Re: [0.48.3] OSD memory leak when scrubbing

2013-01-27 Thread Sylvain Munaut
Hi, Just to keep you posted, upgraded our cluster yesterday to a custom compiled 0.56.1 and it has now been more than 24h and there is no sign on memory leak anymore. Previously it would rise by ~ 100 M every 24h almost like clock work and now, it's been slightly more than 24h and memory is

Re: [0.48.3] OSD memory leak when scrubbing

2013-01-27 Thread Sage Weil
On Sun, 27 Jan 2013, Sylvain Munaut wrote: Hi, Just to keep you posted, upgraded our cluster yesterday to a custom compiled 0.56.1 and it has now been more than 24h and there is no sign on memory leak anymore. Previously it would rise by ~ 100 M every 24h almost like clock work and now,

Re: [0.48.3] OSD memory leak when scrubbing

2013-01-27 Thread Sylvain Munaut
Hi, Just to keep you posted, upgraded our cluster yesterday to a custom compiled 0.56.1 and it has now been more than 24h and there is no sign on memory leak anymore. Previously it would rise by ~ 100 M every 24h almost like clock work and now, it's been slightly more than 24h and memory is

Re: page allocation failures on osd nodes

2013-01-27 Thread Andrey Korolyov
On Sat, Jan 26, 2013 at 12:41 PM, Andrey Korolyov and...@xdel.ru wrote: On Sat, Jan 26, 2013 at 3:40 AM, Sam Lang sam.l...@inktank.com wrote: On Fri, Jan 25, 2013 at 10:07 AM, Andrey Korolyov and...@xdel.ru wrote: Sorry, I have written too less yesterday because of being sleepy. That`s

[PATCH 1/2] utime: fix narrowing conversion compiler warning in sleep()

2013-01-27 Thread Danny Al-Gaaf
Fix compiler warning: ./include/utime.h: In member function 'void utime_t::sleep()': ./include/utime.h:139:50: warning: narrowing conversion of '((utime_t*)this)-utime_t::tv.utime_t::anonymous struct::tv_sec' from '__u32 {aka unsigned int}' to '__time_t {aka long int}' inside { } is ill-formed

[PATCH 0/2] fix some compiler warnings

2013-01-27 Thread Danny Al-Gaaf
Attached two patches to fix some compiler warnings. Danny Al-Gaaf (2): utime: fix narrowing conversion compiler warning in sleep() rbd: don't ignore return value of system() src/include/utime.h | 2 +- src/rbd.cc | 36 ++-- 2 files changed, 31

[PATCH 2/2] rbd: don't ignore return value of system()

2013-01-27 Thread Danny Al-Gaaf
Check for the return value of system() and handle the error if needed Signed-off-by: Danny Al-Gaaf danny.al-g...@bisect.de --- src/rbd.cc | 36 ++-- 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/src/rbd.cc b/src/rbd.cc index 833188a..bdbc684

Re: libs3 build errors

2013-01-27 Thread Cesar Mello
I blew away libs3/build and then it caught the correct libxml2 paths on the next build. This happened on two systems but I cannot reproduce it now :( Thanks, Noah Just happened the same thing in both my machines after I tried to build with rest-bench (configure --with-rest-bench). After

Re: RadosGW performance and disk space usage

2013-01-27 Thread Cesar Mello
Hi, Just tried rest-bench. This little tool is wonderful, thanks! I still have to learn lots of things. So please don't spend much time explaining me, but instead please give me any pointers to documentation or source code that can be useful. As a curiosity, I'm pasting the results from my

[PATCH 0/6] more fixes for MDS cluster recovery

2013-01-27 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com Patch 1 is an updated version of patch 19 in previous patch series. The rest patches fix additional issue of MDS cluster recovery. With these patches, my 3 MDS step (thrash_exports=1, verify_scatter=1, two clients ran fsstress) passed overnight test that

[PATCH 1/6] mds: fix for MDCache::disambiguate_imports

2013-01-27 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com In the resolve stage, if no MDS claims other MDS's disambiguous subtree import, the subtree's dir_auth is undefined. Signed-off-by: Yan, Zheng zheng.z@intel.com --- src/mds/MDCache.cc | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git

[PATCH 2/6] mds: add projected rename's subtree bounds to ESubtreeMap

2013-01-27 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com Signed-off-by: Yan, Zheng zheng.z@intel.com --- src/mds/MDCache.cc | 10 -- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc index 5d88075..9ad6919 100644 --- a/src/mds/MDCache.cc +++

[PATCH 3/6] mds: fix 'discover' handling in the rejoin stage

2013-01-27 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com If the MDS is the resolve stage, current MDCache::handle_discover() only handles 'discover' from MDS that it has already gotten rejoin acknowledgement. This can cause circular wait because MDCache::rejoin_gather_finish() fetches reconnected inodes before

[PATCH 5/6] mds: mark export bounds for cross authority directory rename

2013-01-27 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com this guarantees that the importing MDS gets directory fragment's up-to-date fragstat/rstat. Signed-off-by: Yan, Zheng zheng.z@intel.com --- src/mds/Server.cc | 13 - 1 file changed, 12 insertions(+), 1 deletion(-) diff --git

[PATCH 6/6] mds: clear inode dirty after slave rename finishes.

2013-01-27 Thread Yan, Zheng
From: Yan, Zheng zheng.z@intel.com The inode is linked to a non-auth directory, so remove it from LogSegment's dirty inode list. Signed-off-by: Yan, Zheng zheng.z@intel.com --- src/mds/Server.cc | 5 - 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/src/mds/Server.cc

Re: RadosGW performance and disk space usage

2013-01-27 Thread Dan Mick
On 1/25/2013 9:35 PM, Dan Mick wrote: If the S3 API is not well suited to my scenario, then my effort should be better directed to porting or writing a native ceph client for Windows. I just need an API to read and write/append blocks to files. Any comments are really appreciated. Hopefully