RepoMirrors
/
node_exporter
mirror of https://github.com/prometheus/node_exporter
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

filesystem: fix mountTimeout not working issue (#2903) 

Signed-off-by: DongWei <jiangxuege@hotmail.com>
This commit is contained in:
DongWei 2024-02-14 22:36:16 +08:00 committed by GitHub
parent 6d18ce7bca
commit 9f1f791ac2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
collector/filesystem_linux.go
View File

@ -122,16 +122,8 @@ func (c *filesystemCollector) processStat(labels filesystemLabels) filesystemSta
buf := new(unix.Statfs_t)
err := unix.Statfs(rootfsFilePath(labels.mountPoint), buf)
stuckMountsMtx.Lock()
close(success)
// If the mount has been marked as stuck, unmark it and log it's recovery.
if _, ok := stuckMounts[labels.mountPoint]; ok {
level.Debug(c.logger).Log("msg", "Mount point has recovered, monitoring will resume", "mountpoint", labels.mountPoint)
delete(stuckMounts, labels.mountPoint)
}
stuckMountsMtx.Unlock()
if err != nil {
level.Debug(c.logger).Log("msg", "Error on statfs() system call", "rootfs", rootfsFilePath(labels.mountPoint), "err", err)
return filesystemStats{
@ -161,17 +153,29 @@ func stuckMountWatcher(mountPoint string, success chan struct{}, logger log.Logg
select {
case <-success:
// Success
// If the mount has been marked as stuck, unmark it and log it's recovery.
stuckMountsMtx.Lock()
defer stuckMountsMtx.Unlock()
if _, ok := stuckMounts[mountPoint]; ok {
level.Debug(logger).Log("msg", "Mount point has recovered, monitoring will resume", "mountpoint", mountPoint)
delete(stuckMounts, mountPoint)
}
case <-mountCheckTimer.C:
// Timed out, mark mount as stuck
stuckMountsMtx.Lock()
defer stuckMountsMtx.Unlock()
select {
case <-success:
// Success came in just after the timeout was reached, don't label the mount as stuck
// If the mount has been marked as stuck, unmark it and log it's recovery.
if _, ok := stuckMounts[mountPoint]; ok {
level.Debug(logger).Log("msg", "Mount point has recovered, monitoring will resume", "mountpoint", mountPoint)
delete(stuckMounts, mountPoint)
}
default:
level.Debug(logger).Log("msg", "Mount point timed out, it is being labeled as stuck and will not be monitored", "mountpoint", mountPoint)
stuckMounts[mountPoint] = struct{}{}
}
stuckMountsMtx.Unlock()
}
}