Kiu/VictoriaMetrics
Kiu/VictoriaMetrics
1
0
Fork 0
mirror of https://github.com/VictoriaMetrics/VictoriaMetrics.git synced 2024-11-23 12:31:07 +01:00
Code Issues Actions 8 Packages Projects Releases Wiki Activity

docs: link to active time series, churn rate and high cardinality questions

Browse Source
This commit is contained in:
Aliaksandr Valialkin 2021-08-27 14:44:53 +03:00
parent c8c153fb91
commit 321da535fa
4 changed files with 42 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
README.md
View File

@ -65,8 +65,8 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
[Outperforms InfluxDB and TimescaleDB by up to 20x](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae).
* [Uses 10x less RAM than InfluxDB](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893)
and [up to 7x less RAM than Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f)
when dealing with millions of unique time series (aka high cardinality).
* Optimized for time series with high churn rate. Think about [prometheus-operator](https://github.com/coreos/prometheus-operator) metrics from frequent deployments in Kubernetes.
when dealing with millions of unique time series (aka [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality)).
* Optimized for time series with [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate). Think about [prometheus-operator](https://github.com/coreos/prometheus-operator) metrics from frequent deployments in Kubernetes.
* High data compression, so [up to 70x more data points](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4)
may be crammed into limited storage comparing to TimescaleDB
and [up to 7x less storage space is required comparing to Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f).
@ -99,7 +99,7 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
* [Prometheus exposition format](#how-to-import-data-in-prometheus-exposition-format).
* [Arbitrary CSV data](#how-to-import-csv-data).
* Supports metrics' relabeling. See [these docs](#relabeling) for details.
* Can deal with high cardinality and high churn rate issues using [series limiter](#cardinality-limiter).
* Can deal with [high cardinality issues](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) and [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) issues using [series limiter](#cardinality-limiter).
* Ideally works with big amounts of time series data from APM, Kubernetes, IoT sensors, connected cars, industrial telemetry, financial data and various [Enterprise workloads](https://victoriametrics.com/enterprise.html).
* Has open source [cluster version](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/cluster).
* See also technical [Articles about VictoriaMetrics](https://docs.victoriametrics.com/Articles.html).
@ -760,7 +760,7 @@ Note that background merges may never occur for data from previous months, so st
In this case [forced merge](#forced-merge) may help freeing up storage space.
It is recommended verifying which metrics will be deleted with the call to `http://<victoria-metrics-addr>:8428/api/v1/series?match[]=<timeseries_selector_for_delete>`
before actually deleting the metrics. By default this query will only scan active series in the past 5 minutes, so you may need to
before actually deleting the metrics. By default this query will only scan series in the past 5 minutes, so you may need to
adjust `start` and `end` to a suitable range to achieve match hits.
The `/api/v1/admin/tsdb/delete_series` handler may be protected with `authKey` if `-deleteAuthKey` command-line flag is set.
@ -1096,7 +1096,7 @@ with scrape intervals exceeding `5m`.
VictoriaMetrics uses lower amounts of CPU, RAM and storage space on production workloads compared to competing solutions (Prometheus, Thanos, Cortex, TimescaleDB, InfluxDB, QuestDB, M3DB) according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html).
VictoriaMetrics capacity scales linearly with the available resources. The needed amounts of CPU and RAM highly depends on the workload - the number of active time series, series churn rate, query types, query qps, etc. It is recommended setting up a test VictoriaMetrics for your production workload and iteratively scaling CPU and RAM resources until it becomes stable according to [troubleshooting docs](#troubleshooting). A single-node VictoriaMetrics works perfectly with the following production workload according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html):
VictoriaMetrics capacity scales linearly with the available resources. The needed amounts of CPU and RAM highly depends on the workload - the number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series), series [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate), query types, query qps, etc. It is recommended setting up a test VictoriaMetrics for your production workload and iteratively scaling CPU and RAM resources until it becomes stable according to [troubleshooting docs](#troubleshooting). A single-node VictoriaMetrics works perfectly with the following production workload according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html):
* Ingestion rate: 1.5+ million samples per second
* Active time series: 50+ million
@ -1296,18 +1296,18 @@ It is recommended setting up alerts in [vmalert](https://docs.victoriametrics.co
The most interesting metrics are:
* `vm_cache_entries{type="storage/hour_metric_ids"}` - the number of time series with new data points during the last hour
aka active time series.
* `increase(vm_new_timeseries_created_total[1h])` - time series churn rate during the previous hour.
aka [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `increase(vm_new_timeseries_created_total[1h])` - time series [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) during the previous hour.
* `sum(vm_rows{type=~"storage/.*"})` - total number of `(timestamp, value)` data points in the database.
* `sum(rate(vm_rows_inserted_total[5m]))` - ingestion rate, i.e. how many samples are inserted int the database per second.
* `vm_free_disk_space_bytes` - free space left at `-storageDataPath`.
* `sum(vm_data_size_bytes)` - the total size of data on disk.
* `increase(vm_slow_row_inserts_total[5m])` - the number of slow inserts during the last 5 minutes.
If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling
of the current number of active time series.
of the current number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `increase(vm_slow_metric_name_loads_total[5m])` - the number of slow loads of metric names during the last 5 minutes.
If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling
of the current number of active time series.
of the current number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
VictoriaMetrics also exposes currently running queries with their execution times at `/api/v1/status/active_queries` page.
@ -1327,8 +1327,8 @@ VictoriaMetrics returns TSDB stats at `/api/v1/status/tsdb` page in the way simi
By default VictoriaMetrics doesn't limit the number of stored time series. The limit can be enforced by setting the following command-line flags:
* `-storage.maxHourlySeries` - limits the number of time series that can be added during the last hour. Useful for limiting the number of active time series.
* `-storage.maxDailySeries` - limits the number of time series that can be added during the last day. Useful for limiting daily churn rate.
* `-storage.maxHourlySeries` - limits the number of time series that can be added during the last hour. Useful for limiting the number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `-storage.maxDailySeries` - limits the number of time series that can be added during the last day. Useful for limiting daily [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate).
Both limits can be set simultaneously. If any of these limits is reached, then incoming samples for new time series are dropped. A sample of dropped series is put in the log with `WARNING` level.
@ -1369,7 +1369,7 @@ These limits are approximate, so VictoriaMetrics can underflow/overflow the limi
See [this article for technical details](https://valyala.medium.com/wal-usage-looks-broken-in-modern-time-series-databases-b62a627ab704).
* If VictoriaMetrics works slowly and eats more than a CPU core per 100K ingested data points per second,
then it is likely you have too many active time series for the current amount of RAM.
then it is likely you have too many [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series) for the current amount of RAM.
VictoriaMetrics [exposes](#monitoring) `vm_slow_*` metrics such as `vm_slow_row_inserts_total` and `vm_slow_metric_name_loads_total`, which could be used
as an indicator of low amounts of RAM. It is recommended increasing the amount of RAM on the node with VictoriaMetrics in order to improve
ingestion and query performance in this case.
@ -1396,7 +1396,7 @@ These limits are approximate, so VictoriaMetrics can underflow/overflow the limi
It may be needed in order to suppress default gap filling algorithm used by VictoriaMetrics - by default it assumes
each time series is continuous instead of discrete, so it fills gaps between real samples with regular intervals.
* Metrics and labels leading to high cardinality or high churn rate can be determined at `/api/v1/status/tsdb` page. See [these docs](#tsdb-stats) for details.
* Metrics and labels leading to [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) or [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) can be determined at `/api/v1/status/tsdb` page. See [these docs](#tsdb-stats) for details.
* New time series can be logged if `-logNewSeries` command-line flag is passed to VictoriaMetrics.

6
docs/BestPractices.md
View File

@ -36,7 +36,7 @@ Prometheus doesn't drop data during the VictoriaMetrics restart. See [this artic
* tls, -tlsCertFile and -tlsKeyFile for switching from HTTP to HTTPS.
* httpAuth.username and -httpAuth.password for protecting all the HTTP endpoints with [HTTP Basic Authentication](https://en.wikipedia.org/wiki/Basic_access_authentication).
* deleteAuthKey for protecting /api/v1/admin/tsdb/delete_series endpoint. See how to [delete time series](https://docs.victoriametrics.com/#how-to-delete-time-series).
* snapshotAuthKey for protecting /snapshot* endpoints. See [how to work with snapshots](https://docs.victoriametrics.com/#how-to-work-with-snapshots).
* snapshotAuthKey for protecting `/snapshot*` endpoints. See [how to work with snapshots](https://docs.victoriametrics.com/#how-to-work-with-snapshots).
* forceMergeAuthKey for protecting /internal/force_merge endpoint. See [force merge docs](https://docs.victoriametrics.com/#forced-merge).
* search.resetCacheAuthKey for protecting /internal/resetRollupResultCache endpoint. See [backfilling](https://docs.victoriametrics.com/vmbackup.html#backfilling) for more details.
@ -53,10 +53,10 @@ It is preferable to authorize all incoming requests from untrusted networks wit
Storage space: VictoriaMetrics needs less than a byte per data point on average. So, ~260GB is required to store a month-long insert stream of 100K data points per second. The actual storage size depends largely on data randomness (entropy). Higher randomness means higher storage size requirements. Read [this article](https://medium.com/faun/victoriametrics-achieving-better-compression-for-time-series-data-than-gorilla-317bc1f95932) for details.
## RAM
RAM size: VictoriaMetrics needs less than 1KB per active time series. Therefore, ~1GB of RAM is required for 1M active time series. Time series are considered active if new data points have been added recently or if they have been recently queried. The number of active time series may be obtained from vm_cache_entries{type="storage/hour_metric_ids"} metric exported on the /metrics page. VictoriaMetrics stores various caches in RAM. Memory size for these caches may be limited with -memory.allowedPercent or -memory.allowedBytes flags.
RAM size: VictoriaMetrics needs less than 1KB per [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series). Therefore, ~1GB of RAM is required for 1M active time series. Time series are considered active if new data points have been added recently or if they have been recently queried. The number of active time series may be obtained from vm_cache_entries{type="storage/hour_metric_ids"} metric exported on the /metrics page. VictoriaMetrics stores various caches in RAM. Memory size for these caches may be limited with -memory.allowedPercent or -memory.allowedBytes flags.
## CPU
CPU cores: VictoriaMetrics needs one CPU core per 300K inserted data points per second. So, ~4 CPU cores are required for processing the insert stream of 1M data points per second. The ingestion rate may be lower for high cardinality data or for time series with a high number of labels. See [this article](https://valyala.medium.com/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893) for details. If you see lower numbers per CPU core, it is likely that the active time series info doesn't fit in your caches and you will need more RAM to lower CPU usage.
CPU cores: VictoriaMetrics needs one CPU core per 300K inserted data points per second. So, ~4 CPU cores are required for processing the insert stream of 1M data points per second. The ingestion rate may be lower for [high cardinality data](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) or for time series with a high number of labels. See [this article](https://valyala.medium.com/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893) for details. If you see lower numbers per CPU core, it is likely that the [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series) info doesn't fit in your caches and you will need more RAM to lower CPU usage.
## Technical Support and Services
If you have questions about installing or using this software pleasecheck this and other documents first. Answers to the most frequently askedquestions can be found on the Technical Papers webpage or in VictoriaMetrics community channels. If you need further assistance with VictoriaMetrics, please contact us at info@victoriametrics.com - we’ll be happy to help.

26
docs/README.md
View File

@ -65,8 +65,8 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
[Outperforms InfluxDB and TimescaleDB by up to 20x](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae).
* [Uses 10x less RAM than InfluxDB](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893)
and [up to 7x less RAM than Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f)
when dealing with millions of unique time series (aka high cardinality).
* Optimized for time series with high churn rate. Think about [prometheus-operator](https://github.com/coreos/prometheus-operator) metrics from frequent deployments in Kubernetes.
when dealing with millions of unique time series (aka [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality)).
* Optimized for time series with [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate). Think about [prometheus-operator](https://github.com/coreos/prometheus-operator) metrics from frequent deployments in Kubernetes.
* High data compression, so [up to 70x more data points](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4)
may be crammed into limited storage comparing to TimescaleDB
and [up to 7x less storage space is required comparing to Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f).
@ -99,7 +99,7 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
* [Prometheus exposition format](#how-to-import-data-in-prometheus-exposition-format).
* [Arbitrary CSV data](#how-to-import-csv-data).
* Supports metrics' relabeling. See [these docs](#relabeling) for details.
* Can deal with high cardinality and high churn rate issues using [series limiter](#cardinality-limiter).
* Can deal with [high cardinality issues](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) and [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) issues using [series limiter](#cardinality-limiter).
* Ideally works with big amounts of time series data from APM, Kubernetes, IoT sensors, connected cars, industrial telemetry, financial data and various [Enterprise workloads](https://victoriametrics.com/enterprise.html).
* Has open source [cluster version](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/cluster).
* See also technical [Articles about VictoriaMetrics](https://docs.victoriametrics.com/Articles.html).
@ -760,7 +760,7 @@ Note that background merges may never occur for data from previous months, so st
In this case [forced merge](#forced-merge) may help freeing up storage space.
It is recommended verifying which metrics will be deleted with the call to `http://<victoria-metrics-addr>:8428/api/v1/series?match[]=<timeseries_selector_for_delete>`
before actually deleting the metrics. By default this query will only scan active series in the past 5 minutes, so you may need to
before actually deleting the metrics. By default this query will only scan series in the past 5 minutes, so you may need to
adjust `start` and `end` to a suitable range to achieve match hits.
The `/api/v1/admin/tsdb/delete_series` handler may be protected with `authKey` if `-deleteAuthKey` command-line flag is set.
@ -1096,7 +1096,7 @@ with scrape intervals exceeding `5m`.
VictoriaMetrics uses lower amounts of CPU, RAM and storage space on production workloads compared to competing solutions (Prometheus, Thanos, Cortex, TimescaleDB, InfluxDB, QuestDB, M3DB) according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html).
VictoriaMetrics capacity scales linearly with the available resources. The needed amounts of CPU and RAM highly depends on the workload - the number of active time series, series churn rate, query types, query qps, etc. It is recommended setting up a test VictoriaMetrics for your production workload and iteratively scaling CPU and RAM resources until it becomes stable according to [troubleshooting docs](#troubleshooting). A single-node VictoriaMetrics works perfectly with the following production workload according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html):
VictoriaMetrics capacity scales linearly with the available resources. The needed amounts of CPU and RAM highly depends on the workload - the number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series), series [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate), query types, query qps, etc. It is recommended setting up a test VictoriaMetrics for your production workload and iteratively scaling CPU and RAM resources until it becomes stable according to [troubleshooting docs](#troubleshooting). A single-node VictoriaMetrics works perfectly with the following production workload according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html):
* Ingestion rate: 1.5+ million samples per second
* Active time series: 50+ million
@ -1296,18 +1296,18 @@ It is recommended setting up alerts in [vmalert](https://docs.victoriametrics.co
The most interesting metrics are:
* `vm_cache_entries{type="storage/hour_metric_ids"}` - the number of time series with new data points during the last hour
aka active time series.
* `increase(vm_new_timeseries_created_total[1h])` - time series churn rate during the previous hour.
aka [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `increase(vm_new_timeseries_created_total[1h])` - time series [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) during the previous hour.
* `sum(vm_rows{type=~"storage/.*"})` - total number of `(timestamp, value)` data points in the database.
* `sum(rate(vm_rows_inserted_total[5m]))` - ingestion rate, i.e. how many samples are inserted int the database per second.
* `vm_free_disk_space_bytes` - free space left at `-storageDataPath`.
* `sum(vm_data_size_bytes)` - the total size of data on disk.
* `increase(vm_slow_row_inserts_total[5m])` - the number of slow inserts during the last 5 minutes.
If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling
of the current number of active time series.
of the current number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `increase(vm_slow_metric_name_loads_total[5m])` - the number of slow loads of metric names during the last 5 minutes.
If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling
of the current number of active time series.
of the current number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
VictoriaMetrics also exposes currently running queries with their execution times at `/api/v1/status/active_queries` page.
@ -1327,8 +1327,8 @@ VictoriaMetrics returns TSDB stats at `/api/v1/status/tsdb` page in the way simi
By default VictoriaMetrics doesn't limit the number of stored time series. The limit can be enforced by setting the following command-line flags:
* `-storage.maxHourlySeries` - limits the number of time series that can be added during the last hour. Useful for limiting the number of active time series.
* `-storage.maxDailySeries` - limits the number of time series that can be added during the last day. Useful for limiting daily churn rate.
* `-storage.maxHourlySeries` - limits the number of time series that can be added during the last hour. Useful for limiting the number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `-storage.maxDailySeries` - limits the number of time series that can be added during the last day. Useful for limiting daily [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate).
Both limits can be set simultaneously. If any of these limits is reached, then incoming samples for new time series are dropped. A sample of dropped series is put in the log with `WARNING` level.
@ -1369,7 +1369,7 @@ These limits are approximate, so VictoriaMetrics can underflow/overflow the limi
See [this article for technical details](https://valyala.medium.com/wal-usage-looks-broken-in-modern-time-series-databases-b62a627ab704).
* If VictoriaMetrics works slowly and eats more than a CPU core per 100K ingested data points per second,
then it is likely you have too many active time series for the current amount of RAM.
then it is likely you have too many [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series) for the current amount of RAM.
VictoriaMetrics [exposes](#monitoring) `vm_slow_*` metrics such as `vm_slow_row_inserts_total` and `vm_slow_metric_name_loads_total`, which could be used
as an indicator of low amounts of RAM. It is recommended increasing the amount of RAM on the node with VictoriaMetrics in order to improve
ingestion and query performance in this case.
@ -1396,7 +1396,7 @@ These limits are approximate, so VictoriaMetrics can underflow/overflow the limi
It may be needed in order to suppress default gap filling algorithm used by VictoriaMetrics - by default it assumes
each time series is continuous instead of discrete, so it fills gaps between real samples with regular intervals.
* Metrics and labels leading to high cardinality or high churn rate can be determined at `/api/v1/status/tsdb` page. See [these docs](#tsdb-stats) for details.
* Metrics and labels leading to [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) or [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) can be determined at `/api/v1/status/tsdb` page. See [these docs](#tsdb-stats) for details.
* New time series can be logged if `-logNewSeries` command-line flag is passed to VictoriaMetrics.

26
docs/Single-server-VictoriaMetrics.md
View File

@ -69,8 +69,8 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
[Outperforms InfluxDB and TimescaleDB by up to 20x](https://medium.com/@valyala/measuring-vertical-scalability-for-time-series-databases-in-google-cloud-92550d78d8ae).
* [Uses 10x less RAM than InfluxDB](https://medium.com/@valyala/insert-benchmarks-with-inch-influxdb-vs-victoriametrics-e31a41ae2893)
and [up to 7x less RAM than Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f)
when dealing with millions of unique time series (aka high cardinality).
* Optimized for time series with high churn rate. Think about [prometheus-operator](https://github.com/coreos/prometheus-operator) metrics from frequent deployments in Kubernetes.
when dealing with millions of unique time series (aka [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality)).
* Optimized for time series with [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate). Think about [prometheus-operator](https://github.com/coreos/prometheus-operator) metrics from frequent deployments in Kubernetes.
* High data compression, so [up to 70x more data points](https://medium.com/@valyala/when-size-matters-benchmarking-victoriametrics-vs-timescale-and-influxdb-6035811952d4)
may be crammed into limited storage comparing to TimescaleDB
and [up to 7x less storage space is required comparing to Prometheus, Thanos or Cortex](https://valyala.medium.com/prometheus-vs-victoriametrics-benchmark-on-node-exporter-metrics-4ca29c75590f).
@ -103,7 +103,7 @@ See also [articles and slides about VictoriaMetrics from our users](https://docs
* [Prometheus exposition format](#how-to-import-data-in-prometheus-exposition-format).
* [Arbitrary CSV data](#how-to-import-csv-data).
* Supports metrics' relabeling. See [these docs](#relabeling) for details.
* Can deal with high cardinality and high churn rate issues using [series limiter](#cardinality-limiter).
* Can deal with [high cardinality issues](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) and [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) issues using [series limiter](#cardinality-limiter).
* Ideally works with big amounts of time series data from APM, Kubernetes, IoT sensors, connected cars, industrial telemetry, financial data and various [Enterprise workloads](https://victoriametrics.com/enterprise.html).
* Has open source [cluster version](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/cluster).
* See also technical [Articles about VictoriaMetrics](https://docs.victoriametrics.com/Articles.html).
@ -764,7 +764,7 @@ Note that background merges may never occur for data from previous months, so st
In this case [forced merge](#forced-merge) may help freeing up storage space.
It is recommended verifying which metrics will be deleted with the call to `http://<victoria-metrics-addr>:8428/api/v1/series?match[]=<timeseries_selector_for_delete>`
before actually deleting the metrics. By default this query will only scan active series in the past 5 minutes, so you may need to
before actually deleting the metrics. By default this query will only scan series in the past 5 minutes, so you may need to
adjust `start` and `end` to a suitable range to achieve match hits.
The `/api/v1/admin/tsdb/delete_series` handler may be protected with `authKey` if `-deleteAuthKey` command-line flag is set.
@ -1100,7 +1100,7 @@ with scrape intervals exceeding `5m`.
VictoriaMetrics uses lower amounts of CPU, RAM and storage space on production workloads compared to competing solutions (Prometheus, Thanos, Cortex, TimescaleDB, InfluxDB, QuestDB, M3DB) according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html).
VictoriaMetrics capacity scales linearly with the available resources. The needed amounts of CPU and RAM highly depends on the workload - the number of active time series, series churn rate, query types, query qps, etc. It is recommended setting up a test VictoriaMetrics for your production workload and iteratively scaling CPU and RAM resources until it becomes stable according to [troubleshooting docs](#troubleshooting). A single-node VictoriaMetrics works perfectly with the following production workload according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html):
VictoriaMetrics capacity scales linearly with the available resources. The needed amounts of CPU and RAM highly depends on the workload - the number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series), series [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate), query types, query qps, etc. It is recommended setting up a test VictoriaMetrics for your production workload and iteratively scaling CPU and RAM resources until it becomes stable according to [troubleshooting docs](#troubleshooting). A single-node VictoriaMetrics works perfectly with the following production workload according to [our case studies](https://docs.victoriametrics.com/CaseStudies.html):
* Ingestion rate: 1.5+ million samples per second
* Active time series: 50+ million
@ -1300,18 +1300,18 @@ It is recommended setting up alerts in [vmalert](https://docs.victoriametrics.co
The most interesting metrics are:
* `vm_cache_entries{type="storage/hour_metric_ids"}` - the number of time series with new data points during the last hour
aka active time series.
* `increase(vm_new_timeseries_created_total[1h])` - time series churn rate during the previous hour.
aka [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `increase(vm_new_timeseries_created_total[1h])` - time series [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) during the previous hour.
* `sum(vm_rows{type=~"storage/.*"})` - total number of `(timestamp, value)` data points in the database.
* `sum(rate(vm_rows_inserted_total[5m]))` - ingestion rate, i.e. how many samples are inserted int the database per second.
* `vm_free_disk_space_bytes` - free space left at `-storageDataPath`.
* `sum(vm_data_size_bytes)` - the total size of data on disk.
* `increase(vm_slow_row_inserts_total[5m])` - the number of slow inserts during the last 5 minutes.
If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling
of the current number of active time series.
of the current number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `increase(vm_slow_metric_name_loads_total[5m])` - the number of slow loads of metric names during the last 5 minutes.
If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling
of the current number of active time series.
of the current number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
VictoriaMetrics also exposes currently running queries with their execution times at `/api/v1/status/active_queries` page.
@ -1331,8 +1331,8 @@ VictoriaMetrics returns TSDB stats at `/api/v1/status/tsdb` page in the way simi
By default VictoriaMetrics doesn't limit the number of stored time series. The limit can be enforced by setting the following command-line flags:
* `-storage.maxHourlySeries` - limits the number of time series that can be added during the last hour. Useful for limiting the number of active time series.
* `-storage.maxDailySeries` - limits the number of time series that can be added during the last day. Useful for limiting daily churn rate.
* `-storage.maxHourlySeries` - limits the number of time series that can be added during the last hour. Useful for limiting the number of [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series).
* `-storage.maxDailySeries` - limits the number of time series that can be added during the last day. Useful for limiting daily [churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate).
Both limits can be set simultaneously. If any of these limits is reached, then incoming samples for new time series are dropped. A sample of dropped series is put in the log with `WARNING` level.
@ -1373,7 +1373,7 @@ These limits are approximate, so VictoriaMetrics can underflow/overflow the limi
See [this article for technical details](https://valyala.medium.com/wal-usage-looks-broken-in-modern-time-series-databases-b62a627ab704).
* If VictoriaMetrics works slowly and eats more than a CPU core per 100K ingested data points per second,
then it is likely you have too many active time series for the current amount of RAM.
then it is likely you have too many [active time series](https://docs.victoriametrics.com/FAQ.html#what-is-active-time-series) for the current amount of RAM.
VictoriaMetrics [exposes](#monitoring) `vm_slow_*` metrics such as `vm_slow_row_inserts_total` and `vm_slow_metric_name_loads_total`, which could be used
as an indicator of low amounts of RAM. It is recommended increasing the amount of RAM on the node with VictoriaMetrics in order to improve
ingestion and query performance in this case.
@ -1400,7 +1400,7 @@ These limits are approximate, so VictoriaMetrics can underflow/overflow the limi
It may be needed in order to suppress default gap filling algorithm used by VictoriaMetrics - by default it assumes
each time series is continuous instead of discrete, so it fills gaps between real samples with regular intervals.
* Metrics and labels leading to high cardinality or high churn rate can be determined at `/api/v1/status/tsdb` page. See [these docs](#tsdb-stats) for details.
* Metrics and labels leading to [high cardinality](https://docs.victoriametrics.com/FAQ.html#what-is-high-cardinality) or [high churn rate](https://docs.victoriametrics.com/FAQ.html#what-is-high-churn-rate) can be determined at `/api/v1/status/tsdb` page. See [these docs](#tsdb-stats) for details.
* New time series can be logged if `-logNewSeries` command-line flag is passed to VictoriaMetrics.