I use noatime,nodiratime on my BackupPC store (ext4). Since in the steady-state most BackupPC operations on the pool should be reads, it should definitely make a difference. However, I don't have benchmark data to show how much.
Craig On Thu, Apr 11, 2019 at 3:28 PM <backu...@kosowsky.org> wrote: > Made a real difference when running BackupPC_migrateV3toV4 > > Now relatime still updates the atime when files change or when atime > is older than 24 hours (so presumably each file atime is updated at > least once if nothing else was done for 24 hours before the migration) > > Would noatime make migrations materially faster by eliminating at > least the first atime write? > > > _______________________________________________ > BackupPC-users mailing list > BackupPC-users@lists.sourceforge.net > List: https://lists.sourceforge.net/lists/listinfo/backuppc-users > Wiki: http://backuppc.wiki.sourceforge.net > Project: http://backuppc.sourceforge.net/ >
_______________________________________________ BackupPC-users mailing list BackupPC-users@lists.sourceforge.net List: https://lists.sourceforge.net/lists/listinfo/backuppc-users Wiki: http://backuppc.wiki.sourceforge.net Project: http://backuppc.sourceforge.net/
