Whamcloud - gitweb
grev [Thu, 12 Mar 2009 16:56:29 +0000 (16:56 +0000)]
b=18761
i=Oleg.Drokin
declare array fix
girish [Thu, 12 Mar 2009 11:43:03 +0000 (11:43 +0000)]
b=15524
i=adilger
i=kalpak
sanity test 102 changes for lustre-tar package
grev [Wed, 11 Mar 2009 16:06:28 +0000 (16:06 +0000)]
b=18696
i=Tappro
new RECOVERY_RANDOM_SCALE test;
zconf_umount_clients fn remote command fix;
grev [Wed, 11 Mar 2009 16:04:14 +0000 (16:04 +0000)]
file recovery-random-scale.sh was added on branch b_release_1_8_0 on 2009-03-11 16:06:28 +0000
yangsheng [Wed, 11 Mar 2009 10:45:08 +0000 (10:45 +0000)]
Branch b_release_1_8_0
b=17701
Extra patch for swab lov.
tappro [Wed, 11 Mar 2009 09:04:38 +0000 (09:04 +0000)]
- set correct thread in rq_srv_thread for requests processing in
process_recovery_queue()
b:18221
i:adilger,rread,johann
tianzy [Wed, 11 Mar 2009 08:28:16 +0000 (08:28 +0000)]
Branch b_release_1_8_0
add more At debug info and fix a problem in test_68 in replay-single.sh
b=18426
i=nathan.rutman
yangsheng [Wed, 11 Mar 2009 07:04:30 +0000 (07:04 +0000)]
Branch b_release_1_8_0
b=17701
i=adilger, nathan
Fixed the lov_getstripe works well in Big-Endian.
girish [Sun, 8 Mar 2009 08:14:16 +0000 (08:14 +0000)]
b=17846
i=adilger
i=h.huang
changes to regression test after landing 17846 Lustre patch. make sure all files are not extracted on OST id 0
tappro [Fri, 6 Mar 2009 21:27:58 +0000 (21:27 +0000)]
- use invalidate_mapping_pages for old kernels in case of disabled ROC for simplicity
b:18718
i:adilger,johann
johann [Fri, 6 Mar 2009 19:47:47 +0000 (19:47 +0000)]
Branch b_release_1_8_0
b=18558
fix warning.
yangsheng [Fri, 6 Mar 2009 17:54:09 +0000 (17:54 +0000)]
Branch b_release_1_8_0
b=18718
i=johann, shadow
Fixed build issues for sles9.
stinson1947 [Thu, 5 Mar 2009 23:08:48 +0000 (23:08 +0000)]
updated for estimated 1.8.0 release date
johann [Thu, 5 Mar 2009 21:34:31 +0000 (21:34 +0000)]
Branch b_release_1_8_0
b=18154
i=shadow
i=johann (original patch from bobijam)
always calls ptlrpc_import_recovery_state_machine() in
invalidate_import_thread() because otherwise threads sleeping on
the import's imp_recovery_waitq could be never woken up.
tappro [Thu, 5 Mar 2009 06:54:15 +0000 (06:54 +0000)]
- use truncate instead of invalidate to drop referenced pages from cache. This
is needed to disable ROC correctly
b:18520
i:adilger,green
green [Wed, 4 Mar 2009 19:13:48 +0000 (19:13 +0000)]
b=17614
r=adilger, shadow
Do not put cancelled locks into replay list, hold references on locks in replay list
zam [Wed, 4 Mar 2009 18:43:19 +0000 (18:43 +0000)]
Branch b_release_1_8_0
b=17397
i=alexey.zhuravlev
i=andrew.perepechko
To avoid a deadlock in case of concurrent punch/write requests from one
client, filter writes and filter truncates are serialized by i_alloc_sem,
allowing multiple writes or single truncate.
johann [Tue, 3 Mar 2009 17:50:52 +0000 (17:50 +0000)]
Branch b_release_1_8_0
b=18414
i=nathan
i=shadow
fix watchdog timeout printed on the console. This was wrong since
support variable watchdogs has been landed.
zhanghc [Tue, 3 Mar 2009 16:42:37 +0000 (16:42 +0000)]
b=17757
clear DISP_OPEN_LOCK flag in "reconstruct_open"
if the corresponding lock was canceled
i=Green
i=Johann
johann [Tue, 3 Mar 2009 15:08:48 +0000 (15:08 +0000)]
Branch b_release_1_8_0
b=18374
i=adilger
i=shadow
use memmove instead of memcpy when shrinking the reply since the two memory
areas can overlap.
grev [Tue, 3 Mar 2009 13:02:31 +0000 (13:02 +0000)]
b=17524
reset_enospc fn: fix defect of previous commit
grev [Fri, 27 Feb 2009 00:38:21 +0000 (00:38 +0000)]
b=17524
i=Adilger
exhaust_precreations, reset_enospc, test_27n, test_27s fixes
grev [Fri, 27 Feb 2009 00:16:49 +0000 (00:16 +0000)]
fix typo in b=17839 commit (made while ported from HEAD)
nathan [Thu, 26 Feb 2009 19:51:45 +0000 (19:51 +0000)]
b=18606
i=adigler
i=johann
use pool of "all" if specified pool is empty
girish [Thu, 26 Feb 2009 06:19:48 +0000 (06:19 +0000)]
b=17846
i=girish
i=h.huang
o=adilger
ignore stripe index 0 when setting striping via setxattr
grev [Wed, 25 Feb 2009 16:52:48 +0000 (16:52 +0000)]
b=18468
o=Adilger
i=Oleg.Drokin
i=grev
make racer harder
fanyong [Wed, 25 Feb 2009 16:36:30 +0000 (16:36 +0000)]
Branch b_release_1_8_0
b=15691
i=huanghua
i=yep
Another diagnostic patch to collect more log when error.
grev [Tue, 24 Feb 2009 22:41:36 +0000 (22:41 +0000)]
b=17839
i=Brian
cmd3-17 port to acc-sm
grev [Fri, 20 Feb 2009 21:25:42 +0000 (21:25 +0000)]
b=18443
i=Adilger
remove obsolete tests scripts
grev [Thu, 19 Feb 2009 22:18:01 +0000 (22:18 +0000)]
b=18521
i=Alex.Zhuravlev
sanity test_151, t-f localize var fix
nathan [Wed, 18 Feb 2009 00:04:39 +0000 (00:04 +0000)]
b=18266
allow pool_cmd to work on MGS with no MDT or client
b=18516
fix parsing to correctly handle hex OST numbers
i=jc.lafoucriere
i=johann
grev [Tue, 17 Feb 2009 20:42:18 +0000 (20:42 +0000)]
b=18285
i=Rahul
i=Nathan
test_32a fix: remove mount client part
vs [Tue, 17 Feb 2009 20:16:40 +0000 (20:16 +0000)]
b=18428
i=shadow,tappro,rread
do not send requests to inactive targets
girish [Mon, 16 Feb 2009 07:47:42 +0000 (07:47 +0000)]
b=18470
i=johann
i=adilger
Correct error handling
jxiong [Sun, 15 Feb 2009 02:35:14 +0000 (02:35 +0000)]
b=15428
r=adilger
Fixed a crash issue for raid56-zerocopy
grev [Fri, 13 Feb 2009 19:54:12 +0000 (19:54 +0000)]
b=18333
i=Oleg.Drokin
add flock to default mount opts
grev [Fri, 13 Feb 2009 13:44:13 +0000 (13:44 +0000)]
fix typo for
b=16488
i=Oleg.Drokin
RACER acc-sm test suit
grev [Thu, 12 Feb 2009 18:51:55 +0000 (18:51 +0000)]
b=17839
i=Brian
recovery-mds-scale for SLOW=no
grev [Thu, 12 Feb 2009 16:14:38 +0000 (16:14 +0000)]
revert b=17839 commit
grev [Thu, 12 Feb 2009 15:32:45 +0000 (15:32 +0000)]
b=17839
i=Brian
recovery-mds-scale for SLOW=no
girish [Wed, 11 Feb 2009 18:08:16 +0000 (18:08 +0000)]
b=18417
o=h.huang
i=girish
Fix typo from last commit which caused test-framework to exit wrongly
girish [Wed, 11 Feb 2009 06:55:51 +0000 (06:55 +0000)]
b=18417
i=kalpak
i=girish
o=adilger
cleanup correctly after sanity 102 tests
jxiong [Tue, 10 Feb 2009 07:05:18 +0000 (07:05 +0000)]
b=15428
r=adilger
Fix a crash issue for raid5 zercopy patch.
tianzy [Tue, 10 Feb 2009 04:29:47 +0000 (04:29 +0000)]
Branch b_release_1_8_0
add an entry under /proc to support what policy(RR or QOS) will be used.
b=18334
i=nathan
i=adilger
grev [Mon, 9 Feb 2009 23:44:35 +0000 (23:44 +0000)]
b=18366
i=Johann
test_5 ENOSPC fix
johann [Mon, 9 Feb 2009 14:59:19 +0000 (14:59 +0000)]
Branch b_release_1_8_0
i=johann (patch from Tappro)
i=shadow
Return only valid cookies, empty slot for failed ones.
This fixes a memory corruption causing random oops.
johann [Mon, 9 Feb 2009 14:57:20 +0000 (14:57 +0000)]
Branch b_release_1_8_0
b=18374
i=shadow
i=tappro
Wait for mds_fl_synced to be set during recovery before allowing clients
to reconnect. This is done to make sure that llog is properly set up.
johann [Mon, 9 Feb 2009 14:56:09 +0000 (14:56 +0000)]
Branch b_release_1_8_0
b=18067
i=johann
i=adilger
Change oap magic LASSERT into LASSERTF to aid debugging.
green [Mon, 9 Feb 2009 00:17:38 +0000 (00:17 +0000)]
b=16823
r=adilger,shadow
Update offset calculations for 32 bit platforms
yangsheng [Thu, 5 Feb 2009 07:49:49 +0000 (07:49 +0000)]
Branch b_release_1_8_0
b=17459
i=adilger, bobijam
Fixed ext2_{...}_bit() works well in BIGENDIAN.
yangsheng [Thu, 5 Feb 2009 07:43:06 +0000 (07:43 +0000)]
Branch b_release_1_8_0
b=17379
i=johann, bobijam
Fixed correct depth for test-140.
grev [Tue, 3 Feb 2009 13:32:57 +0000 (13:32 +0000)]
b=17899
i=Johann
test_53* fix: rm dirs used at start
tianzy [Tue, 3 Feb 2009 06:44:35 +0000 (06:44 +0000)]
Branch b_release_1_8_0
use QUOTA_REQ_RETURNED to replace -EAGAIN when a quota req is finished.
b=18307
i=johann
i=panda
grev [Mon, 2 Feb 2009 13:53:14 +0000 (13:53 +0000)]
remove debug line
grev [Mon, 2 Feb 2009 12:59:18 +0000 (12:59 +0000)]
b=16818
i=Nathan
get rid of set_obd_timeout(), improve test_26*
kalpak [Mon, 2 Feb 2009 09:15:37 +0000 (09:15 +0000)]
b=17895
i=adilger
i=alex
While using HA for Lustre servers with Linux RAID, it is possible that MMP will not detect multiple mounts. To make this work we need to unplug the device queue in RAID when the MMP block is being written. Also while reading the MMP block, we should read it from disk and not the cached one.
huanghua [Thu, 29 Jan 2009 09:08:55 +0000 (09:08 +0000)]
Branch b_release_1_8_0
b=18318
i=rahul
i=pravin
reserve larger reply buffer for close and unlink:
2.0 mds wire protocol returns capabilities.
girish [Wed, 28 Jan 2009 11:29:40 +0000 (11:29 +0000)]
Return EXT_UNSET_BLOCK from ext3_ext_next_leaf_block.
Patch was missing for 2.6.22
Added changelog entry along with newer build version.
b=16114
shadow [Wed, 28 Jan 2009 09:09:30 +0000 (09:09 +0000)]
don't lose wakeup for imp_recovery_waitq
Branch b_release_1_8_0
b=18154
i=nathan
i=rread
girish [Wed, 28 Jan 2009 03:52:26 +0000 (03:52 +0000)]
b=16895
i=adilger (o=johann)
i=girish
dont assert on lvfs_check_rdonly()
yangsheng [Sat, 24 Jan 2009 18:11:57 +0000 (18:11 +0000)]
Branch b_release_1_8_0
b=15593
i=nikita, shadow
Force to remove the suid in interop environment.
grev [Sat, 24 Jan 2009 09:16:51 +0000 (09:16 +0000)]
b=18045
i=Adilger
-- get rid of Hendrix rates values
-- create NUM_FILES -le IFree
-- use mdsrate for cleanup instead of rm
huanghua [Sat, 24 Jan 2009 02:09:36 +0000 (02:09 +0000)]
Branch b_release_1_8_0
b=17777
i=robert.read
as Robert suggests, get lustre version with more precise match.
huanghua [Fri, 23 Jan 2009 17:09:51 +0000 (17:09 +0000)]
b=17777
i=grev
i=adilger
i=robert.read
test scripts improvement to enable interop testing between 1.8 and 2.0
grev [Fri, 23 Jan 2009 13:55:43 +0000 (13:55 +0000)]
b=18279
i=Nathan
AT tests cleanup: run setup/cleanup only if AT tests run
shadow [Fri, 23 Jan 2009 13:32:34 +0000 (13:32 +0000)]
don't leak openhandle in ESTALE case.
Branch b_release_1_8_0
b=16417
i=green
i=johann
i=bobijam
tianzy [Fri, 23 Jan 2009 09:50:27 +0000 (09:50 +0000)]
Branch b_release_1_8_0
when there is any inactive ost, refuse to do quotacheck
b=18151
i=johann
i=andrew.perepechko
tianzy [Fri, 23 Jan 2009 06:21:14 +0000 (06:21 +0000)]
Branch b_release_1_8_0
fix the test issue of test_12 in sanity-quota.sh
b=18151
i=johann
i=panda
girish [Thu, 22 Jan 2009 07:37:33 +0000 (07:37 +0000)]
b=18173
i=adilger
i=kalpak
If there is error during mount, MMP should error out correctly
girish [Wed, 21 Jan 2009 18:38:51 +0000 (18:38 +0000)]
b=16895
i=adilger (o=johann)
i=girish
don't LASSERT on read-only device
huanghua [Wed, 21 Jan 2009 18:22:18 +0000 (18:22 +0000)]
Branch b_release_1_8_0
b=18267
i=yong.fan
i=rahul.deshmukh
pass default group value, that is 0, to ost:
this is for such interop: 1.8 client + 1.8 mds + 2.0 ost.
yury [Wed, 21 Jan 2009 16:48:03 +0000 (16:48 +0000)]
b=17310
r=johann
- tmp fix for long connect rpc interpreyt which causes the assert
tianzy [Wed, 21 Jan 2009 02:56:48 +0000 (02:56 +0000)]
Branch b_release_1_8_0
take refcount of export when quotacheck is going on
b=18126
i=shadow
i=panda
shadow [Tue, 20 Jan 2009 12:08:22 +0000 (12:08 +0000)]
always handle mds connect as reconnect.
Branch b_release_1_8_0
b=18224
i=johhan
i=green
i=adilger
i=wangdi
shadow [Tue, 20 Jan 2009 09:02:21 +0000 (09:02 +0000)]
don't confuse mds_finish_transno() with PTR_ERR(-ENOENT)
Branch b_release_1_8_0
b=18238
i=green
i=umka
kalpak [Tue, 20 Jan 2009 04:43:58 +0000 (04:43 +0000)]
b=17942
i=adilger
i=girish
update fiemap structures and API to match upstream
shadow [Mon, 19 Jan 2009 21:21:30 +0000 (21:21 +0000)]
release lock refernce only after add page to pages list.
Branch b_release_1_8_0
b=17972
i=shadow
i=johann
zhanghc [Tue, 13 Jan 2009 23:54:06 +0000 (23:54 +0000)]
b=17787
1, print the actual time to wait for
lock cancellation in "waiting_locks_callback"
2, compare resource in "ost_rw_hpreq_lock_match"
3, replace "LDLM_ERROR" with "LDLM_WARN" if a lock
is completed after waiting more than obd_timeout
i=vitaly.fertman
i=johann
tappro [Tue, 13 Jan 2009 07:21:42 +0000 (07:21 +0000)]
- replace assert with cwarn when gap is found in objids. This is allowed
situation due to inode reuse
b:18168
i:adilger, shadow
shadow [Sun, 11 Jan 2009 08:29:34 +0000 (08:29 +0000)]
wait until mds<>ost connect finished.
Branch b_release_1_8_0
b=18150
i=grev
shadow [Sun, 11 Jan 2009 07:16:58 +0000 (07:16 +0000)]
resolve compile issue after 16919 landing.
b=16919
Branch b_release_1_8_0
green [Sat, 10 Jan 2009 06:45:17 +0000 (06:45 +0000)]
b=18016
r=deen,wangdi
page index type in ll_read_ahead_page should be pgoff_t, not int
yury [Fri, 9 Jan 2009 12:29:36 +0000 (12:29 +0000)]
b=18114
r=umka,bzzz
- patch from shadow to fix use after free in lov_cleanup()
green [Fri, 9 Jan 2009 04:35:08 +0000 (04:35 +0000)]
b=16919
r=adilger,shadow
Implement replay of bulk write RPCs, allow servers to reply to write RPCs before
all the metadata was finally committed to disk
vs [Wed, 7 Jan 2009 23:47:40 +0000 (23:47 +0000)]
b=17694
i=adilger
run the test in separate directory
tappro [Tue, 6 Jan 2009 07:27:25 +0000 (07:27 +0000)]
- clear abort_recovery flag in target_recovery_check_and_stop()
- evict delay_list in class_handle_stale_exports() also if no delayed recovery
b:18148
i:bzzz, shadow
wangdi [Tue, 6 Jan 2009 01:39:10 +0000 (01:39 +0000)]
Branch: b_release_1_8_0
remove test 160 for bug16117
yury [Mon, 5 Jan 2009 20:04:28 +0000 (20:04 +0000)]
b=18080
- synchronize test with HEAD version and rename it to test_35 (just like in HEAD);
- OBD_RACE in all execution branches in ldlm_lock_decref_internal() to balance OBD_RACE in bl_ast
and prevent hanging.
wangdi [Sat, 3 Jan 2009 02:00:32 +0000 (02:00 +0000)]
Branch: b_release_1_8_0
b=16117
The patch from Andreas to handle the corrupt debug log nicely for lctl df.
i=adilger,wangdi
yury [Wed, 31 Dec 2008 16:16:40 +0000 (16:16 +0000)]
b=18127
- reformat after test 46a which uses 6 OST
grev [Tue, 30 Dec 2008 12:16:07 +0000 (12:16 +0000)]
b=17797
i=H.Huang
test_57b remote mds fix
stinson1947 [Mon, 29 Dec 2008 15:53:21 +0000 (15:53 +0000)]
Updated version for the 1.8.0 release candidate.
shadow [Mon, 29 Dec 2008 08:39:45 +0000 (08:39 +0000)]
send ACTIVATE event only if connect finished and import have state FULL.
Branch b_release_1_8_0
i=addilger
i=tappro
i=green
tianzy [Mon, 29 Dec 2008 07:19:09 +0000 (07:19 +0000)]
Branch b_release_1_8_0
fix test problems in test_18 of sanity-quota.sh
b=17985
i=shadow
tappro [Thu, 25 Dec 2008 07:10:42 +0000 (07:10 +0000)]
- move extra functionality from interrupt handler function
b:18103
i:adilger, bzzz
shadow [Wed, 24 Dec 2008 21:13:39 +0000 (21:13 +0000)]
checking maximal acl size before set.
Branch b_release_1_8_0
b=17636
i=johann
i=deen
anserper [Wed, 24 Dec 2008 17:34:18 +0000 (17:34 +0000)]
b=18083
i=Yong Fan
i=Andrew Perepechko
Enforce op. quota file format for MDS too
yury [Wed, 24 Dec 2008 13:02:56 +0000 (13:02 +0000)]
r=shadow
- check for OBD_FAIL_OBD_LLOG_SETUP fail_loc regardless ->lop_setup definition. This is required because
after changes in mds_ost llog setup, which is now done on behalf of separate thread, we need to make
llog_setup() fail in context of mds start thread to make the test actualy work. And those llogs which
get initialized in mds start thread do not have ->lop_setup defined.
zhanghc [Wed, 24 Dec 2008 11:54:58 +0000 (11:54 +0000)]
b=17757
remove redundant code in previous patch
i=tappro
zhanghc [Wed, 24 Dec 2008 11:06:02 +0000 (11:06 +0000)]
b=18043
fix a bug in lov_ost_pool_extend, which
use "min" instead of "max" incorrectly
i=nathan.rutman
i=jc.lafoucriere