Whamcloud - gitweb
fs/lustre-release.git
15 years agoallow vars to be overriden from the command line
nic [Thu, 6 Oct 2005 18:13:00 +0000 (18:13 +0000)]
allow vars to be overriden from the command line

15 years agob1_4_xattr don't need special requirement for lnet since it's re-based
ericm [Wed, 5 Oct 2005 17:22:34 +0000 (17:22 +0000)]
b1_4_xattr don't need special requirement for lnet since it's re-based
on b1_4 now.

15 years agob1_4_xattr need same lnet as b1_4_newconfig
ericm [Wed, 5 Oct 2005 05:12:17 +0000 (05:12 +0000)]
b1_4_xattr need same lnet as b1_4_newconfig

15 years ago* make scheduler threads balance rx and tx more evenly
pjkirner [Thu, 29 Sep 2005 20:04:40 +0000 (20:04 +0000)]
* make scheduler threads balance rx and tx more evenly
* move peer allocation outside spin lock
* fix bug with irqs not being disabled on spinlocks that need syncronzation with callbacks

15 years agoBranch b1_4
adilger [Thu, 29 Sep 2005 06:03:30 +0000 (06:03 +0000)]
Branch b1_4
Add "make srpm" target for <drum roll>making .src.rpm files</drum roll>.

15 years agoadd makefile for standalone quota.
lsy [Mon, 26 Sep 2005 08:19:04 +0000 (08:19 +0000)]
add makefile for  standalone quota.

15 years agoGroup lock code to pass test 58.
brian [Sat, 24 Sep 2005 03:25:58 +0000 (03:25 +0000)]
Group lock code to pass test 58.

15 years agoBackout changes made to day in efforts to make test 41 work. It passes with
brian [Sat, 24 Sep 2005 03:06:38 +0000 (03:06 +0000)]
Backout changes made to day in efforts to make test 41 work.  It passes with
code checked out prior to all of these changes.

15 years ago- minor optimization to avoid extra expenses related to OST A/M/D in the
alex [Sat, 24 Sep 2005 01:23:23 +0000 (01:23 +0000)]
- minor optimization to avoid extra expenses related to OST A/M/D in the
  path of LOV EA revalidation

15 years ago- re-fill size/blocks attributes in open reply if ea lov has been changed
alex [Sat, 24 Sep 2005 00:33:55 +0000 (00:33 +0000)]
- re-fill size/blocks attributes in open reply if ea lov has been changed
- yank granted update locks in the same case in order to invalidate
  cached size/blocks attributes on clients

15 years ago- missed bit from test 41 debugging
alex [Sat, 24 Sep 2005 00:21:24 +0000 (00:21 +0000)]
- missed bit from test 41 debugging

15 years ago- OST A/M/D should work OK in non-CMD setup
alex [Sat, 24 Sep 2005 00:17:35 +0000 (00:17 +0000)]
- OST A/M/D should work OK in non-CMD setup

15 years agor=alex
brian [Fri, 23 Sep 2005 22:45:21 +0000 (22:45 +0000)]
r=alex

Possible fix for file size mismatch between mds and osts.

15 years agoHEAD
wangdi [Fri, 23 Sep 2005 13:47:31 +0000 (13:47 +0000)]
HEAD
remove debug patch for test41

15 years agoBranch: HEAD
wangdi [Fri, 23 Sep 2005 12:57:23 +0000 (12:57 +0000)]
Branch: HEAD
try tmp patch for failed test41

15 years ago- don't enable capabilities by default
alex [Thu, 22 Sep 2005 20:04:01 +0000 (20:04 +0000)]
- don't enable capabilities by default

15 years agob=7148
alex [Thu, 22 Sep 2005 19:09:45 +0000 (19:09 +0000)]
b=7148
r=alex (original patch by don milos)

 - revalide i_size/i_blocks along with LOV EA in case of OSS removal

15 years ago- drop ll_capa_stat flag in order to preven flood
alex [Wed, 21 Sep 2005 23:09:14 +0000 (23:09 +0000)]
- drop ll_capa_stat flag in order to preven flood

15 years ago- make default key timelife 3 days long
alex [Wed, 21 Sep 2005 23:00:34 +0000 (23:00 +0000)]
- make default key timelife 3 days long

15 years ago- generate capability in open resend case
alex [Wed, 21 Sep 2005 21:14:26 +0000 (21:14 +0000)]
- generate capability in open resend case
- regression test for the case

15 years ago- additional debug to catch the case when client gets openhandle w/o capa
alex [Wed, 21 Sep 2005 20:42:37 +0000 (20:42 +0000)]
- additional debug to catch the case when client gets openhandle w/o capa

15 years agoadd debug msg for gss seq window.
ericm [Wed, 21 Sep 2005 18:52:32 +0000 (18:52 +0000)]
add debug msg for gss seq window.

15 years ago- drop needless capas upon close
alex [Wed, 21 Sep 2005 18:17:14 +0000 (18:17 +0000)]
- drop needless capas upon close

15 years agodrop truncate capa after ll_truncate.
lsy [Wed, 21 Sep 2005 17:46:04 +0000 (17:46 +0000)]
drop truncate capa after ll_truncate.

15 years agomore debug message.
lsy [Wed, 21 Sep 2005 15:45:19 +0000 (15:45 +0000)]
more debug message.

15 years agoadd b1_4_mountconf using lnet
nathan [Wed, 21 Sep 2005 14:29:51 +0000 (14:29 +0000)]
add b1_4_mountconf using lnet

15 years agomessage cleanup.
lsy [Wed, 21 Sep 2005 12:40:34 +0000 (12:40 +0000)]
message cleanup.

15 years ago- swab capa data in mdc_replay_open(), the sequence can be:
alex [Wed, 21 Sep 2005 12:40:32 +0000 (12:40 +0000)]
- swab capa data in mdc_replay_open(), the sequence can be:
  1) ll_file_open() has a request with capa
  2) the inode is already opened, so we close just received openhandle
  3) mds fails, recovers, ptlrpcd replays open request
  4) ll_set_capa() finds capa in replayed open request non-swabbed - BUG

15 years agoput capa before calling ll_renew_capa, in case it might get updated.
lsy [Wed, 21 Sep 2005 12:02:28 +0000 (12:02 +0000)]
put capa before calling ll_renew_capa, in case it might get updated.

15 years ago- don't make noise if we found needed capa
alex [Wed, 21 Sep 2005 11:07:08 +0000 (11:07 +0000)]
- don't make noise if we found needed capa
- minor cleanups

15 years ago- nobody needs these warnings any more
alex [Wed, 21 Sep 2005 11:01:02 +0000 (11:01 +0000)]
- nobody needs these warnings any more

15 years agodon't make too much noise.
lsy [Wed, 21 Sep 2005 10:08:19 +0000 (10:08 +0000)]
don't make too much noise.

15 years agoexport symbol.
lsy [Wed, 21 Sep 2005 09:51:50 +0000 (09:51 +0000)]
export symbol.

15 years agomake noise when capa not found.
lsy [Wed, 21 Sep 2005 09:39:53 +0000 (09:39 +0000)]
make noise when capa not found.

15 years agomissed i_gen
ericm [Wed, 21 Sep 2005 08:37:50 +0000 (08:37 +0000)]
missed i_gen

15 years ago- pack fake reply if mds_getattr() couldn't lookup fid. otherwise
alex [Wed, 21 Sep 2005 08:36:11 +0000 (08:36 +0000)]
- pack fake reply if mds_getattr() couldn't lookup fid. otherwise
  mds_handle() will oops.

15 years ago- in order to prevent flood during renewing capa for deleted inodes:
alex [Wed, 21 Sep 2005 07:16:25 +0000 (07:16 +0000)]
- in order to prevent flood during renewing capa for deleted inodes:
  - mds_getattr() returns regular errors in rq_status
  - mdc_interpret_getattr() interprets it properly

15 years agoclient capa list is sorted.
lsy [Wed, 21 Sep 2005 06:58:38 +0000 (06:58 +0000)]
client capa list is sorted.
new capa for mds and oss should be added at the end. (so it should be sorted too)

15 years agothe missing part of last capa fix.
ericm [Wed, 21 Sep 2005 05:06:59 +0000 (05:06 +0000)]
the missing part of last capa fix.

15 years agoremove stale capa structure from mds/filter obd.
ericm [Wed, 21 Sep 2005 01:19:14 +0000 (01:19 +0000)]
remove stale capa structure from mds/filter obd.

15 years agoon OSS compare the whole capa structure because we might have 2 capa only
ericm [Wed, 21 Sep 2005 01:01:01 +0000 (01:01 +0000)]
on OSS compare the whole capa structure because we might have 2 capa only
have difference in expiry time.

15 years agoBranch b1_4
adilger [Wed, 21 Sep 2005 00:02:40 +0000 (00:02 +0000)]
Branch b1_4
Update the CVS commit script to add a reminder about HLD/DLD updates.
r=design meeting

15 years ago- one more DEBUG_CAPA() to make sure we use proper capability to check
alex [Tue, 20 Sep 2005 23:41:33 +0000 (23:41 +0000)]
- one more DEBUG_CAPA() to make sure we use proper capability to check
  permissions

15 years ago- typo fixed
alex [Tue, 20 Sep 2005 23:01:21 +0000 (23:01 +0000)]
- typo fixed

15 years ago- bump capa cache size on MDS/OSS to 3000 to decrease cache refill load
alex [Tue, 20 Sep 2005 22:52:22 +0000 (22:52 +0000)]
- bump capa cache size on MDS/OSS to 3000 to decrease cache refill load

15 years ago- allocate tfm per every sign procedure (tfm isn't thread-safe)
alex [Tue, 20 Sep 2005 22:51:19 +0000 (22:51 +0000)]
- allocate tfm per every sign procedure (tfm isn't thread-safe)

15 years agocleanup debug message.
lsy [Tue, 20 Sep 2005 21:39:06 +0000 (21:39 +0000)]
cleanup debug message.

15 years agotypo.
lsy [Tue, 20 Sep 2005 16:23:46 +0000 (16:23 +0000)]
typo.

15 years agoadd debug for capa_key.
lsy [Tue, 20 Sep 2005 15:52:39 +0000 (15:52 +0000)]
add debug for capa_key.

15 years ago- warn if HMAC's don't match
alex [Tue, 20 Sep 2005 13:25:11 +0000 (13:25 +0000)]
- warn if HMAC's don't match

15 years agoadd debug msg, and some cleanup.
lsy [Tue, 20 Sep 2005 12:37:20 +0000 (12:37 +0000)]
add debug msg, and some cleanup.
capa_renew should use tcapa instead of capa.

15 years ago- needless \n grrrrr
alex [Tue, 20 Sep 2005 10:57:25 +0000 (10:57 +0000)]
- needless \n grrrrr

15 years ago- additional debug
alex [Tue, 20 Sep 2005 10:53:44 +0000 (10:53 +0000)]
- additional debug

15 years ago- minor typo: CDEBUG() doesn't add \n at the end
alex [Tue, 20 Sep 2005 09:38:36 +0000 (09:38 +0000)]
- minor typo: CDEBUG() doesn't add \n at the end

15 years agochange debug level.
lsy [Tue, 20 Sep 2005 08:25:05 +0000 (08:25 +0000)]
change debug level.

15 years agollite doesn't put it.
lsy [Tue, 20 Sep 2005 06:26:23 +0000 (06:26 +0000)]
llite doesn't put it.

15 years agocapa_renew should increase the refc.
lsy [Tue, 20 Sep 2005 06:03:08 +0000 (06:03 +0000)]
capa_renew should increase the refc.

15 years agoupdate struct lustre_capa_data too with the introduction of igen.
lsy [Tue, 20 Sep 2005 03:26:04 +0000 (03:26 +0000)]
update struct lustre_capa_data too with the introduction of igen.

15 years agoadd inode generation in capability.
ericm [Tue, 20 Sep 2005 03:05:40 +0000 (03:05 +0000)]
add inode generation in capability.

15 years ago- make noise if capa hasn't been passed even
alex [Mon, 19 Sep 2005 19:55:27 +0000 (19:55 +0000)]
- make noise if capa hasn't been passed even

15 years ago- additional debug for capa denies
alex [Mon, 19 Sep 2005 19:00:52 +0000 (19:00 +0000)]
- additional debug for capa denies

15 years agoBranch: HEAD
wangdi [Mon, 19 Sep 2005 07:31:08 +0000 (07:31 +0000)]
Branch: HEAD
typo fix about ldlm flags

15 years agoroundup gss credential timeout down to avoid expiration between accept &
ericm [Mon, 19 Sep 2005 07:11:07 +0000 (07:11 +0000)]
roundup gss credential timeout down to avoid expiration between accept &
authorize on server, or check & encrypt rpc on client.

15 years ago- protect i_nlink in smfs_mkdir() as well
alex [Sun, 18 Sep 2005 16:06:52 +0000 (16:06 +0000)]
- protect i_nlink in smfs_mkdir() as well

15 years agoBranch: HEAD
wangdi [Sun, 18 Sep 2005 04:15:57 +0000 (04:15 +0000)]
Branch: HEAD
uuid of client mdc and osc will be modified in mds ost add

15 years ago- protect i_nlink from concurrent changing
alex [Sat, 17 Sep 2005 22:48:46 +0000 (22:48 +0000)]
- protect i_nlink from concurrent changing

15 years agob=7268
alex [Sat, 17 Sep 2005 22:33:52 +0000 (22:33 +0000)]
b=7268

 - increase timeout for bulk PUT/GET a little bit

15 years agotemporarily disable sanity 57b which lead to LBUG.
ericm [Sat, 17 Sep 2005 07:49:51 +0000 (07:49 +0000)]
temporarily disable sanity 57b which lead to LBUG.
thanks tappro.

15 years agoBranch: HEAD
wangdi [Sat, 17 Sep 2005 06:40:20 +0000 (06:40 +0000)]
Branch: HEAD
tmp fix about ost add/del, reset osc uuid in mds, but not reset mdc uuid in mds

15 years agoprevent null_audit case
tappro [Sat, 17 Sep 2005 01:09:18 +0000 (01:09 +0000)]
prevent null_audit case

15 years agob=7230
tappro [Fri, 16 Sep 2005 23:30:58 +0000 (23:30 +0000)]
b=7230

update mtime as well as size on MDS and in llite

15 years ago- obd_disconnect(sbi->ll_dt_exp) clears namespace and lets inodes go, we
alex [Fri, 16 Sep 2005 22:23:31 +0000 (22:23 +0000)]
- obd_disconnect(sbi->ll_dt_exp) clears namespace and lets inodes go, we
  shouldn't release crypto subsystem before, because it's used in ll_clear_inode()

15 years ago- revert debugging bits back - it breaks everything
alex [Fri, 16 Sep 2005 22:18:40 +0000 (22:18 +0000)]
- revert debugging bits back - it breaks everything

15 years agosimple fix for inconsistent mtime on different client, commit to test if
niu [Fri, 16 Sep 2005 18:41:24 +0000 (18:41 +0000)]
simple fix for inconsistent mtime on different client, commit to test if
it's helpful.
- b 7230

15 years agoadd command null_audit in lctl
tappro [Fri, 16 Sep 2005 16:12:08 +0000 (16:12 +0000)]
add command null_audit in lctl

15 years agodo LASSERT if *name is not NULL
tappro [Fri, 16 Sep 2005 16:11:27 +0000 (16:11 +0000)]
do LASSERT if *name is not NULL

15 years agoBranch: HEAD
wangdi [Fri, 16 Sep 2005 15:52:26 +0000 (15:52 +0000)]
Branch: HEAD
missing update lvb_mtime

15 years agoadd null_audit command to lctl which will make audit silent. For testing purposes.
tappro [Fri, 16 Sep 2005 15:48:53 +0000 (15:48 +0000)]
add null_audit command to lctl which will make audit silent. For testing purposes.

15 years agoBranch: HEAD
wangdi [Fri, 16 Sep 2005 15:27:35 +0000 (15:27 +0000)]
Branch: HEAD
fix LDLM flags defination confilct

15 years agor=alex
tappro [Fri, 16 Sep 2005 12:45:20 +0000 (12:45 +0000)]
r=alex
 do d_delete() for backfs dentry as vfs_unlink/rmdir do

15 years ago- dump i_mode as well
alex [Fri, 16 Sep 2005 12:35:02 +0000 (12:35 +0000)]
- dump i_mode as well

15 years ago- check for non-zero inum
alex [Fri, 16 Sep 2005 12:34:33 +0000 (12:34 +0000)]
- check for non-zero inum

15 years ago- removed not needed error message
yury [Fri, 16 Sep 2005 10:46:07 +0000 (10:46 +0000)]
- removed not needed error message

15 years agorevert part of last change.
lsy [Fri, 16 Sep 2005 10:27:13 +0000 (10:27 +0000)]
revert part of last change.

15 years agoigrab() before ll_renew_capa() in case inode is cleared.
lsy [Fri, 16 Sep 2005 10:15:53 +0000 (10:15 +0000)]
igrab() before ll_renew_capa() in case inode is cleared.

15 years ago- we don't need this LBUG during acceptance
alex [Fri, 16 Sep 2005 09:49:24 +0000 (09:49 +0000)]
- we don't need this LBUG during acceptance

15 years agob=7340
alex [Fri, 16 Sep 2005 09:47:58 +0000 (09:47 +0000)]
b=7340

 - setup cr_replayid immediately because it might take long to get to
   mdc_set_open_replay_data() and replay can happen in meantime

15 years agohack: wait rsi really be cleaned up before module unload.
ericm [Fri, 16 Sep 2005 07:11:57 +0000 (07:11 +0000)]
hack: wait rsi really be cleaned up before module unload.

15 years ago- added some more noise in unlink time when errors to see what happening
yury [Fri, 16 Sep 2005 06:21:49 +0000 (06:21 +0000)]
- added some more noise in unlink time when errors to see what happening

15 years agoBranch: HEAD
wangdi [Fri, 16 Sep 2005 06:18:34 +0000 (06:18 +0000)]
Branch: HEAD
revert back ldlm flags and make them compatiable with b1_4, according to andreas comments.

15 years ago- check for bad inode in smfs_do_lookup()
alex [Fri, 16 Sep 2005 01:05:26 +0000 (01:05 +0000)]
- check for bad inode in smfs_do_lookup()

15 years agob=6866
alex [Fri, 16 Sep 2005 01:04:41 +0000 (01:04 +0000)]
b=6866
r=adilger(original patch)

  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.

15 years agoadd an assert, from alex.
ericm [Fri, 16 Sep 2005 00:14:21 +0000 (00:14 +0000)]
add an assert, from alex.

15 years agoBranch: HEAD
wangdi [Thu, 15 Sep 2005 17:53:50 +0000 (17:53 +0000)]
Branch: HEAD
add flock fix patch of Donm
fix about build warning in lustre_dlm.h

15 years agoBranch: HEAD
wangdi [Thu, 15 Sep 2005 17:19:21 +0000 (17:19 +0000)]
Branch: HEAD
land posix flock patch of Don.

15 years agob=7272
alex [Thu, 15 Sep 2005 16:34:55 +0000 (16:34 +0000)]
b=7272

 - very messy debug bits to check for double direntries

15 years agob=8654
tappro [Thu, 15 Sep 2005 13:42:19 +0000 (13:42 +0000)]
b=8654
revert back last changes after testing.

15 years agob=8654
tappro [Thu, 15 Sep 2005 10:29:27 +0000 (10:29 +0000)]
b=8654
 turn on stat auditing on client for testing purpose

15 years agob=8654
tappro [Thu, 15 Sep 2005 10:26:45 +0000 (10:26 +0000)]
b=8654
- delay notification for audit_transfer in case of create
- remove unneeded list_head declaration

15 years agob=7272
alex [Thu, 15 Sep 2005 09:47:58 +0000 (09:47 +0000)]
b=7272

 - check dentry after removing