Re: Help with inconsistent pg on EC pool, v9.0.2

[David Zafman <dzafman@xxxxxxxxxx>]

I don't know about removing the OSD from the CRUSH map.  That seems like 
overkill to me.

I just realized a possible better way.  It would have been to take OSD 
down not out.  Remove the ECs PG with the bad chunk.  Bring it up again 
and let recovery repair just the single missing PG on the single OSD 
with no other disruption.

David

On 8/28/15 11:28 AM, Aaron Ten Clay wrote:
> Thanks for the tip, David. I've marked osd.21 down and out and will wait
> for recovery. I've never had success manually manipulating the OSD contents
> - I assume I can achieve the same result by removing osd.21 from the CRUSH
> map, "ceph osd rm 21", then recreating it from scratch as though I'd lost a
> disk?
>
> -Aaron
>
> On Fri, Aug 28, 2015 at 11:17 AM, David Zafman <dzafman@xxxxxxxxxx> wrote:
>
> > Without my latest branch which hasn't merged yet, you can't repair an EC
> > pg in the situation that the shard with a bad checksum is in the first k
> > chunks.
> >
> > A way to fix it would be to take that osd down/out and let recovery
> > regenerate the chunk.  Remove the pg from the osd (ceph-objectstore-tool)
> > and then you can bring the osd back up/in.
> >
> > David
> >
> >
> > On 8/28/15 11:06 AM, Samuel Just wrote:
> >
> > > David, does this look familiar?
> > > -Sam
> > >
> > > On Fri, Aug 28, 2015 at 10:43 AM, Aaron Ten Clay <aarontc@xxxxxxxxxxx>
> > > wrote:
> > >
> > > > Hi Cephers,
> > > >
> > > > I'm trying to resolve an inconsistent pg on an erasure-coded pool,
> > > > running
> > > > Ceph 9.0.2. I can't seem to get Ceph to run a repair or even deep-scrub
> > > > the
> > > > pg again. Here's the background, with my attempted resolution steps
> > > > below.
> > > > Hopefully someone can steer me in the right direction. Thanks in advance!
> > > >
> > > > Current state:
> > > > # ceph health detail
> > > > HEALTH_ERR 1 pgs inconsistent; 1 scrub errors; noout flag(s) set
> > > > pg 2.36 is active+clean+inconsistent, acting
> > > > [1,21,12,9,0,10,14,7,18,20,5,4,22,16]
> > > > 1 scrub errors
> > > > noout flag(s) set
> > > >
> > > > I started by looking at the log file for osd.1, where I found the cause
> > > > of
> > > > the inconsistent report:
> > > >
> > > > 2015-08-24 00:43:10.391621 7f09fcff9700  0 log_channel(cluster) log
> > > > [INF] :
> > > > 2.36 deep-scrub starts
> > > > 2015-08-24 01:54:59.933532 7f09fcff9700 -1 log_channel(cluster) log
> > > > [ERR] :
> > > > 2.36s0 shard 21(1): soid 576340b6/10000005990.00000199/head//2 candidate
> > > > had
> > > > a read error
> > > > 2015-08-24 02:34:41.380740 7f09fcff9700 -1 log_channel(cluster) log
> > > > [ERR] :
> > > > 2.36s0 deep-scrub 0 missing, 1 inconsistent objects
> > > > 2015-08-24 02:34:41.380757 7f09fcff9700 -1 log_channel(cluster) log
> > > > [ERR] :
> > > > 2.36 deep-scrub 1 errors
> > > >
> > > > I checked osd.21, where this report appears:
> > > >
> > > > 2015-08-24 01:54:56.477020 7f707cbd4700  0 osd.21 pg_epoch: 31958
> > > > pg[2.36s1(
> > > > v 31957'43013 (7132'39997,31957'43013] local-les=31951 n=34556 ec=136
> > > > les/c
> > > > 31951/31954 31945/31945/31924) [1,21,12,9,0,10,14,7,18,20,5,4,22,16] r=1
> > > > lpr=31945 pi=1131-31944/7827 luod=0'0 crt=31957'43011 active] _scan_list
> > > > 576340b6/10000005990.00000199/head//2 got incorrect hash on read
> > > >
> > > > So, based upon the ceph documentation, I thought I could repair the pg by
> > > > executing "ceph pg repair 2.36". When I run this, while watching the mon
> > > > log, I see the command dispatch:
> > > >
> > > > 2015-08-28 10:14:17.964017 mon.0 [INF] from='client.?
> > > > 10.42.5.61:0/1002181'
> > > > entity='client.admin' cmd=[{"prefix": "pg repair", "pgid": "2.36"}]:
> > > > dispatch
> > > >
> > > > But I never see a "finish" in the mon log, like most ceph commands
> > > > return.
> > > > (Not sure if I should expect to see a finish, just noting it doesn't
> > > > occur.)
> > > >
> > > > Also, tailing the logs for any OSD in the acting set for pg 2.36, I never
> > > > see anything about a repair. The same case holds when I try "ceph pg 2.36
> > > > deep-scrub" - command dispatched, but none of the OSDs care. In the past
> > > > on
> > > > other clusters, I've seen "[INF] : pg.id repair starts" messages in the
> > > > OSD
> > > > log after executing "ceph pg nn.yy repair".
> > > >
> > > > Further confusing me, I do see osd.1 start and finish other pg
> > > > deep-scrubs,
> > > > before and after executing "ceph pg 2.36 deep-scrub".
> > > >
> > > > I know EC pools are special in several ways, but nothing in the Ceph
> > > > manual
> > > > seems to indicate I can't deep-scrub or repair pgs in an EC pool...
> > > >
> > > > Thanks for reading and any suggestions. I'm happy to provide complete log
> > > > files or more details if I've left out any information that could be
> > > > helpful.
> > > >
> > > > ceph -s: http://hastebin.com/xetohugibi
> > > > ceph pg dump: http://hastebin.com/bijehoheve
> > > > ceph -v: ceph version 9.0.2 (be422c8f5b494c77ebcf0f7b95e5d728ecacb7f0)
> > > > ceph osd dump: http://hastebin.com/fitajuzeca
> > > >
> > > > -Aaron
> > > >
> > > >
> > > > _______________________________________________
> > > > ceph-users mailing list
> > > > ceph-users@xxxxxxxxxxxxxx
> > > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com