Whamcloud - gitweb
shaver [Tue, 2 Dec 2003 19:59:51 +0000 (19:59 +0000)]
Allow override of automake name for testing with other versions.
phil [Fri, 28 Nov 2003 06:54:22 +0000 (06:54 +0000)]
b=2254
At truncate time, ext3 is zeroing indirect blocks and writing a
transaction to the journal. At some point, perhaps when that
transaction commits, it gives the dirty buffer for that indirect block
to the buffer cache to write to disk. Meanwhile, having marked that
block as unused, it reallocates it to us as a normal data block into
which IOR puts some data.
The obdfilter writes that block with brw_kiovec, which writes
immediately to the disk with no regard for what data might be in the
buffer cache. Shortly thereafter, the buffer cache writes the block
of zeroes over top our valuable data.
The correct fix is to modify our special ext3 block allocation code to
look in the buffer cache for us, and discard any pending writes to the
newly-allocated blocks, much like the direct I/O code does. As a
workaround, for kernels which do not yet have this change, I added
some code to the obdfilter to do this after the call to
ext3_map_inode_page returns.
This introduces kernel version 32, but doesn't force an upgrade. I
updated the kernel patches for 2.4.18 and 2.4.20, but not 2.6. I also:
- tested the ext3_map_inode_page change on vanilla-2.4.20
- tested the workaround change on chaos-2.4.18
- compile-tested a version 32 chaos-2.4.18 kernel
adilger [Sat, 22 Nov 2003 19:31:12 +0000 (19:31 +0000)]
Add fsfilt_map_inode_page() instead of calling ext3_map_inode_page()
directly from filter_direct_io(). Update fsfilt_extN.c.
adilger [Mon, 17 Nov 2003 19:26:26 +0000 (19:26 +0000)]
Allow current b_devel to work with older (read LLNL) kernels until they are
updated. Bumped LUSTRE_KERNEL_VERSION to 31 so we know which kernels have
the required patches, but don't make it a hard requirement.
b=1933
phil [Fri, 14 Nov 2003 09:24:20 +0000 (09:24 +0000)]
I touched one thing in lustre_mds.h, and I was dismayed to see the
entire source tree rebuild!
It took just a few minutes to remove a number of #includes which
violated all manner of abstraction boundary. ericm assures me that I
have not broken anything major in liblustre.
Also, I moved a good chunk of inline functions into llite_internal.h
(which is where I secretly believe that most of lustre_lite.h will end up),
and renamed ll_ino2fid (which no longer takes an inode) to mdc_pack_fid.
zab [Thu, 13 Nov 2003 20:21:21 +0000 (20:21 +0000)]
Silence most of the warnings in the x86_64 build, and kill some Real Bugs in
the process. (sanity checked in an x86 uml build, as well)
- include linux/init.h from some modules that use __init and company
- x86_64 has 64 bit longs but uses 'long long' for u64 in the kernel. we
add its own specific section to LP*64 definitions. Sadly, there are still
a huge number of warnings from this gcc when we try to LP*64 print uint64_t
obdo arguments.
- use min_t in some defines to avoid the duplicate const prefacing that comes
with nesting min()
- LPX64 printing -1UL doesn't work so well
- i_nlink can be any of unsigned short, int, or long. when printing cast
to unsigned long.
- kern_addr_valid takes a 'unsigned long' argument and shifts it.. sigh.
- don't #define EXPORT_SYMTAB in the source, that's the job of the kernel
makefiles
- x86_64/suse has THREAD_SIZE defined in userspace
- s/long flags/unsigned long flags/. Again.
- va_list ap = NULL; is not legal, as far as I know. it doesn't seem
to actually do anything in this code path either.
- x86_64 passes CONFIG_X86 but had thread->rsp as the stack pointer. this
code is going away eventually anyway.
- print a pointer with %p, not %x
- some portals callback pointer definitions used size_t while some nal's
functions used ptl_size_t in the function defintions. I switched the
functions over to avoid pushing changes on all the nals.
phil [Mon, 10 Nov 2003 20:47:31 +0000 (20:47 +0000)]
rename fsfilt_set_last_rcvd to fsfilt_add_journal_cb, because that's
what it does
adilger [Fri, 7 Nov 2003 17:25:57 +0000 (17:25 +0000)]
Bump kernel version to 30 because of portals_debug_dumpstack() kernel patch.
Put workaround in place until l30 kernels are available so we can work.
alex [Wed, 29 Oct 2003 22:38:27 +0000 (22:38 +0000)]
- async commit/wait API have been changed a bit. it used oti_handler, but
it must not
alex [Tue, 28 Oct 2003 13:19:11 +0000 (13:19 +0000)]
- b2188: filter fixes: sync transaction, commit earlier
alex [Thu, 23 Oct 2003 21:42:33 +0000 (21:42 +0000)]
- trusted EAs support in ext3
- MAX_VERSION increase
phil [Sat, 11 Oct 2003 22:28:00 +0000 (22:28 +0000)]
b=99
Andreas's sync patch, with an (almost) related journal cleanup to remove
fsfilt_journal_data; we no longer use this barely-maintained eature,
and our special files don't see normal write()s anyways
rread [Wed, 8 Oct 2003 07:06:20 +0000 (07:06 +0000)]
landing b_lcfg to b_devel
- llog network api for processing the log from the client
- config messages changed to use struct lustre_cfg and struct
portals_cfg
- lctl record options save config messages to log on the mds
- ll_fill_super supports fetching the log and replaying to setup
the devices needed for mount.
- small changes to lctl interface to support new config protocol.
- newdev is now a no-op.
- cfg_device <device name> is used to set the target device for
detach and cleanup.
phil [Tue, 7 Oct 2003 22:09:26 +0000 (22:09 +0000)]
- remove unsupported chaos-2.4.20 from which_patch; fit lines in 80 columns
- disable "mds_cleanup_orphans()" function, which LBUGs in at least
one reasonably common case
braam [Tue, 7 Oct 2003 06:33:13 +0000 (06:33 +0000)]
- bump the version
adilger [Fri, 3 Oct 2003 16:17:19 +0000 (16:17 +0000)]
Print out generation values as unsigned instead of hex to be consistent and
remove confusion when debugging.
youfeng [Tue, 30 Sep 2003 06:07:37 +0000 (06:07 +0000)]
b 1585 Support immutable attributes to prevent accidental file deletion from the archives
youfeng [Fri, 26 Sep 2003 03:58:48 +0000 (03:58 +0000)]
b=1615
a greppable magic string to aid LLNL in extracting the lustre messages from
syslog. "Lustre:" for less important messages, and "LustreError" for more
important messages.
shaver [Thu, 25 Sep 2003 15:12:08 +0000 (15:12 +0000)]
Raise kernel version to 27 on b_devel as well.
phil [Thu, 25 Sep 2003 05:47:08 +0000 (05:47 +0000)]
re-committing to b_devel:
b=1967
r=phil
Alex's patch, introducing the first half of pdirops. This enables it
for the back-end ext3 fs at runtime (if built against a
pdirops-enabled kernel), but doesn't yet fully integrate hashed
locking throughout.
niu [Thu, 11 Sep 2003 07:39:23 +0000 (07:39 +0000)]
* add bproc series.
phil [Tue, 9 Sep 2003 04:49:09 +0000 (04:49 +0000)]
land b_llog on b_devel:
reorganization and API update of the logging infrastructure. minimal
changes to the other code.
phil [Tue, 9 Sep 2003 03:54:14 +0000 (03:54 +0000)]
merge b_llpmd into b_devel. the major highlights:
- new I/O backend
- new client page cache and llite/lov/osc plumbing
- pre-creation of OST objects
- most of the OBD protocol now revolves around exports, not obd_devices
phil [Fri, 22 Aug 2003 22:51:10 +0000 (22:51 +0000)]
merge HEAD into b_devel, including socknal autoconnect and new v24 kernel
adilger [Fri, 22 Aug 2003 07:29:28 +0000 (07:29 +0000)]
Call the superblock pointer sb.
adilger [Tue, 19 Aug 2003 22:17:20 +0000 (22:17 +0000)]
journal_start() returns ERR_PTR() and not NULL on failure.
phil [Sat, 16 Aug 2003 18:50:24 +0000 (18:50 +0000)]
b=1776
r=shaver
Change the read_record and write_record APIs to return 0 on success
and a negative error. Any short read/write is reported as -EIO.
It used to return the number of bytes completed, which meant that the
error checking code had to be duplicated everywhere. A short I/O in
either of these functions is always a failure.
(As a nice side effect, one of the orphan functions got this wrong, so
this gets us somewhat closer to having that infrastructure)
adilger [Fri, 15 Aug 2003 20:03:30 +0000 (20:03 +0000)]
Add extra assertions from bug 1648 to b_devel. They have been running fine
on ALC and my system for a week, and will tell us if we do bad things with
the journal (i.e. forget to commit or imbalanced start/commit).
mfrey [Mon, 4 Aug 2003 15:14:13 +0000 (15:14 +0000)]
rebase b_qos on b_devel instead of b_ad
adilger [Wed, 30 Jul 2003 20:35:06 +0000 (20:35 +0000)]
Ensure OST objids are unique even after a crash by using the mount count as
a generation number. Remove old "superhack" code.
Add a "force_sync" parameter to filter_update_server_data() and
fsfilt_write_record() so that we ensure the mount_count is safe on disk
when the OST has started.
b=294
r=phil
eeb [Sat, 26 Jul 2003 16:59:25 +0000 (16:59 +0000)]
* Guarded #define EXPORT_SYMTAB
* Bit the bullet and #defined PTL_MTU
NB currently defined in <portals/lib-types.h>; maybe should move...
braam [Fri, 25 Jul 2003 23:17:07 +0000 (23:17 +0000)]
- updat \7fe the version.
shaver [Fri, 25 Jul 2003 23:04:25 +0000 (23:04 +0000)]
b=1600: my version of Andreas' patch to use write_record to ensure that the
MDS server data is written at creation time
b=1597: cope with entering recovery/replay without a preceding timeout
We pass this initial single-node/single-mount replay test, yay.
cvs2svn [Fri, 25 Jul 2003 17:58:24 +0000 (17:58 +0000)]
This commit was manufactured by cvs2svn to create branch 'unlabeled-1.4.6'.
phil [Fri, 25 Jul 2003 17:58:07 +0000 (17:58 +0000)]
merge b_devel into HEAD, which will become 0.7.3
- dozens and dozens of fixes for working with 2.6 kernels
- new 2.4 kernel APIs
- uncountable bug fixes
phil [Fri, 25 Jul 2003 17:57:53 +0000 (17:57 +0000)]
b=2225 fix obd_self_export issues
wangdi [Fri, 25 Jul 2003 09:29:49 +0000 (09:29 +0000)]
file spec2series.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:29:48 +0000 (09:29 +0000)]
file rpatch.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:29:47 +0000 (09:29 +0000)]
file patchfns.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:29:46 +0000 (09:29 +0000)]
file parse-patch.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:29:45 +0000 (09:29 +0000)]
file apatch.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:47 +0000 (09:28 +0000)]
file unapplied.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:46 +0000 (09:28 +0000)]
file top.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:45 +0000 (09:28 +0000)]
file setup.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:44 +0000 (09:28 +0000)]
file series.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:43 +0000 (09:28 +0000)]
file remove.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:42 +0000 (09:28 +0000)]
file refresh.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:41 +0000 (09:28 +0000)]
file push.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:40 +0000 (09:28 +0000)]
file previous.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:39 +0000 (09:28 +0000)]
file pop.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:38 +0000 (09:28 +0000)]
file patches.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:37 +0000 (09:28 +0000)]
file next.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:36 +0000 (09:28 +0000)]
file new.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:35 +0000 (09:28 +0000)]
file import.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:34 +0000 (09:28 +0000)]
file fork.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:33 +0000 (09:28 +0000)]
file files.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:32 +0000 (09:28 +0000)]
file diff.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:31 +0000 (09:28 +0000)]
file delete.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:30 +0000 (09:28 +0000)]
file applied.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:28:29 +0000 (09:28 +0000)]
file add.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:26:54 +0000 (09:26 +0000)]
file quilt.pot was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:26:53 +0000 (09:26 +0000)]
file fr.po was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:26:52 +0000 (09:26 +0000)]
file de.po was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:26:51 +0000 (09:26 +0000)]
file Makefile was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:24:30 +0000 (09:24 +0000)]
file backup-files.c was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:23:25 +0000 (09:23 +0000)]
file docco.txt was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:23:24 +0000 (09:23 +0000)]
file README.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:22:18 +0000 (09:22 +0000)]
file install-sh was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:19:52 +0000 (09:19 +0000)]
file quilt.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:19:51 +0000 (09:19 +0000)]
file guards.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:19:50 +0000 (09:19 +0000)]
file guards.1 was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:08 +0000 (09:18 +0000)]
file quilt.spec.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:07 +0000 (09:18 +0000)]
file quilt.changes was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:06 +0000 (09:18 +0000)]
file configure.ac was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:05 +0000 (09:18 +0000)]
file bash_completion was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:04 +0000 (09:18 +0000)]
file TODO was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:03 +0000 (09:18 +0000)]
file README was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:02 +0000 (09:18 +0000)]
file Makefile.in was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:01 +0000 (09:18 +0000)]
file COPYING was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:18:00 +0000 (09:18 +0000)]
file BUGS was initially added on branch b_unify.
wangdi [Fri, 25 Jul 2003 09:17:59 +0000 (09:17 +0000)]
file AUTHORS was initially added on branch b_unify.
shaver [Thu, 24 Jul 2003 19:07:08 +0000 (19:07 +0000)]
file replay-single.sh was initially added on branch b_devel.
wangdi [Wed, 23 Jul 2003 09:44:10 +0000 (09:44 +0000)]
file kernel.spec.in was initially added on branch b_unify.
braam [Wed, 23 Jul 2003 04:31:26 +0000 (04:31 +0000)]
file kgdb-2.6.0-test1 was initially added on branch b_unify.
wangdi [Tue, 22 Jul 2003 15:03:00 +0000 (15:03 +0000)]
file vfs_nointent_2.6.0-test1.patch was initially added on branch b_unify.
wangdi [Tue, 22 Jul 2003 15:01:54 +0000 (15:01 +0000)]
file vfs_nointent_2.6.0-test1.pc was initially added on branch b_unify.
wangdi [Tue, 22 Jul 2003 15:00:17 +0000 (15:00 +0000)]
file lkcd-cvs-2.6.0-test1.pc was initially added on branch b_unify.
wangdi [Tue, 22 Jul 2003 14:59:16 +0000 (14:59 +0000)]
file lkcd-cvs-2.6.0-test1.patch was initially added on branch b_unify.
phil [Tue, 22 Jul 2003 14:05:26 +0000 (14:05 +0000)]
partial merge of b_unify into b_devel (20030722_0202)
phil [Tue, 22 Jul 2003 13:50:37 +0000 (13:50 +0000)]
partial merge of b_unify into b_devel (20030722_0202)
braam [Tue, 22 Jul 2003 07:06:28 +0000 (07:06 +0000)]
file kgdb_2.6.0_test1 was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:05:30 +0000 (07:05 +0000)]
file vfs_intent_2.6.0-test1.pc was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:05:29 +0000 (07:05 +0000)]
file lkcd-kernel-changes-2.6.0-test1.pc was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:05:28 +0000 (07:05 +0000)]
file kexec-2.6.0-full.pc was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:05:27 +0000 (07:05 +0000)]
file 2.6.0-test1-mm2.pc was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:04:58 +0000 (07:04 +0000)]
file vfs_intent_2.6.0-test1.patch was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:04:57 +0000 (07:04 +0000)]
file lkcd-kernel-changes-2.6.0-test1.patch was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:04:56 +0000 (07:04 +0000)]
file kexec-2.6.0-full.patch was initially added on branch b_unify.
braam [Tue, 22 Jul 2003 07:04:54 +0000 (07:04 +0000)]
file 2.6.0-test1-mm2.patch was initially added on branch b_unify.
zab [Tue, 22 Jul 2003 06:38:56 +0000 (06:38 +0000)]
file rw24.c was initially added on branch b_llpio.