Kiu/Node_Exporter
Kiu/Node_Exporter
1
0
Fork 0
mirror of https://github.com/prometheus/node_exporter.git synced 2024-12-03 15:31:05 +01:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Revert "filesystem: fix mountTimeout not working issue (#2903)" (#2932)

Browse Source 
This reverts commit 9f1f791ac2.

Signed-off-by: Ben Kochie <superq@gmail.com>
This commit is contained in:
Ben Kochie 2024-02-20 10:31:08 +01:00 committed by GitHub
parent 12192475c8
commit 3a02ab1cf0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
collector/filesystem_linux.go
View File

@ -123,8 +123,16 @@ 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 {
labels.deviceError = err.Error()
level.Debug(c.logger).Log("msg", "Error on statfs() system call", "rootfs", rootfsFilePath(labels.mountPoint), "err", err)
@ -155,29 +163,17 @@ 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()
}
}