[Gluster-users] Very slow ls

[Peter B.]

You mention "cached results".
Is there any information about possible tweaks (e.g. caching, smb-modules,
etc) regarding directory listings in the GlusterFS docs?

At our institution (A/V archive), the speed of our current GlusterFS
installation (v3.4) has already received some complaints. So I'm also very
interested in anything possible to improve this.


Thanks in advance,
Pb


Am Mi, 5.08.2015, 20:02 schrieb Ben Turner:
> I am seeing a pretty big perf regression with ls -l on the 3.7 branch:
>
> https://bugzilla.redhat.com/show_bug.cgi?id=1250241
>
> Even when running on cached results I am not seeing what I saw on 3.6:
>
> total threads = 32
> total files = 316100
>  98.78% of requested files processed, minimum is  70.00
> 20.056840 sec elapsed time
> 15760.209342 files/sec
>
> In my 3.6 tests I was seeing 20k+ files per second uncached.
>
> -b