8000 Reload all scrape pools concurrently by prymitive · Pull Request #16595 · prometheus/prometheus · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Reload all scrape pools concurrently #16595

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 9, 2025
Merged

Reload all scrape pools concurrently #16595

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
04ae5d5
Reload all scrape pools concurrently
prymitive May 13, 2025
639fa66
Address PR review feedback
prymitive May 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 38 additions & 20 deletions scrape/manager.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ import (
config_util "github.com/prometheus/common/config"
"github.com/prometheus/common/model"
"github.com/prometheus/common/promslog"
"go.uber.org/atomic"

"github.com/prometheus/prometheus/config"
"github.com/prometheus/prometheus/discovery/targetgroup"
Expand Down Expand Up @@ -284,29 +285,46 @@ func (m *Manager) ApplyConfig(cfg *config.Config) error {
}

// Cleanup and reload pool if the configuration has changed.
var failed bool
for name, sp := range m.scrapePools {
switch cfg, ok := m.scrapeConfigs[name]; {
case !ok:
sp.stop()
delete(m.scrapePools, name)
case !reflect.DeepEqual(sp.config, cfg):
err := sp.reload(cfg)
if err != nil {
m.logger.Error("error reloading scrape pool", "err", err, "scrape_pool", name)
failed = true
}
fallthrough
case ok:
if l, ok := m.scrapeFailureLoggers[cfg.ScrapeFailureLogFile]; ok {
sp.SetScrapeFailureLogger(l)
} else {
sp.logger.Error("No logger found. This is a bug in Prometheus that should be reported upstream.", "scrape_pool", name)
var (
failed atomic.Bool
wg sync.WaitGroup
toDelete sync.Map // Stores the list of names of pools to delete.
)
for poolName, pool := range m.scrapePools {
wg.Add(1)
cfg, ok := m.scrapeConfigs[poolName]
// Reload each scrape pool in a dedicated goroutine so we don't have to wait a long time
// if we have a lot of scrape pools to update.
go func(name string, sp *scrapePool, cfg *config.ScrapeConfig, ok bool) {
defer wg.Done()
switch {
case !ok:
sp.stop()
toDelete.Store(name, struct{}{})
case !reflect.DeepEqual(sp.config, cfg):
err := sp.reload(cfg)
if err != nil {
m.logger.Error("error reloading scrape pool", "err", err, "scrape_pool", name)
failed.Store(true)
}
fallthrough
case ok:
if l, ok := m.scrapeFailureLoggers[cfg.ScrapeFailureLogFile]; ok {
sp.SetScrapeFailureLogger(l)
} else {
sp.logger.Error("No logger found. This is a bug in Prometheus that should be reported upstream.", "scrape_pool", name)
}
}
}
}(poolName, pool, cfg, ok)
}
wg.Wait()

toDelete.Range(func(name, _ any) bool {
delete(m.scrapePools, name.(string))
return true
})

if failed {
if failed.Load() {
return errors.New("failed to apply the new configuration")
}
return nil
Expand Down
Loading
0