Whamcloud - gitweb
fs/lustre-release.git
18 years ago Mgs hold on the mgs_open_llog as resources on llog, and each resource will...
lincent [Wed, 26 Oct 2005 18:58:28 +0000 (18:58 +0000)]
  Mgs hold on the mgs_open_llog as resources on llog, and each resource will be locked by
ldlm_llog.
      Each different version llog for one filesystem/pool will have same mgs_open_llog, and
different version_desc(or llog patch), which descripe llog cmds the client/mds should run to keep up with current llog version.

      Also, mgs_open_llog will contain current updated llog , and the llog patch just contain the
specail llog_hdr_bitmap , which set valid bits to the llog cmds need to run for the client hold the old
llog version.

18 years agoBranch b1_4_mountconf
nathan [Wed, 19 Oct 2005 23:03:08 +0000 (23:03 +0000)]
Branch b1_4_mountconf
b=6663
extents and mballoc should not be defaults

18 years ago new mgc, mgs codes
lincent [Mon, 17 Oct 2005 14:09:06 +0000 (14:09 +0000)]
 new mgc, mgs codes

18 years ago change portals mechnism to lnet mecnism in mountconf
lincent [Mon, 17 Oct 2005 14:01:33 +0000 (14:01 +0000)]
   change portals mechnism to lnet mecnism in mountconf

18 years ago mgc codes
lincent [Mon, 17 Oct 2005 12:22:45 +0000 (12:22 +0000)]
 mgc codes

18 years agoBranch b1_4_mountconf
nathan [Sat, 15 Oct 2005 00:14:24 +0000 (00:14 +0000)]
Branch b1_4_mountconf
b=6663
get rid of run_cmds where possible

18 years agob=5831,6224
nathan [Tue, 11 Oct 2005 00:47:41 +0000 (00:47 +0000)]
b=5831,6224
Phil wanted to be sure these made it into mountconf.

18 years agosome fixes on llog
lincent [Mon, 10 Oct 2005 13:28:40 +0000 (13:28 +0000)]
some fixes on llog

18 years agonew llog_ldlm
lincent [Mon, 10 Oct 2005 11:28:07 +0000 (11:28 +0000)]
new llog_ldlm

18 years agonew llog_ldlm process and mgc_enqueue
lincent [Mon, 10 Oct 2005 11:25:21 +0000 (11:25 +0000)]
new llog_ldlm process and mgc_enqueue

18 years agonew file for mgc llog and new lock on mgc
lincent [Mon, 10 Oct 2005 11:17:46 +0000 (11:17 +0000)]
new file for mgc llog and new lock on mgc

18 years agofix llog_create to old pattern
lincent [Sun, 9 Oct 2005 09:40:05 +0000 (09:40 +0000)]
fix llog_create to old pattern

18 years agoadapt to lnet from portals
lincent [Sun, 9 Oct 2005 09:26:41 +0000 (09:26 +0000)]
adapt to lnet from portals

18 years agoBranch b1_4_mountconf
nathan [Wed, 28 Sep 2005 00:21:55 +0000 (00:21 +0000)]
Branch b1_4_mountconf
b=8010
dynamically allocate lmd options, change lmd parsing to work for 2.4
fix leaky mgc_setup

18 years agoBranch b1_4_mountconf
nathan [Tue, 27 Sep 2005 00:12:52 +0000 (00:12 +0000)]
Branch b1_4_mountconf
b=8013
move options parsing from mount.lustre into kernel

18 years agoBranch b1_4_mountconf
nathan [Tue, 20 Sep 2005 23:33:07 +0000 (23:33 +0000)]
Branch b1_4_mountconf
b=8341
update b1_4_mountconf from b1_4_newconfig: now with LNET

18 years agoThis commit was manufactured by cvs2svn to create branch 'b1_4_mountconf'.
cvs2svn [Mon, 19 Sep 2005 22:37:05 +0000 (22:37 +0000)]
This commit was manufactured by cvs2svn to create branch 'b1_4_mountconf'.

18 years agoBranch b1_4_newconfig2
nathan [Mon, 19 Sep 2005 22:37:04 +0000 (22:37 +0000)]
Branch b1_4_newconfig2
b=8187
minor cleanup

18 years ago MGS/MGC requests.
lincent [Mon, 12 Sep 2005 14:36:59 +0000 (14:36 +0000)]
   MGS/MGC requests.

18 years ago*** empty log message ***
lincent [Tue, 30 Aug 2005 16:46:07 +0000 (16:46 +0000)]
*** empty log message ***

18 years agonew mgs llog mechanism
lincent [Wed, 24 Aug 2005 17:58:35 +0000 (17:58 +0000)]
new mgs llog mechanism

18 years ago new llog open mechanism
lincent [Mon, 22 Aug 2005 16:38:13 +0000 (16:38 +0000)]
   new llog open mechanism
   next step:
       update llogs

18 years ago mgs_handler
lincent [Mon, 15 Aug 2005 18:32:59 +0000 (18:32 +0000)]
 mgs_handler
 change the name from mgs_hander.c to mgs_handler.c

18 years agomgs operations
lincent [Mon, 15 Aug 2005 18:24:26 +0000 (18:24 +0000)]
mgs operations

18 years agoBranch b1_4_newconfig2
nathan [Thu, 11 Aug 2005 23:57:59 +0000 (23:57 +0000)]
Branch b1_4_newconfig2
b=6663
add lov manual cleanup

18 years agoBranch b1_4_newconfig2
nathan [Thu, 11 Aug 2005 18:35:20 +0000 (18:35 +0000)]
Branch b1_4_newconfig2
b=6663
mount and umount working for bare mds

18 years agoBranch b1_4_newconfig2
nathan [Wed, 10 Aug 2005 23:43:07 +0000 (23:43 +0000)]
Branch b1_4_newconfig2
b=6663
fixup mntget and mntput

18 years ago Assigned mgc_obd in mgc_fs_setup
lincent [Wed, 10 Aug 2005 18:58:15 +0000 (18:58 +0000)]
 Assigned mgc_obd in mgc_fs_setup

18 years agoBranch b1_4_newconfig2
nathan [Wed, 10 Aug 2005 00:23:07 +0000 (00:23 +0000)]
Branch b1_4_newconfig2
b=6663
resolve mgc symbols

18 years agoBranch b1_4_newconfig2
nathan [Tue, 9 Aug 2005 23:55:32 +0000 (23:55 +0000)]
Branch b1_4_newconfig2
b=6663
move fs registration out of llite

18 years agoBranch b1_4_newconfig2
nathan [Tue, 9 Aug 2005 16:22:11 +0000 (16:22 +0000)]
Branch b1_4_newconfig2
b=6663
denser llog reader output

18 years ago*** empty log message ***
lincent [Tue, 9 Aug 2005 10:28:28 +0000 (10:28 +0000)]
*** empty log message ***

18 years agonew version llog_reader
lincent [Tue, 9 Aug 2005 09:23:18 +0000 (09:23 +0000)]
new version llog_reader

18 years agoBranch b1_4_newconfig2
nathan [Tue, 9 Aug 2005 00:07:48 +0000 (00:07 +0000)]
Branch b1_4_newconfig2
b=6663
mkfs.lustre now creates startup logs through mds, soon to be mcobd

18 years ago*** empty log message ***
lincent [Mon, 8 Aug 2005 09:10:43 +0000 (09:10 +0000)]
*** empty log message ***

18 years agoBranch b1_4_newconfig2
nathan [Sat, 6 Aug 2005 00:11:47 +0000 (00:11 +0000)]
Branch b1_4_newconfig2
b=6663
add mount reference code

18 years ago mgs_handler mgs_fs_setup
lincent [Fri, 5 Aug 2005 14:18:12 +0000 (14:18 +0000)]
 mgs_handler mgs_fs_setup

18 years agoBranch b1_4_newconfig2
nathan [Fri, 5 Aug 2005 01:08:40 +0000 (01:08 +0000)]
Branch b1_4_newconfig2
b=6663
mgc_setup should look more like confobd setup than client setup

18 years agoBranch b1_4_newconfig2
nathan [Fri, 5 Aug 2005 00:26:04 +0000 (00:26 +0000)]
Branch b1_4_newconfig2
b=6663
trying to add mgc_fs_setup/cleanup

18 years agoBranch b1_4_newconfig2
nathan [Wed, 3 Aug 2005 23:55:42 +0000 (23:55 +0000)]
Branch b1_4_newconfig2
b=6663
remove client llogs from mkfs.lustre

18 years ago add fsname in llog to support several fs configs in the same mgs
lincent [Wed, 3 Aug 2005 22:06:58 +0000 (22:06 +0000)]
 add fsname in llog to support several fs configs in the same mgs

18 years agoBranch b1_4_newconfig2
nathan [Wed, 3 Aug 2005 21:39:45 +0000 (21:39 +0000)]
Branch b1_4_newconfig2
b=6663
change mgmtnid to mgsnid

18 years agoBranch b1_4_newconfig2
nathan [Wed, 3 Aug 2005 21:21:15 +0000 (21:21 +0000)]
Branch b1_4_newconfig2
b=6663
use mgc_obd instead of mgmt_obd

18 years ago no rcvd file in mgs
lincent [Wed, 3 Aug 2005 21:06:24 +0000 (21:06 +0000)]
  no rcvd file in mgs

18 years agoBranch b1_4_newconfig2
nathan [Wed, 3 Aug 2005 00:34:12 +0000 (00:34 +0000)]
Branch b1_4_newconfig2
b=6663
common last_rcvd
starting llog writing

18 years agonew export for mgc , mgs
lincent [Tue, 2 Aug 2005 14:17:13 +0000 (14:17 +0000)]
new export for mgc , mgs

18 years agoadd mgc mgs to Makefile
lincent [Tue, 2 Aug 2005 10:31:06 +0000 (10:31 +0000)]
add mgc mgs to Makefile

18 years agonew mgc obd
lincent [Tue, 2 Aug 2005 10:26:45 +0000 (10:26 +0000)]
new mgc obd

18 years agonew head file for mgc/mgs
lincent [Tue, 2 Aug 2005 10:20:55 +0000 (10:20 +0000)]
new head file for mgc/mgs

18 years agob=6663
nathan [Mon, 1 Aug 2005 23:22:19 +0000 (23:22 +0000)]
b=6663
sort out the inter-module dependencies.
lvfs had a loop with obdclass, so moved mount there

18 years agoBranch b1_4_newconfig2
nathan [Sat, 30 Jul 2005 00:12:31 +0000 (00:12 +0000)]
Branch b1_4_newconfig2
b=6663
continue working toward DLD. Compiles, mgc stubbed

18 years agoBranch b1_4_newconfig2
nathan [Wed, 27 Jul 2005 23:11:32 +0000 (23:11 +0000)]
Branch b1_4_newconfig2
b=6663
ongoing toward DLD: lvfs_mount.c etc.

18 years agob=6663
nathan [Mon, 25 Jul 2005 23:55:56 +0000 (23:55 +0000)]
b=6663
adding lvfs_mount, begin changes to llite_lib.c

18 years agoBranch b1_4_newconfig2
nathan [Sat, 23 Jul 2005 01:28:54 +0000 (01:28 +0000)]
Branch b1_4_newconfig2
b=6663
continued mkfs refinement

18 years agoBranch b1_4_newconfig2
nathan [Fri, 22 Jul 2005 00:40:20 +0000 (00:40 +0000)]
Branch b1_4_newconfig2
b=6663
add mds, client llog writing

18 years agoBranch b1_4_newconfig2
nathan [Tue, 19 Jul 2005 00:14:56 +0000 (00:14 +0000)]
Branch b1_4_newconfig2
b=6663
rework mkfs.lustre per DLD (in progress)

18 years agoBranch b1_4_newconfig2
nathan [Fri, 15 Jul 2005 20:00:15 +0000 (20:00 +0000)]
Branch b1_4_newconfig2
b=6663
rework mount and mkfs structs to delineate persistent and non-persistent data.

18 years agoBranch b1_4_newconfig2
nathan [Fri, 15 Jul 2005 02:07:22 +0000 (02:07 +0000)]
Branch b1_4_newconfig2
b=6663
begin port of mountconf to new portals 1_4

18 years agoThis commit was manufactured by cvs2svn to create branch 'b1_4_newconfig2'.
cvs2svn [Thu, 14 Jul 2005 10:35:10 +0000 (10:35 +0000)]
This commit was manufactured by cvs2svn to create branch 'b1_4_newconfig2'.

18 years ago* Changed find_route to always return an empty list, to complement
eeb [Thu, 14 Jul 2005 10:35:09 +0000 (10:35 +0000)]
*   Changed find_route to always return an empty list, to complement
    the change in find_local_servers which returns all servers.

18 years ago* restored commented-out UUID handling for non-local servers
eeb [Thu, 14 Jul 2005 10:24:37 +0000 (10:24 +0000)]
*   restored commented-out UUID handling for non-local servers

18 years agob=3984
alex [Sun, 10 Jul 2005 23:10:17 +0000 (23:10 +0000)]
b=3984

 - b_ldlm_newlocking landed. we need it to pass some CMD2 performance tests
   NOTE: the new locking rules introduced by the patch are still experimental!

18 years ago- drop reference for open replay data in mdc_commit_open() instead of
alex [Sun, 10 Jul 2005 23:05:06 +0000 (23:05 +0000)]
- drop reference for open replay data in mdc_commit_open() instead of
  mdc_commit_close() as in some cases we may have no close at all

18 years ago- out of date warning has been removed
alex [Sun, 10 Jul 2005 22:12:32 +0000 (22:12 +0000)]
- out of date warning has been removed

18 years ago- make 512-bytes inode size by default: with new EAs (fid, parent) we just
alex [Sun, 10 Jul 2005 22:07:43 +0000 (22:07 +0000)]
- make 512-bytes inode size by default: with new EAs (fid, parent) we just
  can't fit 256-bytes inodes

18 years ago- convert CWARN() to CDEBUG()
alex [Sun, 10 Jul 2005 20:38:42 +0000 (20:38 +0000)]
- convert CWARN() to CDEBUG()

18 years ago- we don't need deadlock-monitor in general series
alex [Sun, 10 Jul 2005 19:53:09 +0000 (19:53 +0000)]
- we don't need deadlock-monitor in general series

18 years agob=6817
alex [Sun, 10 Jul 2005 19:52:22 +0000 (19:52 +0000)]
b=6817

 - b_size_on_mds landed (prototype for CMD2 w/o recovery support on OST)

18 years ago- minor debug level change to have only DEBUG_REQ with D_RPCTRACE
alex [Sun, 10 Jul 2005 18:36:24 +0000 (18:36 +0000)]
- minor debug level change to have only DEBUG_REQ with D_RPCTRACE

18 years ago- update enqueue time upon lock conversion otherwise we get too long
alex [Sun, 10 Jul 2005 18:31:06 +0000 (18:31 +0000)]
- update enqueue time upon lock conversion otherwise we get too long
  enqueue wait time warning

18 years agomds_open() better to check permission even it's open request for device
ericm [Sun, 10 Jul 2005 05:17:51 +0000 (05:17 +0000)]
mds_open() better to check permission even it's open request for device
files, otherwise client vfs will check that and failed siliently which
cause request leak. (client's interaction with vfs seems not perfect --
can't handle all error cases)

18 years agotry to be a little bit more nice to remote use: as long as it be mapped
ericm [Sat, 9 Jul 2005 19:33:55 +0000 (19:33 +0000)]
try to be a little bit more nice to remote use: as long as it be mapped
to an local user, the supp groups of target usr will take part in fs
access checking.

18 years agoadjust gss timeout valud, don't use fixed value.
ericm [Sat, 9 Jul 2005 16:04:16 +0000 (16:04 +0000)]
adjust gss timeout valud, don't use fixed value.

18 years agoBranch HEAD
wangdi [Sat, 9 Jul 2005 03:19:27 +0000 (03:19 +0000)]
Branch HEAD
fix a typo in sanity-cmobd.sh

18 years ago- putting file fid into o_inline for cases when crow object may be created. It will...
yury [Fri, 8 Jul 2005 15:23:42 +0000 (15:23 +0000)]
- putting file fid into o_inline for cases when crow object may be created. It will be used later for storing into OSS object EA what is needed for quota.

18 years ago* newconfig liblustre/tcpnal runs sanity OK
eeb [Fri, 8 Jul 2005 14:51:21 +0000 (14:51 +0000)]
*    newconfig liblustre/tcpnal runs sanity OK

18 years agob=6285
tappro [Fri, 8 Jul 2005 13:57:25 +0000 (13:57 +0000)]
b=6285
- remove few debug and LBUG()

18 years ago- cleanups in cobd and cmobd
yury [Fri, 8 Jul 2005 10:35:04 +0000 (10:35 +0000)]
- cleanups in cobd and cmobd
- moved cmobd's level in lconf to be under mountpoint. This prevents oops in local config when both cobd and cmobd are used and refer to the same master device.

18 years ago- using push_ctxt() and pop_ctxt() when setting uid/gid in filter_create_object(...
yury [Fri, 8 Jul 2005 07:29:45 +0000 (07:29 +0000)]
- using push_ctxt() and pop_ctxt() when setting uid/gid in filter_create_object() at Alex's suggest.

18 years ago - add things to /etc/modules.conf | /etc/modprobe.conf
jacob [Thu, 7 Jul 2005 21:43:41 +0000 (21:43 +0000)]
 - add things to /etc/modules.conf | /etc/modprobe.conf
 - tweaks to init scripts for SLES 9

18 years agouid == gid is no longer a valid assumption.
buffalo-pull [Thu, 7 Jul 2005 18:04:09 +0000 (18:04 +0000)]
uid == gid is no longer a valid assumption.

18 years ago* first signs of life from newconfig tcpnal + liblustre echo_client
eeb [Thu, 7 Jul 2005 17:48:33 +0000 (17:48 +0000)]
*   first signs of life from newconfig tcpnal + liblustre echo_client

18 years agoland b_hd_sec on HEAD. various security fixes.
ericm [Thu, 7 Jul 2005 17:41:19 +0000 (17:41 +0000)]
land b_hd_sec on HEAD. various security fixes.

18 years agob=7039
alex [Thu, 7 Jul 2005 16:29:19 +0000 (16:29 +0000)]
b=7039

 - additional debug info: dump backtrace

18 years ago- minor typo
alex [Thu, 7 Jul 2005 14:27:05 +0000 (14:27 +0000)]
- minor typo

18 years agob=6285
alex [Thu, 7 Jul 2005 14:23:22 +0000 (14:23 +0000)]
b=6285

 - sometimes mds_getattr_lock() is asked to refresh attributes by fid.
   it doesn't take LOOKUP lock, thus has no protected from concurrent
   unlink. this means mds_getattr_lock() can return already unlinked
   (and being removed) inode. to avoid this we check i_nlink right
   after we got UPDATE lock and return -ENOENT if nlink is zero

18 years agob=6913
alex [Thu, 7 Jul 2005 13:38:55 +0000 (13:38 +0000)]
b=6913

 - retract extents lock from clients even if OSS hasn't created object yet

18 years ago- minor comment about openlock and test 24n from sanity.sh
alex [Thu, 7 Jul 2005 13:03:01 +0000 (13:03 +0000)]
- minor comment about openlock and test 24n from sanity.sh

18 years agob=6285
tappro [Thu, 7 Jul 2005 12:21:56 +0000 (12:21 +0000)]
b=6285
- more debug info was added

18 years agob=6285
tappro [Thu, 7 Jul 2005 08:33:07 +0000 (08:33 +0000)]
b=6285
- add LBUG() to get kernel-logs in case of this issue

18 years ago- better to make vfs_create() to set correct uid and gid for new inode, as dirtying...
yury [Thu, 7 Jul 2005 07:57:07 +0000 (07:57 +0000)]
- better to make vfs_create() to set correct uid and gid for new inode, as dirtying inode in ext3 is too expensive. Thanks to Andreas.

19 years agob=7023
alex [Wed, 6 Jul 2005 21:53:09 +0000 (21:53 +0000)]
b=7023

 - export can be failed asynchronously with regard to processing request.
   this case cause open rpc to be replied to zero transno. zero transno
   means no reference for request and open request gets freed after
   ll_file_open() though mdc_open_data still has a reference on the
   request. and this causes oops when mdc_close() tries to access the
   request. the workaround is to take additional reference on the request
   for mdc_open_data

19 years ago- disable test 24n: it fails because of disabled opencache. current
alex [Wed, 6 Jul 2005 21:06:19 +0000 (21:06 +0000)]
- disable test 24n: it fails because of disabled opencache. current
  mds_open() doesn't take lookup lock and client can't maintain
  dcache in coherence

19 years ago- make recovery-small.sh working correct with local configuration (1 mds)
alex [Wed, 6 Jul 2005 20:13:41 +0000 (20:13 +0000)]
- make recovery-small.sh working correct with local configuration (1 mds)

19 years ago- passing full options page to do_kern_mount() in confobd and smfs too like it is...
yury [Wed, 6 Jul 2005 16:49:20 +0000 (16:49 +0000)]
- passing full options page to do_kern_mount() in confobd and smfs too like it is done in MDS and OST

19 years ago- removed not used vars in client_obd_setup()
yury [Wed, 6 Jul 2005 12:41:36 +0000 (12:41 +0000)]
- removed not used vars in client_obd_setup()
- many fixes and improvements suggested by Andreas
- removed not used function inode_update_time()

19 years agominor fix in lmv_get_mea_and_update_object().
niu [Wed, 6 Jul 2005 07:53:00 +0000 (07:53 +0000)]
minor fix in lmv_get_mea_and_update_object().

19 years agoconvert to u64 in case of overflow.
niu [Wed, 6 Jul 2005 07:48:59 +0000 (07:48 +0000)]
convert to u64 in case of overflow.
- b 6450

19 years agoBranch b1_4
adilger [Tue, 5 Jul 2005 23:46:12 +0000 (23:46 +0000)]
Branch b1_4
Fix catamount build breakage, may be able to remove entirely at some point.
b=6923

19 years agoNeed to get values from netstat "unresolved" because the port numbers returned
brian [Tue, 5 Jul 2005 21:31:00 +0000 (21:31 +0000)]
Need to get values from netstat "unresolved" because the port numbers returned
are used in numerical comparisons.