Re: Rebalancing

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]


I’ve at least verified on the Jewel clusters that using `ceph osd reweight` would reset the weight back to 1 when that respective OSD is marked OUT and IN.





From: Dan Van Der Ster <daniel.vanderster@xxxxxxx>
Date: Thursday, 16 November 2017 at 2:24 PM
To: Pavan Rallabhandi <PRallabhandi@xxxxxxxxxxxxxxx>
Cc: "ceph-large@xxxxxxxxxxxxxx" <ceph-large@xxxxxxxxxxxxxx>
Subject: EXT: Re: [Ceph-large] Rebalancing



On 16 Nov 2017, at 09:17, Pavan Rallabhandi <PRallabhandi@xxxxxxxxxxxxxxx> wrote:


is it still not a problem (as the OSD weights would be reset to 1) if those reweighted OSDs go OUT of the cluster and later get marked IN?


This has never posed a problem in any of our clusters. I can't say if that's because we almost never have osds going out then back in, or if it's because that issue (forgetting the reweight) was fixed.


-- dan

Ceph-large mailing list

[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [XFS]

  Powered by Linux