Whamcloud - gitweb
pschwan [Fri, 4 Apr 2003 04:36:58 +0000 (04:36 +0000)]
- squelch apparently-harmless "STRANGE intent release" message
- Zach's recent commit started using GPLONLY symbols, which my UML
can't resolve without a dorky preprocessor hack. Oh well.
- Print the remote NID in timeout and "cancel out of sync" messages,
so they're useful
pschwan [Wed, 2 Apr 2003 03:56:06 +0000 (03:56 +0000)]
b=957
- Infrastructure for the pinger thread; needs multi-rpc and some refinements
- Add last_request_time to obd_export
- Fixed export leak in lov_brw success case
- test22 rears its head again: tar gets pissy if it can't access $PWD,
which is common for homedirs at LLNL. cd to /tmp before running tar.
Merged many of the changes from b_proto:
- multi-rpc infrastructure, but not the key bits
- removed some bitfield flags in favour of individual struct members
- merged obd_brw_write and obd_brw_read into a single obd_brw_internal
- move the Elan-related page wrangling from the IOD into the OSC
zab [Wed, 2 Apr 2003 00:03:16 +0000 (00:03 +0000)]
fix up file size and cache mechanisms to account for the disconnect between
acquiring a file region extent and getting 0..N callbacks for obd locks that
the acquiry generated.
- truncate_inode_pages(,0) could race with dirtying and lose data. when a lock
is canceled we now purge/invalidate the (striped) pages that were covered by
the (lov->obd) lock
- remove the getattr flag business and instead do getattrs around every lock
acquiry. this brings us closer to how things will behave when we return
file size with locks, but it will slow things down until then.
- maintain an rbtree of extents which record the page offsets that are dirty
in the page cache. for now it helps us decide if we should trust getattr.
in the future it will help purging and the write space reservation.
- always round extents to page size in osc_enqueue
- while I'm in here, get rid of the ISBLK stuff in _file_write and let
generic_file_write set ppos to i_size under the i_sem
this has passed tests under a large lov with /tmp backing, but do keep an eye
out for data/size inconsistency problems.
pschwan [Mon, 24 Mar 2003 17:41:09 +0000 (17:41 +0000)]
Add Zach's patch to export truncate_complete_page(); still needs an
hp-pnnl and vanilla equivalent
pengzhao [Tue, 18 Mar 2003 05:22:39 +0000 (05:22 +0000)]
adding error handling in runas.c in case the malloc() fails
cvs2svn [Mon, 17 Mar 2003 20:48:25 +0000 (20:48 +0000)]
This commit was manufactured by cvs2svn to create branch 'unlabeled-1.2.2'.
adilger [Mon, 17 Mar 2003 20:48:24 +0000 (20:48 +0000)]
Seems I missed the cutoff for the old b_devel branch, and this was lost.
adilger [Mon, 17 Mar 2003 20:23:42 +0000 (20:23 +0000)]
Quiet a couple of ia64 compile warnings.
amrutjoshi [Sat, 15 Mar 2003 16:20:05 +0000 (16:20 +0000)]
file vanilla-2.5.63 was initially added on branch b_devel.
amrutjoshi [Sat, 15 Mar 2003 16:20:04 +0000 (16:20 +0000)]
file lustre-2.5.63.pc was initially added on branch b_devel.
amrutjoshi [Sat, 15 Mar 2003 16:20:03 +0000 (16:20 +0000)]
file lustre-2.5.63.patch was initially added on branch b_devel.
amrutjoshi [Sat, 15 Mar 2003 16:20:02 +0000 (16:20 +0000)]
file extN.patch-2.5.63 was initially added on branch b_devel.
thantry [Sat, 15 Mar 2003 02:36:04 +0000 (02:36 +0000)]
file mkdirdeep.c was initially added on branch b_devel.
thantry [Sat, 15 Mar 2003 02:35:56 +0000 (02:35 +0000)]
Bugzilla 895
adilger [Sat, 15 Mar 2003 01:32:48 +0000 (01:32 +0000)]
file extN-delete_thread.diff was initially added on branch b_devel.
adilger [Sat, 15 Mar 2003 01:32:47 +0000 (01:32 +0000)]
file ext3-orphan_lock.diff was initially added on branch b_devel.
adilger [Fri, 14 Mar 2003 21:12:05 +0000 (21:12 +0000)]
file ext3-truncate_blocks.diff was initially added on branch b_devel.
zab [Thu, 13 Mar 2003 22:20:12 +0000 (22:20 +0000)]
- remove the lli_open_count that was accidentally re-introduced with b_io
- silence an unused variable warning in runas
pengzhao [Thu, 13 Mar 2003 04:56:19 +0000 (04:56 +0000)]
runas.c is modified to use execvp() instead of system(), suggested by Zach
adilger [Wed, 12 Mar 2003 00:58:10 +0000 (00:58 +0000)]
file checkstack.pl was initially added on branch b_devel.
cvs2svn [Tue, 11 Mar 2003 23:37:57 +0000 (23:37 +0000)]
This commit was manufactured by cvs2svn to create branch 'unlabeled-1.2.2'.
pschwan [Tue, 11 Mar 2003 23:37:27 +0000 (23:37 +0000)]
merge b_devel into HEAD. Includes:
- client-side I/O cache
- O_DIRECT fixes for IA64
- liblustre improvements
- various small bug fixes
adilger [Tue, 11 Mar 2003 21:07:11 +0000 (21:07 +0000)]
Remove obsolete rh-8.0 series file.
pengzhao [Tue, 11 Mar 2003 07:17:05 +0000 (07:17 +0000)]
file runas.c was initially added on branch branch_bug828.
pengzhao [Tue, 11 Mar 2003 07:17:03 +0000 (07:17 +0000)]
Bug 828 is fixed by Peng Zhao, arrpoved by Andreas.
runas.c allows the root to "runas" another user to do things.
adilger [Sat, 8 Mar 2003 15:59:27 +0000 (15:59 +0000)]
file ext3-2.5-noread.diff was initially added on branch b_devel.
shaver [Fri, 7 Mar 2003 20:16:03 +0000 (20:16 +0000)]
file ptlrpc_module.c was initially added on branch b_recovery.
shaver [Fri, 7 Mar 2003 20:16:02 +0000 (20:16 +0000)]
file ptlrpc_internal.h was initially added on branch b_recovery.
amrutjoshi [Wed, 5 Mar 2003 06:47:27 +0000 (06:47 +0000)]
Commenting out liblustre from make targets until Makefile.am in liblustre is fixed
adilger [Tue, 4 Mar 2003 17:30:44 +0000 (17:30 +0000)]
Remove extraneous whitespace.
rread [Tue, 4 Mar 2003 00:38:12 +0000 (00:38 +0000)]
b=941: zab's fix for ia64 compiles. untested, but it does compile
rread [Tue, 4 Mar 2003 00:38:08 +0000 (00:38 +0000)]
file iod-stock-24-exports_hp.patch was initially added on branch b_devel.
pschwan [Sun, 2 Mar 2003 05:58:14 +0000 (05:58 +0000)]
land b_io on b_devel (b_io will be deleted as soon as it's confirmed
that the merge happend without incident)
pschwan [Sun, 2 Mar 2003 05:23:24 +0000 (05:23 +0000)]
land 0.5.20.3 b_devel onto HEAD (b_devel will remain)
behlendo [Fri, 28 Feb 2003 03:31:35 +0000 (03:31 +0000)]
- Flush every line so it works better with pdsh
adilger [Thu, 27 Feb 2003 23:44:48 +0000 (23:44 +0000)]
file ext3-largefile.diff was initially added on branch b_devel.
adilger [Thu, 27 Feb 2003 08:04:45 +0000 (08:04 +0000)]
Update HP VFS patch for v13.
pschwan [Wed, 26 Feb 2003 23:10:14 +0000 (23:10 +0000)]
b=912
- Lustre patch version 13:
- merge the iod-rmap-exports patch from b_io
- add and export __d_rehash, which optionally avoids taking dcache_lock
- fix bug 912 race by calling d_rehash without dropping the dcache_lock
- Fix earlier botched patch for 913
shaver [Tue, 25 Feb 2003 16:40:47 +0000 (16:40 +0000)]
file recovery-cleanup.sh was initially added on branch b_devel.
adilger [Tue, 25 Feb 2003 01:02:17 +0000 (01:02 +0000)]
Changed to use absolte paths instead of relative paths for symbols in case
that made a difference (it didn't).
shaver [Mon, 24 Feb 2003 21:48:17 +0000 (21:48 +0000)]
file mlink.c was initially added on branch b_devel.
shaver [Mon, 24 Feb 2003 21:45:58 +0000 (21:45 +0000)]
Dropped-request and -reply tests for link and unlink.
shaver [Mon, 24 Feb 2003 19:37:04 +0000 (19:37 +0000)]
Dropped-request and dropped-reply tests for rename.
shaver [Mon, 24 Feb 2003 19:35:18 +0000 (19:35 +0000)]
- Quell (spurious, but I don't blame gcc for getting it wrong) "uninitialized
use of dchild" warning.
- Reconstruct rename replies (easy, until I go back and make them all work in
the failed-over case).
shaver [Mon, 24 Feb 2003 17:05:30 +0000 (17:05 +0000)]
- macroize and share check-for-resent-req code.
- defensive assertion in mds_close_mfd to help catch dentry mismanagement
- transnos for getattr_name and open, always.
- don't free the repmsg too early when we're dropping replies for testing
- ldlm_intent_policy knows how to fix up lock handles for reconstructed requests,
and not give the lock away to the client twice
- tchmod exits with errno on failure.
adilger [Sat, 22 Feb 2003 22:23:44 +0000 (22:23 +0000)]
Update lcrash map-making script.
braam [Sat, 22 Feb 2003 03:15:55 +0000 (03:15 +0000)]
file .cvsignore was initially added on branch b_devel.
adilger [Fri, 21 Feb 2003 11:44:54 +0000 (11:44 +0000)]
file compile.sh was initially added on branch b_devel.
braam [Fri, 21 Feb 2003 11:05:36 +0000 (11:05 +0000)]
file Makefile.am was initially added on branch b_devel.
braam [Fri, 21 Feb 2003 11:05:35 +0000 (11:05 +0000)]
file libtest.c was initially added on branch b_devel.
pschwan [Thu, 20 Feb 2003 22:16:51 +0000 (22:16 +0000)]
fix uninitialized variable warning
pschwan [Thu, 20 Feb 2003 22:07:11 +0000 (22:07 +0000)]
b=892
osc_close used to walk through the request list, trying to find the
corresponding osc_open. This is slow, racy and doomed to failure, so we
need to instead save a point to the request in osc_open.
Instead of passing a handle up to whoever called us, pass 32 bytes of
opaque data. These get passed back to us at various points, through
the obdo's inline field.
amrutjoshi [Thu, 20 Feb 2003 11:51:12 +0000 (11:51 +0000)]
Fixed to make version_tag.pl work outside srcdir.
shaver [Thu, 20 Feb 2003 09:02:07 +0000 (09:02 +0000)]
You might not believe it, but the open-reply tests pass now.
shaver [Thu, 20 Feb 2003 08:59:38 +0000 (08:59 +0000)]
Reconstruct replies for open. Lightly tested (successful open case).
shaver [Thu, 20 Feb 2003 07:36:15 +0000 (07:36 +0000)]
- Store open-request XID in the MFD, so that we can find it during reply
reconstruction.
- Untested reply reconstruction for GETATTR_NAME (easy) and OPEN (not easy,
ahem).
- Don't leak dentry refs when reconstructing replies for reint_setattr or
reint_create.
- Don't double-dput dchild if dentry_open fails. (Not yet in test suite, bug
894 filed to trick someone into adding it.)
pschwan [Thu, 20 Feb 2003 07:09:40 +0000 (07:09 +0000)]
don't LBUG if we can't lookup the parent in mds_open and mds_reint_create; it's
entirely possible that we're racing with rmdir()
rread [Thu, 20 Feb 2003 06:52:52 +0000 (06:52 +0000)]
file lustre_peer.c was initially added on branch b_malt.
shaver [Wed, 19 Feb 2003 22:01:20 +0000 (22:01 +0000)]
file statone.c was initially added on branch b_devel.
shaver [Wed, 19 Feb 2003 20:28:42 +0000 (20:28 +0000)]
Add tests for reply reconstruction and request retransmission for
reint_setattr.
thantry [Wed, 19 Feb 2003 19:53:19 +0000 (19:53 +0000)]
file test.txt was initially added on branch b_intel.
braam [Wed, 19 Feb 2003 04:30:16 +0000 (04:30 +0000)]
file lustre_peer.c was initially added on branch b_devel.
braam [Wed, 19 Feb 2003 04:30:15 +0000 (04:30 +0000)]
file lustre_handles.c was initially added on branch b_devel.
braam [Wed, 19 Feb 2003 04:29:17 +0000 (04:29 +0000)]
file lustre_handles.h was initially added on branch b_devel.
adilger [Tue, 18 Feb 2003 23:06:05 +0000 (23:06 +0000)]
Minor fixup.
adilger [Tue, 18 Feb 2003 23:02:40 +0000 (23:02 +0000)]
Update HP PNNL kernel patch for new VFS changes.
Remove patch hunks which are calling user_path_walk_it(..., NULL)
pschwan [Tue, 18 Feb 2003 19:39:44 +0000 (19:39 +0000)]
merge b_setattr into b_devel. The highlights:
- proper LDLM_DEBUG macro fix, for gcc 3.2 (850)
- failed open()s could cause deadlock; fixed (867, 869)
- stop cancelling OST locks when files are closed (481)
- overlapping XID spaces caused network corruption (851, 853)
- fix unsafe fsfilt counter arithmetic; change to atomic_t
- setattr_raw added, to do single-RPC, server-side setattrs
- fix crashy race condition between ptlrpc_free_req and osc_close
pschwan [Tue, 18 Feb 2003 05:45:08 +0000 (05:45 +0000)]
file acceptance-metadata-double.sh was initially added on branch b_setattr.
pschwan [Mon, 17 Feb 2003 18:44:21 +0000 (18:44 +0000)]
merge b_devel into b_setattr. highlights:
- kernel 2.5 and liblustre build changes
- fixes to Makefile.am for 7.3-era versions of automake, which is quite possibly
the worst piece of software with which I come in contact on a daily basis
- small unlink fix
shorthair [Mon, 17 Feb 2003 16:20:58 +0000 (16:20 +0000)]
temporarily modification for compilation on uml2.5.59
(some struct has changed in 2.5, such as timespec, kdev_t)
braam [Mon, 17 Feb 2003 10:24:15 +0000 (10:24 +0000)]
- the bulk of the build fixes for liblustre. Note
that all user level programs now need to include
<liblustre.h> (as is done in the utils and test
directories.
braam [Mon, 17 Feb 2003 10:23:22 +0000 (10:23 +0000)]
file liblustre.h was initially added on branch b_devel.
shaver [Fri, 14 Feb 2003 20:50:06 +0000 (20:50 +0000)]
Don't be outsmarted by the dcache, mkay?
amrutjoshi [Fri, 14 Feb 2003 18:45:32 +0000 (18:45 +0000)]
Added support to specify the lustre obj dir.
shaver [Thu, 13 Feb 2003 07:25:49 +0000 (07:25 +0000)]
New transno regimen:
- no more transno semaphore: the LDLM is the one true source of concurrency
control
- allocate transnos and log requests for failed requests too
- record request status and open-disposition in last_rcvd as well
- mds_finish_transno commits the handle, if there is one (and creates its own
for the last_rcvd update, if needed).
Much nicer (IMO) error-handling in mds_reint.c and such. At the least, 85%
fewer gotos.
Rename "last_rcvd" to "(last_)transno" in various places, because it's clearer
that way (again, IMO).
Warning (type mismatch) fixes in osc_request that were bugging me.
adilger [Thu, 13 Feb 2003 02:40:00 +0000 (02:40 +0000)]
Fixups to HP patch.
pschwan [Wed, 12 Feb 2003 18:00:59 +0000 (18:00 +0000)]
backport Andreas's IT_READLINK fix
pschwan [Wed, 12 Feb 2003 17:15:12 +0000 (17:15 +0000)]
Oversight in mds_open, forgot to save locks for reply-ack; fixed.
adilger [Wed, 12 Feb 2003 16:52:26 +0000 (16:52 +0000)]
Remove use of old config stuff from acceptance-metadata-single.sh.
Don't use hard-coded paths.
amrutjoshi [Wed, 12 Feb 2003 12:24:26 +0000 (12:24 +0000)]
Added mkdirmany to lustre-lite rpm.
amrutjoshi [Wed, 12 Feb 2003 10:38:03 +0000 (10:38 +0000)]
Made changes so that tinderbox runtest doesnt fail
adilger [Wed, 12 Feb 2003 03:25:26 +0000 (03:25 +0000)]
Remove unused IT_RENAME intent.
Revert revalidate2 reversion.
Update vfs_intent_hp.patch to include new exec changes.
pschwan [Tue, 11 Feb 2003 23:51:23 +0000 (23:51 +0000)]
changelog update
pschwan [Tue, 11 Feb 2003 23:45:51 +0000 (23:45 +0000)]
b=850
Call LDLM_DEBUG0 instead of LDLM_DEBUG when there are no arguments.
This is a temporary workaround for gcc 3.2 that I really hate.
adilger [Tue, 11 Feb 2003 23:43:25 +0000 (23:43 +0000)]
file ext3-2.4-ino_t.diff was initially added on branch b_devel.
adilger [Tue, 11 Feb 2003 22:25:06 +0000 (22:25 +0000)]
Merge BA OST fixes from b_devel.
pschwan [Tue, 11 Feb 2003 20:47:08 +0000 (20:47 +0000)]
I don't want to release an already-outdated v10 kernel just for 0.5.20, so
make 0.5.20 compatible with v11
braam [Sun, 9 Feb 2003 09:10:58 +0000 (09:10 +0000)]
file vanilla-2.5 was initially added on branch b_devel.
braam [Sun, 9 Feb 2003 09:10:56 +0000 (09:10 +0000)]
file lustre-2.5.pc was initially added on branch b_devel.
cvs2svn [Fri, 7 Feb 2003 18:02:18 +0000 (18:02 +0000)]
This commit was manufactured by cvs2svn to create branch 'unlabeled-1.2.2'.
pschwan [Fri, 7 Feb 2003 18:01:04 +0000 (18:01 +0000)]
Merge b_md into HEAD
* bug fixes
- Fix ldlm_lock_match on the MDS to avoid matching remote locks (592)
- Fix fsfilt_extN_readpage() to read a full page of directory
entries, or fake the remainder if PAGE_SIZE != blocksize (500)
- Avoid extra mdc_getattr() in ll_intent_lock when possible (534, 604)
- Fix imbalanced LOV object allocation and out-of-bound access (469)
- Most intent operations were removed, in favour of a new RPC mode
that does a single RPC to the server and bypasses most of the VFS
- All LDLM resource ID arrays were removed in favour of ldlm_res_id
- Aggressively cancel local locks on DLM servers
- mds_reint_unlink sends EA to the client if it's the last nlink.
client uses that EA to unlink OST objects.
- mds_reint_{rename,unlink,link} were rewritten to take ordered locks
- recursive symlinks were fixed (440)
- fixed NULL deref in DEBUG_REQ
- filter_update_lastobjid no longer calls sync, which annoyed extN
- fixed multi-client small-writes to a single file problem (445)
- fixed mtime updates during file writes (607)
- fixed vector writes on obdfilter causing problems when ENOSPC (670)
- fixed bug in obd_brw_read/write() (under guise of testing 367)
- fixed Linux OST size reporting problem (444, 656)
- OST now updates object mtime with writes or setattr (607, 619)
- client verifies file size before zeroing page past EOF (445)
- OST now writes last allocated objid to disk with allocation (108)
- LOV on echo now works (409)
* protocol changes
- mds_reint_unlink sends a new buffer, with the EA included. this
buffer is only valid if body->valid & OBD_MD_FLEASIZE, which is only
set if a regular file was being unlinked, and it was the last link
- use PtlGet from the target for bulk writes (315)
- OST now updates object mtime with writes or setattr (607, 619)
- LDLM now has a grant-time callback to revalidate locked items, if
necessary (604)
- Many MDS operations were reorganized to combat race conditions
* other changes
- Merge b_intel branch (updated lprocfs code) - now at /proc/fs/lustre
- configure check to avoid gcc version 2.96
20000731-2.96-98 (606)
pschwan [Fri, 7 Feb 2003 17:06:27 +0000 (17:06 +0000)]
I think Peter forgot to commit the version change
eeb [Fri, 7 Feb 2003 15:59:13 +0000 (15:59 +0000)]
file obdiolib.h was initially added on branch b_md.
eeb [Fri, 7 Feb 2003 15:59:12 +0000 (15:59 +0000)]
file obdiolib.c was initially added on branch b_md.
eeb [Fri, 7 Feb 2003 15:59:11 +0000 (15:59 +0000)]
file obdbarrier.c was initially added on branch b_md.
zab [Thu, 6 Feb 2003 02:14:59 +0000 (02:14 +0000)]
- braindead first pass at a ptlbd backing store, it'll do for now
zab [Thu, 6 Feb 2003 00:26:29 +0000 (00:26 +0000)]
- move to single ptlrpc code paths on the ptlbd client and server which know
to switch between _put and _get for read and write. in the process, clean
up the ridiculous callback/refcounting mess that was the first attempt.
- also, pass through to blk_ioctl() when people ask us to flush.
adilger [Wed, 5 Feb 2003 21:45:40 +0000 (21:45 +0000)]
file createtest.c was initially added on branch b_md.
adilger [Mon, 3 Feb 2003 18:31:08 +0000 (18:31 +0000)]
file exports_hp.txt was initially added on branch b_md.
adilger [Mon, 3 Feb 2003 18:31:06 +0000 (18:31 +0000)]
file exports_hp.pc was initially added on branch b_md.