mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2024-12-12 04:32:00 +01:00
app/vmagent: add remoteWrite.retryMinInterval and remoteWrite.retryMaxTime flags (#6289)
## Describe Your Changes
Add RemoteWrite Retry Controls
This PR introduces two new flags to the remote write functionality:
- remoteWrite.retryMinInterval
- remoteWrite.retryMaxTime
These flags provide finer control over the retry behavior for
remoteWrite operations, allowing users to customize the minimum interval
between retries and the maximum duration for retry attempts.
Fixes #5486.
## Checklist
- [x] The following checks are mandatory:
My change adheres [VictoriaMetrics contributing
guidelines](https://docs.victoriametrics.com/contributing/).
---------
Signed-off-by: Yury Akudovich <ya@matterlabs.dev>
Co-authored-by: hagen1778 <roman@victoriametrics.com>
(cherry picked from commit d0f5a9d77a)
This commit is contained in:
Yury Akudovich
hagen1778
parent
e24ebe3e54
commit
f759371c00
@ -34,8 +34,10 @@ var (
|
||||
rateLimit = flagutil.NewArrayInt("remoteWrite.rateLimit", 0, "Optional rate limit in bytes per second for data sent to the corresponding -remoteWrite.url. "+
|
||||
"By default, the rate limit is disabled. It can be useful for limiting load on remote storage when big amounts of buffered data "+
|
||||
"is sent after temporary unavailability of the remote storage. See also -maxIngestionRate")
|
||||
sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", time.Minute, "Timeout for sending a single block of data to the corresponding -remoteWrite.url")
|
||||
proxyURL = flagutil.NewArrayString("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
|
||||
sendTimeout = flagutil.NewArrayDuration("remoteWrite.sendTimeout", time.Minute, "Timeout for sending a single block of data to the corresponding -remoteWrite.url")
|
||||
retryMinInterval = flagutil.NewArrayDuration("remoteWrite.retryMinInterval", time.Second, "The minimum delay between retry attempts to send a block of data to the corresponding -remoteWrite.url. Every next retry attempt will double the delay to prevent hammering of remote database. See also -remoteWrite.retryMaxInterval")
|
||||
retryMaxTime = flagutil.NewArrayDuration("remoteWrite.retryMaxTime", time.Minute, "The max time spent on retry attempts to send a block of data to the corresponding -remoteWrite.url. Change this value if it is expected for -remoteWrite.url to be unreachable for more than -remoteWrite.retryMaxTime. See also -remoteWrite.retryMinInterval")
|
||||
proxyURL = flagutil.NewArrayString("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
|
||||
"Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234")
|
||||
|
||||
tlsHandshakeTimeout = flagutil.NewArrayDuration("remoteWrite.tlsHandshakeTimeout", 20*time.Second, "The timeout for establishing tls connections to the corresponding -remoteWrite.url")
|
||||
@ -90,6 +92,9 @@ type client struct {
|
||||
fq *persistentqueue.FastQueue
|
||||
hc *http.Client
|
||||
|
||||
retryMinInterval time.Duration
|
||||
retryMaxTime time.Duration
|
||||
|
||||
sendBlock func(block []byte) bool
|
||||
authCfg *promauth.Config
|
||||
awsCfg *awsapi.Config
|
||||
@ -143,13 +148,15 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
|
||||
Timeout: sendTimeout.GetOptionalArg(argIdx),
|
||||
}
|
||||
c := &client{
|
||||
sanitizedURL: sanitizedURL,
|
||||
remoteWriteURL: remoteWriteURL,
|
||||
authCfg: authCfg,
|
||||
awsCfg: awsCfg,
|
||||
fq: fq,
|
||||
hc: hc,
|
||||
stopCh: make(chan struct{}),
|
||||
sanitizedURL: sanitizedURL,
|
||||
remoteWriteURL: remoteWriteURL,
|
||||
authCfg: authCfg,
|
||||
awsCfg: awsCfg,
|
||||
fq: fq,
|
||||
hc: hc,
|
||||
retryMinInterval: retryMinInterval.GetOptionalArg(argIdx),
|
||||
retryMaxTime: retryMaxTime.GetOptionalArg(argIdx),
|
||||
stopCh: make(chan struct{}),
|
||||
}
|
||||
c.sendBlock = c.sendBlockHTTP
|
||||
|
||||
@ -396,11 +403,11 @@ func (c *client) newRequest(url string, body []byte) (*http.Request, error) {
|
||||
// sendBlockHTTP sends the given block to c.remoteWriteURL.
|
||||
//
|
||||
// The function returns false only if c.stopCh is closed.
|
||||
// Otherwise it tries sending the block to remote storage indefinitely.
|
||||
// Otherwise, it tries sending the block to remote storage indefinitely.
|
||||
func (c *client) sendBlockHTTP(block []byte) bool {
|
||||
c.rl.Register(len(block))
|
||||
maxRetryDuration := timeutil.AddJitterToDuration(time.Minute)
|
||||
retryDuration := timeutil.AddJitterToDuration(time.Second)
|
||||
maxRetryDuration := timeutil.AddJitterToDuration(c.retryMaxTime)
|
||||
retryDuration := timeutil.AddJitterToDuration(c.retryMinInterval)
|
||||
retriesCount := 0
|
||||
|
||||
again:
|
||||
|
||||
@ -28,6 +28,7 @@ The value of `instance` label for those scrape targets will be changed from `<ad
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent/): allow overriding the `sample_limit` option at [scrape_configs](https://docs.victoriametrics.com/sd_configs/#scrape_configs) when a label `__sample_limit__` is specified for target. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6665). Thanks to @zoglam for the [pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6666).
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent/): reduce memory usage when scraping targets with big response body. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6759).
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent/) and [Single-node VictoriaMetrics](https://docs.victoriametrics.com/): stop adding default port 80/443 for scrape URLs without a port. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6792).
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent.html): add flags `-remoteWrite.retryMinInterval` and `-remoteWrite.retryMaxTime` for adjusting remote-write requests retry policy. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5486). Thanks to @yorik for the [pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6289).
|
||||
* FEATURE: [vmalert](https://docs.victoriametrics.com/vmalert/): add command-line flag `-notifier.headers` to allow configuring additional headers for all requests sent to the corresponding `-notifier.url`.
|
||||
* FEATURE: [vmalert-tool](https://docs.victoriametrics.com/vmalert-tool/): add `-external.label` and `-external.url` command-line flags, in the same way as these flags are supported by vmalert. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6735).
|
||||
* FEATURE: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmrestore](https://docs.victoriametrics.com/vmrestore/), [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager/): use exponential backoff for retries when uploading or downloading data from S3. This should reduce the number of failed uploads and downloads when S3 is temporarily unavailable. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6732).
|
||||
|
||||
@ -2168,6 +2168,14 @@ See the docs at https://docs.victoriametrics.com/vmagent/ .
|
||||
Empty values are set to default value.
|
||||
-remoteWrite.relabelConfig string
|
||||
Optional path to file with relabeling configs, which are applied to all the metrics before sending them to -remoteWrite.url. See also -remoteWrite.urlRelabelConfig. The path can point either to local file or to http url. See https://docs.victoriametrics.com/vmagent/#relabeling
|
||||
-remoteWrite.retryMaxTime array
|
||||
The max time spent on retry attempts to send a block of data to the corresponding -remoteWrite.url. Change this value if it is expected for -remoteWrite.url to be unreachable for more than -remoteWrite.retryMaxTime. See also -remoteWrite.retryMinInterval (default 1m0s)
|
||||
Supports array of values separated by comma or specified via multiple flags.
|
||||
Empty values are set to default value.
|
||||
-remoteWrite.retryMinInterval array
|
||||
The minimum delay between retry attempts to send a block of data to the corresponding -remoteWrite.url. Every next retry attempt will double the delay to prevent hammering of remote database. See also -remoteWrite.retryMaxInterval (default 1s)
|
||||
Supports array of values separated by comma or specified via multiple flags.
|
||||
Empty values are set to default value.
|
||||
-remoteWrite.roundDigits array
|
||||
Round metric values to this number of decimal digits after the point before writing them to remote storage. Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. By default, digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. This option may be used for improving data compression for the stored metrics (default 100)
|
||||
Supports array of values separated by comma or specified via multiple flags.
|
||||
|
||||
Loading…
Reference in New Issue
Block a user