Whamcloud - gitweb
fs/lustre-release.git
19 years agoBranch b1_4
adilger [Mon, 6 Jun 2005 21:33:10 +0000 (21:33 +0000)]
Branch b1_4
Move class_fail_export() outside #ifdef __KERNEL__ for liblustre to compile
(even though this is a server-side only function).
b=5921

19 years agoUpdate ChangeLog
lwang [Mon, 6 Jun 2005 10:06:39 +0000 (10:06 +0000)]
Update ChangeLog

19 years agoBranch b1_4
adilger [Sat, 4 Jun 2005 23:59:04 +0000 (23:59 +0000)]
Branch b1_4
Ignore "sec" option to avoid buffalo breakage.  Hopefully temporary.

19 years agoBranch b1_4
adilger [Fri, 3 Jun 2005 22:32:21 +0000 (22:32 +0000)]
Branch b1_4
Put filter_destroy(), filter_setattr() into filter_internal.h so we can
call them directly in filter_log.c instead of using obd_*() indirection.
Minor code reorg of filter_llog_finish() for the same reason.

19 years agoBranch b1_4
adilger [Fri, 3 Jun 2005 22:23:21 +0000 (22:23 +0000)]
Branch b1_4
Quiet liblustre compile warning.
b=6420

19 years agoBranch b1_4
adilger [Fri, 3 Jun 2005 22:15:53 +0000 (22:15 +0000)]
Branch b1_4
Remove redundant ptlrpc_fail_export() function, use class_fail_export().
Move EXPORT_SYMBOL functions to where the function is defined, for clarity.
Move lov_merge_* declarations to a header (same as b_cray).
Fix some compile warnings for liblustre.
b=5921

19 years agoBranch b1_4
adilger [Fri, 3 Jun 2005 19:56:23 +0000 (19:56 +0000)]
Branch b1_4
Don't disable debug during sanityN.sh

19 years agoBranch b1_4
adilger [Fri, 3 Jun 2005 18:11:02 +0000 (18:11 +0000)]
Branch b1_4
Setting a default stripe on the filesystem root prevented the
filesystem from being remounted.
The client was sending extra request flags in the root getattr
request and did not allocate a reply buffer for the dir EA.
b=6367
r=phil

19 years agoBranch b1_4
adilger [Thu, 2 Jun 2005 18:10:36 +0000 (18:10 +0000)]
Branch b1_4
Setting a default stripe on the filesystem root prevented the
filesystem from being remounted.
The client was sending extra request flags in the root getattr
request and did not allocate a reply buffer for the dir EA.
b=6367
r=phil

19 years agoBranch b1_4
adilger [Wed, 1 Jun 2005 23:18:33 +0000 (23:18 +0000)]
Branch b1_4
Some minor updates from b1_4_quota that I had in my tree for a long time.
There are more updates that need to be landed, but these are pretty safe.

19 years agoBranch b1_4
adilger [Wed, 1 Jun 2005 22:57:08 +0000 (22:57 +0000)]
Branch b1_4
Add rate-limiting for DEBUG_REQ messages going to the console.
b=6411

19 years agoBranch b1_4
adilger [Wed, 1 Jun 2005 18:45:09 +0000 (18:45 +0000)]
Branch b1_4
b=5275 : NFSD is looking up ".." which was broken in ext3 directories
that had grown large enough to become hashed.  Now, when looking up
"." or ".." in a hashed directory we explicitly search block 0, which
is where those entries will be kept (in addition to the htree index root)
instead of the hash of "." or "..".  Patch is included in 2.6-mm.
r=sct

19 years agoBranch b1_4
adilger [Wed, 1 Jun 2005 08:59:53 +0000 (08:59 +0000)]
Branch b1_4
Quiet spurious console error messages when an OST is deactivated on the MDS.
Don't NULL-deref pd->pd_set if allocation failed.  We will just ping later.
b=6346
r=nathan

19 years agoBranch: b1_4
green [Wed, 1 Jun 2005 08:38:33 +0000 (08:38 +0000)]
Branch: b1_4
b=5654

Take i_alloc_sem in nfsd_setattr to be on par with rest of the kernel.

19 years agoBranch b1_4
adilger [Wed, 1 Jun 2005 07:10:16 +0000 (07:10 +0000)]
Branch b1_4
Add /proc/sys/vm/vm_gfp_debug to the 2.4.21-rhel kernel.
b=6422

19 years agoBranch b1_4
adilger [Tue, 31 May 2005 18:15:45 +0000 (18:15 +0000)]
Branch b1_4
On x86_64 the kernel declares __u64 as long long, but userspace uses long.
Fix LP*64 printf format macros to handle this difference to quiet warnings.

19 years agob=3790
green [Tue, 31 May 2005 15:31:28 +0000 (15:31 +0000)]
b=3790
Move changelog entry to the bottom of list.

19 years agoBranch b1_4
adilger [Mon, 30 May 2005 21:27:50 +0000 (21:27 +0000)]
Branch b1_4
Set -1 debugging for replay-single test 42.
b=5493

19 years agoBranch b1_4
adilger [Mon, 30 May 2005 20:46:53 +0000 (20:46 +0000)]
Branch b1_4
Ignore fsfilt-ldiskfs.s

19 years agoBranch b1_4
adilger [Mon, 30 May 2005 19:32:41 +0000 (19:32 +0000)]
Branch b1_4
Change lib64 search order to avoid stale .pyc files.

19 years agoBranch b1_4
adilger [Sun, 29 May 2005 08:23:38 +0000 (08:23 +0000)]
Branch b1_4
Change build version to 1.4.2.4

19 years agob=3790
green [Sun, 29 May 2005 07:56:25 +0000 (07:56 +0000)]
b=3790
Changelog update

19 years agoBranch: b1_4
green [Sun, 29 May 2005 07:51:24 +0000 (07:51 +0000)]
Branch: b1_4
b=3790
r=adilger
Introudce fsprivate member of struct file, to be used as filesystem's private data pointer

19 years agoBranch: b1_4
green [Sat, 28 May 2005 21:31:08 +0000 (21:31 +0000)]
Branch: b1_4

Instead of commenting out all LL_CDEBUG_PAGE usage, make LL_CDEBUG_PAGE
to work both in kernel and not.

19 years agob=6412
jacob [Fri, 27 May 2005 22:45:48 +0000 (22:45 +0000)]
b=6412

check in the right file.

Severity   : major
Frequency  : occasional
Bugzilla   : 6412
Description: Nodes with an elan id of 0 trigger a failed assertion

19 years agob=6412
jacob [Fri, 27 May 2005 22:41:57 +0000 (22:41 +0000)]
b=6412

Severity   : major
Frequency  : occasional
Bugzilla   : 6412
Description: Nodes with an elan id of 0 trigger a failed assertion

19 years agob=6286
jacob [Fri, 27 May 2005 22:28:59 +0000 (22:28 +0000)]
b=6286
r=adilger

Severity   : enhancement
Bugzilla   : 6296
Description: Default groups are now added by lconf
Details    : You can now run lconf --group <servicename> without having to
             manually add groups with lmc.

19 years agob=6377
jacob [Fri, 27 May 2005 21:34:59 +0000 (21:34 +0000)]
b=6377
r=adilger

Use obd_recovering instead of obd_recoverable_clients to check if the
obd is in recovery.

abort_recovery didn't set obd_recoverable_clients to 0 (which it now
does), so if recovery was aborted, the server would never ping-evict
clients (which can lead to extra exports, possibly requiring recovery
to be aborted).

19 years agoremove liblustre change entry. it's not enabled by default, and the
jacob [Fri, 27 May 2005 21:22:33 +0000 (21:22 +0000)]
remove liblustre change entry.  it's not enabled by default, and the
few customers whom it affects already know about it.

19 years agoBranch b1_4
adilger [Fri, 27 May 2005 11:56:46 +0000 (11:56 +0000)]
Branch b1_4
Don't LASSERT OST in ptlrpc if a client sends a bad bulk request.
b=6345

19 years agoBranch b1_4 - merge from b_cray
adilger [Fri, 27 May 2005 11:53:38 +0000 (11:53 +0000)]
Branch b1_4 - merge from b_cray
Remove unused growth_count set_info.

19 years agoBranch b1_4
adilger [Fri, 27 May 2005 11:40:06 +0000 (11:40 +0000)]
Branch b1_4
Make very verbose message an LCONSOLE_ERROR() for future use.

19 years agoBranch b1_4 - merge from b_cray
adilger [Fri, 27 May 2005 11:38:29 +0000 (11:38 +0000)]
Branch b1_4 - merge from b_cray
Use l_export_chain instead of l_pending chain on client for SYNC
ldlm_cancel_lru cancellations.
b=5666

19 years agoBranch b1_4
adilger [Fri, 27 May 2005 11:35:45 +0000 (11:35 +0000)]
Branch b1_4
Initialize (currently unused) l_childof member of lock struct.

19 years agoBranch b1_4
adilger [Fri, 27 May 2005 11:30:57 +0000 (11:30 +0000)]
Branch b1_4
Don't return an "error" (pid) from ptlrpc_import_recovery_state_machine()
from kernel_thread().
r=alex (original fix)

19 years agoBranch b1_4
adilger [Fri, 27 May 2005 11:17:41 +0000 (11:17 +0000)]
Branch b1_4
Always include liblustre in DIST_SUBDIRS

19 years agoBranch b1_4
adilger [Fri, 27 May 2005 11:10:03 +0000 (11:10 +0000)]
Branch b1_4
Fix .netmatch method to work with older Pythons.
Only reduce OST inode counts for larger OSTs.
b=5044

19 years agoBranch b1_4
adilger [Thu, 26 May 2005 23:33:14 +0000 (23:33 +0000)]
Branch b1_4
Don't complain about llog padding record swabbing.

19 years agoBranch: b1_4
green [Thu, 26 May 2005 21:07:30 +0000 (21:07 +0000)]
Branch: b1_4

Liblustre revival.
Liblustre can be compiled and works now.

19 years ago5541: extra peer list
lwang [Thu, 26 May 2005 09:23:00 +0000 (09:23 +0000)]
5541: extra peer list

19 years agoBranch b1_4
adilger [Wed, 25 May 2005 19:38:15 +0000 (19:38 +0000)]
Branch b1_4
Quiet spurious lov_iocontrol() error messages for PPC64 TCGETS, et. al.  ioctls.
Print file offsets in both decimal and hex for debugging.
b=5947

19 years agob=6371
jacob [Wed, 25 May 2005 15:57:45 +0000 (15:57 +0000)]
b=6371
r=adilger, r=phil

Severity   : major
Frequency  : rare
Bugzilla   : 6371
Description: After recovery, certain operations trigger a failed
             assertion on a client.
Details    : Failing over an mds, using lconf -d --failover, while a
             client was doing a readdir() call would cause the client to
             LBUG after recovery completed and the readdir() was resent.

19 years agoBranch b1_4_bug3389
adilger [Wed, 25 May 2005 15:33:38 +0000 (15:33 +0000)]
Branch b1_4_bug3389
Move upcall stuff to lustre/lvfs/upcall_cache.c instead of mds_groups.c.
Rename all of the functions upcall_cache_* to match HEAD.
Pass upcall_cache * as parameter instead of mds_obd *.
Improve some error messages.
b=3389
b=6367 (default striping on root dir fix included)
r=phil

19 years ago* changed __clear_page_ll_data(page) to make page_cache_release(page)
eeb [Wed, 25 May 2005 15:05:59 +0000 (15:05 +0000)]
*    changed __clear_page_ll_data(page) to make page_cache_release(page)
     the last thing it does.

19 years agoBranch b1_4
adilger [Tue, 24 May 2005 22:24:48 +0000 (22:24 +0000)]
Branch b1_4
Comments and other purely cosmetic fixes.

19 years agoBranch b1_4
adilger [Tue, 24 May 2005 22:04:05 +0000 (22:04 +0000)]
Branch b1_4
Comment what med_open_lock is locking.

19 years agoBranch b1_4_bug3389
adilger [Tue, 24 May 2005 16:03:45 +0000 (16:03 +0000)]
Branch b1_4_bug3389
Add support for supplementary groups via upcall on the MDS.
b=3389, b=6253

19 years agoBranch b1_4
adilger [Sat, 21 May 2005 08:20:35 +0000 (08:20 +0000)]
Branch b1_4
Use 64-bit interface for truncate, so that it is possible to ./truncate
files larger than 2GB in UML.

19 years agoBranch b1_4
adilger [Sat, 21 May 2005 08:16:46 +0000 (08:16 +0000)]
Branch b1_4
Print out numeric device if no name can be found for 2.6.
r=nathan

19 years agofix formatting
jacob [Fri, 20 May 2005 23:26:29 +0000 (23:26 +0000)]
fix formatting

19 years agob=6359
jacob [Fri, 20 May 2005 23:25:36 +0000 (23:25 +0000)]
b=6359
r=adilger, phil

Severity:  : enhancement
Bugzilla   : 3262, 6359
Description: Attempts to reconnect to servers are now more aggressive.
Details    : This builds on the enhanced upcall-less recovery that was added
             in 1.4.2.  When trying to reconnect to servers,  clients will
             now try each server in the failover group every 10 seconds.  By
             default, clients would previously try one server every 25 seconds.

19 years agoBranch b1_4
adilger [Fri, 20 May 2005 23:07:42 +0000 (23:07 +0000)]
Branch b1_4
Do it right.

19 years agoBranch b1_4
adilger [Fri, 20 May 2005 23:06:35 +0000 (23:06 +0000)]
Branch b1_4
Increase fsx size for acceptance-small.sh to something reasonable.

19 years agoadd the now-required -DLUSTRE_UTILS=1 to the Lustre build as well
phil [Fri, 20 May 2005 22:39:47 +0000 (22:39 +0000)]
add the now-required -DLUSTRE_UTILS=1 to the Lustre build as well

19 years agoprint more useful things
jacob [Fri, 20 May 2005 20:47:48 +0000 (20:47 +0000)]
print more useful things

19 years agoBranch b1_4
adilger [Fri, 20 May 2005 20:16:27 +0000 (20:16 +0000)]
Branch b1_4
Print a useful error on failure.

19 years agoBranch b1_4
adilger [Fri, 20 May 2005 17:38:57 +0000 (17:38 +0000)]
Branch b1_4
Remove some extraneous logic in mdc_rename_pack().  We already check this
same thing in ll_i2uctxt() as called by ll{,u}_prepare_mdc_op_data() from
ll{,u}_rename_raw().  Verified with POSIX this has no effect.

19 years agoBranch b1_4
adilger [Fri, 20 May 2005 17:17:53 +0000 (17:17 +0000)]
Branch b1_4
Remove unused and duplicating-function file simple.c.  All of this has
been moved into lvfs*.c

19 years agob=4855
jacob [Thu, 19 May 2005 20:56:34 +0000 (20:56 +0000)]
b=4855
r=phil (original patch)

handle crc32_le being a module or disabled.

19 years agob=6349
jacob [Thu, 19 May 2005 17:35:56 +0000 (17:35 +0000)]
b=6349
r=adilger

print the nid instead of the export uuid (if available) when
ping-evicting clients

19 years agoBranch b1_4
adilger [Wed, 18 May 2005 17:11:14 +0000 (17:11 +0000)]
Branch b1_4
It was possible to get multiple mfd references during close and client
eviction, leading to either mds_close() or mds_mfd_close() referencing
a freed mfd.

Now we remove the mfd from the mfd_list and the handle hash under lock so
that once it starts on the road to destruction it is not possible to get a
new reference to it.  Also add comments on usage of mfd-related functions!
b=3819, b=4364, b=4397, b=6313
r=green

19 years agor=phil
jacob [Wed, 18 May 2005 00:51:54 +0000 (00:51 +0000)]
r=phil

stop lying just to be popular.

19 years agolsy reported that LL_CDEBUG_PAGE in osc_checksum_bulk wouldn't compile,
phil [Tue, 17 May 2005 16:25:58 +0000 (16:25 +0000)]
lsy reported that LL_CDEBUG_PAGE in osc_checksum_bulk wouldn't compile,
because the outer scope defines a variable "page_count", and LL_CDEBUG_PAGE
wants to call the VM function page_count().

I still can't figure out why it works fine for me, but I've stopped trying.
Changing the name of the variable is easier.

19 years agofix up for readline (the old one can not handle long input)
lwang [Tue, 17 May 2005 08:43:37 +0000 (08:43 +0000)]
fix up for readline (the old one can not handle long input)

19 years agob=5902
phil [Tue, 17 May 2005 04:04:09 +0000 (04:04 +0000)]
b=5902
r=adilger

Many improvements to the code that checksums I/O, among them:
- add a switch to enable or disable them at runtime
- check the pages while under llite's control, and the buffers while under
  the osc/ost's
- if the server and client see different checksums, try to figure out where
  it went wrong
- use the kernel crc32 routine

19 years agob=6200
phil [Tue, 17 May 2005 03:41:19 +0000 (03:41 +0000)]
b=6200
A bug in MDS/OSS recovery could cause the OSS to fail a (ctxt == NULL)
assertion.

There's little harm in just aborting MDS/OSS recovery and letting
it try again next time, so I removed the LASSERT and return an error instead.
We can revisit it when we put the knife in the llog code for real.

19 years agoBranch b1_4
adilger [Mon, 16 May 2005 22:57:48 +0000 (22:57 +0000)]
Branch b1_4
Disable fsync-under-recovery test, which is preventing remaining tests
from running.
b=5494
r=nathan

19 years agoBranch b1_4
adilger [Mon, 16 May 2005 18:22:42 +0000 (18:22 +0000)]
Branch b1_4
Decrease the ldlm_timeout if obd_timeout is dropped.  It doesn't really make
sense to have AST timeouts longer than the RPC timeouts, but is mostly only
noticable in our regression tests (recovery-small.sh test 10 in particular).
b=6172

19 years agoBranch b1_4
adilger [Mon, 16 May 2005 18:01:46 +0000 (18:01 +0000)]
Branch b1_4
Use a timeout instead of killing writemany - the OST failover may not have
happened yet.
r=nathan

19 years agoBranch b1_4
adilger [Mon, 16 May 2005 17:54:59 +0000 (17:54 +0000)]
Branch b1_4
Make sure that test 52 writemany will exit at some point.
Put writemany usage message at top of code so it is easily found.
r=nathan

19 years ago*** empty log message ***
larry [Sun, 15 May 2005 23:21:51 +0000 (23:21 +0000)]
*** empty log message ***

19 years agoBranch b1_4
adilger [Sat, 14 May 2005 10:32:37 +0000 (10:32 +0000)]
Branch b1_4
Add regression test for reading from a file with no objects (reads zeros,
stops at EOF).
b=6242, b=6243

19 years agoupdate to new errata
jacob [Fri, 13 May 2005 18:54:53 +0000 (18:54 +0000)]
update to new errata

19 years agoBranch b1_4
nathan [Fri, 13 May 2005 18:11:51 +0000 (18:11 +0000)]
Branch b1_4
b=6301
r=adilger
Prevent damage due to racing export disconnects

19 years agoland b_release_1_4_2:
jacob [Fri, 13 May 2005 18:04:05 +0000 (18:04 +0000)]
land b_release_1_4_2:

 - qsnet patches for sles 2.6 and rhel 2.4

19 years agoBranch b1_4
adilger [Thu, 12 May 2005 23:13:24 +0000 (23:13 +0000)]
Branch b1_4
Move all pagecache vs. directio handling into filter_clear_page_cache()
and add comments about what is going on here and why.

Use the fs-specific ->invalidatepage called from truncate_complete_page()
instead of calling block_invalidatepage() directly.

Wait on page for the 2.6 code, and use 2.6 functions and have compat
macros for 2.4 instead.
b=4892
r=green

19 years agoBranch b1_4
adilger [Thu, 12 May 2005 21:28:49 +0000 (21:28 +0000)]
Branch b1_4
Update ChangeLog to new format.

19 years agoBranch b1_4
adilger [Thu, 12 May 2005 20:42:39 +0000 (20:42 +0000)]
Branch b1_4
Add obd_name to message.
b=6301

19 years agoBranch b1_4
adilger [Wed, 11 May 2005 22:04:03 +0000 (22:04 +0000)]
Branch b1_4
Ensure the PING_INTERVAL is at least 1s, otherwise obd_timeout < 4 can
cause severe heartburn.

19 years agoBranch: b1_4
green [Wed, 11 May 2005 21:16:30 +0000 (21:16 +0000)]
Branch: b1_4
b=6243
r=adilger

Properly return 0 for reads that are totally after EOF.

19 years agoBranch b1_4
adilger [Wed, 11 May 2005 19:23:49 +0000 (19:23 +0000)]
Branch b1_4
Revert previous commit, it was confusingly correct.
b=6289

19 years agoBranch b1_4
adilger [Wed, 11 May 2005 18:28:46 +0000 (18:28 +0000)]
Branch b1_4
Pass OBD_BRW_WRITE to filter_alloc_iobuf() from preprw_write().  This
parameter is actually unused at this time, so no real effect.
b=6289
r=fergal (original change)

19 years agoBranch b1_4
adilger [Wed, 11 May 2005 18:03:07 +0000 (18:03 +0000)]
Branch b1_4
Update build version to 1.4.2.2bgl

19 years agoBranch b1_4
adilger [Wed, 11 May 2005 17:51:37 +0000 (17:51 +0000)]
Branch b1_4
Fix typo in bug number.

19 years agoBranch b1_4
nathan [Wed, 11 May 2005 00:07:36 +0000 (00:07 +0000)]
Branch b1_4
b=5493
add asserts to help track this down

19 years agoBranch b1_4
nathan [Tue, 10 May 2005 21:28:44 +0000 (21:28 +0000)]
Branch b1_4
b=5949

19 years agoBranch b1_4
adilger [Tue, 10 May 2005 20:32:23 +0000 (20:32 +0000)]
Branch b1_4
Increase the LDLM AST timeout.  With the lock reordering in bug 5492 et.al.
we now hold ns_lock over vmtruncate.
b=6172
r=phil

19 years agoBranch b1_4
nathan [Tue, 10 May 2005 15:25:39 +0000 (15:25 +0000)]
Branch b1_4
b=6223
r=adilger
Fix lfs find to handle arbitrary number of targets

19 years agoBranch b1_4
adilger [Mon, 9 May 2005 06:05:24 +0000 (06:05 +0000)]
Branch b1_4
Fix compile warning.

19 years ago2.4.29 does not need smp_num_siblings export patch as this is already exported
green [Sun, 8 May 2005 20:49:11 +0000 (20:49 +0000)]
2.4.29 does not need smp_num_siblings export patch as this is already exported

19 years agoMove CONFIG_KALLSYMS question from ISDN menu to kernel hacking menu
green [Sun, 8 May 2005 20:33:40 +0000 (20:33 +0000)]
Move CONFIG_KALLSYMS question from ISDN menu to kernel hacking menu
in 2.4.29 patch

19 years agokallsyms patch for 2.4.29
green [Sun, 8 May 2005 20:22:48 +0000 (20:22 +0000)]
kallsyms patch for 2.4.29
Separated uml & non-uml 2.4.29 series

19 years agob=5907
green [Fri, 6 May 2005 20:22:39 +0000 (20:22 +0000)]
b=5907
r=adilger

Testcase for the bug.

19 years agofix subsystem type
adilger [Fri, 6 May 2005 14:55:49 +0000 (14:55 +0000)]
fix subsystem type

19 years agoBranch: b1_4
adilger [Thu, 5 May 2005 22:28:36 +0000 (22:28 +0000)]
Branch: b1_4
Add bug reference for workaround.
b=6155

19 years agoBranch b1_4
nathan [Thu, 5 May 2005 21:52:47 +0000 (21:52 +0000)]
Branch b1_4
b=5949
r=adilger
Various fixes to make --failover under load safer

19 years agob=6243
green [Thu, 5 May 2005 20:54:22 +0000 (20:54 +0000)]
b=6243
Export clear_user_skas as well (uml-only again)

19 years ago- I committed the ext3-patch-fuzz patch, but forgot to add it to the series
phil [Thu, 5 May 2005 20:50:41 +0000 (20:50 +0000)]
- I committed the ext3-patch-fuzz patch, but forgot to add it to the series
- add the recent clear_user export patch to my uml series

19 years agoBranch: b1_4
adilger [Thu, 5 May 2005 20:16:49 +0000 (20:16 +0000)]
Branch: b1_4
Remove unused function.  class_find_client_obd_notype() does the same and
is more generic.
b=6242

19 years agoBranch: b1_4
adilger [Thu, 5 May 2005 19:41:27 +0000 (19:41 +0000)]
Branch: b1_4
Reorder ll_async_page slightly so the ints are together (slight savings on
64-bit arches).