Open ThomasWaldmann opened 2 years ago
For the record I experienced similar slowdowns on NFS, with many previous releases which got some fixes in the later 1.1 releases, and again with borg 1.2, this was discussed at https://github.com/borgbackup/borg/issues/4498. See also https://github.com/borgbackup/borg/issues/3039. Thanks for looking at it!
Note: debugging this on a specific system right now, keeping some notes here.
Is this a BUG / ISSUE report or a QUESTION?
Unclear yet.
System information. For client/server mode post info for both machines.
Your borg version (borg -V).
1.1.17
Operating system (distribution) and version.
Redhat or rh-derivate.
Hardware / network configuration, and filesystems used.
6(?) cores, 32GB RAM
How much data is handled by borg?
TBD
Full borg commandline that lead to the problem (leave away excludes and passwords)
Roughly this:
Describe the problem you're observing.
Sometimes backup slows down from the usual 100..1000 unchanged files per second (status U) to only a few per second.
Usually when run as a nightly cronjob. When trying to reproduce interactively, it is hard to reproduce.
Analysis / Suspicions
When processing lots of unchanged files, borg is doing:
stat
call on the src file to determine ctime,size for change detectionU
status), it will not need to read the file contents as they did not change and are already in the repo. thus there is not a lot of data volume read from the source neither there is a lot of data written to the repo.--nobsdflags --noacls --noxattrs
.--numeric-owner
(borg 1.1) or--numeric-ids
(borg > 1.1.x).Other stuff coming to mind as difference between cron use and interactive use:
Notes
Added now
--numeric-owner --noatime --noacls --noxattrs --nobsdflags
to try if this resolves the issue.Also considering monitoring with
atop
and doing a timestamped strace when it's running slowly.