Whamcloud - gitweb
fs/lustre-release.git
15 years agoLand b_release_1_4_3 onto HEAD (20050619_0305)
adilger [Sun, 19 Jun 2005 09:18:22 +0000 (09:18 +0000)]
Land b_release_1_4_3 onto HEAD (20050619_0305)
b=6411 : enable rate-limiting of console error messages, and some console
         errors now go only to the kernel log.  Use CERROR/CWARN where
 appropriate to allow rate-limiting of these messages.
b=1693 : add /proc/sys/portals/catastrophe entry which will report if
         that node has previously LBUGged.

15 years agob=6871
alex [Sat, 18 Jun 2005 13:39:35 +0000 (13:39 +0000)]
b=6871

 - drop fail_loc to 0 in test 20

15 years agoAllow sanity.sh to work with zconf.
brian [Sat, 18 Jun 2005 03:15:29 +0000 (03:15 +0000)]
Allow sanity.sh to work with zconf.
Taken from b1_4 branch.  Thanx nic and adilger.

15 years ago- fix in lmv.sh to use it along with sanityN.sh
yury [Fri, 17 Jun 2005 16:44:54 +0000 (16:44 +0000)]
- fix in lmv.sh to use it along with sanityN.sh

15 years ago* Backed out vib magic change; it's not required since the acceptor
eeb [Fri, 17 Jun 2005 10:24:41 +0000 (10:24 +0000)]
*  Backed out vib magic change; it's not required since the acceptor
   isn't involved.

15 years ago* Make vibnal's magic unique before binary compatibility becomes an issue
eeb [Fri, 17 Jun 2005 10:04:35 +0000 (10:04 +0000)]
*    Make vibnal's magic unique before binary compatibility becomes an issue

15 years agodon't assume PDSH as ssh, which caused troubles for testing.
ericm [Thu, 16 Jun 2005 22:19:50 +0000 (22:19 +0000)]
don't assume PDSH as ssh, which caused troubles for testing.

15 years ago* Use FMR in vibnal to avoid allocating huge contiguous memory for QPs
eeb [Thu, 16 Jun 2005 21:55:17 +0000 (21:55 +0000)]
*     Use FMR in vibnal to avoid allocating huge contiguous memory for QPs
      which caused bug 6436

15 years agochange back on PTL_NETID_ANY in portals, which was committed to HEAD
wangchao [Thu, 16 Jun 2005 11:22:11 +0000 (11:22 +0000)]
change back on PTL_NETID_ANY in portals, which was committed to HEAD

15 years agolctl flush command to flush the cache of idmap, lsd, and gss svc context
wangchao [Thu, 16 Jun 2005 10:23:59 +0000 (10:23 +0000)]
lctl flush command to flush the cache of idmap, lsd, and gss svc context

15 years ago- use mknod to avoid cross-ref mkdir
alex [Thu, 16 Jun 2005 09:16:15 +0000 (09:16 +0000)]
- use mknod to avoid cross-ref mkdir

15 years ago- use DEFAULT recovery behaviour
alex [Thu, 16 Jun 2005 06:35:38 +0000 (06:35 +0000)]
- use DEFAULT recovery behaviour

15 years agoland b_hd_sec_client_oss onto HEAD.
ericm [Wed, 15 Jun 2005 20:24:42 +0000 (20:24 +0000)]
land b_hd_sec_client_oss onto HEAD.

15 years agoEnsure that /sbin and /usr/sbin are in the remote $PATH so that sysctl can be
brian [Wed, 15 Jun 2005 18:45:15 +0000 (18:45 +0000)]
Ensure that /sbin and /usr/sbin are in the remote $PATH so that sysctl can be
found on the remote node.
b=6281

15 years ago* Removed spurious vibnal CERROR
eeb [Wed, 15 Jun 2005 10:15:20 +0000 (10:15 +0000)]
*   Removed spurious vibnal CERROR

15 years agoMissed another aspect of the expect expression.
brian [Wed, 15 Jun 2005 00:42:38 +0000 (00:42 +0000)]
Missed another aspect of the expect expression.

15 years agoacl scripts: different enviroments may output differently.
ericm [Tue, 14 Jun 2005 22:59:58 +0000 (22:59 +0000)]
acl scripts: different enviroments may output differently.

15 years agoacl test scripts: remove user substitution; remove obsolete files.
ericm [Tue, 14 Jun 2005 19:34:54 +0000 (19:34 +0000)]
acl test scripts: remove user substitution; remove obsolete files.

15 years agoneed convert hostname to nid in local.sh
ericm [Tue, 14 Jun 2005 19:08:08 +0000 (19:08 +0000)]
need convert hostname to nid in local.sh

15 years agoBranch:b_hd_crypto
wangdi [Tue, 14 Jun 2005 12:42:27 +0000 (12:42 +0000)]
Branch:b_hd_crypto
crypto api prototype
1) add gs_obd and gsc_obd
2) cleanup in ll_fill_super and lustre_common_fill_super
3) some modification in lconf and lmc

15 years ago- fixed inverted condition, committed missed bits from cobd
yury [Tue, 14 Jun 2005 09:32:38 +0000 (09:32 +0000)]
- fixed inverted condition, committed missed bits from cobd

15 years ago- changed name convention in cobd, thus all MD related methods have _md_ prefix like...
yury [Tue, 14 Jun 2005 09:21:11 +0000 (09:21 +0000)]
- changed name convention in cobd, thus all MD related methods have _md_ prefix like cobd_md_getstatus(),
all data layer related have _dt_prefix and common one like cobd_connect() have no prefix at all.

- added hack to mdc_intent_lock() and cobd_md_intent_lock() to distinguish cobd case in mdc_intent_lock() and do not raise -ESTALE if obtained lock is not coherent wiht store id due to generation after switchin to cache cobd. This is dirty hack of course, but it should be for a while to pass cmobd/cobd related tests and Peter agreed it ok for now.

15 years agoForgot closing brace in expect expression.
brian [Mon, 13 Jun 2005 18:37:51 +0000 (18:37 +0000)]
Forgot closing brace in expect expression.

15 years agosome minor changes in lsd upcall.
ericm [Mon, 13 Jun 2005 17:45:26 +0000 (17:45 +0000)]
some minor changes in lsd upcall.

15 years agominor change for debug msg.
ericm [Mon, 13 Jun 2005 16:01:33 +0000 (16:01 +0000)]
minor change for debug msg.

15 years ago- removed canceling unused locks in cobd in switching time as this is done in disconn...
yury [Mon, 13 Jun 2005 13:24:56 +0000 (13:24 +0000)]
- removed canceling unused locks in cobd in switching time as this is done in disconnect path.

15 years ago- fixed typos in comments and some alingment in cobd.
yury [Mon, 13 Jun 2005 12:28:32 +0000 (12:28 +0000)]
- fixed typos in comments and some alingment in cobd.
- added canceling unused locks before disconnecting master/cache exports in cobd_iocontrol()

- added lmv_cancel_unused() to cancel unused locks from llite correctly instead of using
direct ldlm_cli_cancel_unused() on lmv namespace.

- removed not used ll_mdc_cancel_unused()

15 years ago- update from HEAD
alex [Mon, 13 Jun 2005 09:08:47 +0000 (09:08 +0000)]
- update from HEAD

15 years ago- revert back the change: it breaks replay-dual
alex [Sun, 12 Jun 2005 18:09:42 +0000 (18:09 +0000)]
- revert back the change: it breaks replay-dual

15 years ago* 6474: changes to low-level vibnal IB QP tunables
eeb [Sat, 11 Jun 2005 12:11:34 +0000 (12:11 +0000)]
*  6474: changes to low-level vibnal IB QP tunables

15 years agoAllow GSS password to be passed to the test-framework in $GSS_PASS.
brian [Fri, 10 Jun 2005 23:23:57 +0000 (23:23 +0000)]
Allow GSS password to be passed to the test-framework in $GSS_PASS.

15 years agogss: be albe to parse signed int when lsvcgssd send error downcall; some
ericm [Thu, 9 Jun 2005 21:58:50 +0000 (21:58 +0000)]
gss: be albe to parse signed int when lsvcgssd send error downcall; some
code adjustment.

15 years ago* vibnal 6361 fix: change QP creation tunables & HCA name
eeb [Thu, 9 Jun 2005 17:53:11 +0000 (17:53 +0000)]
*  vibnal 6361 fix: change QP creation tunables & HCA name

*  vibnal 6436 fix: don't LBUG when QP creation fails

15 years agominor change for buffalo test of client-oss,
wangchao [Thu, 9 Jun 2005 15:56:41 +0000 (15:56 +0000)]
minor change for buffalo test of client-oss,
let lconf be able to accept --mds_sec but ignore it.
llmount.c is able to accept mds_sec option but ignore it,
so it doesn't need change for this purpose.

for h_hd_sec_client_oss, it also needs the change to lconf
to accept --sec but ignore it.

after client-oss landing, we will make it integrated.

15 years agoNeed device mapper support for LVM.
brian [Wed, 8 Jun 2005 17:11:03 +0000 (17:11 +0000)]
Need device mapper support for LVM.

15 years agoScript used to create directory tree for PackageMaker in OS X.
liangzhen [Wed, 8 Jun 2005 09:05:25 +0000 (09:05 +0000)]
Script used to create directory tree for PackageMaker in OS X.

15 years agoSmall fix for install/uninstall scripts.
liangzhen [Wed, 8 Jun 2005 07:48:17 +0000 (07:48 +0000)]
Small fix for install/uninstall scripts.

15 years agoBranch: HEAD
wangdi [Tue, 7 Jun 2005 16:07:59 +0000 (16:07 +0000)]
Branch: HEAD
1)set lsm when cmobd reint create one inode on master mds
2)some minor fix in cobd

15 years agofix rawrpc, don't drop buffer before rpc really finished on wire, portals
ericm [Tue, 7 Jun 2005 00:53:04 +0000 (00:53 +0000)]
fix rawrpc, don't drop buffer before rpc really finished on wire, portals
callback might arrive very late.

15 years agofile openibnal_modparams.c was initially added on branch b_hd_newconfig.
eeb [Mon, 6 Jun 2005 21:22:23 +0000 (21:22 +0000)]
file openibnal_modparams.c was initially added on branch b_hd_newconfig.

15 years agor=alex
tappro [Mon, 6 Jun 2005 18:15:39 +0000 (18:15 +0000)]
r=alex
- replace iget() in smfs_init_inode_info() with igrab()

15 years agoBranch: HEAD
wangdi [Mon, 6 Jun 2005 16:12:09 +0000 (16:12 +0000)]
Branch: HEAD
some fix in lmc and lconf for WB cache test
1)add more options for single oss with cache and master lmv
2)some fixes for WB cache test script

15 years agoland b_hd_sec onto HEAD, some debugging code also kept.
ericm [Sun, 5 Jun 2005 21:14:54 +0000 (21:14 +0000)]
land b_hd_sec onto HEAD, some debugging code also kept.

15 years agoBranch: HEAD
wangdi [Sun, 5 Jun 2005 06:33:04 +0000 (06:33 +0000)]
Branch: HEAD
some fixes for WB cache
1)reorganization for cobd_setup, add cache_real_exp, master_real_exp for real
  connection
2)the fix in lmc for wrong lov_index

15 years ago* Fixed 5858: vibnal arp retries
eeb [Fri, 3 Jun 2005 09:36:56 +0000 (09:36 +0000)]
*     Fixed 5858: vibnal arp retries

15 years agoBoot time sysctl setting for Lustre OS X.
liangzhen [Fri, 3 Jun 2005 09:21:56 +0000 (09:21 +0000)]
Boot time sysctl setting for Lustre OS X.

15 years ago- remove non-needed CERROR
alex [Fri, 3 Jun 2005 08:30:48 +0000 (08:30 +0000)]
- remove non-needed CERROR

15 years agoadd more and adjust acl test script.
ericm [Fri, 3 Jun 2005 02:52:55 +0000 (02:52 +0000)]
add more and adjust acl test script.

15 years agoadd a sunrpc cache_put patch for testing.
ericm [Thu, 2 Jun 2005 22:19:36 +0000 (22:19 +0000)]
add a sunrpc cache_put patch for testing.

15 years agohandle .tgz files
jacob [Thu, 2 Jun 2005 19:48:14 +0000 (19:48 +0000)]
handle .tgz files

15 years agofile vibnal_modparams.c was initially added on branch b_hd_newconfig.
eeb [Thu, 2 Jun 2005 07:09:23 +0000 (07:09 +0000)]
file vibnal_modparams.c was initially added on branch b_hd_newconfig.

15 years agofile statfs64-cast-unsigned-2.4-rhel.patch was initially added on branch b_release_1_4_3.
jacob [Thu, 2 Jun 2005 06:29:49 +0000 (06:29 +0000)]
file statfs64-cast-unsigned-2.4-rhel.patch was initially added on branch b_release_1_4_3.

15 years agofile nfs_statfs-toomanyfiles-rhel-2.4.patch was initially added on branch b_release_1...
jacob [Thu, 2 Jun 2005 06:29:46 +0000 (06:29 +0000)]
file nfs_statfs-toomanyfiles-rhel-2.4.patch was initially added on branch b_release_1_4_3.

15 years agofix cred flags during client gss upcall; adjust timeout value.
ericm [Thu, 2 Jun 2005 05:58:14 +0000 (05:58 +0000)]
fix cred flags during client gss upcall; adjust timeout value.

15 years agofile ranal_modparams.c was initially added on branch b_hd_newconfig.
eeb [Wed, 1 Jun 2005 21:22:15 +0000 (21:22 +0000)]
file ranal_modparams.c was initially added on branch b_hd_newconfig.

15 years agoBranch: HEAD
wangdi [Wed, 1 Jun 2005 14:31:46 +0000 (14:31 +0000)]
Branch: HEAD
some fixes for WB cache

15 years agob=6427
alex [Wed, 1 Jun 2005 10:26:37 +0000 (10:26 +0000)]
b=6427

 - pass OBD_MD_FLID for raw lookup

15 years agoBranch HEAD
adilger [Wed, 1 Jun 2005 07:42:11 +0000 (07:42 +0000)]
Branch HEAD
Build fix for HEAD.
r=oleg (original fix)

15 years ago- one more fix about jumping to wrong label in mds_create_objects()
yury [Wed, 1 Jun 2005 07:12:10 +0000 (07:12 +0000)]
- one more fix about jumping to wrong label in mds_create_objects()

15 years ago- fixed jump to wrong label in mds_create_objects() in error path.
yury [Wed, 1 Jun 2005 07:06:45 +0000 (07:06 +0000)]
- fixed jump to wrong label in mds_create_objects() in error path.

15 years ago- minor fixes in smfs to support raw lookups
alex [Tue, 31 May 2005 21:39:59 +0000 (21:39 +0000)]
- minor fixes in smfs to support raw lookups

15 years agoBranch: b_cray-1_4_2
green [Tue, 31 May 2005 20:25:50 +0000 (20:25 +0000)]
Branch: b_cray-1_4_2
If liblustre was built, add liblustre.{a,so} to the lustre package

15 years agoadd larry's changes that allow using mpirun or yod for running IOR.
nic [Tue, 31 May 2005 20:04:25 +0000 (20:04 +0000)]
add larry's changes that allow using mpirun or yod for running IOR.

15 years agob=5843
alex [Tue, 31 May 2005 19:52:48 +0000 (19:52 +0000)]
b=5843

 - don't postpone orphan unlinks because

15 years agoquiet some verbose gss messages.
ericm [Tue, 31 May 2005 18:28:51 +0000 (18:28 +0000)]
quiet some verbose gss messages.

15 years agoBranch b1_4
adilger [Tue, 31 May 2005 18:15:47 +0000 (18:15 +0000)]
Branch b1_4
On x86_64 the kernel declares __u64 as long long, but userspace uses long.
Fix LP*64 printf format macros to handle this difference to quiet warnings.

15 years agoBrach HEAD
wangdi [Tue, 31 May 2005 14:52:12 +0000 (14:52 +0000)]
Brach HEAD
r:alex
add lookup-raw patches for raw lookup acceptance tests

15 years ago- don't try to show nid for non-connected exports
alex [Tue, 31 May 2005 12:41:17 +0000 (12:41 +0000)]
- don't try to show nid for non-connected exports

15 years ago- add debug message
tappro [Tue, 31 May 2005 11:31:54 +0000 (11:31 +0000)]
- add debug message

15 years agob=6379
alex [Tue, 31 May 2005 11:20:31 +0000 (11:20 +0000)]
b=6379

 - even a simpler fix: just skip removal if orphan is already unlinked
   semaphore on pending dir should be enough

15 years agob=6414,6366
tappro [Tue, 31 May 2005 11:02:50 +0000 (11:02 +0000)]
b=6414,6366
r=alex

it seems that this ASSERT is not needed here really. Such case is allowed

15 years ago* Fix for 6357: handle RapidArray memory registration failures.
eeb [Tue, 31 May 2005 10:24:25 +0000 (10:24 +0000)]
*   Fix for 6357: handle RapidArray memory registration failures.

15 years ago- show nid for stale clients
alex [Tue, 31 May 2005 10:10:25 +0000 (10:10 +0000)]
- show nid for stale clients

15 years ago- export show_task()
alex [Tue, 31 May 2005 07:58:02 +0000 (07:58 +0000)]
- export show_task()

15 years agob=6379
alex [Tue, 31 May 2005 07:16:22 +0000 (07:16 +0000)]
b=6379

 - check for open count only in mds_cleanup_orphans()
 - drop orphan flag to avoid simultaneous unlinking from PENDING/

15 years agob=6403
alex [Tue, 31 May 2005 06:41:53 +0000 (06:41 +0000)]
b=6403

 - revert wrong fix back

15 years agoHEAD
adilger [Mon, 30 May 2005 20:25:33 +0000 (20:25 +0000)]
HEAD
Fix error messages.

15 years ago- minor debug message fix
alex [Mon, 30 May 2005 13:50:05 +0000 (13:50 +0000)]
- minor debug message fix

15 years agob=6403
alex [Mon, 30 May 2005 11:30:07 +0000 (11:30 +0000)]
b=6403

 - remove ugly debug bits
 - dump FL_REPLAY reqs once after connect to avoid flooding

15 years ago- more compilation fixes after discussing them with Andreas
yury [Mon, 30 May 2005 07:42:57 +0000 (07:42 +0000)]
- more compilation fixes after discussing them with Andreas

15 years agob=6413
alex [Sun, 29 May 2005 22:43:10 +0000 (22:43 +0000)]
b=6413

 - wake recovery thread up on any {REQ|LOCK}_REPLAY_DONE

15 years agob=6379
alex [Sun, 29 May 2005 21:03:52 +0000 (21:03 +0000)]
b=6379

 - drop orphan flag to prevent a race between mds_cleanup_orphans() and
   mds_mfd_close() when the both try to unlink the same orphan

15 years ago- many gcc4 compilation fixes (warnings)
yury [Sun, 29 May 2005 16:17:17 +0000 (16:17 +0000)]
- many gcc4 compilation fixes (warnings)

15 years agob=6403
alex [Sun, 29 May 2005 09:34:30 +0000 (09:34 +0000)]
b=6403

 - ll_dentry_iput() clears all l_ast_data and this makes impossible to
   close a file upon openlock cancel

15 years ago- minor debug messages fixes
alex [Sat, 28 May 2005 11:16:28 +0000 (11:16 +0000)]
- minor debug messages fixes

15 years agoBranch b1_4
adilger [Fri, 27 May 2005 22:45:28 +0000 (22:45 +0000)]
Branch b1_4
Re-enable rate-limiting of CDEBUG messages.  The lack of which is causing
grief on large clusters during recovery.
b=4311

15 years agofile llog_reader.c was initially added on branch b_cray_newconfig.
lincent [Fri, 27 May 2005 21:31:04 +0000 (21:31 +0000)]
file llog_reader.c was initially added on branch b_cray_newconfig.

15 years agob=6403
alex [Fri, 27 May 2005 21:02:00 +0000 (21:02 +0000)]
b=6403

 - additional check because a req with FL_REPLAY can be w/o repmsg

15 years ago- landing MOD (MDS Originated destroy) plus few ldlm and MDS fixes.
yury [Fri, 27 May 2005 18:19:41 +0000 (18:19 +0000)]
- landing MOD (MDS Originated destroy) plus few ldlm and MDS fixes.

15 years agob=6403
alex [Fri, 27 May 2005 13:38:44 +0000 (13:38 +0000)]
b=6403

 - additional debug mess(age?) to learn 6K depth open req queue on cnbuild

15 years agob=6366
tappro [Fri, 27 May 2005 12:51:54 +0000 (12:51 +0000)]
b=6366
r=alex
- delete_inode() for backfs inode should be called synchronous with smfs. To do this smfs_clear_inode_info() is called from smfs_delete_inode().

15 years agoBranch HEAD
wangdi [Fri, 27 May 2005 09:50:41 +0000 (09:50 +0000)]
Branch HEAD
add types.h in Makefile.am for some tests build

15 years agob=6403
alex [Thu, 26 May 2005 22:55:27 +0000 (22:55 +0000)]
b=6403

 - the situation looks valid with opencache locks, but it floods consoles
   over. make it silent for a while

15 years agoupdate to krb5 script: check krytab for root.
ericm [Thu, 26 May 2005 19:19:56 +0000 (19:19 +0000)]
update to krb5 script: check krytab for root.

15 years agob=6394
ericm [Thu, 26 May 2005 19:14:59 +0000 (19:14 +0000)]
b=6394
* don't touch base rpcpipe chain.
* invalidate svc gss cache item in case of init error.

15 years ago- minor log format fix
alex [Thu, 26 May 2005 19:02:36 +0000 (19:02 +0000)]
- minor log format fix

15 years agoquite some unnecessary messages and a compiler warning.
ericm [Thu, 26 May 2005 17:13:15 +0000 (17:13 +0000)]
quite some unnecessary messages and a compiler warning.

15 years agob=6398
alex [Thu, 26 May 2005 17:05:54 +0000 (17:05 +0000)]
b=6398

 - additional assert

15 years ago- don't log open replays
alex [Thu, 26 May 2005 16:59:58 +0000 (16:59 +0000)]
- don't log open replays

15 years agob=6398
alex [Thu, 26 May 2005 11:08:39 +0000 (11:08 +0000)]
b=6398

 - target_start_recovery_thread() starts a thread and must wait for
   completion because that thread sets recovering flag. but routine
   kernel_thread() returns pid > 0 in successful case, while the
   target_start_recover_thread() expects 0. so, first routine
   target_start_recovery_thread() returns immediately and chain
   mds_postsetup() -> mds_dt_connect() is called with obd_recovering==0.
   so, mds_postrecov_common() is called and it calls mds_cleanup_orphans()