Hi Chris,
The problem you reported is quite common in small Ceph clusters.
I suggest tuning the following in /etc/pve/ceph.conf in [osd] section:
osd max backfills = 1
osd recovery max active = 1
This should make the recovery "slower" and thus should make VMs
responsive. Recovery will still be noticeable though.
Cheers
Eneko
On 19/12/14 12:36, Chris Murray wrote:
That would make sense. Thank you Dietmar, I'll give them a try.
Sent from my HTC
----- Reply message -----
From: "Dietmar Maurer" <[email protected]>
To: "[email protected]" <[email protected]>, "Chris Murray"
<[email protected]>
Subject: [PVE-User] CEPH: How to remove an OSD without experiencing inactive
placement groups
Date: Fri, Dec 19, 2014 10:48
I understand this is an emerging technology with active development;
just want to check I'm not missing anything obvious or haven't
fundamentally misunderstood how it works. I didn't expect the loss of
1/9 of the devices in the pool to cease IO, especially when every object
exists three times.
This looks like a crush related problem to me. crush maps sometime have problems
with
small setups (also see crush tunables). But I suggest to ask that on the ceph
list.
-----
No virus found in this message.
Checked by AVG - www.avg.com
Version: 2015.0.5577 / Virus Database: 4253/8761 - Release Date: 12/18/14
_______________________________________________
pve-user mailing list
[email protected]
http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user
--
Zuzendari Teknikoa / Director Técnico
Binovo IT Human Project, S.L.
Telf. 943575997
943493611
Astigarraga bidea 2, planta 6 dcha., ofi. 3-2; 20180 Oiartzun (Gipuzkoa)
www.binovo.es
_______________________________________________
pve-user mailing list
[email protected]
http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user
