Whamcloud - gitweb
root [Tue, 12 Jan 2010 23:12:31 +0000 (07:12 +0800)]
b=21471 fix race problem during recovery
during recovery, "class_unlink_export", "class_set_export_delayed"
and "target_queue_last_replay_reply" maybe race duirng processing
(increase/decrease) "obd_recoverable_clients" and "obd_delayed_clients"
and cause the recovery to wait forever
i=tappro@sun.com
i=yong.fan@sun.com
Johann Lombardi [Thu, 14 Jan 2010 10:59:00 +0000 (11:59 +0100)]
b=20020 don't shrink if no mds_body
i=andrew
i=dmitry
Fix bug found on lol when the group upcall returns EIDRM.
We incorrectly shrink the reply while there is no mds_body.
Elena Gryaznova [Wed, 13 Jan 2010 22:28:01 +0000 (01:28 +0300)]
b=19387 integrate LST into acc-sm
i=Maxim.Patlasov
i=He.Huang
new acc-sm test suite: LNET_SELFTEST
Brian Behlendorf [Wed, 13 Jan 2010 22:28:18 +0000 (23:28 +0100)]
b=21800 fix spurious message from shrink_slab reporing negative nr
i=johann
i=andrew
Elena Gryaznova [Mon, 11 Jan 2010 12:25:00 +0000 (15:25 +0300)]
b=19702 fix COUNT to work properly
i=Andrew.Perepechko
Elena Gryaznova [Wed, 13 Jan 2010 20:19:21 +0000 (23:19 +0300)]
b=20866 DEPS assignment needs quotes
o=Brian
i=grev
Elena Gryaznova [Wed, 13 Jan 2010 20:00:58 +0000 (23:00 +0300)]
b=20918 improve log warning
i=Brian
Nathan Rutman [Wed, 13 Jan 2010 17:58:56 +0000 (09:58 -0800)]
b=21746 compare full fsname when erasing config files for writeconf
i=breitz
i=brian
Alexander.Zarochentev [Sun, 10 Jan 2010 19:57:06 +0000 (22:57 +0300)]
b=20816 improve simulation of late reply
ignore obd_fail_timeout for ping replies.
i=robert.read
i=johann
i=tappro
Alexander.Zarochentev [Sun, 10 Jan 2010 19:56:26 +0000 (22:56 +0300)]
b=20816 fix replay-single test 67b
Exhausting precreation before testing delayed file creation on OST.
i=johann
i=robert.read
Brian J. Murrell [Sat, 9 Jan 2010 14:34:22 +0000 (09:34 -0500)]
b=21759 Miscellaneous build fixes
The message string given to fatal() cannot be slit with line continuations
as you would strings elsewhere -- for whatever reason. So let's just un-
split them for now.
Coding style fixups.
Adds a "--set-var" option to lbuild to set/override an environment variable.
This is mainly meant for lbuild testers.
Fix missing - from tar so that the --exclude parameters will be honoured.
Some stderr->stdout redirections to get output into the correct log.
i=wangyb
i=yangsheng
Brian J. Murrell [Sat, 9 Jan 2010 04:36:05 +0000 (23:36 -0500)]
b=20617 old-school builds sles9 too
A portion of the patch for this didn't seem to get committed causing
SLES9 builds to fail.
Johann Lombardi [Fri, 8 Jan 2010 22:46:06 +0000 (23:46 +0100)]
bump version to 1.8.1.60
Johann Lombardi [Fri, 8 Jan 2010 22:44:03 +0000 (23:44 +0100)]
Disable async journal commit & cancel lock before replay features by default
This reverts commit
d7bdeb27b53b12f8c567fa220f82e1ca2a10a470.
Brian J. Murrell [Fri, 8 Jan 2010 16:38:20 +0000 (11:38 -0500)]
b=21586 More stderr/stdout redirections
Just a few more redirections to get some commands' output into the
appropriate log files.
We should actually return the 255, not just assign it to a unused variable.
i=yangsheng
i=wangyb
brian [Fri, 8 Jan 2010 16:38:19 +0000 (11:38 -0500)]
b=20315 Use libexecdir
Use the more standard libexecdir for scripts.
i=adilger
o=Christopher Morrone
Brian J. Murrell [Fri, 8 Jan 2010 16:38:18 +0000 (11:38 -0500)]
b=21754 RPM version update fix
It seems that Suse will release an updated RPM without updating the
kernel inside. In doing so, the kernel and the RPM file name have
different specifications of the version.
This fix allows for that.
i=yangsheng
i=wangyb
Brian J. Murrell [Fri, 8 Jan 2010 16:38:17 +0000 (11:38 -0500)]
b=21757 Update per make oldconfig.
Make oldconfig always winds up removing CONFIG_SD_IOSTATS from the RHEL4
config file on i686, so we should remove it from the source.
Dmitry Zogin [Fri, 8 Jan 2010 16:08:32 +0000 (11:08 -0500)]
b=20247 Disabling printing D_NETERROR messages on the console.
i=he.huang
i=johann
i=adilger
Remove neterror from libcfs_printk since it is too chatty
and can flood the console.
Johann Lombardi [Fri, 8 Jan 2010 15:24:51 +0000 (16:24 +0100)]
b=20805 rate limit D_NETERR messages
i=isaac
i=liang
add CNETERR() macro that uses CDEBUG_LIMIT() for D_NETERR messages
Girish Shilamkar [Fri, 8 Jan 2010 09:35:31 +0000 (15:05 +0530)]
b=20301 Fix mkfs.lustre for 16TB+ LUNs
Patch by James Simmons
i=adilger
i=girish
Mounting 16TB LUNs failed due to three bugs in mkfs.lustre. This patch
fixes this.
Brian J. Murrell [Thu, 7 Jan 2010 19:47:38 +0000 (14:47 -0500)]
b=20617 Update old-school build with new API changes
The API changes that were part of the previous landing for bug
20617 require that the old_school build be updated as well.
i=wangyb
i=yangsheng
Fan Yong [Thu, 7 Jan 2010 02:34:02 +0000 (10:34 +0800)]
b=20456 unregistering should be zero if no RPC inflight
1) unregistering should be zero if no RPC inflight, but not true for the converse case.
2) code cleanup.
i=robert.read
i=rahul.deshmukh
Dmitry Zogin [Wed, 6 Jan 2010 16:28:31 +0000 (11:28 -0500)]
b=21656 Quiet dirty_max CERROR
The atomic_read() allowing the atomic_inc() are not covered
by a lock. Thus they may safely race and trip this CERROR()
unless we add in a small fudge factor (+1).
i=adilger
i=dmitry.zogin
yangsheng [Tue, 5 Jan 2010 13:52:49 +0000 (21:52 +0800)]
b=21592 BLKGETSIZE64 redefinition on some platform.
i=adilger
i=panda
root [Fri, 1 Jan 2010 05:50:58 +0000 (13:50 +0800)]
b=21681 suppress bogus transno error
suppress the "server went back in time" error message
which is always printed even in the common case after
a client eviction
i=hongchao.zhang@sun.com
i=andrew.perepechko@sun.com
LiuYing [Mon, 28 Dec 2009 01:01:46 +0000 (09:01 +0800)]
b=21420 MDS panic and hanging client processes
Replace exp_ops_stats with exp_nid_stats->nid_stats
i=wangdi
i=nathan
Andrew Perepechko [Thu, 24 Dec 2009 19:38:27 +0000 (22:38 +0300)]
updating LUSTRE_FIX from 58 to 59
Andrew Perepechko [Thu, 24 Dec 2009 19:37:20 +0000 (22:37 +0300)]
b=21670 revert new version of find_linux_devel_paths
i=Andrew Perepechko
o=Brian Murrell
Andrew Perepechko [Thu, 24 Dec 2009 19:33:59 +0000 (22:33 +0300)]
b=16774 replay-single 85a, 85b tests to check the cancellation of unused locks during recovery
i=Oleg Drokin
i=Tom Wang
i=Elena Gryaznova
Andrew Perepechko [Thu, 24 Dec 2009 17:11:51 +0000 (20:11 +0300)]
b=21692 fix format specifiers in setattr
i=Girish Shilamkar
Andrew Perepechko [Thu, 24 Dec 2009 15:24:19 +0000 (18:24 +0300)]
b=21586 further build message cleanups
i=Yibin Wang
i=Sheng Yang
Andrew Perepechko [Thu, 24 Dec 2009 14:51:14 +0000 (17:51 +0300)]
b=21670 make the code compilable with ppc/rhel5
i=Oleg Drokin
Andrew Perepechko [Thu, 24 Dec 2009 14:45:35 +0000 (17:45 +0300)]
b=21670 getopt fixes in tests/mpi
i=Brian Murrell
getopt returns int, at the same time "char" type can have the same range as "unsigned char" type and, thus, unable to hold -1 rc from getopt
Andrew Perepechko [Wed, 23 Dec 2009 22:22:44 +0000 (01:22 +0300)]
b=21670 fix invalid var type to hold getopt rc
i=Andreas Dilger
Andrew Perepechko [Wed, 23 Dec 2009 20:40:05 +0000 (23:40 +0300)]
b=21670 fix format specifiers and type cast in LQS_DEBUG
i=Andreas Dilger
Andrew Perepechko [Wed, 23 Dec 2009 16:26:00 +0000 (19:26 +0300)]
b=21671 format specifiers fixes and casting fixes in ldiskfs
i=Andrew Perepechko
i=Rahul Deshmukh
mismatched format specifiers and variable types for printf-like functions caused warnings and build failures
Andrew Perepechko [Wed, 23 Dec 2009 15:59:03 +0000 (18:59 +0300)]
b=21669 cast the le64 to %llu in all ext*mmp patches
i=Andreas Dilger
i=Andrew Perepechko
a bunch of fixes for extN_warnings in ldiskfs to avoid compilation warnings
yangsheng [Wed, 23 Dec 2009 07:21:19 +0000 (15:21 +0800)]
b=19557 actually make lustre_hash_for_each_empty() more efficient
i=johann
i=herring3
Andrew Perepechko [Tue, 22 Dec 2009 16:09:25 +0000 (19:09 +0300)]
b=21670 fix format specifier in check_cur_qunit to avoid warnings
i=Sheng Yang
i=Dmitry Zogin
Wang Di [Mon, 21 Dec 2009 22:43:58 +0000 (17:43 -0500)]
b=20607 Correct the refcount of lov_request_set
i=Andreas Dilger
i=Eric May
yangsheng [Sat, 19 Dec 2009 17:43:56 +0000 (01:43 +0800)]
b=18213 really interrupt the sleep in osc_enter_cache on signals
i=zhanghc
i=yangsheng
Nathan Rutman [Fri, 18 Dec 2009 21:38:56 +0000 (13:38 -0800)]
b=21571 stacksize and locking fixes for loadgen patch from umka i=adilger i=nathan
johann [Fri, 18 Dec 2009 22:57:26 +0000 (23:57 +0100)]
bump verion to 1.8.1.58 & changelog cleanup
johann [Fri, 18 Dec 2009 22:16:18 +0000 (23:16 +0100)]
Merge branch 'b1_8' of git.lustre.org:prime/lustre into b1_8
Oleg Droking [Fri, 18 Dec 2009 22:13:15 +0000 (23:13 +0100)]
b=20989 fix race in nfs export code
No need to look up the inode first anyway since
ll_prep_inode is perfectly capable of finding
correct inode if needed
i=bzzz
i=johann
Andrew Perepechko [Fri, 18 Dec 2009 22:09:00 +0000 (01:09 +0300)]
b=21489 make xid checks atomic
i=Johann Lombardi
i=Vitaly Fertman
lock when checking xid value during setattr and write
Andrew Perepechko [Fri, 18 Dec 2009 19:56:35 +0000 (22:56 +0300)]
Merge branch 'b1_8' of git.lustre.org:prime/lustre into b1_8
yangsheng [Thu, 17 Dec 2009 17:25:19 +0000 (01:25 +0800)]
b=21411 Avoid infinite loop when bulk IO delayed.
The rq_deadline calculated base on cfs_time_current_sec() when AT enabled,
So the early reply always send between client&server. And the request
never be timeout in some case.
i=nathan
i=johann
Andrew Perepechko [Fri, 18 Dec 2009 13:59:12 +0000 (16:59 +0300)]
b=21489 mtime could be spoiled by a write callback
i=Johann Lombardi
i=Vitaly Fertman
write callback with some stale mtime could "undo" a later setattr
johann [Fri, 18 Dec 2009 11:08:29 +0000 (12:08 +0100)]
Enable async journal commit & cancel lock before replay features by default
Although async journal commit (bug 19128) and cancel
lock before replay (16774) will be disabled by default
in 1.8.2, i would like to run the daily tests with
those features enabled for a couple of days.
Cliff White [Thu, 17 Dec 2009 20:47:31 +0000 (12:47 -0800)]
b=19673 add max_dir size mount option
i=girish.shilamkar
i=johann
Elena Gryaznova [Thu, 17 Dec 2009 19:15:33 +0000 (22:15 +0300)]
b=21547 add cascading_rw into lustre mpi tests
o=James Simmons
i=Johann
i=grev
Hongchao.Zhang@Sun.COM [Fri, 18 Dec 2009 19:44:34 +0000 (03:44 +0800)]
b=21252 add reference on extent lock during readahead
add an extra LCK_PR reference on the extent lock
covering the readhead page to pin it during the readahead
i=oleg.drokin@sun.com
i=johann@sun.com
i=tom.wang@sun.com
Brian J. Murrell [Thu, 17 Dec 2009 13:58:11 +0000 (08:58 -0500)]
b=21532 various build fixes for rhel4 and sles9
various build fixes for rhel4 and sles9 including:
- configure checks for and backports of:
* atomic_inc_not_zero
* atomic_cmpxchg
- don't include linux/pagevec.h in llite/lloop.c as it causes some duplicate
definitions when it's later included by another source file
- use LPU64 portability formats
Brian J. Murrell [Thu, 17 Dec 2009 15:09:47 +0000 (10:09 -0500)]
b=21586 clarify lbuild error reporting
clarify the reporting of build errors by:
- disabling xtrace during the stack trace printing
- moving the ccache statistics printing exit trap so that it's only
installed if ccache has been enabled
- remove some useless $() constructs around function calls
- only send the untrapped error debuggery to me
i=wangyb
i=yangsheng
johann [Thu, 17 Dec 2009 14:22:43 +0000 (15:22 +0100)]
b=21527 don't use vendors own CFLAGS for the lustre build
johann [Thu, 17 Dec 2009 13:22:10 +0000 (14:22 +0100)]
b=21582 make sure not to use cached statfs info in fail()
Use client_up which sleeps for 1s before running statfs.
It grants that we are not using cached statfs info, since patch
from bug 20065 has been landed.
i=grev
Landen [Thu, 17 Dec 2009 03:52:25 +0000 (11:52 +0800)]
b=18630 avoid the race of acquiring/releasing quota
Before this patch, checking and computing the info of lqs
are located in two different functions(check_cur_qunit()
and schedule_dqacq()). It is racy. With this patch, they
will all happen in one function(check_cur_qunit()).
i=johann
i=panda
Hongchao.Zhang@Sun.COM [Wed, 16 Dec 2009 08:09:14 +0000 (16:09 +0800)]
b=16774 fix a issue caused by LDLM_POLICY_SKIP_LOCK
introduce a new lock flag LDLM_FL_SKIPPED to avoid
checking locks repeatly in ldlm_cancel_lru_local()
i=oleg.drokin@sun.com
i=hongchao.zhang@sun.com
Dmitry Zogin [Wed, 16 Dec 2009 21:59:44 +0000 (16:59 -0500)]
b=20722 Make watchdog timer messages more clear and descriptive.
i=adilger
johann [Wed, 16 Dec 2009 23:13:40 +0000 (00:13 +0100)]
b=19884 add replay-dual test_14b to always except list
Brian J. Murrell [Wed, 16 Dec 2009 20:22:57 +0000 (15:22 -0500)]
b=21527 Use %configure in the RPM SPEC file
use the %configure macro defined by the RPM installation so that the
vendor's filesystem hierarchy preferences are observered
i=wangyb
i=yangsheng
johann [Wed, 16 Dec 2009 21:43:12 +0000 (22:43 +0100)]
b=20765 handle -EINTR in osc_interpret_create()
i=tappro
i=zam
Brian J. Murrell [Wed, 16 Dec 2009 17:41:00 +0000 (12:41 -0500)]
b=21600 Fix unitialized pointer
gcc warns that ctx may be used prior to assignment, so initialize it
at declaration
i=rread
i=johann
Liang Zhen [Wed, 16 Dec 2009 16:07:41 +0000 (00:07 +0800)]
b=21396 LNET soft lockups in socknal_connd thread
don't hog CPU for active-connecting if another connd is accepting
connecting-requst from the same peer
i=isaac
i=maxim
Johann Lombardi [Wed, 16 Dec 2009 13:29:56 +0000 (14:29 +0100)]
b=19887 force reconnect in test 26a
i=grev
Dmitry Zogin [Tue, 15 Dec 2009 15:46:04 +0000 (10:46 -0500)]
b=17682 limit performance impact of rpctrace, dlmtrace & quota (real commit)
Performance improvements for debug messages with
D_RPCTRACE, D_LDLM, D_QUOTA
previous commit (
995342ab73da4ac8e364f90d2b26a88a5eef4801)
only included the changelog entry.
i=alexey.lyashkov
i=andrew.perepechko
i=johann
Dmitry Zogin [Tue, 15 Dec 2009 15:46:04 +0000 (10:46 -0500)]
b=17682 limit performance impact of rpctrace, dlmtrace & quota
Performance improvements for debug messages with
D_RPCTRACE, D_LDLM, D_QUOTA.
i=alexey.lyashkov
i=andrew.perepechko
i=johann
Johann Lombardi [Wed, 16 Dec 2009 12:44:56 +0000 (13:44 +0100)]
b=21147 fix silent conflict with patch from bug 21379
Andrew Perepechko [Wed, 16 Dec 2009 00:31:19 +0000 (03:31 +0300)]
b=21147 be tolerant to setting the same type and version of quota
i=Johann Lombardi
i=ZhiYong Tian
Brian Reitz [Mon, 14 Dec 2009 06:49:06 +0000 (00:49 -0600)]
Remove lustrecvs. Not needed for git
Brian Reitz [Sat, 12 Dec 2009 14:10:18 +0000 (08:10 -0600)]
Introduce .gitignore files.
The top level .gitignore file is new and is an attempt at
pulling in some of the common items that you might get for
free (by default)with CVS. The other subdir/.gitignore files
are translated versions of their corresponding .cvsignore
file. Because CVS does not descend into a subdir when
applying a ingore rule we have to prepend a "/" to
the pathname to get git to behave the same way.
Brian Reitz [Sat, 12 Dec 2009 14:06:41 +0000 (08:06 -0600)]
Add ldiskfs/build symlink
cvs2svn [Fri, 11 Dec 2009 04:40:35 +0000 (04:40 +0000)]
This commit was manufactured by cvs2svn to create branch 'git_cnv_b1_8'.
robert.read [Fri, 11 Dec 2009 04:40:33 +0000 (04:40 +0000)]
Branch HEAD
Another test commit to ensure cvs is back to normal.
robert.read [Fri, 11 Dec 2009 02:35:38 +0000 (02:35 +0000)]
Branch HEAD
Test commit to ensure cvs is back to normal.
robert.read [Fri, 11 Dec 2009 01:40:25 +0000 (01:40 +0000)]
Branch HEAD
Updating ChangeLog supported kernel section.
johann [Thu, 10 Dec 2009 22:31:04 +0000 (22:31 +0000)]
Branch b1_8
b=19557
i=adilger
i=andrew
add cond_resched() calls to lustre_hash_for_each_empty() to avoid hogging
the cpu when many locks to process on disconnect/eviction.
johann [Thu, 10 Dec 2009 22:31:00 +0000 (22:31 +0000)]
Branch b1_8
b=19557
i=adilger
i=andrew
add cond_resched() calls to lustre_hash_for_each_empty() to avoid hogging
the cpu when many locks to process on disconnect/eviction.
stinson1947 [Thu, 10 Dec 2009 17:32:03 +0000 (17:32 +0000)]
Updated for 1.8.2 build 07.
stinson1947 [Thu, 10 Dec 2009 17:30:44 +0000 (17:30 +0000)]
Updated for 2.0 build 32.
johann [Thu, 10 Dec 2009 17:06:02 +0000 (17:06 +0000)]
Branch b1_8
b=16356
disable test 2 since it is known not to work until we have
version checking for lock replay
johann [Thu, 10 Dec 2009 17:03:17 +0000 (17:03 +0000)]
Branch b1_8
b=19023
the patch from bug 19023 is landed now.
dzogin [Thu, 10 Dec 2009 13:52:52 +0000 (13:52 +0000)]
Branch HEAD
b=21259
i=andrew.perepechko
i=alexey.lyashkov
----------------------------------------------------------------------
Modified Files:
lustre/ChangeLog lustre/obdclass/linux/linux-module.c
----------------------------------------------------------------------
Description: Allow non-root access for "lfs check".
Details : Added a check in obd_class_ioctl() for OBD_IOC_PING_TARGET.
dzogin [Thu, 10 Dec 2009 13:41:52 +0000 (13:41 +0000)]
Branch b1_8
b=21409
i=grev
----------------------------------------------------------------------
Modified Files:
Tag: b1_8
lustre/tests/test-framework.sh
The small fix for test-framework to make code in 1.8 and HEAD consistent
----------------------------------------------------------------------
brian [Thu, 10 Dec 2009 12:59:39 +0000 (12:59 +0000)]
b=19689
i=adilger
i=bobijam
i=nathan
o=Jim Garlick
Change tunefs.lustre and mkfs.lustre --mountfsoptions so that
exactly the specified mount options are used.
Leaving off any "mandatory" mount options is an error.
Leaving off any default mount options causes a warning, but is allowed.
Change errors=remount-ro from mandatory to default.
Sanitize the mount string before storing it.
Update man pages accordingly.
This hopefully makes two awkward situations less so:
- making errors=panic the default (before we had to append errors=remount-ro
and hope ldiskfs parsing caused the last option to override the first)
- setting other mount options on the OST's dropped mballoc,extents
without warning.
grev [Thu, 10 Dec 2009 12:40:19 +0000 (12:40 +0000)]
b=20237
i=Robert.Read
more tests gather logs changes
grev [Thu, 10 Dec 2009 12:21:09 +0000 (12:21 +0000)]
b=21115
i=Robert.Read
mount the same config on all clients
grev [Thu, 10 Dec 2009 12:06:26 +0000 (12:06 +0000)]
b=21115
i=Robert.Read
mount the same config on all clients
tappro [Thu, 10 Dec 2009 11:29:36 +0000 (11:29 +0000)]
Branch b1_8
b=21240
revert wrongly committed code from another patch
tappro [Thu, 10 Dec 2009 11:08:50 +0000 (11:08 +0000)]
Branch b1_8
b=21240
i=rread, johann
don't exit from test on recovery error
grev [Thu, 10 Dec 2009 10:58:01 +0000 (10:58 +0000)]
b=20580
o=Johann
i=Andrew.Perepechko
i=grev
directio allocates the buffer twice, reduce test filesize
tianzy [Thu, 10 Dec 2009 06:07:03 +0000 (06:07 +0000)]
Branch HEAD
When a reply is wrong, lquota will try to remove the qunit in order
to avoid other threads hanging on it.
b=21372
i=yong.fan
isaac [Thu, 10 Dec 2009 05:15:35 +0000 (05:15 +0000)]
b=20853,i=isaac:
- Mark portal 63 as reserved for Cray DVS.
grev [Wed, 9 Dec 2009 21:05:40 +0000 (21:05 +0000)]
b=20580
i=Johann
skip test 78 for local OST
grev [Wed, 9 Dec 2009 20:47:51 +0000 (20:47 +0000)]
b=21142
i=Andrew.Perepechko
test_cascading_rw: return if skip
grev [Wed, 9 Dec 2009 17:59:32 +0000 (17:59 +0000)]
b=21142
i=Andrew.Perepechko
test_cascading_rw: return if skip
isaac [Wed, 9 Dec 2009 16:35:32 +0000 (16:35 +0000)]
- update mxlnd to upstream revision r224.
pravins [Wed, 9 Dec 2009 16:18:35 +0000 (16:18 +0000)]
b=21128
i=rread
i=adilger
get stack dump on stack usage overflow.