing data into the vmagent. See https://docs.victoriametrics.com/stream-aggregation/#ignore-aggregation-intervals-on-start")
streamAggrGlobalDropInputLabels = flagutil.NewArrayString("streamAggr.dropInputLabels", "An optional list of labels to drop from samples for aggregator "+
"before stream de-duplication and aggregation . See https://docs.victoriametrics.com/stream-aggregation/#dropping-unneeded-labels")
// Per URL config
streamAggrConfig = flagutil.NewArrayString("remoteWrite.streamAggr.config", "Optional path to file with stream aggregation config for the corresponding -remoteWrite.url. "+
"See https://docs.victoriametrics.com/stream-aggregation/ . "+
"See also -remoteWrite.streamAggr.keepInput, -remoteWrite.streamAggr.dropInput and -remoteWrite.streamAggr.dedupInterval")
streamAggrDropInput = flagutil.NewArrayBool("remoteWrite.streamAggr.dropInput", "Whether to drop all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.keepInput and https://docs.victoriametrics.com/stream-aggregation/")
streamAggrKeepInput = flagutil.NewArrayBool("remoteWrite.streamAggr.keepInput", "Whether to keep all the input samples after the aggregation "+
"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. By default, only aggregates samples are dropped, while the remaining samples "+
"are written to the corresponding -remoteWrite.url . See also -remoteWrite.streamAggr.dropInput and https://docs.victoriametrics.com/stream-aggregation/")
streamAggrDedupInterval = flagutil.NewArrayDuration("remoteWrite.streamAggr.dedupInterval", 0, "Input samples are de-duplicated with this interval before optional aggregation "+
"with -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. See also -dedup.minScrapeInterval and https://docs.victoriametrics.com/stream-aggregation/#deduplication")
streamAggrIgnoreOldSamples = flagutil.NewArrayBool("remoteWrite.streamAggr.ignoreOldSamples", "Whether to ignore input samples with old timestamps outside the current "+
"aggregation interval for the corresponding -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. "+
"See https://docs.victoriametrics.com/stream-aggregation/#ignoring-old-samples")
streamAggrIgnoreFirstIntervals = flagutil.NewArrayInt("remoteWrite.streamAggr.ignoreFirstIntervals", 0, "Number of aggregation intervals to skip after the start "+
"for the corresponding -remoteWrite.streamAggr.config at the corresponding -remoteWrite.url. Increase this value if "+
"you observe incorrect aggregation results after vmagent restarts. It could be caused by receiving bufferred delayed data from clients pushing data into the vmagent. "+
"See https://docs.victoriametrics.com/stream-aggregation/#ignore-aggregation-intervals-on-start")
streamAggrDropInputLabels = flagutil.NewArrayString("remoteWrite.streamAggr.dropInputLabels", "An optional list of labels to drop from samples "+
"before stream de-duplication and aggregation with -remoteWrite.streamAggr.config and -remoteWrite.streamAggr.dedupInterval at the corresponding -remoteWrite.url. "+
"Multiple labels per remoteWrite.url must be delimited by '^^': -remoteWrite.streamAggr.dropInputLabels='replica^^az,replica'. "+
"See https://docs.victoriametrics.com/stream-aggregation/#dropping-unneeded-labels")
)
// CheckStreamAggrConfigs checks -remoteWrite.streamAggr.config and -streamAggr.config.
func CheckStreamAggrConfigs() error {
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
// Check global config
sas, err := newStreamAggrConfigGlobal()
if err != nil {
return err
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sas.MustStop()
if len(*streamAggrConfig) > len(*remoteWriteURLs) {
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
return fmt.Errorf("too many -remoteWrite.streamAggr.config args: %d; it mustn't exceed the number of -remoteWrite.url args: %d", len(*streamAggrConfig), len(*remoteWriteURLs))
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
pushNoop := func(_ []prompbmarshal.TimeSeries) {}
for idx := range *streamAggrConfig {
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sas, err := newStreamAggrConfigPerURL(idx, pushNoop)
if err != nil {
return err
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sas.MustStop()
}
return nil
}
func reloadStreamAggrConfigs() {
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
reloadStreamAggrConfigGlobal()
for _, rwctx := range rwctxsGlobal {
rwctx.reloadStreamAggrConfig()
}
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
func reloadStreamAggrConfigGlobal() {
path := *streamAggrGlobalConfig
if path == "" {
return
}
logger.Infof("reloading stream aggregation configs pointed by -streamAggr.config=%q", path)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_total{path=%q}`, path)).Inc()
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sasNew, err := newStreamAggrConfigGlobal()
if err != nil {
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_errors_total{path=%q}`, path)).Inc()
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, path)).Set(0)
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
logger.Errorf("cannot reload -streamAggr.config=%q; continue using the previously loaded config; error: %s", path, err)
return
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sas := sasGlobal.Load()
if !sasNew.Equal(sas) {
sasOld := sasGlobal.Swap(sasNew)
sasOld.MustStop()
logger.Infof("successfully reloaded -streamAggr.config=%q", path)
} else {
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sasNew.MustStop()
logger.Infof("-streamAggr.config=%q wasn't changed since the last reload", path)
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, path)).Set(1)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, path)).Set(fasttime.UnixTimestamp())
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
func initStreamAggrConfigGlobal() {
sas, err := newStreamAggrConfigGlobal()
if err != nil {
logger.Fatalf("cannot initialize gloabl stream aggregators: %s", err)
}
if sas != nil {
filePath := sas.FilePath()
sasGlobal.Store(sas)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, filePath)).Set(1)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, filePath)).Set(fasttime.UnixTimestamp())
stream aggregation: perform deduplication for all received data when … (#6711) …specifying `-streamAggr.dedupInterval` or `-remoteWrite.streamAggr.dedupInterval` command-line flag [The documentation](https://docs.victoriametrics.com/stream-aggregation/) contains conflicting descriptions regarding deduplication for non-matched series when `-remoteWrite.streamAggr.config` and / or `-streamAggr.config` are set: 1. Statement below says **all the received data** is deduplicated: >[vmagent](https://docs.victoriametrics.com/vmagent/) supports relabeling, deduplication and stream aggregation for all the received data, scraped or pushed. Then, the collected data will be forwarded to specified -remoteWrite.url destinations. The data processing order is the following: >1. all the received data is relabeled according to the specified [-remoteWrite.relabelConfig](https://docs.victoriametrics.com/vmagent/#relabeling) (if it is set) >2. all the received data is deduplicated according to specified [-streamAggr.dedupInterval](https://docs.victoriametrics.com/stream-aggregation/#deduplication) (if it is set to duration bigger than 0) 2. Another statement says the deduplication is performed individually for the **matching samples** >The de-deduplication is performed after applying [relabeling](https://docs.victoriametrics.com/vmagent/#relabeling) and before performing the aggregation. If the -remoteWrite.streamAggr.config and / or -streamAggr.config is set, then the de-duplication is performed individually per each [stream aggregation config](https://docs.victoriametrics.com/stream-aggregation/#stream-aggregation-config) for the matching samples after applying [input_relabel_configs](https://docs.victoriametrics.com/stream-aggregation/#relabeling). Considering the following deduplication use cases: 1. To apply deduplication(globally or for specific remoteWrite destination) for all the received data, scraped or pushed --- using `-streamAggr.dedupInterval` or `-remoteWrite.streamAggr.dedupInterval`. 2. To deduplicate and aggregate metrics that match the rule `match` filters --- using `-remoteWrite.streamAggr.config` and specifiying `dedup_interval` option in [stream aggregation config](https://docs.victoriametrics.com/stream-aggregation/#stream-aggregation-config). 3. To deduplicate all the received data while having `streamAggr.config` for some metrics --- no way for a single vmagent now, need to set up two level vmagents This PR implements case3. --------- Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>
2024-09-03 10:47:05 +02:00
}
dedupInterval := streamAggrGlobalDedupInterval.Duration()
if dedupInterval > 0 {
deduplicatorGlobal = streamaggr.NewDeduplicator(pushToRemoteStoragesTrackDropped, dedupInterval, *streamAggrGlobalDropInputLabels, "dedup-global")
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
}
}
func (rwctx *remoteWriteCtx) initStreamAggrConfig() {
idx := rwctx.idx
sas, err := rwctx.newStreamAggrConfig()
if err != nil {
logger.Fatalf("cannot initialize stream aggregators: %s", err)
}
if sas != nil {
filePath := sas.FilePath()
rwctx.sas.Store(sas)
rwctx.streamAggrKeepInput = streamAggrKeepInput.GetOptionalArg(idx)
rwctx.streamAggrDropInput = streamAggrDropInput.GetOptionalArg(idx)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, filePath)).Set(1)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, filePath)).Set(fasttime.UnixTimestamp())
stream aggregation: perform deduplication for all received data when … (#6711) …specifying `-streamAggr.dedupInterval` or `-remoteWrite.streamAggr.dedupInterval` command-line flag [The documentation](https://docs.victoriametrics.com/stream-aggregation/) contains conflicting descriptions regarding deduplication for non-matched series when `-remoteWrite.streamAggr.config` and / or `-streamAggr.config` are set: 1. Statement below says **all the received data** is deduplicated: >[vmagent](https://docs.victoriametrics.com/vmagent/) supports relabeling, deduplication and stream aggregation for all the received data, scraped or pushed. Then, the collected data will be forwarded to specified -remoteWrite.url destinations. The data processing order is the following: >1. all the received data is relabeled according to the specified [-remoteWrite.relabelConfig](https://docs.victoriametrics.com/vmagent/#relabeling) (if it is set) >2. all the received data is deduplicated according to specified [-streamAggr.dedupInterval](https://docs.victoriametrics.com/stream-aggregation/#deduplication) (if it is set to duration bigger than 0) 2. Another statement says the deduplication is performed individually for the **matching samples** >The de-deduplication is performed after applying [relabeling](https://docs.victoriametrics.com/vmagent/#relabeling) and before performing the aggregation. If the -remoteWrite.streamAggr.config and / or -streamAggr.config is set, then the de-duplication is performed individually per each [stream aggregation config](https://docs.victoriametrics.com/stream-aggregation/#stream-aggregation-config) for the matching samples after applying [input_relabel_configs](https://docs.victoriametrics.com/stream-aggregation/#relabeling). Considering the following deduplication use cases: 1. To apply deduplication(globally or for specific remoteWrite destination) for all the received data, scraped or pushed --- using `-streamAggr.dedupInterval` or `-remoteWrite.streamAggr.dedupInterval`. 2. To deduplicate and aggregate metrics that match the rule `match` filters --- using `-remoteWrite.streamAggr.config` and specifiying `dedup_interval` option in [stream aggregation config](https://docs.victoriametrics.com/stream-aggregation/#stream-aggregation-config). 3. To deduplicate all the received data while having `streamAggr.config` for some metrics --- no way for a single vmagent now, need to set up two level vmagents This PR implements case3. --------- Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>
2024-09-03 10:47:05 +02:00
}
dedupInterval := streamAggrDedupInterval.GetOptionalArg(idx)
if dedupInterval > 0 {
alias := fmt.Sprintf("dedup-%d", idx+1)
var dropLabels []string
if streamAggrDropInputLabels.GetOptionalArg(idx) != "" {
dropLabels = strings.Split(streamAggrDropInputLabels.GetOptionalArg(idx), "^^")
}
rwctx.deduplicator = streamaggr.NewDeduplicator(rwctx.pushInternalTrackDropped, dedupInterval, dropLabels, alias)
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
}
}
func (rwctx *remoteWriteCtx) reloadStreamAggrConfig() {
path := streamAggrConfig.GetOptionalArg(rwctx.idx)
if path == "" {
return
}
logger.Infof("reloading stream aggregation configs pointed by -remoteWrite.streamAggr.config=%q", path)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_total{path=%q}`, path)).Inc()
sasNew, err := rwctx.newStreamAggrConfig()
if err != nil {
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reloads_errors_total{path=%q}`, path)).Inc()
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, path)).Set(0)
logger.Errorf("cannot reload -remoteWrite.streamAggr.config=%q; continue using the previously loaded config; error: %s", path, err)
return
}
sas := rwctx.sas.Load()
if !sasNew.Equal(sas) {
sasOld := rwctx.sas.Swap(sasNew)
sasOld.MustStop()
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
logger.Infof("successfully reloaded -remoteWrite.streamAggr.config=%q", path)
} else {
sasNew.MustStop()
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
logger.Infof("-remoteWrite.streamAggr.config=%q wasn't changed since the last reload", path)
}
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_successful{path=%q}`, path)).Set(1)
metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_streamaggr_config_reload_success_timestamp_seconds{path=%q}`, path)).Set(fasttime.UnixTimestamp())
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
func newStreamAggrConfigGlobal() (*streamaggr.Aggregators, error) {
path := *streamAggrGlobalConfig
if path == "" {
return nil, nil
}
opts := &streamaggr.Options{
DedupInterval: streamAggrGlobalDedupInterval.Duration(),
DropInputLabels: *streamAggrGlobalDropInputLabels,
IgnoreOldSamples: *streamAggrGlobalIgnoreOldSamples,
IgnoreFirstIntervals: *streamAggrGlobalIgnoreFirstIntervals,
KeepInput: *streamAggrGlobalKeepInput,
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
}
sas, err := streamaggr.LoadFromFile(path, pushToRemoteStoragesTrackDropped, opts, "global")
if err != nil {
return nil, fmt.Errorf("cannot load -streamAggr.config=%q: %w", *streamAggrGlobalConfig, err)
}
return sas, nil
}
func (rwctx *remoteWriteCtx) newStreamAggrConfig() (*streamaggr.Aggregators, error) {
return newStreamAggrConfigPerURL(rwctx.idx, rwctx.pushInternalTrackDropped)
}
func newStreamAggrConfigPerURL(idx int, pushFunc streamaggr.PushFunc) (*streamaggr.Aggregators, error) {
path := streamAggrConfig.GetOptionalArg(idx)
if path == "" {
return nil, nil
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
alias := fmt.Sprintf("%d:secret-url", idx+1)
if *showRemoteWriteURL {
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
alias = fmt.Sprintf("%d:%s", idx+1, remoteWriteURLs.GetOptionalArg(idx))
}
var dropLabels []string
if streamAggrDropInputLabels.GetOptionalArg(idx) != "" {
dropLabels = strings.Split(streamAggrDropInputLabels.GetOptionalArg(idx), "^^")
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
opts := &streamaggr.Options{
DedupInterval: streamAggrDedupInterval.GetOptionalArg(idx),
DropInputLabels: dropLabels,
IgnoreOldSamples: streamAggrIgnoreOldSamples.GetOptionalArg(idx),
IgnoreFirstIntervals: streamAggrIgnoreFirstIntervals.GetOptionalArg(idx),
KeepInput: streamAggrKeepInput.GetOptionalArg(idx),
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
sas, err := streamaggr.LoadFromFile(path, pushFunc, opts, alias)
if err != nil {
return nil, fmt.Errorf("cannot load -remoteWrite.streamAggr.config=%q: %w", path, err)
}
app/vmagent/remotewrite: follow-up for f153f54d11250da050aa93bc4fa9b7ba9e144691 - Move the remaining code responsible for stream aggregation initialization from remotewrite.go to streamaggr.go . This improves code maintainability a bit. - Properly shut down streamaggr.Aggregators initialized inside remotewrite.CheckStreamAggrConfigs(). This prevents from potential resource leaks. - Use separate functions for initializing and reloading of global stream aggregation and per-remoteWrite.url stream aggregation. This makes the code easier to read and maintain. This also fixes INFO and ERROR logs emitted by these functions. - Add an ability to specify `name` option in every stream aggregation config. This option is used as `name` label in metrics exposed by stream aggregation at /metrics page. This simplifies investigation of the exposed metrics. - Add `path` label additionally to `name`, `url` and `position` labels at metrics exposed by streaming aggregation. This label should simplify investigation of the exposed metrics. - Remove `match` and `group` labels from metrics exposed by streaming aggregation, since they have little practical applicability: it is hard to use these labels in query filters and aggregation functions. - Rename the metric `vm_streamaggr_flushed_samples_total` to less misleading `vm_streamaggr_output_samples_total` . This metric shows the number of samples generated by the corresponding streaming aggregation rule. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove the metric `vm_streamaggr_stale_samples_total`, since it is unclear how it can be used in practice. This metric has been added in the commit 861852f2624895e01f93ce196607c72616ce2a94 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6462 - Remove Alias and aggrID fields from streamaggr.Options struct, since these fields aren't related to optional params, which could modify the behaviour of the constructed streaming aggregator. Convert the Alias field to regular argument passed to LoadFromFile() function, since this argument is mandatory. - Pass Options arg to LoadFromFile() function by reference, since this structure is quite big. This also allows passing nil instead of Options when default options are enough. - Add `name`, `path`, `url` and `position` labels to `vm_streamaggr_dedup_state_size_bytes` and `vm_streamaggr_dedup_state_items_count` metrics, so they have consistent set of labels comparing to the rest of streaming aggregation metrics. - Convert aggregator.aggrStates field type from `map[string]aggrState` to `[]aggrOutput`, where `aggrOutput` contains the corresponding `aggrState` plus all the related metrics (currently only `vm_streamaggr_output_samples_total` metric is exposed with the corresponding `output` label per each configured output function). This simplifies and speeds up the code responsible for updating per-output metrics. This is a follow-up for the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . See https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6604 - Added missing urls to docs ( https://docs.victoriametrics.com/stream-aggregation/ ) in error messages. These urls help users figuring out why VictoriaMetrics or vmagent generates the corresponding error messages. The urls were removed for unknown reason in the commit 2eb1bc4f814037ae87ac6556011ae0d3caee6bc8 . - Fix incorrect update for `vm_streamaggr_output_samples_total` metric in flushCtx.appendSeriesWithExtraLabel() function. While at it, reduce memory usage by limiting the maximum number of samples per flush to 10K. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5467 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6268
2024-07-15 18:01:37 +02:00
return sas, nil
}