Whamcloud - gitweb
James Simmons [Mon, 18 Jan 2010 17:36:07 +0000 (18:36 +0100)]
b=21370 sanity 27x: double the qos_maxage timeout
i=adilger
Johann Lombardi [Mon, 18 Jan 2010 15:50:39 +0000 (16:50 +0100)]
b=19742 add missing fiemap patches to rhel5 series
i=adilger
i=girish
Johann Lombardi [Mon, 18 Jan 2010 15:01:59 +0000 (16:01 +0100)]
b=21846 define lqs_key for quota lqs
i=adilger
i=landen
Johann Lombardi [Mon, 18 Jan 2010 14:53:27 +0000 (15:53 +0100)]
update supported kernels in changelog and which_patch
yangsheng [Mon, 18 Jan 2010 14:35:18 +0000 (22:35 +0800)]
b=20758 Update kernel to 2.6.16.60-0.42.8.
i=johann
i=landen
Johann Lombardi [Mon, 18 Jan 2010 10:10:33 +0000 (11:10 +0100)]
b=18690 disable rehash for quota
quota can uses a key of 0 for root and the rehash code
assert on this. Disable rehashing for quota lqs for now.
Terry Rutledge [Sat, 16 Jan 2010 18:26:35 +0000 (11:26 -0700)]
Updated with correct version string for 1.8.2 RC1.
Terry Rutledge [Sat, 16 Jan 2010 18:25:01 +0000 (11:25 -0700)]
Updated for 1.8.2 RC1. Added release date.
Girish Shilamkar [Sat, 16 Jan 2010 17:34:06 +0000 (18:34 +0100)]
b=21564 add changelog entry
Girish Shilamkar [Sat, 16 Jan 2010 16:16:57 +0000 (21:46 +0530)]
b=21564 Print mmp_check_interval in kmmpd, fix sles10 & rhel5/ext3 too
The patch not only prints mmp_check_interval but also makes it possible
to abort mount operation in case it takes too long.
i=adilger
Johann Lombardi [Sat, 16 Jan 2010 14:39:22 +0000 (15:39 +0100)]
b=21574 more pinger fixes
i=oleg
i=andrew
- ptlrpc_update_next_ping(): don't postpone next ping when "soon"
is set and a ping request is already scheduled before the new
deadline.
- It is usually fine to extend the deadline for the next ping
since we are granted that the pinger will wake up before
this new deadline and update his timer.
However, the purpose of ptlrpc_pinger_commit_expected() is to
schedule ping earlier. To support this, i've changed
ptlrpc_update_next_ping() to wake up the pinger if the new
ping deadline is before the pinger is supposed to wake up.
Johann Lombardi [Sat, 16 Jan 2010 14:27:17 +0000 (15:27 +0100)]
b=21574 PING_INTERVAL_SHORT should not postpone the next ping
i=oleg
i=andrew
Most our tests run with obd_timeout=20s, so PING_INTERVAL=5s, while
PING_INTERVAL_SHORT=7s. ptlrpc_pinger_commit_expected() was actually
not intended to delay pings.
Although we would prefer to schedule the next ping after a
bit more than 5s (jbd commit time), using 5s instead of 7s
is not a big deal since we will have to only wait for 5
additional seconds in the worst case.
Johann Lombardi [Sat, 16 Jan 2010 14:21:28 +0000 (15:21 +0100)]
b=21574 define ptlrpc_pinger_commit_expected for liblustre
i=oleg
i=andrew
Johann Lombardi [Sat, 16 Jan 2010 14:19:03 +0000 (15:19 +0100)]
b=21574 schedule ping asap instead of delaying it
i=oleg
i=andrew
The intent was to schedule a ping as soon as possible to know
sooner rather than later that the transno has been committed.
This is used by the async journal feature to unpin pages
in memory sooner.
Johann Lombardi [Sat, 16 Jan 2010 14:16:03 +0000 (15:16 +0100)]
b=20928 skip sanity 202 on ib since unaligned dio not supported by o2iblnd
Girish Shilamkar [Sat, 16 Jan 2010 08:32:41 +0000 (14:02 +0530)]
b=21564 Print mmp_check_interval in kmmpd
The patch not only prints mmp_check_interval but also makes it possible
to abort mount operation in case it takes too long.
i=adilger
Johann Lombardi [Sat, 16 Jan 2010 01:04:38 +0000 (02:04 +0100)]
add missing changelog entries
Johann Lombardi [Sat, 16 Jan 2010 00:21:12 +0000 (01:21 +0100)]
b=18399 add missing patch to sles11 series
Ed Giesen [Sat, 16 Jan 2010 00:15:25 +0000 (01:15 +0100)]
b=21097 fix md5sum error in metadata-updates.sh
Johann Lombardi [Sat, 16 Jan 2010 00:05:23 +0000 (01:05 +0100)]
bump version
Johann Lombardi [Fri, 15 Jan 2010 23:36:37 +0000 (00:36 +0100)]
fix another build issue
Johann Lombardi [Fri, 15 Jan 2010 16:37:42 +0000 (17:37 +0100)]
fix build issue
Dmitry Zogin [Fri, 15 Jan 2010 14:35:48 +0000 (09:35 -0500)]
b=21565 filter_last_id() NULL dereference
lprocfs_filter_rd_last_id() should check for the fully setup obd device,
before proceeding further.
i=johann
i=andrew.perepechko
Johann Lombardi [Fri, 15 Jan 2010 11:03:58 +0000 (12:03 +0100)]
b=11680 don't call LBUG if reading force_lbug
Should not happen because the permission is 0200,
but better to check.
Johann Lombardi [Fri, 15 Jan 2010 10:32:27 +0000 (11:32 +0100)]
b=18690 enable rehash for hash tables that intended to use it
Christopher J. Morrone [Fri, 15 Jan 2010 00:27:17 +0000 (01:27 +0100)]
b=11680 Add /proc/sys/lnet/force_lbug
This patch adds a proc entry called force_lbug.
Brian J. Murrell [Thu, 14 Jan 2010 21:15:02 +0000 (16:15 -0500)]
b=19720 use min_t() to force comparison to unsigned
In older kernels num_online_cpus() is an int, and in newer
kernels it is an unsigned so force the comparison to unsigned
so that it's portable to both new and old kernels.
i=panda
i=whitebear
yangsheng [Thu, 14 Jan 2010 13:55:18 +0000 (21:55 +0800)]
b=21411 Improvement for AT.
i=nathan
i=tappro
Johann Lombardi [Thu, 14 Jan 2010 14:20:02 +0000 (15:20 +0100)]
fix tiny nit from previous commit
Johann Lombardi [Thu, 14 Jan 2010 14:16:54 +0000 (15:16 +0100)]
fix build error on ia64/ppc64
Johann Lombardi [Thu, 14 Jan 2010 13:13:07 +0000 (14:13 +0100)]
fix changelog
Johann Lombardi [Thu, 14 Jan 2010 13:00:47 +0000 (14:00 +0100)]
quiet noisy error message when rehash is disabled
Rehash is sometimes disabled temporarily, so quiet
message printed on the console when cur_bits != max_bits.
Alexander.Zarochentev [Thu, 14 Jan 2010 08:56:57 +0000 (11:56 +0300)]
b=21716 Reduce memory consumptions in directio utility
use one memory mapped file buffer in directio.c instead of two.
i=tappro
i=andrew.perepechko
Fan Yong [Thu, 14 Jan 2010 02:34:48 +0000 (10:34 +0800)]
b=20139 prevent parent thread to be killed before its child becoming daemon
Prevent parent thread to be killed before its child becoming daemon.
i=tappro
i=robert
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