Whamcloud - gitweb
fs/lustre-release.git
21 years ago- remove the README file Zach wrote. I placed it on the project wiki
braam [Sun, 8 Dec 2002 10:01:53 +0000 (10:01 +0000)]
- remove the README file Zach wrote.  I placed it on the project wiki
- add two initial patches for 2.5 as in use with 2.5.44
 - these require breaking up in components etc as Zach suggests

21 years ago- bring in akpm's patch management scripts and a first cut at
zab [Sat, 7 Dec 2002 00:21:14 +0000 (00:21 +0000)]
- bring in akpm's patch management scripts and a first cut at
  patch-2.4.18-14 and patch-2.4.18-um against 2.4.18-17.8.0.  the README
  should hopefully make it clear how these are intended to be used.  email
  to follow.

21 years agoUpdate the IA-64 patch
pschwan [Fri, 6 Dec 2002 10:19:14 +0000 (10:19 +0000)]
Update the IA-64 patch

21 years agomerge b_md into HEAD:
pschwan [Fri, 6 Dec 2002 10:11:13 +0000 (10:11 +0000)]
merge b_md into HEAD:
 - lfind did not preserve OST order in output (443)
 - symlinks cause hung clients, incorrect data (439)
 - stop dereferencing request after dropping refcount (457)
 - don't LASSERT(spin_is_locked) on non-SMP (455)
 - fixes for many rename() bugs

21 years agoRemoved all files in this tree, I goofed on the import
morrone [Fri, 6 Dec 2002 01:26:50 +0000 (01:26 +0000)]
Removed all files in this tree, I goofed on the import

21 years agoThis commit was generated by cvs2svn to compensate for changes in r5101,
morrone [Fri, 6 Dec 2002 01:15:13 +0000 (01:15 +0000)]
This commit was generated by cvs2svn to compensate for changes in r5101,
which included commits to RCS files with non-trunk default branches.

21 years agoFirst checkin of auto-test buffalo scripts
morrone [Fri, 6 Dec 2002 01:15:13 +0000 (01:15 +0000)]
First checkin of auto-test buffalo scripts

21 years agofile multifstat.c was initially added on branch b_md.
braam [Thu, 5 Dec 2002 14:48:19 +0000 (14:48 +0000)]
file multifstat.c was initially added on branch b_md.

21 years agofile patch-2.4.18-hp1_pnnl18.2.8qsnet was initially added on branch b_md.
eeb [Thu, 5 Dec 2002 14:22:12 +0000 (14:22 +0000)]
file patch-2.4.18-hp1_pnnl18.2.8qsnet was initially added on branch b_md.

21 years agoland b_md onto HEAD:
pschwan [Thu, 5 Dec 2002 08:42:29 +0000 (08:42 +0000)]
land b_md onto HEAD:
 - LRU counters were broken, causing constant lock purge (433, 432)
 - the first part of the fixes for the ldlm_handle2lock race (419)
 - cleanup unused ll_inode_info field (442)
 - keep ioctl semaphore from serializing test_getattr/brw

21 years agofile local2-hack.xml was initially added on branch b_md.
braam [Thu, 5 Dec 2002 07:54:26 +0000 (07:54 +0000)]
file local2-hack.xml was initially added on branch b_md.

21 years agofile llmount2-hackcleanup.sh was initially added on branch b_md.
braam [Thu, 5 Dec 2002 07:54:25 +0000 (07:54 +0000)]
file llmount2-hackcleanup.sh was initially added on branch b_md.

21 years agofile sanityN.sh was initially added on branch b_md.
braam [Thu, 5 Dec 2002 07:54:24 +0000 (07:54 +0000)]
file sanityN.sh was initially added on branch b_md.

21 years agoLanding b_recovery.
shaver [Thu, 5 Dec 2002 00:31:32 +0000 (00:31 +0000)]
Landing b_recovery.

b=441: garbage on read from stripes with failed OSTs.
b=438: mark OSCs as active before reconnecting during recovery.
b=403: lov_enqueue and lov_cancel need to handle inactive OSTs

21 years agofile genXml was initially added on branch b_ravi_devel.
sravi [Wed, 4 Dec 2002 14:13:21 +0000 (14:13 +0000)]
file genXml was initially added on branch b_ravi_devel.

21 years agob=442
pschwan [Wed, 4 Dec 2002 03:15:15 +0000 (03:15 +0000)]
b=442
Remove lli_intent_lock_handle that none of us seem to have an explanation for.

21 years agoFix typo in acceptance-small.sh
adilger [Mon, 2 Dec 2002 18:06:14 +0000 (18:06 +0000)]
Fix typo in acceptance-small.sh

21 years agoUpdate for new release
adilger [Mon, 2 Dec 2002 08:43:34 +0000 (08:43 +0000)]
Update for new release

21 years agoMerge of b_md to HEAD:
adilger [Mon, 2 Dec 2002 08:39:50 +0000 (08:39 +0000)]
Merge of b_md to HEAD:
- fixes of many metadata bugs:
  - multiple client file opens
  - missing/extra intent releases
  - symlink fixes
- OST/MDS server threads clobbering each other
  - dbench 2 works mostly
- many others too numerous to mention here (ChangeLog is a good record)

21 years agoRemove this .xml file yet one more time.
adilger [Sun, 1 Dec 2002 22:39:02 +0000 (22:39 +0000)]
Remove this .xml file yet one more time.

21 years agoIgnore all generated .xml files.
adilger [Sun, 1 Dec 2002 22:36:51 +0000 (22:36 +0000)]
Ignore all generated .xml files.

21 years agoFix ba-mount.sh so that it saves the config in $config instead of config.
adilger [Sun, 1 Dec 2002 22:32:10 +0000 (22:32 +0000)]
Fix ba-mount.sh so that it saves the config in $config instead of config.
Remove explicit port number.

21 years agoFix compile warnings (hopefully nothing else is missing...)
adilger [Sun, 1 Dec 2002 22:21:44 +0000 (22:21 +0000)]
Fix compile warnings (hopefully nothing else is missing...)

21 years agoLanding b_lock_replay so that Phil can use my ldlm iterators and whatnot for his
shaver [Sun, 1 Dec 2002 03:47:10 +0000 (03:47 +0000)]
Landing b_lock_replay so that Phil can use my ldlm iterators and whatnot for his
upcoming locking work.

Highlights:
 - lock replay infrastructure (needs much more testing, but didn't regress
   anything outside recovery)
 - b=421: ldlm iterators
 - b=348: imports now have service levels, replacing connections' c_level
 - replace c_delayed_head with imp_delayed_list
 - split imp_request_list into imp_replay_list for retained requests and
   imp_sending_list for inflight reqs
 - as a side-effect, clean up rq_refcount story materially
 - client-side recovery is now dispatched via a per-import handler function,
   for better layering and modularity
 - wire imports up to recovery before attempting mounts, for better handling of
   mount-time failures

21 years agoLanding of b_recovery (at last).
shaver [Thu, 28 Nov 2002 20:21:24 +0000 (20:21 +0000)]
Landing of b_recovery (at last).

Highlights:
  - b=324: MDS recovery must replay transactions in strict transno sequence
  - b=325: getattr after OST failure returns -EIO
  - b=326: unlink after OST failure returns -EIO
  - b=400: new client can't join cluster after OST failure
  - b=403: multi-client access failure when OST fails
  - b=410: After an OST failure, lfind incorrectly displays file information
  - b=417: Freeing unreplayable requests twice (aed's fix from b_md)
  - b=402: (partial) give error for lstripe request that exceeds configured OSTs
  - much better support for reconnecting to MDS after network partition
    (still some lock-repeating issues to be resolved for some requests)
  - better support for connecting to multiple MDSes on one host (xid and
    transno and request_list are all per-import now)
  - track disconnecting clients in last_rcvd, for more reliable recovery
  - also, sync last_rcvd after connect/disconnect
  - reduced syslog/CERROR output for recovery (hi, Terry!)
  - server (DLM) timeout is half the system-wide timeout, to avoid cascading
    failure in the face of a dead client
  - don't wait for recovery to finish in order to send disconnect messages
  - removal of c_dying_head
  - don't wait for timeout to trigger recovery after ptl_send_rpc error
  - strict MDS transno ordering via mds_transno_sem (non-optimal, but correct)
  - many !handle -> IS_ERR(handle) fixes around mds_fs_start callers.
  - turn on client-eviction for bulk-timeouts in OST and MDS

21 years agofile llmountcleanup2-hack.sh was initially added on branch b_md.
braam [Tue, 26 Nov 2002 20:59:42 +0000 (20:59 +0000)]
file llmountcleanup2-hack.sh was initially added on branch b_md.

21 years agofile llmount2-hack.sh was initially added on branch b_md.
braam [Tue, 26 Nov 2002 20:59:41 +0000 (20:59 +0000)]
file llmount2-hack.sh was initially added on branch b_md.

21 years agofile setuid.c was initially added on branch b_md.
braam [Mon, 25 Nov 2002 22:20:33 +0000 (22:20 +0000)]
file setuid.c was initially added on branch b_md.

21 years agoWhitespace.
adilger [Mon, 25 Nov 2002 20:26:02 +0000 (20:26 +0000)]
Whitespace.

21 years agoAdded sanity.sh & rundbench tests to Makefile.am EXTRA_DIST
amrutjoshi [Mon, 25 Nov 2002 15:08:38 +0000 (15:08 +0000)]
Added sanity.sh & rundbench tests to Makefile.am EXTRA_DIST

21 years agomerge b_md onto HEAD. as best as I can remember:
pschwan [Mon, 25 Nov 2002 09:17:17 +0000 (09:17 +0000)]
merge b_md onto HEAD.  as best as I can remember:
- fix dentry->d_it clobbering
- credentials weren't being shipped for readdir/getattr operations
- remove invalid assertions triggered during some concurrent MD updates
- many, many updates to llanalyse

21 years agoDon't dump bogus locks, we can deref null pointers therein.
adilger [Sun, 24 Nov 2002 19:45:00 +0000 (19:45 +0000)]
Don't dump bogus locks, we can deref null pointers therein.

21 years agoInclude the portal request/reply number so we know the source of the bad
adilger [Sun, 24 Nov 2002 18:26:58 +0000 (18:26 +0000)]
Include the portal request/reply number so we know the source of the bad
export data.

21 years agoupdate
adilger [Sat, 23 Nov 2002 02:24:12 +0000 (02:24 +0000)]
update

21 years agoFix the many client simultaneous startup bug (b=392).
adilger [Sat, 23 Nov 2002 02:23:10 +0000 (02:23 +0000)]
Fix the many client simultaneous startup bug (b=392).

We just ignore exports with NULL mcd, since they are just being set up.
The clients have a semaphore to prevent multiple setups there.  We could
alternately have a semaphore on the MDS instead of the current spinlock.

21 years agoPrint more information when we get a callback with a bogus export.
pschwan [Fri, 22 Nov 2002 12:37:06 +0000 (12:37 +0000)]
Print more information when we get a callback with a bogus export.
Also, try to see if we can proceed--maybe the rest of the packet is OK.

21 years agouse correct name for toenal_ni
rread [Fri, 22 Nov 2002 01:33:01 +0000 (01:33 +0000)]
use correct name for toenal_ni

21 years ago* add cleanup code for toenal
rread [Fri, 22 Nov 2002 00:36:06 +0000 (00:36 +0000)]
* add cleanup code for toenal

21 years agoChange over to new echo client like runregression-net.sh
adilger [Thu, 21 Nov 2002 18:05:17 +0000 (18:05 +0000)]
Change over to new echo client like runregression-net.sh

21 years agofile version_tag.pl was initially added on branch b_phil.
amrutjoshi [Thu, 21 Nov 2002 10:57:26 +0000 (10:57 +0000)]
file version_tag.pl was initially added on branch b_phil.

21 years agoRemove generated file.
adilger [Thu, 21 Nov 2002 08:06:48 +0000 (08:06 +0000)]
Remove generated file.

21 years agoRemove bogus LBUG and error return code. This was triggered by a non-root
adilger [Thu, 21 Nov 2002 07:18:56 +0000 (07:18 +0000)]
Remove bogus LBUG and error return code.  This was triggered by a non-root
user trying to create a file and getting -EACCES from lookup_one_len().

21 years agoteach runregression-net.sh about echo_client
rread [Thu, 21 Nov 2002 00:34:39 +0000 (00:34 +0000)]
teach runregression-net.sh about echo_client

21 years agoOmission in checkin.
adilger [Wed, 20 Nov 2002 23:27:23 +0000 (23:27 +0000)]
Omission in checkin.

21 years agoFix bad awk in mcr-routed-config.sh, which grabbed every OST UUID instead
adilger [Wed, 20 Nov 2002 22:57:51 +0000 (22:57 +0000)]
Fix bad awk in mcr-routed-config.sh, which grabbed every OST UUID instead
of just the one we wanted.

21 years agoRemove PORT specification, so we get the (correct) default if it changes
adilger [Wed, 20 Nov 2002 22:56:08 +0000 (22:56 +0000)]
Remove PORT specification, so we get the (correct) default if it changes
(and people haven't copied the fixed port number to dozens of configs
like I did.

21 years agoSadly, CVS doesn't handle adding/removing/moving files very well from
adilger [Wed, 20 Nov 2002 20:33:57 +0000 (20:33 +0000)]
Sadly, CVS doesn't handle adding/removing/moving files very well from
branch merges.

21 years agofile ha_assist2 was initially added on branch b_ravi_devel.
sravi [Tue, 19 Nov 2002 18:58:05 +0000 (18:58 +0000)]
file ha_assist2 was initially added on branch b_ravi_devel.

21 years agofile lutils.py was initially added on branch b_ravi_devel.
sravi [Tue, 19 Nov 2002 18:48:38 +0000 (18:48 +0000)]
file lutils.py was initially added on branch b_ravi_devel.

21 years agob=191
pschwan [Mon, 18 Nov 2002 05:28:30 +0000 (05:28 +0000)]
b=191
b=214
b=306
b=385
landing b_brw, which _includes_ all fixes from b_lov.

Roughly, this fixes bugs in 3 general areas:

- OSC was locking one byte too many; fixed.

- several LOV bug fixes, to support adding LOVs and striping over fewer
  than the maximum number

- the brw code was rewritten

See the bugs listed above for more details.  This will be immediately
tagged as 0.5.17.

21 years agofile echo_client.c was initially added on branch b_brw.
pschwan [Sun, 17 Nov 2002 04:50:12 +0000 (04:50 +0000)]
file echo_client.c was initially added on branch b_brw.

21 years agoDon't dereference last_xid and last_committed in a request we just freed.
adilger [Sat, 16 Nov 2002 08:27:40 +0000 (08:27 +0000)]
Don't dereference last_xid and last_committed in a request we just freed.

21 years agoRevert buffalization of acceptance-small.sh in HEAD, that lives in ltest.
adilger [Fri, 15 Nov 2002 20:48:54 +0000 (20:48 +0000)]
Revert buffalization of acceptance-small.sh in HEAD, that lives in ltest.

21 years agoModified to report to buffalo (Buffalized)
alokbhagwat [Fri, 15 Nov 2002 15:40:02 +0000 (15:40 +0000)]
Modified to report to buffalo (Buffalized)

21 years agoDecrement the LOV module use count on connect errors.
adilger [Thu, 14 Nov 2002 23:32:53 +0000 (23:32 +0000)]
Decrement the LOV module use count on connect errors.

21 years agoBug Fix for Bug #369
thantry [Thu, 14 Nov 2002 19:30:23 +0000 (19:30 +0000)]
Bug Fix for Bug #369

21 years agoUpdate acceptance-small.sh from b_lov branch. Allows fully specifying
adilger [Thu, 14 Nov 2002 06:34:46 +0000 (06:34 +0000)]
Update acceptance-small.sh from b_lov branch.  Allows fully specifying
LOV/non-lov configs and/or not running one of those configs, and which of
runtests, sanity, bonnie, dbench NOT to run (by default everything is run).

It could probably just be set up to take a list of configs as command-line
arguments to test instead.  We currently ignore the entire issue of mutli-
client setup.

21 years agorcsid/revision tags make phil weep tears of blood. also, they cause lots
pschwan [Thu, 14 Nov 2002 00:22:15 +0000 (00:22 +0000)]
rcsid/revision tags make phil weep tears of blood.  also, they cause lots
of conflicts.

21 years agoAllow the iozone record size to be specified.
adilger [Wed, 13 Nov 2002 22:27:36 +0000 (22:27 +0000)]
Allow the iozone record size to be specified.

21 years agoAdd bonnie to the mix, and allow not running parts of the test (this should
adilger [Wed, 13 Nov 2002 22:12:43 +0000 (22:12 +0000)]
Add bonnie to the mix, and allow not running parts of the test (this should
automatically detect whether bonnie and dbench are installed and complain
verbosely if not.

21 years agoAdd a start on the bare-bones acceptance test for CVS HEAD merges, which
adilger [Wed, 13 Nov 2002 21:54:48 +0000 (21:54 +0000)]
Add a start on the bare-bones acceptance test for CVS HEAD merges, which
I'm now running against the HEAD to see that it actually passes.

21 years ago- Updated changelog
pschwan [Wed, 13 Nov 2002 19:31:42 +0000 (19:31 +0000)]
- Updated changelog
- Better errors when the LDLM service can't be started
- Remove unnecessary flag from OSC lock cancellation in clear_inode
- If lov_enqueue fails to allocate a lock, zero the handle, so that we don't
  try to decref a bad handle (and LBUG) later

21 years agoComment out variable only used in commented-out code.
adilger [Wed, 13 Nov 2002 19:26:27 +0000 (19:26 +0000)]
Comment out variable only used in commented-out code.
Whitespace.

21 years agoAdd some extra comments and sample configs.
adilger [Wed, 13 Nov 2002 18:13:00 +0000 (18:13 +0000)]
Add some extra comments and sample configs.

21 years agoChange configs to use port 988 instead of 2432.
adilger [Wed, 13 Nov 2002 18:10:44 +0000 (18:10 +0000)]
Change configs to use port 988 instead of 2432.

21 years ago Bug #357, no more gratituous new line..., or typecasting
thantry [Wed, 13 Nov 2002 04:45:22 +0000 (04:45 +0000)]
 Bug #357, no more gratituous new line..., or typecasting

21 years agoName changes to make all file system statistics names common
thantry [Wed, 13 Nov 2002 04:05:47 +0000 (04:05 +0000)]
Name changes to make all file system statistics names common
across the /proc/lustre hierarchy. See comment in Bug #320

21 years agoBug #364: Approver - Robert Reed: Update lustre init script to use lconf.
donmilos [Wed, 13 Nov 2002 03:39:48 +0000 (03:39 +0000)]
Bug #364: Approver - Robert Reed: Update lustre init script to use lconf.

21 years ago1. Bug fix for Bug #320, also needs repair of lconf, since it tries
thantry [Wed, 13 Nov 2002 02:46:41 +0000 (02:46 +0000)]
1. Bug fix for Bug #320, also needs repair of lconf, since it tries
   to insert two devices with the same ID in a router configuration.
2. Added LDLM counters into /proc/lustre hierarchy
3. Fixes for Andreas's comments in Bug #357.
4. Bug #332 fixed, num_devices replaced with num_refs
5. Removed file proc_lustre.c, which was dead code.

21 years agofile lstripe.c was initially added on branch b_lov.
adilger [Tue, 12 Nov 2002 18:50:41 +0000 (18:50 +0000)]
file lstripe.c was initially added on branch b_lov.

21 years agofile lov_pack.c was initially added on branch b_lov.
adilger [Tue, 12 Nov 2002 18:50:27 +0000 (18:50 +0000)]
file lov_pack.c was initially added on branch b_lov.

21 years agoThis file is not being used. Hence, removed.
thantry [Tue, 12 Nov 2002 18:23:57 +0000 (18:23 +0000)]
This file is not being used. Hence, removed.

21 years agoThis file is not being used at all. It is not on the compile path either
thantry [Tue, 12 Nov 2002 18:23:11 +0000 (18:23 +0000)]
This file is not being used at all. It is not on the compile path either
Hence, removed.

21 years agoback out vmalloc changes; there's not enough vmalloc space on MCR for the
pschwan [Tue, 12 Nov 2002 02:13:34 +0000 (02:13 +0000)]
back out vmalloc changes; there's not enough vmalloc space on MCR for the
buffers that we require at startup, if you can believe that

21 years ago- apply andreas's patch to remove u16
pschwan [Tue, 12 Nov 2002 00:13:38 +0000 (00:13 +0000)]
- apply andreas's patch to remove u16
- fix subtle rename() dentry bug

21 years agoComment.
adilger [Tue, 12 Nov 2002 00:05:15 +0000 (00:05 +0000)]
Comment.

21 years agoWrap long lines.
adilger [Tue, 12 Nov 2002 00:04:37 +0000 (00:04 +0000)]
Wrap long lines.

21 years ago2.5 fixes copied from MDS 2.5 code.
adilger [Tue, 12 Nov 2002 00:01:59 +0000 (00:01 +0000)]
2.5 fixes copied from MDS 2.5 code.

21 years agoRemove lprocfs wierdness.
adilger [Tue, 12 Nov 2002 00:01:11 +0000 (00:01 +0000)]
Remove lprocfs wierdness.

21 years agoCommon kernel bug (lots of it in InterMezzo too, AFAIK) - copy_to_user()
adilger [Mon, 11 Nov 2002 23:59:48 +0000 (23:59 +0000)]
Common kernel bug (lots of it in InterMezzo too, AFAIK) - copy_to_user()
returns number of bytes uncopied and not an error code.

21 years agoFixes to the lock LRU
pschwan [Mon, 11 Nov 2002 19:00:40 +0000 (19:00 +0000)]
Fixes to the lock LRU

21 years agoUpdate the file size _before_ taking the read lock, or you will deadlock in
pschwan [Mon, 11 Nov 2002 18:58:58 +0000 (18:58 +0000)]
Update the file size _before_ taking the read lock, or you will deadlock in
some contrived cases.

21 years ago- llanalyze first bugfixes -- use hex when needed!
braam [Sun, 10 Nov 2002 22:10:25 +0000 (22:10 +0000)]
- llanalyze  first bugfixes -- use hex when needed!

21 years ago- nodlm option to llanalyze
braam [Sun, 10 Nov 2002 21:51:19 +0000 (21:51 +0000)]
- nodlm option to llanalyze

21 years ago- a log analyzer to help us work with the Lustre logs even more easily
braam [Sun, 10 Nov 2002 21:47:38 +0000 (21:47 +0000)]
- a log analyzer to help us work with the Lustre logs even more easily
  So far:
   - indentation with spaces for call stack depth
   - select pid
   - --trace (only the call trace)
   - --nonet (leave out networking message)
Written in Perl, very easy to add more features.

21 years agoThe test for a freeing inode was reversed, oops. We want to skip inodes
adilger [Sun, 10 Nov 2002 21:02:35 +0000 (21:02 +0000)]
The test for a freeing inode was reversed, oops.  We want to skip inodes
that are marked I_FREEING.

21 years ago- change the OST / MDT thread names to also include the host pid
braam [Sun, 10 Nov 2002 08:34:42 +0000 (08:34 +0000)]
- change the OST / MDT thread names to also include the host pid
  in case of UML to aid debugging.

21 years agouse vmalloc for OBD_ALLOCs above 16k, like we do in Portals
pschwan [Sat, 9 Nov 2002 20:39:12 +0000 (20:39 +0000)]
use vmalloc for OBD_ALLOCs above 16k, like we do in Portals

21 years agothe first try at lock LRU
pschwan [Sat, 9 Nov 2002 19:40:59 +0000 (19:40 +0000)]
the first try at lock LRU

21 years agoBuild an XML config for connecting to a BA OST for echo testing.
adilger [Fri, 8 Nov 2002 22:10:27 +0000 (22:10 +0000)]
Build an XML config for connecting to a BA OST for echo testing.

21 years agoMinor code cleanups - mostly whitespace.
adilger [Fri, 8 Nov 2002 20:59:56 +0000 (20:59 +0000)]
Minor code cleanups - mostly whitespace.

21 years agoFix minor compiler warning.
adilger [Fri, 8 Nov 2002 20:58:45 +0000 (20:58 +0000)]
Fix minor compiler warning.

21 years agoAdd assertion to LL_GET_INTENT(), because we aren't very non-intent friendly
adilger [Fri, 8 Nov 2002 20:02:18 +0000 (20:02 +0000)]
Add assertion to LL_GET_INTENT(), because we aren't very non-intent friendly
right now.

21 years agoupdate file size in ll_file_read, lest the VFS decide not to call us
pschwan [Fri, 8 Nov 2002 19:33:59 +0000 (19:33 +0000)]
update file size in ll_file_read, lest the VFS decide not to call us

21 years agoFix for many-clients-and-server-on-same-node deadlock. One server task
adilger [Fri, 8 Nov 2002 19:02:41 +0000 (19:02 +0000)]
Fix for many-clients-and-server-on-same-node deadlock.  One server task
can go "in the hole" for at most one maximum-sized request, to avoid
deadlocking when the clients have consumed all of the kmapping reservations.

The server can then complete the request and both the server and client will
release their reservations, allowing further progress to be made.

21 years agoSome additional changes for kmem accounting that I missed.
adilger [Fri, 8 Nov 2002 18:29:13 +0000 (18:29 +0000)]
Some additional changes for kmem accounting that I missed.

21 years agoHighmem deadlock avoidance (server version):
adilger [Fri, 8 Nov 2002 18:25:53 +0000 (18:25 +0000)]
Highmem deadlock avoidance (server version):
- reserve highmem pages before we start doing kmaps to avoid deadlocks
  with multiple threads reserving vectors of pages

21 years agoDramatically increase the randomness of MDC UUIDs
pschwan [Fri, 8 Nov 2002 02:10:58 +0000 (02:10 +0000)]
Dramatically increase the randomness of MDC UUIDs

21 years ago- add something that prints the time every 10,000 creates
braam [Fri, 8 Nov 2002 00:11:51 +0000 (00:11 +0000)]
- add something that prints the time every 10,000 creates

21 years agoUse the fs-method statfs, so we can take into account the EA space needs
adilger [Thu, 7 Nov 2002 23:54:17 +0000 (23:54 +0000)]
Use the fs-method statfs, so we can take into account the EA space needs
for extN (1 block for each inode, excluding special files).