Re: e: mon memory issue

2012-09-10 Thread Sławomir Skowron
I try with radosgw and it's reporting very nice output from valgrind, but still nothing from mon. desc: (none) cmd: /usr/bin/ceph-mon -i 0 --pid-file /var/run/ceph/mon.0.pid -c /etc/ceph/ceph.conf -f time_unit: i #--- snapshot=0 #--- time=0 mem_heap_B=0 mem_heap_extra_B=0

Re: Ceph benchmarks / ceph osd tell X bench

2012-09-10 Thread Sébastien Han
Hi Dieter, Simply run a ceph -w and wait for the output. Cheers. On Sat, Sep 8, 2012 at 8:16 PM, Dieter Kasper d.kas...@kabelmail.de wrote: Hi Sébastien, when running 'ceph osd tell $i bench' who/where will I see the results: osd.0 [INF] bench: wrote 1024 MB in blocks of 4096 KB in

messaging/IO/radosbench results

2012-09-10 Thread Mike Ryan
*Disclaimer*: these results are an investigation into potential bottlenecks in RADOS. The test setup is wholly unrealistic, and these numbers SHOULD NOT be used as an indication of the performance of OSDs, messaging, RADOS, or ceph in general. Executive summary: rados bench has some internal

Re: messaging/IO/radosbench results

2012-09-10 Thread Mark Nelson
On 09/10/2012 03:15 PM, Mike Ryan wrote: *Disclaimer*: these results are an investigation into potential bottlenecks in RADOS. The test setup is wholly unrealistic, and these numbers SHOULD NOT be used as an indication of the performance of OSDs, messaging, RADOS, or ceph in general. Executive

possible to recover a deleted RBD?

2012-09-10 Thread Travis Rhoden
I sheepishly must ask -- is there any way to recover a deleted RBD? The RBD was created using the Linux 3.2 kernel client, running 0.48.1. Removed with rbd rm -p rbd name. I expect the answer to be no, but wanted to check for sure! Thanks, Travis -- To unsubscribe from this list: send the

Re: possible to recover a deleted RBD?

2012-09-10 Thread Josh Durgin
On 09/10/2012 01:55 PM, Travis Rhoden wrote: I sheepishly must ask -- is there any way to recover a deleted RBD? The RBD was created using the Linux 3.2 kernel client, running 0.48.1. Removed with rbd rm -p rbd name. I expect the answer to be no, but wanted to check for sure! Thanks,

mds'es stuck in resolve(and one duplicated?)

2012-09-10 Thread Andrew Thompson
Greetings, Has anyone seen this or got ideas on how to fix it? mdsmap e18399: 3/3/3 up {0=b=up:resolve,1=a=up:resolve(laggy or crashed),2=a=up:resolve(laggy or crashed)} Notice that the 2nd and 3rd mds are the same letter(a). I'm not sure how that happened, I'm guessing a typo in my

Re: [PATCH 1/4] rbd: move locking out of rbd_header_set_snap()

2012-09-10 Thread Josh Durgin
Reviewed-by: Josh Durgin josh.dur...@inktank.com On 09/07/2012 07:50 AM, Alex Elder wrote: Move the calls to get the header semaphore out of rbd_header_set_snap() and into its caller. Signed-off-by: Alex Elder el...@inktank.com --- drivers/block/rbd.c |5 ++--- 1 file changed, 2

Re: [PATCH 2/4] rbd: expand lock protection in rbd_add()

2012-09-10 Thread Josh Durgin
Looking closer, I don't think we need to protect this section at all. The device isn't initialized yet, so nothing else can access the rbd_dev-header. It'd be good to have a comment to that effect. Josh On 09/07/2012 07:50 AM, Alex Elder wrote: Expand the region of code in rbd_add() protected

Re: [PATCH 3/4] rbd: don't register snapshots in bus_add_dev()

2012-09-10 Thread Josh Durgin
Reviewed-by: Josh Durgin josh.dur...@inktank.com On 09/07/2012 07:50 AM, Alex Elder wrote: When rbd_bus_add_dev() is called (one spot--in rbd_add()), the rbd image header has not even been read yet. This means that the list of snapshots will be empty at the time of the call. As a result,

Re: [PATCH 4/4] rbd: use snaps list in rbd_snap_by_name()

2012-09-10 Thread Josh Durgin
On 09/07/2012 07:50 AM, Alex Elder wrote: An rbd_dev structure maintains a list of current snapshots that have already been fully initialized. The entries on the list have type struct rbd_snap, and each entry contains a copy of information that's found in the rbd_dev's snapshot context and

Re: [PATCH 1/9] rbd: assign header name later

2012-09-10 Thread Josh Durgin
Reviewed-by: Josh Durgin josh.dur...@inktank.com On 09/07/2012 08:44 AM, Alex Elder wrote: Move the assignment of the header name for an rbd image a bit later, outside rbd_add_parse_args() and into its caller. Signed-off-by: Alex Elder el...@inktank.com --- drivers/block/rbd.c | 22

[PATCH] osd/ReplicatedPG: set truncate_seq when handling CEPH_OSD_OP_APPEND

2012-09-10 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com We need set truncate_seq when redirect the newop to CEPH_OSD_OP_WRITE, otherwise the code handles CEPH_OSD_OP_WRITE may quietly drop the data. Signed-off-by: Yan, Zheng zheng.z@intel.com --- src/osd/ReplicatedPG.cc | 1 + 1 file changed, 1 insertion(+)

does ceph consider the device performance for distributing data?

2012-09-10 Thread sheng qiu
HI, i have a simple question. for distribution workload among OSDs, does ceph do any online modeling for OSDs, i.e. collect the online IO latency and try to distribute more workloads to lower latency OSDs? or only based on capacity/utilization balance? Thanks, Sheng -- Sheng Qiu Texas A M

Re: does ceph consider the device performance for distributing data?

2012-09-10 Thread Sage Weil
On Mon, 10 Sep 2012, sheng qiu wrote: HI, i have a simple question. for distribution workload among OSDs, does ceph do any online modeling for OSDs, i.e. collect the online IO latency and try to distribute more workloads to lower latency OSDs? or only based on capacity/utilization balance?