Whamcloud - gitweb
fs/lustre-release.git
19 years agoThis commit was manufactured by cvs2svn to create branch 'b_release_1_4_4'.
cvs2svn [Thu, 4 Aug 2005 22:39:56 +0000 (22:39 +0000)]
This commit was manufactured by cvs2svn to create branch 'b_release_1_4_4'.

19 years agoBranch b1_4
adilger [Thu, 4 Aug 2005 22:39:55 +0000 (22:39 +0000)]
Branch b1_4
Add ext3-ialloc patch to Cray patch series, avoids poor inode placement and
filesystem fragmentation on the OSTs.
b=4466
r=alex

19 years agoBranch b1_4
adilger [Thu, 4 Aug 2005 19:06:17 +0000 (19:06 +0000)]
Branch b1_4
Allow the "created" parameter to be NULL.  We don't actually use this data
for anything, and the current obdfilter code just passes in a dummy array
to make the API happy.  This leads to confusion when modifying the code.
b=7049, b=6998

19 years agoBranch b1_4
adilger [Thu, 4 Aug 2005 18:42:46 +0000 (18:42 +0000)]
Branch b1_4
Description: Unusual file access patterns on the MDS may result in inode
             data being lost in very rare circumstances.
Details    : Bad interaction between the ea-in-inode patch and the "no-read"
             code in the 2.6 kernel caused the inode and/or EA data not to
             be read from disk, causing single-file corruption.
b=6866, b=6869
r=alex

19 years agoremove unneeded argument
jacob [Thu, 4 Aug 2005 18:38:49 +0000 (18:38 +0000)]
remove unneeded argument

19 years agoname the cluster using a sort list of node names
jacob [Thu, 4 Aug 2005 18:37:52 +0000 (18:37 +0000)]
name the cluster using a sort list of node names

19 years agoremove stale series
jacob [Thu, 4 Aug 2005 18:11:50 +0000 (18:11 +0000)]
remove stale series

19 years agob=7165
jacob [Thu, 4 Aug 2005 18:06:06 +0000 (18:06 +0000)]
b=7165
b=7224

 - initial support for creating clumanager xml files from lustre xml
 - support for using lustre init script from clumanager
 - more changes to init scripts from scripps

19 years agoFix of careless (miss ;;)
liangzhen [Thu, 4 Aug 2005 09:00:13 +0000 (09:00 +0000)]
Fix of careless (miss ;;)

19 years agostore lustre id in ost object's EA.
niu [Thu, 4 Aug 2005 08:46:29 +0000 (08:46 +0000)]
store lustre id in ost object's EA.

19 years agoCFLAGS for compiling in Tiger
liangzhen [Thu, 4 Aug 2005 07:56:21 +0000 (07:56 +0000)]
CFLAGS for compiling in Tiger

19 years agob=7049
alex [Wed, 3 Aug 2005 21:56:47 +0000 (21:56 +0000)]
b=7049

 - try to unmap buffers from bd-mapping

19 years agoadded test of /proc/fs/lustre/health_check
cliffw [Wed, 3 Aug 2005 19:18:30 +0000 (19:18 +0000)]
added test of /proc/fs/lustre/health_check

19 years agob=7049
alex [Wed, 3 Aug 2005 13:29:38 +0000 (13:29 +0000)]
b=7049

 - it's enough to check for block number

19 years agob=7049
alex [Wed, 3 Aug 2005 12:18:42 +0000 (12:18 +0000)]
b=7049

 - it's better to unmap buffers holding no truncate sem
   note: unmap_underlying_metadata() is commented out to see whether
         a race happens at all

19 years agob=7049
alex [Wed, 3 Aug 2005 12:04:15 +0000 (12:04 +0000)]
b=7049

 - check for aliases in bd-mapping for writes only

19 years agob=7049
alex [Wed, 3 Aug 2005 10:20:08 +0000 (10:20 +0000)]
b=7049

 - let's check whether dirty pages/buffers in bd-mapping

19 years agob=7237
alex [Wed, 3 Aug 2005 07:34:22 +0000 (07:34 +0000)]
b=7237

 - missed wake_up() has been returned
 - few CDEBUG() have changed their level to D_ERROR to simplify debugging

19 years agoMerge b1_4_bug3389 from b1_4 (20050729_0312)
adilger [Tue, 2 Aug 2005 23:29:58 +0000 (23:29 +0000)]
Merge b1_4_bug3389 from b1_4 (20050729_0312)
Description: Mounting a Lustre file system on a node running as an OST could
             lead to deadlocks
Details    : OSTs now allocate memory needed to write out data at
             startup, instead of when needed, to avoid having to
             allocate memory in possibly low memory situations.
             Specifically, if the file system is mounted on on OST,
             memory pressure could force it to try to write out data,
             which it needed to allocate memory to do.  Due to the low
             memory, it would be unable to do so and the node would
             become unresponsive.
b=6514, b=5137

Description: Addition of lconf --service command line option
Details    : lconf now accepts a '--service <arg>' option, which is
             shorthand for 'lconf --group <arg> --select <arg>=<hostname>'
b=7015

Description: Failover mode is now the default for OSTs.
Details    : By default, OSTs will now run in failover mode.  To return to
             the old behaviour, add '--failout' to the lmc line for OSTs.
b=6101

Description: Health checks are now provided for MDS and OSTs
Details    : Additional detailed health check information on MSD and OSTs
             is now provided through the procfs health_check value.
b=1693

Description: Disk fragmentation on the OSTs could eventually cause slowdowns
             after numerous create/delete cycles
Details    : The ext3 inode allocation policy would not allocate new inodes
             very well on the OSTs because there are no new directories
             being created.  Instead we look for groups with free space if
             the parent directories are nearly full.
b=4466

Description: Network or server problems during mount may cause partially
             mounted clients instead of returning an error.
Details    : The config llog parsing code may overwrite the error return
             code during mount error handling, returning success instead
             of an error.
b=6302

19 years agoupdate for current errata
jacob [Tue, 2 Aug 2005 20:29:58 +0000 (20:29 +0000)]
update for current errata

19 years agob=3984
alex [Tue, 2 Aug 2005 19:46:23 +0000 (19:46 +0000)]
b=3984

 - a reference on resource must be taked under spinlock

19 years agoproperly update kernel configs for sles 9 sp 2
jacob [Tue, 2 Aug 2005 19:05:40 +0000 (19:05 +0000)]
properly update kernel configs for sles 9 sp 2

19 years agob=7039
alex [Tue, 2 Aug 2005 18:46:35 +0000 (18:46 +0000)]
b=7039

 - concurrent lock cancelling might find inode dead while it's not yet

19 years agob=7231
alex [Tue, 2 Aug 2005 17:34:20 +0000 (17:34 +0000)]
b=7231

 - asynchronous commit in obdfilter/2.6

19 years agob=7231
alex [Tue, 2 Aug 2005 15:43:33 +0000 (15:43 +0000)]
b=7231

 - wait on bio's completion after commit. to evaluate performance impact

19 years agob=7039
alex [Tue, 2 Aug 2005 09:09:02 +0000 (09:09 +0000)]
b=7039

 - stop progress and dump a log for debugging purposes

19 years agoBranch b1_4
adilger [Tue, 2 Aug 2005 05:52:43 +0000 (05:52 +0000)]
Branch b1_4
Fix indenting problem in lconf causing a use-before-assignment error.
Gotta love python.
b=7221

19 years ago- b_size_on_mds landed on HEAD:
alex [Sun, 31 Jul 2005 12:43:22 +0000 (12:43 +0000)]
- b_size_on_mds landed on HEAD:

  5984 - oops in mdc_set_lock_data
         we must drop lookup lock in ll_clear_inode()
  7216 - abort due to missed clients
 replay already committed (open/close rpcs) requests
 even if some clients haven't connected in time and
 got evicted
  7057 - sanity: test_66: /mnt/lustre/f66 blocks 0 < 8
         send close rpc only when all dirty pages are written
 (otherwise i_blocks isn't valid)
  6817 - don't update attrs. on mds if the client hasn't modified file
         using openhandle being closed

19 years agoland b_hd_remote_acl: support get/set ACL from remote client.
ericm [Sun, 31 Jul 2005 04:49:34 +0000 (04:49 +0000)]
land b_hd_remote_acl: support get/set ACL from remote client.

19 years agoBranch b1_4
adilger [Sat, 30 Jul 2005 00:28:01 +0000 (00:28 +0000)]
Branch b1_4
Add ialloc patch to fc3 series.
b=4644

19 years agob=6266 (oleg's patch)
phil [Sat, 30 Jul 2005 00:05:48 +0000 (00:05 +0000)]
b=6266 (oleg's patch)
Severity   : minor
Bugzilla   : 6266
Frequency  : rare (liblustre)
Description: fsx running with liblustre complained that using truncate() to
             extend the file doesn't work.  This patch corrects that issue.
Details    : This is the liblustre equivalent of the fix for bug 6196.  Fixes
             ATTR_SIZE and lsm use in llu_setattr_raw.

19 years agoBranch b1_4
adilger [Fri, 29 Jul 2005 23:58:00 +0000 (23:58 +0000)]
Branch b1_4
Add ialloc patch to 2.4.29 series.
b=4644

19 years agoupdate patches and scripts for SLES 9 SP2
jacob [Fri, 29 Jul 2005 23:54:55 +0000 (23:54 +0000)]
update patches and scripts for SLES 9 SP2

19 years agoupdate patches and scripts for SLES 9 SP2
jacob [Fri, 29 Jul 2005 23:54:32 +0000 (23:54 +0000)]
update patches and scripts for SLES 9 SP2

19 years agoBranch: b_hd_crypto
wangdi [Fri, 29 Jul 2005 14:06:12 +0000 (14:06 +0000)]
Branch: b_hd_crypto
minor fixes about crypto api

19 years agoland minor fixes from b_hd_sec:
ericm [Thu, 28 Jul 2005 18:31:21 +0000 (18:31 +0000)]
land minor fixes from b_hd_sec:
 * "EA" is used for lustre internal metadata ea. so change user ea's name to
   "XATTR", including ACLs.
 * remove a unnecessary param from md_getattr().
 * various more fixes.

19 years agoMake the ChangeLog crystal clear that although flock has landed, it's not yet
phil [Thu, 28 Jul 2005 00:03:16 +0000 (00:03 +0000)]
Make the ChangeLog crystal clear that although flock has landed, it's not yet
supported

19 years agoadd missing entry for bug 6993
phil [Wed, 27 Jul 2005 23:48:35 +0000 (23:48 +0000)]
add missing entry for bug 6993

19 years agob=7200
alex [Wed, 27 Jul 2005 18:54:34 +0000 (18:54 +0000)]
b=7200

 - protect lock->l_resource from concurrent ldlm_lock_change_resource()

19 years agoBranch b1_4_bug3389
adilger [Wed, 27 Jul 2005 18:18:31 +0000 (18:18 +0000)]
Branch b1_4_bug3389
Fix portals_nid2str() to print something reasonable for Cray NALs.
b=6902
r=bogl

19 years agob=5210
alex [Wed, 27 Jul 2005 17:20:02 +0000 (17:20 +0000)]
b=5210
r=phil(actual patch)

A workaround for the crash in ll_unhash_aliases on 2.6.
The 2.6 lookup code is now lockless (thanks to the RCU machinations), which
allows it to race with the unhashing in ll_unhash_aliases. The 2.6 __d_drop
doesn't leave the list head ->pprev in a safe state, so the next pass through
this loop (which tries to re-hash it after we lose the dput race), would crash.
For the record, it looks like the kernel's own d_prune_aliases is broken in
the very same way, except that instead of crashing immediately, it just leaves
the d_hash pointers poisoned for someone else to crash on.

19 years agoBranch:b_hd_crypto
wangdi [Wed, 27 Jul 2005 09:28:29 +0000 (09:28 +0000)]
Branch:b_hd_crypto
update crypto api code

19 years agoLand b_release_1_4_3 onto b1_4 (20050726_1646)
adilger [Wed, 27 Jul 2005 00:22:00 +0000 (00:22 +0000)]
Land b_release_1_4_3 onto b1_4 (20050726_1646)
Mostly copyright message updates.

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 22:43:05 +0000 (22:43 +0000)]
Branch b1_4
Description: Network or server problems during mount may cause partially
             mounted clients instead of returning an error.
Details    : lustre_process_log() will overwrite the error return code
             during mount error handling, returning success instead of an
             error.  Also, an error during cleanup caused cleanup to stop
     instead of attempting to do the remaining cleanup.
b=6302

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 22:32:20 +0000 (22:32 +0000)]
Branch b1_4
Fix liblustre test in acceptance-small.sh - sanity.sh needs the --target
option even though the LIBLUSTRE_MOUNT_TARGET environment variable is set.

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 22:29:53 +0000 (22:29 +0000)]
Branch b1_4
Pick filesystem type from kernel version, if unset.

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 22:28:58 +0000 (22:28 +0000)]
Branch b1_4
Add '-e' option to iozone to wait for sync before completing.
r=phil

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 22:22:40 +0000 (22:22 +0000)]
Branch b1_4
Remove obsolete extN usage, unused since Lustre 1.0 days.
b=6437

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 22:10:04 +0000 (22:10 +0000)]
Branch b1_4
Remove call to _sysio_shutdown() for catamount, as this causes Lustre
cleanup to happen before all the glibc buffers are flushed.
b=7193
r=bogl

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 21:55:37 +0000 (21:55 +0000)]
Branch b1_4
Description: Disk fragmentation on the OSTs could eventually cause slowdowns
             after numerous create/delete cycles
Details    : The ext3 inode allocation policy would not allocate new inodes
     very well on the OSTs because there are no new directories
     being created.  Instead we look for groups with free space if
     the parent directories are nearly full.
b=4466
r=alex,behlendorf

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 19:43:43 +0000 (19:43 +0000)]
Branch b1_4
Fix typo in lconf.
b=7187

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 19:02:48 +0000 (19:02 +0000)]
Branch b1_4
Rename the 2.6-suse-lnxi.series file to 2.6-suse-newer.series to make it
more clear that this series is applicable to all SuSE kernels and not
just LNXI kernels.
b=5985

19 years agob=6422
green [Tue, 26 Jul 2005 17:17:56 +0000 (17:17 +0000)]
b=6422
r=adilger

Do not dereference reply state when freeing request, if there is no reply state.
Do not return garbage in ptlrpc_service_health_check()

19 years agoBranch b1_4
adilger [Tue, 26 Jul 2005 07:48:15 +0000 (07:48 +0000)]
Branch b1_4
Quiet liblustre compiler warnings on x64_64.

19 years agobug 6854: add jdb error handling patch to rhel-2.4.21, suse-2.4.21-cray, and vanilla...
nikita [Mon, 25 Jul 2005 14:44:18 +0000 (14:44 +0000)]
bug 6854: add jdb error handling patch to rhel-2.4.21, suse-2.4.21-cray, and vanilla-2.4.29 series.

19 years agob=7017
alex [Sat, 23 Jul 2005 20:55:29 +0000 (20:55 +0000)]
b=7017

 - atomic_dec_and_test() with subsequent spin_lock() against the list
   is racy. atomic_dec_and_lock() must be used. otherwise other cpu
   can hit the race window, increment refcount, drop it again and we
   get to the situation when both cpus are freeing the structure

19 years agosome env (cnbuild) can't build without explicitly include
ericm [Fri, 22 Jul 2005 17:23:24 +0000 (17:23 +0000)]
some env (cnbuild) can't build without explicitly include
errno.h

19 years agoland b_hd_pag: rudiment support for PAG.
ericm [Thu, 21 Jul 2005 17:17:36 +0000 (17:17 +0000)]
land b_hd_pag: rudiment support for PAG.

19 years agoCopyright is now License in RPM spec files.
brian [Thu, 21 Jul 2005 14:01:53 +0000 (14:01 +0000)]
Copyright is now License in RPM spec files.

19 years agor=adilger
pjkirner [Thu, 21 Jul 2005 12:46:39 +0000 (12:46 +0000)]
r=adilger
b=7000

Patch to 2.4 kernel patches in #if'ed out code by default.  See bug 7000 for all the details.

19 years agoquiet
jacob [Wed, 20 Jul 2005 21:24:18 +0000 (21:24 +0000)]
quiet

19 years agoFix merge breakage that was originally introduced on b_cray, and then merged over...
pjkirner [Wed, 20 Jul 2005 20:41:21 +0000 (20:41 +0000)]
Fix merge breakage that was originally introduced on b_cray, and then merged over to b1_4.

19 years agoShould allow the uml_switch to be used if wanted.
brian [Wed, 20 Jul 2005 18:06:59 +0000 (18:06 +0000)]
Should allow the uml_switch to be used if wanted.

19 years agoBranch: HEAD
wangdi [Wed, 20 Jul 2005 12:50:30 +0000 (12:50 +0000)]
Branch: HEAD
remove redundant set_md in mds_reint_create and cmobd_reint_create

19 years agoBranch: HEAD
wangdi [Wed, 20 Jul 2005 12:34:28 +0000 (12:34 +0000)]
Branch: HEAD
add setxattr kml post hook for reint set md to master mds.

19 years agoBranch: b1_4
green [Tue, 19 Jul 2005 20:09:47 +0000 (20:09 +0000)]
Branch: b1_4

__ptlrpc_server_free_request should be of void return type as it does not return
anything. Fixes compile warning

19 years agoBranch: HEAD
wangdi [Tue, 19 Jul 2005 12:56:14 +0000 (12:56 +0000)]
Branch: HEAD
should reset mcd_last_close_xid to 0 when reconnect.
b:6102
r:alex

19 years ago- need couple routines to be accessible from modules for size-on-mds feature
alex [Tue, 19 Jul 2005 11:35:38 +0000 (11:35 +0000)]
- need couple routines to be accessible from modules for size-on-mds feature

19 years agob=7098
pjkirner [Mon, 18 Jul 2005 15:51:49 +0000 (15:51 +0000)]
b=7098
r=jacob

Land b_cray bits to b1_4 (except SNAPFS and SMFS per the discussion in the bug)

19 years agoBranch: HEAD
wangdi [Sat, 16 Jul 2005 07:24:10 +0000 (07:24 +0000)]
Branch: HEAD
add kernel-2.6.10-suse-opteron.config for opteron arch

19 years agoi stand corrected
jacob [Fri, 15 Jul 2005 20:40:56 +0000 (20:40 +0000)]
i stand corrected

19 years agoFix sysStatus file creation
cliffw [Fri, 15 Jul 2005 20:09:29 +0000 (20:09 +0000)]
Fix sysStatus file creation

19 years agothis is the fix i intended
jacob [Fri, 15 Jul 2005 20:06:06 +0000 (20:06 +0000)]
this is the fix i intended

19 years agor=adilger,nic
mjmac [Fri, 15 Jul 2005 19:52:29 +0000 (19:52 +0000)]
r=adilger,nic

stage() should return 0 if $STAGEDIR is not set, not 1.

19 years agob=7136
jacob [Fri, 15 Jul 2005 18:52:28 +0000 (18:52 +0000)]
b=7136
r=adilger

just use defaults if --stripe_sz and --stripe_cnt are missing form
--add lov

19 years agob=6422
green [Fri, 15 Jul 2005 12:51:35 +0000 (12:51 +0000)]
b=6422
r=adilger

Support a pool of requests and lustre_msgs when allocating requests.
Use that on osc writeout path.

19 years agoBranch: HEAD
wangdi [Fri, 15 Jul 2005 07:11:18 +0000 (07:11 +0000)]
Branch: HEAD
add fid and group in kml for cmobd test

19 years agomove AC_SUBST into lustre-build.m4 (b=7126)
jacob [Fri, 15 Jul 2005 04:34:12 +0000 (04:34 +0000)]
move AC_SUBST into lustre-build.m4 (b=7126)

19 years agoadd --stage option to lbuild
jacob [Thu, 14 Jul 2005 23:04:14 +0000 (23:04 +0000)]
add --stage option to lbuild

19 years agorevert a broken change from an earlier fix
jacob [Thu, 14 Jul 2005 23:00:40 +0000 (23:00 +0000)]
revert a broken change from an earlier fix

19 years agoBranch b1_4
adilger [Thu, 14 Jul 2005 22:53:45 +0000 (22:53 +0000)]
Branch b1_4
Use a wildcard for /usr/share/lustre.

19 years agojust remove unused macro as i can't get it to work right anyway
jacob [Thu, 14 Jul 2005 22:25:09 +0000 (22:25 +0000)]
just remove unused macro as i can't get it to work right anyway

19 years agomy mind fell out of m4 mode for a moment
jacob [Thu, 14 Jul 2005 22:02:43 +0000 (22:02 +0000)]
my mind fell out of m4 mode for a moment

19 years agoBranch b1_4
adilger [Thu, 14 Jul 2005 21:58:57 +0000 (21:58 +0000)]
Branch b1_4
Fix compile problem for LDLM_NUM_THREADS macro in liblustre case.
b=6422

19 years agorestripe snmp to b1_4 so that andreas will add the right globs later
jacob [Thu, 14 Jul 2005 21:50:07 +0000 (21:50 +0000)]
restripe snmp to b1_4 so that andreas will add the right globs later

19 years agoremove harmless error message when snmp is not present
jacob [Thu, 14 Jul 2005 21:47:27 +0000 (21:47 +0000)]
remove harmless error message when snmp is not present

19 years agoadd support for the snmp module.
jacob [Thu, 14 Jul 2005 21:10:04 +0000 (21:10 +0000)]
add support for the snmp module.

19 years agoThis commit was generated by cvs2svn to compensate for changes in r49775,
jacob [Thu, 14 Jul 2005 21:00:40 +0000 (21:00 +0000)]
This commit was generated by cvs2svn to compensate for changes in r49775,
which included commits to RCS files with non-trunk default branches.

19 years agoInitial import of lustre-snmp module.
jacob [Thu, 14 Jul 2005 21:00:40 +0000 (21:00 +0000)]
Initial import of lustre-snmp module.

19 years agoBranch: b1_4
green [Thu, 14 Jul 2005 20:48:03 +0000 (20:48 +0000)]
Branch: b1_4
b=6422
r=adilger

Pleallocate reply states for services, and use those preallocated RSes
when low on memory.

19 years agoBranch b1_4
adilger [Thu, 14 Jul 2005 17:17:31 +0000 (17:17 +0000)]
Branch b1_4
Fix patch mismerge.
b=7122

19 years agooops
jacob [Thu, 14 Jul 2005 17:11:21 +0000 (17:11 +0000)]
oops

19 years ago - skip modules lacking a tag
jacob [Thu, 14 Jul 2005 17:02:25 +0000 (17:02 +0000)]
 - skip modules lacking a tag
 - print a summary of failed updates/checkouts at the end
 - also return an error status in this case

19 years agosort correctly
jacob [Thu, 14 Jul 2005 16:23:21 +0000 (16:23 +0000)]
sort correctly

19 years agofrom b_cray: add --with-lustre-hack and --with-sockets to configure line for libsysio
jacob [Thu, 14 Jul 2005 16:19:32 +0000 (16:19 +0000)]
from b_cray: add --with-lustre-hack and --with-sockets to configure line for libsysio

19 years agoRevert Tom's commit. It breaks recovery.
brian [Thu, 14 Jul 2005 14:25:34 +0000 (14:25 +0000)]
Revert Tom's commit.  It breaks recovery.
r=alex
r=umka

19 years agoBranch HEAD
wangdi [Thu, 14 Jul 2005 12:46:48 +0000 (12:46 +0000)]
Branch HEAD
add fid and group in kml log

19 years agospin_is_locked() always return false in UP kernel.
ericm [Thu, 14 Jul 2005 03:05:21 +0000 (03:05 +0000)]
spin_is_locked() always return false in UP kernel.

19 years agominor: verbose on sec register.
ericm [Wed, 13 Jul 2005 22:22:17 +0000 (22:22 +0000)]
minor: verbose on sec register.

19 years agoconf-sanity: don't start/stop lsvcgssd/lgssd frequently.
ericm [Wed, 13 Jul 2005 22:08:59 +0000 (22:08 +0000)]
conf-sanity: don't start/stop lsvcgssd/lgssd frequently.