Re: [ceph-users] re: Upgrade 0.80.5 to 0.80.8 --the VM's read requestbecome too slow

2015-02-21 Thread Alexandre DERUMIER
so maybe can sure this problem is cause from 0.80.8 That's a good news if you are sure that it's come from 0.80.8 The applied commits between 0.80.7 and 0.80.8 is here: https://github.com/ceph/ceph/compare/v0.80.7...v0.80.8 Now, we need to find which of them is for librados/librbd. -

Re: [ceph-users] HELP FOR CEPH SOURCE CODE

2015-02-21 Thread Stefan Priebe - Profihost AG
This will be very difficult with a broken keyboard! Am 21.02.2015 um 12:16 schrieb khyati joshi kpjosh...@gmail.com: I WANT TO ADD 2 NEW FEATURES IN CEPH NAMELY GARBAGE COLLECTION AND REPLICA BALANCING.BUT I DONT KNOW WHICH SOURCE CODE TO CHANGE AND HOW? I WANT TO KNOW EXACT AND STEPWISE

[ceph-users] HELP FOR CEPH SOURCE CODE

2015-02-21 Thread khyati joshi
I WANT TO ADD 2 NEW FEATURES IN CEPH NAMELY GARBAGE COLLECTION AND REPLICA BALANCING.BUT I DONT KNOW WHICH SOURCE CODE TO CHANGE AND HOW? I WANT TO KNOW EXACT AND STEPWISE PROCEDURE FOR CHANGING SOURCE CODE AND TESTING IT.DO I NEED TO EXTRACT ZIP FILE OF SOURCE CODE OR NEED TO INSTALL ANYTHING

[ceph-users] Fwd: OSD fail on client writes

2015-02-21 Thread Jeffrey McDonald
Hi, We have a ceph Giant installation with a radosgw interface. There are 198 OSDs on seven OSD servers and we're seeing OSD failures on the system when users try to write files via the s3 interface.We're more likely to see the failures if the files are larger than 1 GB and if the files go

Re: [ceph-users] HELP FOR CEPH SOURCE CODE

2015-02-21 Thread Michael Andersen
C++ is case sensitive, it will be very difficult... On Feb 21, 2015 3:44 AM, Stefan Priebe - Profihost AG s.pri...@profihost.ag wrote: This will be very difficult with a broken keyboard! Am 21.02.2015 um 12:16 schrieb khyati joshi kpjosh...@gmail.com: I WANT TO ADD 2 NEW FEATURES IN CEPH

[ceph-users] Radosgw keeps writing to specific OSDs wile there other free OSDs

2015-02-21 Thread B L
Hi Ceph community, I’m trying to upload some file with 5GB size, through radosgw, I have 9 OSDs deployed on 3 machines, and my cluster is healthy. The problem is: the 5GB file is being uploaded to osd.0 and osd.1 ,which are near full, while the other OSDs have more space that can have this