Whamcloud - gitweb
fs/lustre-release.git
11 years agob=21140 Fix srv_threads_running counting.
Alexander.Zarochentsev [Wed, 12 May 2010 10:29:19 +0000 (14:29 +0400)]
b=21140 Fix srv_threads_running counting.

It was possible to overload n_active_request processing incoming requests and
break the thread reservation logic. Likely, it was responsible to the long
processing of requests.

The patch makes srv_threads_running to exactly count only running not sleeping
threads. All threads accounting and comparing/reservation of threads are done
under the service spinlock so it produce a reliable result. The thread
reservation logic is based on new srv_threads_running value and cannot be
confused by not active sleeping threads. The thread reservation logic is
concentrated now in one place, where the wakeup condition is checked (now in
ptlrpc_main_check_event), once a thread is woken up, it is counted as running
and does further work w/o additional checks.

i=zhen.liang
i=robert.read

11 years agob=22683 remove unnecessary check and assert in the cfs_hash function.
Wang Di [Tue, 11 May 2010 17:58:48 +0000 (13:58 -0400)]
b=22683 remove unnecessary check and assert in the cfs_hash function.

o=Eric.Barton
i=Robert.Read
i=Di.Wang

11 years agob=13698 allow e2fsck part of lfsck.sh to be run without lfsck
Vladimir Saveliev [Tue, 11 May 2010 06:40:46 +0000 (10:40 +0400)]
b=13698 allow e2fsck part of lfsck.sh to be run without lfsck

this combines initial patch from Andreas (https://bugzilla.lustre.org/attachment.cgi?id=29696)
and several necessary fixes (https://bugzilla.lustre.org/attachment.cgi?id=29747)

i=adilger

11 years agob=20562 increase LUSTRE_SEQ_META_WIDTH to keep FLD compact
Rahul Deshmukh [Tue, 11 May 2010 06:25:30 +0000 (11:55 +0530)]
b=20562 increase LUSTRE_SEQ_META_WIDTH to keep FLD compact

Fixed the build error for fc11 and fc12 patchless client.

i=rread

11 years agob=22598 diagnostic patch for lock cancel callback error processing
Fan Yong [Tue, 11 May 2010 03:01:45 +0000 (11:01 +0800)]
b=22598 diagnostic patch for lock cancel callback error processing

diagnostic patch for lock cancel callback error processing.

i=robert
i=di.wang

11 years agob=19986 cleanup lock to eliminate former test cases effect before replay-single test_53
Fan Yong [Tue, 11 May 2010 01:55:54 +0000 (09:55 +0800)]
b=19986 cleanup lock to eliminate former test cases effect before replay-single test_53

cleanup lock to eliminate former test cases effect before replay-single test_53

i=robert
i=di.wang

11 years agob=18143 Make VBR compatible with pdirops.
Mikhail Pershin [Sun, 9 May 2010 09:09:23 +0000 (13:09 +0400)]
b=18143 Make VBR compatible with pdirops.

i=zam
i=bzzz

11 years agob=22283 clarify writeconf in man page
Nathan Rutman [Fri, 7 May 2010 22:33:29 +0000 (15:33 -0700)]
b=22283 clarify writeconf in man page

11 years agob=22671 Check for modules directly instead of keeping state
Nathan Rutman [Fri, 7 May 2010 19:29:07 +0000 (12:29 -0700)]
b=22671 Check for modules directly instead of keeping state

i=nico
i=rread

11 years agob=22581 LOADS env var in ncli.sh should allow overwrite
Elena Gryaznova [Fri, 7 May 2010 16:07:54 +0000 (20:07 +0400)]
b=22581 LOADS env var in ncli.sh should allow overwrite

i=Minh.Diep

11 years agob=22522 do not remove from res_list without locks
Oleg Drokin [Wed, 5 May 2010 23:35:58 +0000 (19:35 -0400)]
b=22522 do not remove from res_list without locks

Patch in bug 21501 moved list manipulation of res_list outside or res_lock
introducing a race window in flock code. Move it back under the lock.

i=rread
i=adilger

11 years agob=22669 fix fault page index handler in newer kernel.
Eric Mei [Wed, 5 May 2010 01:14:34 +0000 (19:14 -0600)]
b=22669 fix fault page index handler in newer kernel.

r=wangdi
r=rread

11 years agob=21502 symlink compatibility between 1.6 and 2.0
Rahul Deshmukh [Tue, 4 May 2010 15:16:01 +0000 (20:46 +0530)]
b=21502 symlink compatibility between 1.6 and 2.0

Fixed the sleep in spin lock, inode->i_sb->s_op-> dirty_inode(inode)
was called with spin lock held.

i=bzzz
i=pravin

11 years agob=22683 don't manipulate hash in lov_sub_enter/lov_sub_exit.
Eric Mei [Tue, 4 May 2010 14:30:09 +0000 (08:30 -0600)]
b=22683 don't manipulate hash in lov_sub_enter/lov_sub_exit.

r=wangdi
r=rread

11 years agoRevert "b=19427 correct lmm_object_id and reserve fids for fid-on-OST." 1.10.0.41a v1_10_0_41a
Robert Read [Fri, 30 Apr 2010 16:23:28 +0000 (09:23 -0700)]
Revert "b=19427 correct lmm_object_id and reserve fids for fid-on-OST."

This reverts commit 4c01e64e0a72c1682ebf0a8bd4cccf99fd04cd88.

This caused the interop issue seen in bug 22730.

11 years agoPrepare for Build 41 1.10.0.41 v1_10_0_41
Robert Read [Thu, 29 Apr 2010 22:09:34 +0000 (15:09 -0700)]
Prepare for Build 41

11 years agob=16680 remove some noisy debug messages
Fan Yong [Thu, 29 Apr 2010 06:06:37 +0000 (14:06 +0800)]
b=16680 remove some noisy debug messages

Remove some noisy debug messages.

i=robert.read
i=rahul.deshmukh

11 years agob=20326 Test suite for MMP feature
Jian Yu [Thu, 29 Apr 2010 05:59:13 +0000 (13:59 +0800)]
b=20326 Test suite for MMP feature

Tests for multiple mount protection (MMP) feature.

i=andreas.dilger
i=grev

11 years agob=22069 port "llapi_get_connect_flags()" API from b1_8 to master
Fan Yong [Thu, 29 Apr 2010 05:37:03 +0000 (13:37 +0800)]
b=22069 port "llapi_get_connect_flags()" API from b1_8 to master

Port "llapi_get_connect_flags()" API from b1_8 to master.

i=robert.read
i=landen

11 years agob=22075 buffalo-v2 should detect test timeouts
Manoj Joseph [Thu, 29 Apr 2010 03:27:21 +0000 (21:27 -0600)]
b=22075 buffalo-v2 should detect test timeouts

buffalo-v2 now detects test timeouts. It now generates status entries
in results.yml after a sub-test completes. If the test status is missing
a timeout is assumed to have occured.

i=robert.read
i=grev

11 years agob=21962 Quote the error message in results.yaml
Manoj Joseph [Thu, 29 Apr 2010 03:27:20 +0000 (21:27 -0600)]
b=21962 Quote the error message in results.yaml

Quote and escape the error message in results.yaml

i=robert.read
i=nicolas.williams

11 years agob=22582 remove leading / from fid2path results print full path if given mountpoint
Nathan Rutman [Wed, 28 Apr 2010 18:04:59 +0000 (11:04 -0700)]
b=22582 remove leading / from fid2path results print full path if given mountpoint

i=manoj
i=rread

11 years agob=22456 Remove files for unsupported kernels
Robert Read [Wed, 28 Apr 2010 17:06:59 +0000 (10:06 -0700)]
b=22456 Remove files for unsupported kernels

Removes support for fc3, fc5, rhel4, sles10, 2.6.18 vanilla and 2.6.22 vanilla.

i=adilger

11 years agob=18649 set wait_recovery_complete() MAX value to max recovery time estimated
Elena Gryaznova [Tue, 27 Apr 2010 15:32:56 +0000 (19:32 +0400)]
b=18649 set wait_recovery_complete() MAX value to max recovery time estimated

i=Mikhail.Pershin

11 years agob=20918 t-f max recovery time estimation
Elena Gryaznova [Tue, 27 Apr 2010 15:23:04 +0000 (19:23 +0400)]
b=20918 t-f max recovery time estimation

i=Nathan.Rutman
i=Brian.Murrell

inform user about the estimated maximum recovery time value
to help him to set the server FAILOVER period properly

11 years agob=22342 process racer condition between statahead and rename/unlink operation
Fan Yong [Tue, 27 Apr 2010 05:23:03 +0000 (13:23 +0800)]
b=22342 process racer condition between statahead and rename/unlink operation

1) process racer condition between statahead and rename/unlink operation
2) replace "lli_lock" with "lli_sa_lock" for statahead related processing

i=robert.read
i=tom.wang

11 years agob=22634 hold "mds_qonoff_sem" when call "lustre_read_quota()", and check parameter...
Fan Yong [Tue, 27 Apr 2010 03:36:53 +0000 (11:36 +0800)]
b=22634 hold "mds_qonoff_sem" when call "lustre_read_quota()", and check parameter properly in such function

1) replace "cfs_semaphore_t" with "cfs_rw_semaphore_t" for "mds_qonoff_sem" to enhance the parallel processing of quota related operations
2) hold "mds_qonoff_sem" when call "lustre_read_quota()", and check parameter properly in such function

i=robert.read
i=landen

11 years agob=22614 enlarge MDSSIZE/OSTSIZE to increase default journal size for conf-sanity
Fan Yong [Tue, 27 Apr 2010 02:51:27 +0000 (10:51 +0800)]
b=22614 enlarge MDSSIZE/OSTSIZE to increase default journal size for conf-sanity

1) enlarge MDSSIZE/OSTSIZE to increase default journal size for conf-sanity
2) journal handler error process in lustre_commit_dquot

i=robert.read
i=landen

11 years agob=21251 ha.sh: Fix ha_wait_loads and ha_dump_logs
Li Wei [Tue, 27 Apr 2010 02:28:09 +0000 (10:28 +0800)]
b=21251 ha.sh: Fix ha_wait_loads and ha_dump_logs

Report existence of hanging workloads.  Ignore "lctl dk" failures, since
some nodes may be down.

i=robert.read

11 years agob=21251 Add lustre/tests/ha.sh
Li Wei [Tue, 27 Apr 2010 02:28:08 +0000 (10:28 +0800)]
b=21251 Add lustre/tests/ha.sh

This is a simple failover test script that works with configurations
controlled by a CRM and have multiple targets per server.

i=robert.read
i=grev

11 years agoRevert "b=21379 Fix orphans proceeding in osc_create"
Robert Read [Mon, 26 Apr 2010 22:11:52 +0000 (15:11 -0700)]
Revert "b=21379 Fix orphans proceeding in osc_create"

This reverts commit 2deb4f149f4601f9128fd39efd4705573520f277.

11 years agob=22458 move lcw_dump out of softirq context.
Eric Mei [Mon, 26 Apr 2010 14:59:52 +0000 (08:59 -0600)]
b=22458 move lcw_dump out of softirq context.

Now the message dump is done in thread context in lc_watchdogd.

r=rread
r=nathan

11 years agob=21128 run sync ldlm_bl_to_thread_list() in separate thread to save stack space.
pravin [Mon, 26 Apr 2010 13:15:26 +0000 (18:45 +0530)]
b=21128 run sync ldlm_bl_to_thread_list() in separate thread to save stack space.

i=oleg.drokin
i=rahul

11 years agob=22637 MDS returns OBD_MD_FLSIZE to client only when no OSS object allocated
Fan Yong [Mon, 26 Apr 2010 07:38:37 +0000 (15:38 +0800)]
b=22637 MDS returns OBD_MD_FLSIZE to client only when no OSS object allocated

i=robert.read
i=landen

11 years agob=22513 Remove unecessary lock in read-ahead process.
Wang Di [Mon, 26 Apr 2010 03:57:44 +0000 (23:57 -0400)]
b=22513 Remove unecessary lock in read-ahead process.

i=Robert.Read
i=Eric.Mei

11 years agob=21938 use the same set during replay
hongchao.zhang [Wed, 21 Apr 2010 00:54:53 +0000 (08:54 +0800)]
b=21938 use the same set during replay

some requests use its own ptlrpc_request_set to process its requests, but Lustre
will use a specific ptlrpc_request_set to process the requests during recovery.
this patch fixes this problem to allow the requests to use its own set if it have
one

i=johann@sun.com
i=tappro@sun.com

11 years agob=15936 Unified target cleanups v2
Mikhail Pershin [Sun, 25 Apr 2010 12:09:48 +0000 (16:09 +0400)]
b=15936 Unified target cleanups v2

i=rread
i=andreas

11 years agob=20373 Putting parent lock for rep-ack on create is wasteful
Cliff White [Tue, 6 Apr 2010 06:40:15 +0000 (23:40 -0700)]
b=20373 Putting parent lock for rep-ack on create is wasteful

Do not put locks if no create.

i=robert.read
i=tappro

11 years agob=22310 add a little more comment.
Eric Mei [Fri, 23 Apr 2010 18:48:07 +0000 (12:48 -0600)]
b=22310 add a little more comment.

r=adilger

11 years agob=21678 Add more debug info to lnd_query code path
Isaac Huang [Fri, 23 Apr 2010 04:03:14 +0000 (00:03 -0400)]
b=21678 Add more debug info to lnd_query code path

The peer health code lacked some important debugging info in lnd_query
code paths. This patch added necessary debug prints, not just for bug
21678, but also for future troubleshooting.

i=liang
i=maxim

11 years agob=19427 correct lmm_object_id and reserve fids for fid-on-OST.
Wang Di [Fri, 23 Apr 2010 19:57:04 +0000 (12:57 -0700)]
b=19427 correct lmm_object_id and reserve fids for fid-on-OST.

1. Change lmm_object_id to fid.
2. Cleanup fid spaces reservation (for fid-on-OST).http://arch.lustre.org/index.php?title=Interoperability_fids_zfs#NEW.0
3. Rename group to Seq.

i= Andreas.diger
i= pravin.shelar

11 years agob=22615 fixes for regressions caused by 11063
Vladimir Saveliev [Thu, 22 Apr 2010 19:15:32 +0000 (12:15 -0700)]
b=22615 fixes for regressions caused by 11063

set atime to past under PW EOF extent lock
fix truncate in liblustre

i=vitaly
i=ericm

11 years agob=22507 rm -rf not replicated
Manoj Joseph [Thu, 22 Apr 2010 19:15:28 +0000 (12:15 -0700)]
b=22507 rm -rf not replicated

Support replication of recursive directory removal.

i=nathan.rutman
i=robert.read

11 years agob=22520 set the thread to be uninterrupt before add to waitq
Wang Di [Thu, 22 Apr 2010 19:15:24 +0000 (12:15 -0700)]
b=22520 set the thread to be uninterrupt before add to waitq

In lov_subobject_kill, if the thread needs to wait the object being
freed, it should set the thread to be uninterrupt, otherwise, the thread
might spin there.

i=Eric.mei
i=Robert

11 years agob=22296 Fix script problem for recovery-double-scale
Wang Di [Thu, 22 Apr 2010 19:15:20 +0000 (12:15 -0700)]
b=22296 Fix script problem for recovery-double-scale

Force the test threads stopped before shutdown the clients in
recovery-double-scale.

i=Jack.Chen
i=WangDi

11 years agob=22161 Use LCK_PW for parent lock in mdt_link(). Pdirops test set
Mikhail Pershin [Wed, 21 Apr 2010 18:43:20 +0000 (11:43 -0700)]
b=22161 Use LCK_PW for parent lock in mdt_link(). Pdirops test set

i=adilger
i=bzzz
i=rread

11 years agob=19919 Supply a absolute path.
yangsheng [Wed, 21 Apr 2010 18:43:12 +0000 (11:43 -0700)]
b=19919 Supply a absolute path.

i=andreas
i=johann

11 years agob=22190 Apply 19195 patch to add tls data for recovery thread.
Mikhail Pershin [Wed, 21 Apr 2010 18:43:11 +0000 (11:43 -0700)]
b=22190 Apply 19195 patch to add tls data for recovery thread.

This will be needed anyway when sync journal will be ported

i=zam
i=oleg

11 years agofixed for bug 22237
Rahul Deshmukh [Wed, 21 Apr 2010 18:42:26 +0000 (11:42 -0700)]
fixed for bug 22237

b=22237 replay-single test-13 mmp failure, BUG: warning at
fs/proc/generic.c:764/remove_proc_entry()

The proc entry EXT4_MAX_DIR_SIZE_NAME was not remove in cleanup path. It
is now fixed.

i=johann

11 years agob=22129 add debug patch for 22129
Wang Di [Wed, 21 Apr 2010 18:42:24 +0000 (11:42 -0700)]
b=22129 add debug patch for 22129

i=Robert
i=Fangyong

11 years agob=21379 Fix orphans proceeding in osc_create
Wang Di [Wed, 21 Apr 2010 18:42:20 +0000 (11:42 -0700)]
b=21379 Fix orphans proceeding in osc_create

in "osc_create", there is no need to proceed after the orphans are deleted, which cause the
oscc->oscc_next_id is increased by 1 and break the balance between it and the last objid stored
in "mds->mds_lov_page_array"

o=Zhang Hongchao
i=Johann
I=Tappro

11 years agob=22409 Spurious error messages from smp_processor_id() on preemptible kernel
Dmitry Zogin [Mon, 19 Apr 2010 23:29:32 +0000 (16:29 -0700)]
b=22409 Spurious error messages from smp_processor_id() on preemptible kernel

 Disable a preemption by grabbing the lock in fs_trace_get_tcd() first.
 The function fs_trace_get_tcd() was moved up.

 o=andreas.dilger
 i=johann
 i=dmitry.zogin
 i=nathan.rutman

11 years agob=20953 sanity-quota test 30 fixes
Andrew Perepechko [Mon, 19 Apr 2010 23:29:30 +0000 (16:29 -0700)]
b=20953 sanity-quota test 30 fixes

i=Yong Fan

11 years agob=22310 temporary fix: align readahead window end to 1M rpc boundary.
Eric Mei [Mon, 19 Apr 2010 23:29:27 +0000 (16:29 -0700)]
b=22310 temporary fix: align readahead window end to 1M rpc boundary.

r=wangdi
r=rread

11 years agob=22310 do not break early in osc_io_submit() which might cause sub-optimal rpc size...
Eric Mei [Mon, 19 Apr 2010 23:29:25 +0000 (16:29 -0700)]
b=22310 do not break early in osc_io_submit() which might cause sub-optimal rpc size for read and synchronous write.

i=wangdi
i=rread

11 years agob=21949 echo code fixes.
Vitaly Fertman [Mon, 19 Apr 2010 23:29:21 +0000 (16:29 -0700)]
b=21949 echo code fixes.

i=eric.may
i=bzzz

1. access to a wrong page on echo server commit;
2. wrong lock type enqueue in echo client test_brw code;
3. wrong thread offset initialization in lctl test_brw code;

11 years agob=18478 Fix sanity test_180 to write to correct obj
Robert Read [Mon, 19 Apr 2010 18:24:25 +0000 (11:24 -0700)]
b=18478 Fix sanity test_180 to write to correct obj

Write small amount of data to the object that was created. This
also splits 180 into two tests for using echo client with an osc
and directly to an obdfilter.

i=vitaly

11 years agob=20647 Ensure all needed pids exits before failover in test set 53
Mikhail Pershin [Fri, 16 Apr 2010 20:31:21 +0000 (13:31 -0700)]
b=20647 Ensure all needed pids exits before failover in test set 53

i=rread
i=grev

11 years agob=21826 a small fix for quota files invalidation
Andrew Perepechko [Fri, 16 Apr 2010 20:31:18 +0000 (13:31 -0700)]
b=21826 a small fix for quota files invalidation

i=Johann Lombardi
i=ZhiYong Tian

11 years agob=20615 always send ZC_ACK on non-blocking connection
Liang Zhen [Fri, 16 Apr 2010 20:31:13 +0000 (13:31 -0700)]
b=20615 always send ZC_ACK on non-blocking connection

i=isaac
i=maxim

11 years agob=18948 Speedy recovery
Mikhail Pershin [Fri, 16 Apr 2010 20:30:30 +0000 (13:30 -0700)]
b=18948 Speedy recovery

Add hard and soft time limits for server recovery.

i=andrew.perepechko
i=Hongchao.zhang

11 years agoRevert "b=20647 Ensure all needed pids exits before failover in test set 53"
Robert Read [Thu, 15 Apr 2010 23:06:54 +0000 (16:06 -0700)]
Revert "b=20647 Ensure all needed pids exits before failover in test set 53"

The "Cleanup wait_..._import_state function" part of this patch appears to cause
bug 22594.

This reverts commit 8f6d85eebc312b64d8e8a35b0be3ae137a50a45c.

11 years agob=22147 do not reset owner for lockless lock.
Eric Mei [Thu, 15 Apr 2010 05:39:44 +0000 (22:39 -0700)]
b=22147 do not reset owner for lockless lock.

r=wangdi
r=vitaly

11 years agob=22056 hash_add not under spinlock.
Vitaly Fertman [Thu, 15 Apr 2010 05:39:41 +0000 (22:39 -0700)]
b=22056 hash_add not under spinlock.

a refcount is added to the hash, move hash_add from under spinlock with no race against hash_destroy.

i=green
i=tappro

11 years agoPrepare for build 40. 1.10.0.40 v1_10_0_40
Robert Read [Sun, 11 Apr 2010 18:27:47 +0000 (11:27 -0700)]
Prepare for build 40.

11 years agob=22190 return error on write if rdonly mode is on, don't reply if umount
Mikhail Pershin [Fri, 9 Apr 2010 01:24:07 +0000 (18:24 -0700)]
b=22190 return error on write if rdonly mode is on, don't reply if umount

i=oleg

11 years agob=22359 fix t_id for the recovery thread
Alexander.Zarochentsev [Fri, 9 Apr 2010 01:24:01 +0000 (18:24 -0700)]
b=22359 fix t_id for the recovery thread

arbitrary uninialized value in the recovery thread t_id
was the reason of filter_iobuf_get()) ASSERTION(thread_id <
filter->fo_iobuf_count) failure.

i=tappro
i=andrew.perepechko

11 years agob=11063 set mtime to past under PW EOF extent lock (v6)
Vladimir Saveliev [Fri, 9 Apr 2010 01:24:01 +0000 (18:24 -0700)]
b=11063 set mtime to past under PW EOF extent lock (v6)

(according to HLD: https://bugzilla.lustre.org/attachment.cgi?id=15441).

new IO type (CIT_SETATTR) replaces CIT_TRUNC

Eariler patches
         https://bugzilla.lustre.org/attachment.cgi?id=7933
         https://bugzilla.lustre.org/attachment.cgi?id=7882
are reversed.

i=ericm
i=vitaly

11 years agob=11063 mtime tests
Vladimir Saveliev [Fri, 9 Apr 2010 01:24:00 +0000 (18:24 -0700)]
b=11063 mtime tests

few tests from 11063 and 21114

i=grev

11 years agob=22526 rename num_possible_cpus() to cfs_num_possible_cpus()
Robert Read [Thu, 8 Apr 2010 00:39:06 +0000 (17:39 -0700)]
b=22526 rename num_possible_cpus() to cfs_num_possible_cpus()

a=kenh@cmf.nrl.navy.mil
i=rread

11 years agob=19505 changelogs - distinguish between SETATTR and [acm]time changes
Nathan Rutman [Wed, 13 Jan 2010 22:21:18 +0000 (14:21 -0800)]
b=19505 changelogs - distinguish between SETATTR and [acm]time changes

i=breitz
i=LEIBOVICI Thomas <thomas.leibovici@cea.fr>

11 years agob=21966 can not mount mdt after umount
Rahul Deshmukh [Wed, 7 Apr 2010 17:18:18 +0000 (10:18 -0700)]
b=21966 can not mount mdt after umount

i=johann

11 years agofix typo in recovery-*-scale.sh script
Johann Lombardi [Wed, 7 Apr 2010 08:17:59 +0000 (10:17 +0200)]
fix typo in recovery-*-scale.sh script

11 years agob=22505 Initialize cui_tot_nregs for liblustre
Robert Read [Sat, 3 Apr 2010 02:01:53 +0000 (19:01 -0700)]
b=22505 Initialize cui_tot_nregs for liblustre

Change 910bf010 inadvertantly broke liblustre because cio->cui_tot_nregs
was not initilized, and ccc_io_update_iov was setting cui_nregs
incorrectly.

i=eric.mei
i=yong.fan

11 years agob=22312 sanity test 33c has problems parsing llobdstat when write_bytes is large
root [Tue, 6 Apr 2010 22:23:06 +0000 (15:23 -0700)]
b=22312 sanity test 33c has problems parsing llobdstat when write_bytes is large

i=robert.read@sun.com

11 years agob=21502 symlink compatibility between 1.6 and 2.0
Rahul Deshmukh [Mon, 5 Apr 2010 18:50:40 +0000 (11:50 -0700)]
b=21502 symlink compatibility between 1.6 and 2.0

Fixed the symlink compatibility problem between 1.6/1.8 and 2.0 related to short symlinks.

i=bzzz
i=andreas
i=pravin

11 years agob=20339 Remove LPSZ definition.
pravin [Mon, 5 Apr 2010 18:50:34 +0000 (11:50 -0700)]
b=20339 Remove LPSZ definition.

a=andreas.dilger
i=alexey.lyashkov
i=pravin

11 years agob=20562 Increasing super sequence width so that there will be lesser update to fld...
pravin [Mon, 5 Apr 2010 18:50:26 +0000 (11:50 -0700)]
b=20562 Increasing super sequence width so that there will be lesser update to fld table.

We can not increase LUSTRE_SEQ_META_WIDTH, meta sequence is allocated to client
and client can loose it in case of crash and there is no recovery mechanism.
MDT can not loose super sequence as it is stored on MDT disk.

i=andreas.dilger
i=tappro

11 years agob=21476 fix race between mdt_finish and __mds_lov_synchronize
pravin [Mon, 5 Apr 2010 18:49:56 +0000 (11:49 -0700)]
b=21476 fix race between mdt_finish and __mds_lov_synchronize

i=FanYong
i=Rahul

11 years agob=20647 Ensure all needed pids exits before failover in test set 53
Mikhail Pershin [Mon, 5 Apr 2010 18:49:50 +0000 (11:49 -0700)]
b=20647 Ensure all needed pids exits before failover in test set 53

Cleanup wait_..._import_state function.

i=rread
i=grev

11 years agob=20680 add sleep to expire stat cache
Mikhail Pershin [Mon, 5 Apr 2010 18:49:48 +0000 (11:49 -0700)]
b=20680 add sleep to expire stat cache

i=grev

11 years agob=22235 llapi_uuid_match() prints bogus error message on upgraded filesystem
Dmitry Zogin [Mon, 5 Apr 2010 18:49:44 +0000 (11:49 -0700)]
b=22235 llapi_uuid_match() prints bogus error message on upgraded filesystem

 Change lov_iocontrol(), lmv_iocontrol() and mdc_iocontrol() functions to copy UUID
 string into a buffer before calling *_statfs() functions, so that UUID is
 always set when returning to the caller

 i=andreas.dilger
 i=nathan.rutman

11 years agob=22235 llapi_uuid_match() prints bogus error message on upgraded filesystem
Dmitry Zogin [Mon, 5 Apr 2010 18:49:42 +0000 (11:49 -0700)]
b=22235 llapi_uuid_match() prints bogus error message on upgraded filesystem

   1. Increase the "lfs df" column width to handle TB sized devices cleanly
   2. Allow matching OST names without trailing _UUID v2 (validate lengths)
   3. Allow negating the "--obd" option to "lfs find"
   4. Remove duplicate code in mntdf() iterating over MDTs/OSTs; handle errors

   o=andreas.dilger
   i=dmitry.zogin
   i=nathan.rutman

11 years agob=21527 Fix format for ia64 and ppc64.
Robert Read [Fri, 2 Apr 2010 20:10:24 +0000 (13:10 -0700)]
b=21527 Fix format for ia64 and ppc64.

11 years agob22312 Fix off-by-one bug in second loop in test 33c.
Nicolas Williams [Fri, 2 Apr 2010 21:59:32 +0000 (14:59 -0700)]
b22312 Fix off-by-one bug in second loop in test 33c.

i=robert.read@sun.com

11 years agoUpdated for build 39. 1.10.0.39 v1_10_0_39
Terry Rutledge [Fri, 2 Apr 2010 18:23:52 +0000 (11:23 -0700)]
Updated for build 39.

11 years agoPrepare Build 39.
Robert Read [Fri, 2 Apr 2010 18:18:05 +0000 (11:18 -0700)]
Prepare Build 39.

11 years agob=22225 Remove += and refactor equals_msg
Robert Read [Thu, 18 Mar 2010 23:05:59 +0000 (16:05 -0700)]
b=22225 Remove += and refactor equals_msg

11 years agob=19208 Add ext3_get_inode_flags()
Pravin Shelar [Fri, 2 Apr 2010 17:56:05 +0000 (10:56 -0700)]
b=19208 Add ext3_get_inode_flags()

Expose i_flags to user.
i=rahul
i=fanyong

11 years agob=22327 "lfs df" does not print stats for all mountpoints
Dmitry Zogin [Fri, 19 Mar 2010 02:14:23 +0000 (22:14 -0400)]
b=22327 "lfs df" does not print stats for all mountpoints

 1. print all mounted lustre filesystems with "lfs df"
 2. sanityn test_24b added

11 years agob=21406 remove call to clear_page_dirty_for_io()
Wang Di [Thu, 1 Apr 2010 22:40:41 +0000 (15:40 -0700)]
b=21406 remove call to clear_page_dirty_for_io()

 fix deadlock between kjournald2 trying to acquire the page lock
 owned by an ost_io thread waiting for journal commit.
 o=johann
 i=adiger
 i=girish

11 years agob=21877 protect modification of request flag's bitfield with rq_lock
Mikhail Pershin [Thu, 1 Apr 2010 22:40:41 +0000 (15:40 -0700)]
b=21877 protect modification of request flag's bitfield with rq_lock

11 years agob=22299 do not set lustre read_only device when server umount and keep client records...
Fan Yong [Thu, 1 Apr 2010 22:40:41 +0000 (15:40 -0700)]
b=22299 do not set lustre read_only device when server umount and keep client records for recoverable ones

1) do not set lustre read_only device when server umount
2) keep client records for recoverable ones under failover mode
3) do not ignore "WRITE_SYNC" (which is used by kmmpd block updating) for "dev_check_rdonly()" checking

i=andreas.dilger
i=tappro

11 years agob=21636 diagnostic patch for LDLM_BL_CALLBACK reply processing
Fan Yong [Thu, 1 Apr 2010 22:40:41 +0000 (15:40 -0700)]
b=21636 diagnostic patch for LDLM_BL_CALLBACK reply processing

diagnostic patch for LDLM_BL_CALLBACK reply processing

i=robert.read
i=tom.wang

11 years agob=22312 write_bytes are missing in obdfilter stats
Nicolas Williams [Thu, 1 Apr 2010 22:40:40 +0000 (15:40 -0700)]
b=22312 write_bytes are missing in obdfilter stats

There's a missing lprocfs_counter_add() for LPROC_FILTER_WRITE_BYTES in
filter_io.c:filter_preprw_write().  A test is also delivered.

i=robert.read@sun.com

11 years agob=20433 Move new ChangeLog entry to the top.
Robert Read [Wed, 31 Mar 2010 19:04:34 +0000 (12:04 -0700)]
b=20433 Move new ChangeLog entry to the top.

11 years agob=20057 Add init_logging to replay-vbr
Robert Read [Wed, 31 Mar 2010 18:55:00 +0000 (11:55 -0700)]
b=20057 Add init_logging to replay-vbr

Left out from original autovetting patch.

i=tappro
i=grev
a=manoj

11 years agob=21527 Portability fixes
Robert Read [Wed, 31 Mar 2010 18:15:01 +0000 (11:15 -0700)]
b=21527 Portability fixes

Fix typo in commit 8eaf21f9.

11 years agob=20433 decrease the usage of memory on clients.
Landen [Tue, 30 Mar 2010 22:45:10 +0000 (15:45 -0700)]
b=20433 decrease the usage of memory on clients.

1. On clients, recycle dentries and inodes unused.
2. Delete the code related to ll_deathrow(att 6215 in bug 1443). It
   is useless now.

i=robert.read
i=vladimir.saveliev

11 years agob=19944 promise every cpu has at least 2MB debug memory.
Landen [Tue, 30 Mar 2010 19:00:32 +0000 (12:00 -0700)]
b=19944 promise every cpu has at least 2MB debug memory.

i=johann