Whamcloud - gitweb
fs/lustre-release.git
21 years agoDon't wait forever in sleep_on() if two threads call portals_debug_dumplog()
adilger [Mon, 12 Apr 2004 19:54:43 +0000 (19:54 +0000)]
Don't wait forever in sleep_on() if two threads call portals_debug_dumplog()
at the same time.
b=3107
r=zab

21 years agoDisable ll_readpage() log dumping (for debugging bug 2805), it caused bug 3122.
adilger [Thu, 8 Apr 2004 19:46:57 +0000 (19:46 +0000)]
Disable ll_readpage() log dumping (for debugging bug 2805), it caused bug 3122.
b=3122

21 years agoDon't dereference an ERR_PTR() in the mds_reint_link() error handling path.
adilger [Thu, 8 Apr 2004 19:12:01 +0000 (19:12 +0000)]
Don't dereference an ERR_PTR() in the mds_reint_link() error handling path.
b=3107
r=phil

21 years agoUpdate build tag.
adilger [Wed, 7 Apr 2004 21:53:25 +0000 (21:53 +0000)]
Update build tag.

21 years agoFix patch breakage.
adilger [Wed, 7 Apr 2004 21:52:05 +0000 (21:52 +0000)]
Fix patch breakage.

21 years agoFix duplicate merge of this hunk.
adilger [Wed, 7 Apr 2004 21:46:19 +0000 (21:46 +0000)]
Fix duplicate merge of this hunk.

21 years agoIn ll_file_read() use (*ppos + count - 1) for end of read instead of the value
adilger [Tue, 6 Apr 2004 22:29:15 +0000 (22:29 +0000)]
In ll_file_read() use (*ppos + count - 1) for end of read instead of the value
in policy->l_extent.end.  This makes the intent of the comparison more clear,
and avoids any problems if the policy data is ever changed (e.g. to return the
granted extent or similar).

Useful debugging for lock extent problems.
b=2925

21 years agoMinor correctness fixes for EA compat support:
adilger [Tue, 6 Apr 2004 22:24:54 +0000 (22:24 +0000)]
Minor correctness fixes for EA compat support:
- print the right size in the error message
- work correctly some day in the future when we have v2 EAs
b=3059

21 years agoUse the highest extent to determine the kms value, not the last one.
adilger [Tue, 6 Apr 2004 19:10:44 +0000 (19:10 +0000)]
Use the highest extent to determine the kms value, not the last one.
Try not to grant overlapping locks for the same client, to speed lock cancel.
b=2925
r=phil

21 years agoUpdate version tag.
adilger [Mon, 5 Apr 2004 18:36:21 +0000 (18:36 +0000)]
Update version tag.

21 years agoDebugging for mdc_close oops.
adilger [Mon, 5 Apr 2004 18:19:03 +0000 (18:19 +0000)]
Debugging for mdc_close oops.
b=2410
r=robert

21 years agoDon't update to the kms value for a lock that is just in the process of
adilger [Mon, 5 Apr 2004 18:14:48 +0000 (18:14 +0000)]
Don't update to the kms value for a lock that is just in the process of
being cancelled.
b=3057
r=phil

21 years agoNULL the filter arrays as they are freed to avoid potential problems on cleanup.
adilger [Sat, 3 Apr 2004 19:28:33 +0000 (19:28 +0000)]
NULL the filter arrays as they are freed to avoid potential problems on cleanup.
r=phil

21 years agoInitialize lock handle so that we don't fail ASSERT on error cleanup.
adilger [Sat, 3 Apr 2004 19:27:21 +0000 (19:27 +0000)]
Initialize lock handle so that we don't fail ASSERT on error cleanup.
b=3057
r=phil

21 years agoQuiet compiler warning.
adilger [Sat, 3 Apr 2004 04:40:53 +0000 (04:40 +0000)]
Quiet compiler warning.
b=1557

21 years agoDon't dereference uninitialized variable.
adilger [Sat, 3 Apr 2004 04:39:18 +0000 (04:39 +0000)]
Don't dereference uninitialized variable.
b=2543

21 years agoChange default stripe size based on ALC/ADEV testing.
adilger [Thu, 1 Apr 2004 19:50:19 +0000 (19:50 +0000)]
Change default stripe size based on ALC/ADEV testing.

21 years agoMinor changes to sync b1_2 with HEAD that shouldn't affect anything.
adilger [Thu, 1 Apr 2004 12:04:48 +0000 (12:04 +0000)]
Minor changes to sync b1_2 with HEAD that shouldn't affect anything.

21 years agoMinor changes to sync b1_2 with HEAD that shouldn't affect anything.
adilger [Thu, 1 Apr 2004 12:03:07 +0000 (12:03 +0000)]
Minor changes to sync b1_2 with HEAD that shouldn't affect anything.

21 years agoDisable tests for which fixes are not currently in b1_2.
adilger [Thu, 1 Apr 2004 11:41:45 +0000 (11:41 +0000)]
Disable tests for which fixes are not currently in b1_2.

21 years agoFix sanity test.
adilger [Thu, 1 Apr 2004 06:42:31 +0000 (06:42 +0000)]
Fix sanity test.
b=1414

21 years agoDon't allow setstripe on a file/directory without write permission for same.
adilger [Thu, 1 Apr 2004 00:52:40 +0000 (00:52 +0000)]
Don't allow setstripe on a file/directory without write permission for same.
Regression tests for setstripe permission check.
b=1414

21 years agoFix mismerge from HEAD.
adilger [Thu, 1 Apr 2004 00:48:48 +0000 (00:48 +0000)]
Fix mismerge from HEAD.

21 years agoMerge from HEAD to b1_2 select fixes for 1.2.2
adilger [Wed, 31 Mar 2004 22:36:42 +0000 (22:36 +0000)]
Merge from HEAD to b1_2 select fixes for 1.2.2
b=2922, b=2948, b=1414

21 years agoMerge fixes from b_smallfix to b1_2 for 1.2.2
adilger [Wed, 31 Mar 2004 20:37:02 +0000 (20:37 +0000)]
Merge fixes from b_smallfix to b1_2 for 1.2.2
b=2947, b=2543, b=1557, b=2009

21 years agoKeep tests in sync with HEAD.
adilger [Wed, 31 Mar 2004 19:38:09 +0000 (19:38 +0000)]
Keep tests in sync with HEAD.

21 years agoBump kernel patch version to 34, to match HEAD.
adilger [Wed, 31 Mar 2004 19:30:21 +0000 (19:30 +0000)]
Bump kernel patch version to 34, to match HEAD.
b=2517, b=2399 are the changes for this kernel version

21 years agoFix test errors for 6 & 7 (wasn't waiting for async delete to complete).
adilger [Wed, 31 Mar 2004 04:24:00 +0000 (04:24 +0000)]
Fix test errors for 6 & 7 (wasn't waiting for async delete to complete).
b=2921

21 years agoDon't copy lvb into possibly NULL reply on ldlm_handle_enqueue() error
adilger [Wed, 31 Mar 2004 01:02:01 +0000 (01:02 +0000)]
Don't copy lvb into possibly NULL reply on ldlm_handle_enqueue() error
client won't use it anyways.  Regression test for same.
Fix secondary bug hit during regression tests in mds_mfd_close() cleanup.
b=2983

21 years agoDon't enable D_MALLOC by default, slipped in during debugging.
adilger [Tue, 23 Mar 2004 19:32:58 +0000 (19:32 +0000)]
Don't enable D_MALLOC by default, slipped in during debugging.

21 years agoDon't print an error message for a normal race.
adilger [Tue, 23 Mar 2004 07:16:25 +0000 (07:16 +0000)]
Don't print an error message for a normal race.
b=2526

21 years agobump to 1.2.1
jacob [Mon, 22 Mar 2004 17:38:21 +0000 (17:38 +0000)]
bump to 1.2.1

21 years agoUpdate release date.
adilger [Mon, 22 Mar 2004 17:29:37 +0000 (17:29 +0000)]
Update release date.

21 years agoUpdate build version (final test release).
adilger [Sun, 21 Mar 2004 06:24:23 +0000 (06:24 +0000)]
Update build version (final test release).

21 years agoDon't grow lock extents too much if there are many conflicting lockers. For
adilger [Sun, 21 Mar 2004 06:23:38 +0000 (06:23 +0000)]
Don't grow lock extents too much if there are many conflicting lockers.  For
write locks we grow to at most 32MB upwards and never downwards.  For read
locks we also limit downward growth under contention to try and avoid granting
overlapping locks (cancellation of which is very slow for large files).

This actually improves single-file IOR write performance noticably
(100-500MB/s) with no impact to FPP IOR, but we still suffer on the read
side as eventually the read locks overlap and cancellation is very CPU
intensive.  Fixing bug 20 is the solution to that.
b=2919
r=phil

21 years agoDon't dereference freed lock when lock cancellation is racing with export
adilger [Sun, 21 Mar 2004 06:15:51 +0000 (06:15 +0000)]
Don't dereference freed lock when lock cancellation is racing with export
eviction.
Create a constant for freed memory to make it easier to check.
Test 45 in replay-single is disabled because with or without the patch the
forced client cleanup isn't working properly.
b=2867
r=phil,robert

21 years agoReturn original error code to application.
adilger [Sun, 21 Mar 2004 06:09:05 +0000 (06:09 +0000)]
Return original error code to application.

21 years agoIt isn't necessarily an error when this message appears.
adilger [Sat, 20 Mar 2004 04:36:18 +0000 (04:36 +0000)]
It isn't necessarily an error when this message appears.

21 years agoIf we're going to LBUG on referenced lock, we may as well print an error.
adilger [Sat, 20 Mar 2004 04:25:06 +0000 (04:25 +0000)]
If we're going to LBUG on referenced lock, we may as well print an error.
Dump names of locks in dump instead of number (which changed recently).

21 years agoDeleted wrong definition.
adilger [Sat, 20 Mar 2004 00:16:56 +0000 (00:16 +0000)]
Deleted wrong definition.

21 years agoRemove GNS changes from b1_2.
adilger [Fri, 19 Mar 2004 23:57:51 +0000 (23:57 +0000)]
Remove GNS changes from b1_2.

21 years agob=2399, 2325, 2805
jacob [Fri, 19 Mar 2004 21:20:26 +0000 (21:20 +0000)]
b=2399, 2325, 2805

new kernel patches for chaos-2.4.18 that were committed on other
series files earlier

21 years agoThis commit was manufactured by cvs2svn to create branch 'b1_2'.
cvs2svn [Fri, 19 Mar 2004 19:46:42 +0000 (19:46 +0000)]
This commit was manufactured by cvs2svn to create branch 'b1_2'.

21 years agoDon't commit generated Makefile to CVS.
adilger [Fri, 19 Mar 2004 19:46:41 +0000 (19:46 +0000)]
Don't commit generated Makefile to CVS.
b=1414

21 years agofix for move of lustre_user.h
nic [Fri, 19 Mar 2004 19:46:19 +0000 (19:46 +0000)]
fix for move of lustre_user.h

21 years ago- get liblustre building with automake-recent
zab [Fri, 19 Mar 2004 18:42:43 +0000 (18:42 +0000)]
- get liblustre building with automake-recent

21 years ago- Fix some b_1414 build and formatting issues
phil [Fri, 19 Mar 2004 17:05:44 +0000 (17:05 +0000)]
- Fix some b_1414 build and formatting issues
- Apply Oleg's patch to fix 'lctl modules' (b_cray_portals_merge damage)

21 years agoLanding b_bug1414
shaocheng [Fri, 19 Mar 2004 13:38:35 +0000 (13:38 +0000)]
Landing b_bug1414

21 years ago to make Lustre build with 2.6.3+mm4 and suse 2.6
hitao [Fri, 19 Mar 2004 10:58:58 +0000 (10:58 +0000)]
 to make Lustre build with 2.6.3+mm4 and suse 2.6

21 years agoUpdate the oh-so-important ptlrpc/pack_generic version of
adilger [Fri, 19 Mar 2004 10:04:46 +0000 (10:04 +0000)]
Update the oh-so-important ptlrpc/pack_generic version of
lustre_assert_wire_constants(), without which it is impossible to run a test.

Likely needs to be merged back to b_cray_* from whence it came.

21 years agoFix portals user-space compile breakage on x86_64.
ericm [Fri, 19 Mar 2004 09:30:22 +0000 (09:30 +0000)]
Fix portals user-space compile breakage on x86_64.

21 years agoAllow a file to be opened with our very own O_LOV_DELAY_CREATE.
adilger [Fri, 19 Mar 2004 07:53:25 +0000 (07:53 +0000)]
Allow a file to be opened with our very own O_LOV_DELAY_CREATE.

21 years agoFix typo.
adilger [Fri, 19 Mar 2004 07:10:06 +0000 (07:10 +0000)]
Fix typo.

21 years agoland b_cray_delivery on HEAD
phil [Fri, 19 Mar 2004 06:33:27 +0000 (06:33 +0000)]
land b_cray_delivery on HEAD
liblustre fixes and group lock support

21 years agob=2790
nic [Fri, 19 Mar 2004 05:06:26 +0000 (05:06 +0000)]
b=2790
r=phil

revert global namespace changes

21 years agoGrr, I only had -z9 on dialup, -z3 is nearly as good and much less CPU usage.
adilger [Fri, 19 Mar 2004 03:47:13 +0000 (03:47 +0000)]
Grr, I only had -z9 on dialup, -z3 is nearly as good and much less CPU usage.

21 years agoExample .cvsrc file.
adilger [Fri, 19 Mar 2004 03:40:23 +0000 (03:40 +0000)]
Example .cvsrc file.

21 years agoRemove CVS meta-tag (also removed in previous merge to HEAD).
adilger [Fri, 19 Mar 2004 01:16:12 +0000 (01:16 +0000)]
Remove CVS meta-tag (also removed in previous merge to HEAD).

21 years agob=2776
zab [Fri, 19 Mar 2004 01:10:36 +0000 (01:10 +0000)]
b=2776
r=phil

land b_cray_portals_merge on HEAD.  This consists of four families of changes:

1) Eric's work to change some APIs in Lustre's portals to come into line with
   Cray's portals and the spec.

2) add --with-cray-portals= to the build and use it to cut up the build
   when we're building lustre against external includes for Cray's portals.

3) Move some facilities from portals.o into libcfs.o so that Lustre can
   consume them when it is running against Cray's portals.o.

4) Fix up the liblustre build.  These changes have also made it to
   b_cray_delivery recently.

21 years agoLand b1_2 onto HEAD (20040317_2319)
adilger [Thu, 18 Mar 2004 07:19:06 +0000 (07:19 +0000)]
Land b1_2 onto HEAD (20040317_2319)
b=2939, b=2325, b=2059 (partial), b=2925, b=2399, b=2517

21 years agoRemove useless and unused llite/sysctl.c file.
adilger [Thu, 18 Mar 2004 06:18:45 +0000 (06:18 +0000)]
Remove useless and unused llite/sysctl.c file.

21 years agoremove unecessary debugging
nic [Thu, 18 Mar 2004 03:40:25 +0000 (03:40 +0000)]
remove unecessary debugging

21 years ago- tagging RC_CURRENT
buffalo-pull [Thu, 18 Mar 2004 03:26:21 +0000 (03:26 +0000)]
- tagging RC_CURRENT

21 years agob=2805
nic [Thu, 18 Mar 2004 03:05:27 +0000 (03:05 +0000)]
b=2805

add inode-max-readahead patch to series

21 years agob=2805
nic [Thu, 18 Mar 2004 02:52:54 +0000 (02:52 +0000)]
b=2805

add inode-max-readahead patch to series

21 years agob=2517
nic [Thu, 18 Mar 2004 02:47:48 +0000 (02:47 +0000)]
b=2517

upadate iopen patch for 2.4.21-chaos

21 years agob=2399
nic [Thu, 18 Mar 2004 02:26:30 +0000 (02:26 +0000)]
b=2399

update vfs_intent patch for 2.4.24

21 years agob=2123
nic [Thu, 18 Mar 2004 01:31:33 +0000 (01:31 +0000)]
b=2123

add dcache_refcount_debug patch to hp-pnnl series

21 years ago- fix build warning and an almost certain run-time crash from swapped cerror
zab [Thu, 18 Mar 2004 01:11:30 +0000 (01:11 +0000)]
- fix build warning and an almost certain run-time crash from swapped cerror
  arguments

21 years agoUpdate build version.
adilger [Thu, 18 Mar 2004 01:04:54 +0000 (01:04 +0000)]
Update build version.

21 years agob=2399
nic [Thu, 18 Mar 2004 01:01:17 +0000 (01:01 +0000)]
b=2399

update vfs_intent patch for 2.4.21-chaos

21 years agob=2805
nic [Thu, 18 Mar 2004 01:00:03 +0000 (01:00 +0000)]
b=2805

add inode-max-readahead to rh-2.4.20 kernel series

21 years agoAdd some more useful information to error messages.
adilger [Thu, 18 Mar 2004 00:50:03 +0000 (00:50 +0000)]
Add some more useful information to error messages.
b=2306

21 years agob=2805
nic [Thu, 18 Mar 2004 00:18:43 +0000 (00:18 +0000)]
b=2805

add inode-max-readahead-2.4.24 patch and update kernel series

21 years agob=2517
nic [Thu, 18 Mar 2004 00:16:57 +0000 (00:16 +0000)]
b=2517

update kernel series for new pdirops patch

21 years agoDon't assert bitmap for free of self-export, it might not exist in errors.
adilger [Thu, 18 Mar 2004 00:14:36 +0000 (00:14 +0000)]
Don't assert bitmap for free of self-export, it might not exist in errors.
Don't leak a dentry reference during iopen setup error.
b=2936

21 years agob=2517
nic [Thu, 18 Mar 2004 00:12:08 +0000 (00:12 +0000)]
b=2517

adjust ext3-pdirops patch for chaos-2.4.20 as a result of new iopen-2.4.20 patch

21 years agoUpdate b1_2 from HEAD (20040317_1211)
adilger [Wed, 17 Mar 2004 23:55:43 +0000 (23:55 +0000)]
Update b1_2 from HEAD (20040317_1211)
b=2399, b=2517, landing b_v26

21 years agob=2517
nic [Wed, 17 Mar 2004 23:36:18 +0000 (23:36 +0000)]
b=2517

new iopen-2.4.20 patch

21 years agob=2399
nic [Wed, 17 Mar 2004 22:51:12 +0000 (22:51 +0000)]
b=2399

update kernel patch and series

21 years agob=2399
nic [Wed, 17 Mar 2004 22:49:03 +0000 (22:49 +0000)]
b=2399

update kernel vfs_intent patch and series
add patch to sanity.sh

21 years agob=2766
rread [Wed, 17 Mar 2004 22:04:07 +0000 (22:04 +0000)]
b=2766

Move changelog entry to a new block, since it's not part of 1.2.1.

21 years agob=2766
rread [Wed, 17 Mar 2004 21:56:43 +0000 (21:56 +0000)]
b=2766
r=zab (partial)

Better handling for OST eviction.  Fixes for clearing the page cache,
imp_invalid handling, and improved import_event interface. Also
includes the tests and fixes added from 2732; one of those tests does
not yet passed so it is excepted for now.

21 years agoDon't assert bitmap exists - it won't for error-during-setup self-export destroy
adilger [Wed, 17 Mar 2004 20:55:58 +0000 (20:55 +0000)]
Don't assert bitmap exists - it won't for error-during-setup self-export destroy
b=2936
r=robert

21 years agoChange test 6 slightly to take statfs cache and logs into account.
adilger [Wed, 17 Mar 2004 12:00:44 +0000 (12:00 +0000)]
Change test 6 slightly to take statfs cache and logs into account.
b=2921

21 years agoRevert the reservation part of the bug 2059 changes. This seems to have
adilger [Wed, 17 Mar 2004 11:46:23 +0000 (11:46 +0000)]
Revert the reservation part of the bug 2059 changes.  This seems to have
been causing problems on the OSTs and wasn't the primary reason for applying
this patch to 1.2.
b=2059

21 years agoClean up properly if llog_lvfs_close() fails.
adilger [Wed, 17 Mar 2004 10:53:44 +0000 (10:53 +0000)]
Clean up properly if llog_lvfs_close() fails.
b=2325

21 years agoFix assertion again, sigh.
adilger [Wed, 17 Mar 2004 09:33:32 +0000 (09:33 +0000)]
Fix assertion again, sigh.
b=2925

21 years agoFix assertion for end of loop.
adilger [Wed, 17 Mar 2004 08:21:51 +0000 (08:21 +0000)]
Fix assertion for end of loop.
b=2925

21 years agoReduce number of credits for an UNLINK op (update quota files at most once).
adilger [Wed, 17 Mar 2004 05:37:49 +0000 (05:37 +0000)]
Reduce number of credits for an UNLINK op (update quota files at most once).
Limit our transaction requests to the maximum transaction size regardless.
Handle error case in journal start.
b=2059

21 years ago- tagging RC_CURRENT
buffalo-pull [Wed, 17 Mar 2004 04:29:56 +0000 (04:29 +0000)]
- tagging RC_CURRENT

21 years agoFix reservation vs. grant locking.
adilger [Wed, 17 Mar 2004 04:08:51 +0000 (04:08 +0000)]
Fix reservation vs. grant locking.
b=2059

21 years agob=2939
wangchao [Wed, 17 Mar 2004 02:52:47 +0000 (02:52 +0000)]
b=2939

21 years agoUpdate build version.
adilger [Wed, 17 Mar 2004 01:33:04 +0000 (01:33 +0000)]
Update build version.

21 years agoAutomatically generate fsfilt_extN.c from fsfilt_ext3.c
adilger [Wed, 17 Mar 2004 01:32:17 +0000 (01:32 +0000)]
Automatically generate fsfilt_extN.c from fsfilt_ext3.c
b=2059

21 years agob=2936
adilger [Wed, 17 Mar 2004 01:11:46 +0000 (01:11 +0000)]
b=2936

21 years agoThis commit was manufactured by cvs2svn to create branch 'b1_2'.
cvs2svn [Wed, 17 Mar 2004 01:04:44 +0000 (01:04 +0000)]
This commit was manufactured by cvs2svn to create branch 'b1_2'.

21 years agoland b_v26 (20040316_1603)
nic [Wed, 17 Mar 2004 01:04:43 +0000 (01:04 +0000)]
land b_v26 (20040316_1603)

21 years agoUpdate b1_2 from HEAD (20040316_1727)
adilger [Wed, 17 Mar 2004 01:02:59 +0000 (01:02 +0000)]
Update b1_2 from HEAD (20040316_1727)
b=2939

21 years agob=2936
rread [Wed, 17 Mar 2004 00:26:38 +0000 (00:26 +0000)]
b=2936

Skip closing files for the self_export, and add a test.