[Gluster-users] Tons of dht: Found anomalies in (null)

[Artem Russakovskii]

I think there's something else going on here. Our gluster setup is 4x1
replicate, and there should be no such discrepancies and missing unsynced
data. In my experience the replication part of gluster works very well and
all files replicate correctly to all 4 servers.

Yet a single ls could run for 20 minutes and run into thousands of these
log messages. I think this is worth investigating and fixing. Perhaps it's
some super tiny metadata changes, or the files are there, and this metadata
sync is taking up all this extra time and CPU? I'd love to help diagnose
and fix this.

Sincerely,
Artem

--
Founder, Android Police <http://www.androidpolice.com>, APK Mirror
<http://www.apkmirror.com/>, Illogical Robot LLC
beerpla.net | @ArtemR <http://twitter.com/ArtemR>


On Tue, May 19, 2020 at 4:09 AM Gionatan Danti <g.danti at assyoma.it> wrote:

> Il 2020-05-19 13:07 Susant Palai ha scritto:
> > This can happen when a server goes down (reboot, crash, network
> > partition) during a fop execution. Once the brick is back up, dht will
> > heal the entry so that operation goes smoothly.
> > If there is a resultant error, it should have been logged in the
> > client log.
>
> Understood.
> Thank you for the prompt reply.
>
> --
> Danti Gionatan
> Supporto Tecnico
> Assyoma S.r.l. - www.assyoma.it [1]
> email: g.danti at assyoma.it - info at assyoma.it
> GPG public key ID: FF5F32A8
> ________
>
>
>
> Community Meeting Calendar:
>
> Schedule -
> Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC
> Bridge: https://bluejeans.com/441850968
>
> Gluster-users mailing list
> Gluster-users at gluster.org
> https://lists.gluster.org/mailman/listinfo/gluster-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20200519/4478e507/attachment.html>