how to replace broken mon?

2013-09-04 Thread bernhard glomm
Hi all, after some days of successful creating and destroying rbd's, snapshots, clones and migrating formats all of a sudden one of the monitors doesn't work anymore. I tried to remove and re-add the monitor from the cluster, but that doesn't seem to work either. Here's the situation: I liked

Re: [PATCH 1/2] ceph: Implement readv/preadv for sync operation.

2013-09-04 Thread Yan, Zheng
On 09/03/2013 04:52 PM, majianpeng wrote: For readv/preadv sync-operatoin, ceph only do the first iov. It don't think other iovs.Now implement this. Signed-off-by: Jianpeng Ma majianp...@gmail.com --- fs/ceph/file.c | 175 - 1 file

Re: [PATCH 2/2] ceph: Implement writev/pwritev for sync operation.

2013-09-04 Thread Yan, Zheng
Hi, Thank you for the patch. On 09/03/2013 04:52 PM, majianpeng wrote: For writev/pwritev sync-operatoin, ceph only do the first iov. It don't think other iovs.Now implement this. I divided the write-sync-operation into two functions.One for direct-write,other for none-direct-sync-write.This

Re: [PATCH 2/2] ceph: Implement writev/pwritev for sync operation.

2013-09-04 Thread Yan, Zheng
Hi, Thank you for the patch. On 09/03/2013 04:52 PM, majianpeng wrote: For writev/pwritev sync-operatoin, ceph only do the first iov. It don't think other iovs.Now implement this. I divided the write-sync-operation into two functions.One for direct-write,other for none-direct-sync-write.This

Re: Add Metavariable $imagename

2013-09-04 Thread Mark Nelson
On 09/04/2013 09:46 AM, Mike Dawson wrote: There are currently a few metavariables available for use in ceph.conf: http://ceph.com/docs/master/rados/configuration/ceph-conf/#metavariables In addition to those listed in that document, $pid was added in Bobtail. That allows me to get RBD admin

Add Metavariable $imagename

2013-09-04 Thread Mike Dawson
There are currently a few metavariables available for use in ceph.conf: http://ceph.com/docs/master/rados/configuration/ceph-conf/#metavariables In addition to those listed in that document, $pid was added in Bobtail. That allows me to get RBD admin sockets for libvirt/qemu guests by

Re: Pages still marked with private_2

2013-09-04 Thread David Howells
Milosz Tanski mil...@adfin.com wrote: Am I on the right path here? I think you are! :-) Sorry for not getting back to you earlier, but August has been somewhat compressed due to PTO. David -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to

Re: how to replace broken mon?

2013-09-04 Thread Sage Weil
On Wed, 4 Sep 2013, bernhard glomm wrote: Hi all, after some days of successful creating and destroying rbd's, snapshots, clones and migrating formats all of a sudden one of the monitors doesn't work anymore. I tried to remove and re-add the monitor from the cluster, but that doesn't

Re: Add Metavariable $imagename

2013-09-04 Thread Mike Dawson
Thanks for the feature request Mark! To illustrate where my understanding ends, here is a patch to stub in this functionality: From 137ebc2d5326ca710a5e99e2899fd851b02c10f7 Mon Sep 17 00:00:00 2001 From: Mike Dawson mdaw...@gammacode.com Date: Wed, 4 Sep 2013 11:39:05 -0400 Subject: [PATCH]

[GIT PULL] Ceph updates for 3.12 (part 1)

2013-09-04 Thread Sage Weil
Hi Linus, Please pull this first batch of Ceph updates for 3.12 from git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git for-linus This first batch include several important RBD bug fixes (more coming in part 2), hole punch support, several different cleanups in the page cache

Re: [PATCHv4 0/5] ceph: persistent caching with fscache

2013-09-04 Thread Sage Weil
Hi David! On Wed, 4 Sep 2013, David Howells wrote: Sage Weil s...@inktank.com wrote: David, are the fscache patches here ready for the next merge window? Do you have a preference for whose tree they go through? There's only one problem - patch 1 needs to come _after_ patch 2 to avoid

Re: [PATCHv4 0/5] ceph: persistent caching with fscache

2013-09-04 Thread David Howells
Sage Weil s...@inktank.com wrote: David, are the fscache patches here ready for the next merge window? Do you have a preference for whose tree they go through? There's only one problem - patch 1 needs to come _after_ patch 2 to avoid breaking git bisect. Plus these patches 2 and 4 extend

Re: Add Metavariable $imagename

2013-09-04 Thread Sage Weil
Hi Mike, On Wed, 4 Sep 2013, Mike Dawson wrote: Thanks for the feature request Mark! To illustrate where my understanding ends, here is a patch to stub in this functionality: From 137ebc2d5326ca710a5e99e2899fd851b02c10f7 Mon Sep 17 00:00:00 2001 From: Mike Dawson mdaw...@gammacode.com

Re: [PATCHv4 0/5] ceph: persistent caching with fscache

2013-09-04 Thread Sage Weil
On Wed, 4 Sep 2013, Sage Weil wrote: Hi David! On Wed, 4 Sep 2013, David Howells wrote: Sage Weil s...@inktank.com wrote: David, are the fscache patches here ready for the next merge window? Do you have a preference for whose tree they go through? There's only one problem -

Re: [PATCH 2/5] new fscache interface to check cache consistency

2013-09-04 Thread Milosz Tanski
David, If the cache is withdrawn and we're starting anew I would consider that to okay. I would consider an empty page cache for a cookie to be consistent since there's nothing stale that I can read. Unless there's another synchronization issue that I'm missing in fscache. Thanks, - Milosz On

Re: [PATCH 2/5] new fscache interface to check cache consistency

2013-09-04 Thread David Howells
Milosz Tanski mil...@adfin.com wrote: If the cache is withdrawn and we're starting anew I would consider that to okay. I would consider an empty page cache for a cookie to be consistent since there's nothing stale that I can read. Unless there's another synchronization issue that I'm missing

Re: [PATCH 2/5] new fscache interface to check cache consistency

2013-09-04 Thread Milosz Tanski
David, Is it as simple as stick a mutex at the top of the __fscache_check_consistency function before we try to find the object? This code should be called from a context that can sleep, in the Ceph code we call it from a delayed work queue (revalidate queue). -- Milosz On Wed, Sep 4, 2013 at

v0.68 released

2013-09-04 Thread Sage Weil
Our first development release after Dumpling has arrived! It includes a lot of small cleanups and documentation improvements, as well as the first blueprint from the Emperor CDS to land (support for ZFS). There are also new sample implementations for RADOS classes (cls_hello) and a sample

Re: [PATCH 2/5] new fscache interface to check cache consistency

2013-09-04 Thread Milosz Tanski
David, Is there anyway I can call you at (at your desk) during EST hours. I'd like to talk this part through since I think we're going a bit in circles. I'd like to get this fixed so we can submit the fscache for Ceph code for the upstream kernel in the merge window. Best, -- Milosz On Wed, Sep

Re: wip-libcephfs-rebased-v65 ready for pull

2013-09-04 Thread Sage Weil
Hi Matt, I've just rebased wip-libcephfs on master and will be kicking off some tests shortly. Please take a look at let me know if there is anything missing or if you've run into any issues since this branch was prepared. If everything looks okay I'd like to pull it in this week. Thanks!

Re: [ceph-users] v0.68 released

2013-09-04 Thread Dan Mick
Where are you looking? ceph.com/debian-testing has 0.68 On 09/04/2013 07:12 PM, 이주헌 wrote: Debian/Ubuntu packages is still 0.67.2. -- Dan Mick, Filesystem Engineering Inktank Storage, Inc. http://inktank.com Ceph docs: http://ceph.com/docs -- To unsubscribe from this list: send the line

Ceph-deploy (git from today) fails to create osd on host that does not have a mon

2013-09-04 Thread Mark Kirkwood
Setup: hosts: ceph1, ceph2 Command steps: $ ceph-deploy new ceph1 $ ceph-deploy mon create ceph1 $ ceph-deploy gatherkeys ceph1 $ ceph-deploy disk zap ceph1:/dev/vdb $ ceph-deploy disk zap ceph1:/dev/vdc $ ceph-deploy disk zap ceph2:/dev/vdb $ ceph-deploy disk zap ceph2:/dev/vdc $ ceph-deploy