[PATCH] ceph: Fix oops when handling mdsmap that decreases max_mds

2012-09-20 Thread Yan, Zheng
From: "Yan, Zheng" When i >= newmap->m_max_mds, ceph_mdsmap_get_addr(newmap, i) return NULL. Passing NULL to memcmp() triggers oops. Signed-off-by: Yan, Zheng --- fs/ceph/mds_client.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_clien

ceph 0.48.2

2012-09-20 Thread Smart Weblications GmbH - Florian Wiessner
Hi, i noticed there is 0.48.2 ready - why isn't there any changelog or info on the website? ceph 0.48.2argonaut-1~bpo60+1 -- Mit freundlichen Grüßen, Florian Wiessner Smart Weblications GmbH Martinsberger Str. 1 D-95119 Naila fon.: +49 9282 9638 200 fax.: +49 9282 9638 205 24/7: +49 900 1

mds stuck in replay state

2012-09-20 Thread Tren Blackburn
Hi List; Still rsyncing the same data as the last ticket. However the mds for some reason is stuck in "replay" state. I've tried restarting the mds process to get it to fail over to another node, but regardless of which node is the active mds, it still is in replay state. Not sure how to diagnose

Re: ceph 0.48.2

2012-09-20 Thread Sage Weil
On Thu, 20 Sep 2012, Smart Weblications GmbH - Florian Wiessner wrote: > Hi, > > > i noticed there is 0.48.2 ready - why isn't there any changelog or info on the > website? The release notes are up now. I pushed the final builds from the airport last night along with the tag to git, but should

v0.48.2 argonaut update released

2012-09-20 Thread Sage Weil
Hi everyone, Another update to the stable "argonaut" series has been released. This fixes a few important bugs in rbd and radosgw and includes a series of changes to upstart and deployment related scripts that will allow the upcoming 'ceph-deploy' tool to work with the argonaut release. Upgra

Re: Memory usage of ceph-mds

2012-09-20 Thread Tren Blackburn
On Wed, Sep 19, 2012 at 4:30 PM, Sage Weil wrote: > On Wed, 19 Sep 2012, Tren Blackburn wrote: >> On Wed, Sep 19, 2012 at 2:45 PM, Tren Blackburn wrote: >> > On Wed, Sep 19, 2012 at 2:33 PM, Sage Weil wrote: >> >> On Wed, 19 Sep 2012, Tren Blackburn wrote: >> >>> On Wed, Sep 19, 2012 at 2:12 PM,

Re: [PATCH] mds: Clean up finished two phase commits

2012-09-20 Thread Sage Weil
Applied, thanks! sage On Wed, 19 Sep 2012, Yan, Zheng wrote: > From: "Yan, Zheng" > > When handling master request with slaves, the mds could crash > after receiving all slaves' commit acknowledgement, but before > journalling the ECommitted. Current MDS recovery code does not > handle this c

Re: [PATCH] ceph: Fix oops when handling mdsmap that decreases max_mds

2012-09-20 Thread Sage Weil
Applied, thanks! sage On Thu, 20 Sep 2012, Yan, Zheng wrote: > From: "Yan, Zheng" > > When i >= newmap->m_max_mds, ceph_mdsmap_get_addr(newmap, i) return > NULL. Passing NULL to memcmp() triggers oops. > > Signed-off-by: Yan, Zheng > --- > fs/ceph/mds_client.c | 3 ++- > 1 file changed, 2 i

Re: Why does mkcephfs take approximately 30 seconds per osd on ceph 0.51?

2012-09-20 Thread Tren Blackburn
On Wed, Sep 19, 2012 at 3:38 PM, Josh Durgin wrote: > On 09/18/2012 04:47 PM, Tren Blackburn wrote: >> >> On Tue, Sep 18, 2012 at 4:32 PM, Josh Durgin >> wrote: >>> >>> On 09/18/2012 02:23 PM, Tren Blackburn wrote: On Tue, Sep 18, 2012 at 2:11 PM, Tren Blackburn wrote: >