Skip to content
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.

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

Revert "Fix filesystem mountTimeout not working issue" #2932

Merged
merged 1 commit into from
Feb 20, 2024
Merged
Changes from all commits
Commits
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
22 changes: 9 additions & 13 deletions collector/filesystem_linux.go
Original file line number Diff line number Diff line change
Expand Up @@ -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)
Expand Down Expand Up @@ -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()
}
}

Expand Down
Loading