Re: infernalis build package on debian jessie : dh_install: ceph missing files (usr/lib/libos_tp.so.*), aborting

Sorry,my fault, I had an old --without-lttng flag in my build packages. - Mail original - De: "aderumier" À: "ceph-devel" Envoyé: Mardi 10 Novembre 2015 15:06:19 Objet: infernalis build package on debian jessie : dh_install: ceph missing

data-at-rest compression

Hi All, a while ago we had some conversations here about adding compression support for EC pools. Here is corresponding pull request implementing this feature: https://github.com/ceph/ceph/pull/6524/commits Appropriate blueprint is at:

Backlog for the Ceph tracker

Hi Sam, I crafted a custom query that could be used as a replacement for the backlog plugin http://tracker.ceph.com/projects/ceph/issues?query_id=86 It displays issues that are features or tasks, grouped by target version and ordered by priority. I also created a v10.0.0 version so we can

why ShardedWQ in osd using smart pointer for PG?

hi, all: op_wq is declared as ShardedThreadPool::ShardedWQ < pair > _wq. I do not know why we should use PGRef in this? Because the overhead of the smart pointer is not small. Maybe the raw point PG* is also OK? If op_wq is changed to

Re: Backlog for the Ceph tracker

But http://tracker.ceph.com/projects/ceph/agile_versions looks better :-) On 10/11/2015 16:28, Loic Dachary wrote: > Hi Sam, > > I crafted a custom query that could be used as a replacement for the backlog > plugin > >http://tracker.ceph.com/projects/ceph/issues?query_id=86 > > It

Re: Backlog for the Ceph tracker

On 10/11/2015 16:34, Loic Dachary wrote: > But http://tracker.ceph.com/projects/ceph/agile_versions looks better :-) It appears to be a crippled version of a proprietary product http://www.redminecrm.com/projects/agile/pages/last My vote would be to de-install it since it is even less

Re: why ShardedWQ in osd using smart pointer for PG?

On Tue, Nov 10, 2015 at 7:19 AM, 池信泽 wrote: > hi, all: > > op_wq is declared as ShardedThreadPool::ShardedWQ < pair OpRequestRef> > _wq. I do not know why we should use PGRef in this? > > Because the overhead of the smart pointer is not small. Maybe the >

Preparing infernalis v9.2.1

Hi Abhishek, I created the issue to track the progress of infernalis v9.2.1 at http://tracker.ceph.com/issues/13750 and assigned it to you. There are a dozen issues waiting to be backported and another dozen waiting to be tested in an integration branch. Good luck with driving your first

Re: [ceph-users] Permanent MDS restarting under load

On Tue, Nov 10, 2015 at 6:32 AM, Oleksandr Natalenko wrote: > Hello. > > We have CephFS deployed over Ceph cluster (0.94.5). > > We experience constant MDS restarting under high IOPS workload (e.g. > rsyncing lots of small mailboxes from another storage to CephFS using >

non-fast-forward merges prevented for some branches in GitHub

GitHub.com now has an option in its UI for users to "protect" certain branches. I've enabled the "Disable force-pushes to this branch and prevent it from being deleted" setting for the following repos and branches: ceph.git and ceph-qa-suite.git: - "master" - "jewel" - "infernalis" - "hammer" -

Re: why ShardedWQ in osd using smart pointer for PG?

I wonder if we want to keep the PG from going out of scope at an inopportune time, why snap_trim_queue and scrub_queue declared as xlist instead of xlist? 2015-11-11 2:28 GMT+08:00 Gregory Farnum : > On Tue, Nov 10, 2015 at 7:19 AM, 池信泽 wrote: >> hi,

Re: why ShardedWQ in osd using smart pointer for PG?

The xlist has means of efficiently removing entries from a list. I think you'll find those in the path where we start tearing down a PG, and membership on this list is a bit different from membership in the ShardedThreadPool. It's all about the particulars of each design, and I don't have that in

Re: [ceph-users] v9.2.0 Infernalis released

On Sun, Nov 8, 2015 at 10:41 PM, Alexandre DERUMIER wrote: > Hi, > > debian repository seem to miss librbd1 package for debian jessie > > http://download.ceph.com/debian-infernalis/pool/main/c/ceph/ > > (ubuntu trusty librbd1 is present) This is now fixed and should be now

[CEPH][Crush][Tunables] issue when updating tunables

Hi all, Context: Firefly 0.80.9 Ubuntu 14.04.1 Almost a production platform in an openstack environment 176 OSD (SAS and SSD), 2 crushmap-oriented storage classes , 8 servers in 2 rooms, 3 monitors on openstack controllers Usage: Rados Gateway for object service and RBD as back-end for Cinder

Re: How to modify affiliation?

Hi, You can submit a patch to https://github.com/ceph/ceph/blob/master/.organizationmap Cheers On 10/11/2015 09:21, chen kael wrote: > Hi,ceph-dev > who can tell me how to modify my affiliation? > Thanks! > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the

Re: [CEPH][Crush][Tunables] issue when updating tunables

On Tue, 10 Nov 2015, ghislain.cheval...@orange.com wrote: > Hi all, > > Context: > Firefly 0.80.9 > Ubuntu 14.04.1 > Almost a production platform in an openstack environment > 176 OSD (SAS and SSD), 2 crushmap-oriented storage classes , 8 servers in 2 > rooms, 3 monitors on openstack

How to modify affiliation?

Hi,ceph-dev who can tell me how to modify my affiliation? Thanks! -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: NIC with Erasure offload feature support and Ceph

03-Nov-15 18:07, Gregory Farnum пишет: On Tue, Nov 3, 2015 at 3:15 AM, Mike wrote: Hello! In our project we planing build a petabayte cluster with Erasure pool. Also we looking on Mellanox ConnectX-4 Lx EN Cards/ConnectX-4 EN Cards for using its a offloading erasure

why keep and update rollback info for ReplicatedPG?

Hi, all As I know, rollback is designed for ec-backend to rollback the partial committed transaction like append, stash and attrs. So why do we need to keep and update (can_rollback_to, rollback_info_trimmed_to) every time in _write_log() for ReplicatedBackend? Or it is related to other issues?

Re: a home for backport snippets

Hi, The new snippets home is at https://pypi.python.org/pypi/ceph-workbench and http://ceph-workbench.dachary.org/root/ceph-workbench. The first snippet was merged by Nathan yesterday[1], the backport documentation updated accordingly[2], and I used it after merging half a dozen hammer

Re: [ceph-users] Permanent MDS restarting under load

10.11.2015 22:38, Gregory Farnum wrote: Which requests are they? Are these MDS operations or OSD ones? Those requests appeared in ceph -w output and are the follows: https://gist.github.com/5045336f6fb7d532138f Is that correct that there are OSD operations blocked? osd.3 is one of data

disabling buffer::raw crc cache

Hello, Guys! While running CPU bound 4k block workload, I found that disabling crc cache in the buffer::raw gives around 7% performance improvement. If there is no strong use case which benefit from that cache, we would remove it entirely, otherwise conditionally enable it based on the object

Permanent MDS restarting under load

Hello. We have CephFS deployed over Ceph cluster (0.94.5). We experience constant MDS restarting under high IOPS workload (e.g. rsyncing lots of small mailboxes from another storage to CephFS using ceph-fuse client). First, cluster health goes to HEALTH_WARN state with the following

infernalis build package on debian jessie : dh_install: ceph missing files (usr/lib/libos_tp.so.*), aborting

Hi, I'm trying to build infernalis packages on debian jessie, and I have this error on package build dh_install: ceph missing files (usr/lib/libos_tp.so.*), aborting I think it's related to lltng change from here https://github.com/ceph/ceph/pull/6135 Maybe is it missing an option in