Whamcloud - gitweb
green [Fri, 8 Apr 2005 07:21:54 +0000 (07:21 +0000)]
b=4982
r=adilger
Flush pagecache on ost before doing directio writes, or else we might end up
with stale data being written to disk later.
phil [Fri, 8 Apr 2005 04:24:51 +0000 (04:24 +0000)]
It is so unbelievably embarrassing when I run llobdstat during the training,
it prints Mb/s, and everyone laughs at how CFS can't tell the difference
between megabits and megabytes.
nathan [Thu, 7 Apr 2005 19:30:29 +0000 (19:30 +0000)]
Branch b1_4
b=6080
try to isolate test 24's fallout
adilger [Wed, 6 Apr 2005 22:25:12 +0000 (22:25 +0000)]
Branch: b1_4
Quiet compile warnings on ia64.
adilger [Wed, 6 Apr 2005 21:56:14 +0000 (21:56 +0000)]
Branch: b1_4
Conversely, loff_t is always %llu.
adilger [Wed, 6 Apr 2005 21:52:29 +0000 (21:52 +0000)]
Branch: b1_4
Use LPU64 instead of %llu to print __u64 values, as ia64 uses "long"
for 64-bit numbers.
adilger [Wed, 6 Apr 2005 18:51:23 +0000 (18:51 +0000)]
Branch: b1_4
Revert "last little bit of cleanup" for lli_size_sem locking. Getting this
lock (a semaphore which can sleep) in ll_nopage and/or ll_ap_refresh_count
causes the client to lock up (symptoms include kupdated stuck, no free mem,
client unresponsive to network = elan timeouts).
Still need to figure proper locking solution here. A spinlock is good for
all places except for ll_setattr_raw->vmtruncate path.
b=5654 (added under), b=6057, b=6059, b=6077 (possible fix)
nic [Wed, 6 Apr 2005 15:42:55 +0000 (15:42 +0000)]
add the $TESTNAME to all errors to make auto-vetting easier
adilger [Wed, 6 Apr 2005 12:08:39 +0000 (12:08 +0000)]
Branch: b1_4
Add support for mountfsoptions and clientoptions to LDAP.
b=5873
r=fergal (original patch)
nathan [Wed, 6 Apr 2005 01:55:27 +0000 (01:55 +0000)]
Branch b1_4
b=5949
The end of mds_connect was a mess. In an error case, it dropped too many
export refs. I think this might be the cause of 5949, 6030, 6058
Same commit, different rev. I jumped the gun on undoing this.
nathan [Wed, 6 Apr 2005 01:43:19 +0000 (01:43 +0000)]
Branch b1_4
b=5949
quickly undo broken stuff before anyone realizes it broke.
nathan [Wed, 6 Apr 2005 00:13:30 +0000 (00:13 +0000)]
Branch b1_4
b=5949
The end of mds_connect was a mess. In an error case, it dropped too many
export refs. I think this might be the cause of 5949, 6030, 6058
jacob [Tue, 5 Apr 2005 20:33:00 +0000 (20:33 +0000)]
b=5667
always include our local ioctl.h if _IOW isn't defined, which is
probably only catamount.
eeb [Tue, 5 Apr 2005 18:57:03 +0000 (18:57 +0000)]
* updated lconf symbolic debug masks to be consistent with portals HEAD
adilger [Tue, 5 Apr 2005 01:20:29 +0000 (01:20 +0000)]
Branch: b1_4
Add usleep to allow multiop to start + install signal handler.
b=5959
cvs2svn [Mon, 4 Apr 2005 13:13:26 +0000 (13:13 +0000)]
This commit was manufactured by cvs2svn to create branch 'b1_4'.
yury [Mon, 4 Apr 2005 13:13:25 +0000 (13:13 +0000)]
- landed b_hd_cray_merge3
adilger [Mon, 4 Apr 2005 12:59:33 +0000 (12:59 +0000)]
Branch: b1_4
Forward compat hooks in wire structs.
b=6007
r=jacob
green [Mon, 4 Apr 2005 12:25:22 +0000 (12:25 +0000)]
Added forgottent files needed for quota stuff
eeb [Mon, 4 Apr 2005 10:09:43 +0000 (10:09 +0000)]
* 5852 vibnal patch to detect __u64/void* vv_scatgat_t::v_address and
use appropriately for HIGHMEM support
green [Mon, 4 Apr 2005 08:48:17 +0000 (08:48 +0000)]
Fix quota code problem where on osts objects might be greated with wrong uid/gid
green [Mon, 4 Apr 2005 08:39:27 +0000 (08:39 +0000)]
b=6027
fix the conditions to take into account quota code requirements to
set "out of quota" flags in osc. (Needed to correctly return -EDQUOT errors
to userspace)
green [Sat, 2 Apr 2005 07:38:04 +0000 (07:38 +0000)]
Changelog entry about quota support
adilger [Sat, 2 Apr 2005 01:16:16 +0000 (01:16 +0000)]
Branch: b1_4
Don't abort lfs find if we get an error statting a file, this can happen
if e.g. the MDS is corrupted, which is exactly when we need it to work.
adilger [Sat, 2 Apr 2005 01:14:54 +0000 (01:14 +0000)]
Branch: b1_4
Don't barf if "HOST" is unset.
adilger [Sat, 2 Apr 2005 01:14:10 +0000 (01:14 +0000)]
Branch: b1_4
Fix bug number for excluded test, remove dupe from some merge.
adilger [Sat, 2 Apr 2005 01:13:29 +0000 (01:13 +0000)]
Branch: b1_4
Don't think just any mountpoint with "lustre" in the name is Lustre(tm).
There are no substitutes. (for HP)
jacob [Sat, 2 Apr 2005 01:08:42 +0000 (01:08 +0000)]
bail if we can't compile modules, and reorder uml check so that we can
adilger [Sat, 2 Apr 2005 00:57:21 +0000 (00:57 +0000)]
Branch: b1_4
Quiet annoying grant message.
r=phil
green [Fri, 1 Apr 2005 21:32:29 +0000 (21:32 +0000)]
Landing b1_4_quotaoff to b1_4
jacob [Fri, 1 Apr 2005 20:52:21 +0000 (20:52 +0000)]
b=3048
r=me, originally from adilger
Moves the checking for stripe sizes into the lib, so all callers get
this. Properly checks for dirstripe default removal, and always
prints the directory default striping.
nathan [Fri, 1 Apr 2005 19:36:38 +0000 (19:36 +0000)]
b=3026
r=boc
support for arbitrary number of OSTs
green [Fri, 1 Apr 2005 15:50:59 +0000 (15:50 +0000)]
Fix rhel4 compile errors for me
green [Fri, 1 Apr 2005 15:46:59 +0000 (15:46 +0000)]
b=5985
r=adilger
Do not drop LOOKUP_LINK_NOTLAST flag not set by us (in case of recursive
symlinks)
green [Fri, 1 Apr 2005 15:00:52 +0000 (15:00 +0000)]
b=6000
Do not search any VMAs in NULL mm. Fixes NFS exporting problems for HP.
nathan [Fri, 1 Apr 2005 00:20:05 +0000 (00:20 +0000)]
build all b1_4 derivatives with bgl portals
ericm [Thu, 31 Mar 2005 23:42:51 +0000 (23:42 +0000)]
since b_hd_sec has landed, all security branches should simply use
portals from HEAD now.
ericm [Thu, 31 Mar 2005 22:18:52 +0000 (22:18 +0000)]
land lustre part of b_hd_sec on HEAD.
ericm [Thu, 31 Mar 2005 21:55:51 +0000 (21:55 +0000)]
land portals part of b_hd_sec on HEAD.
jacob [Thu, 31 Mar 2005 21:21:39 +0000 (21:21 +0000)]
b=3048
r=me, adilger
when creating new directories, inherit parent's striping
jacob [Thu, 31 Mar 2005 21:18:27 +0000 (21:18 +0000)]
b=6017
r=adilger
add --abort-recovery option to lconf
eeb [Thu, 31 Mar 2005 16:50:04 +0000 (16:50 +0000)]
* 6020 openibnal CM callback fixes
- CM_ABORT + LASSERT(no more CM callbacks) on all CM errors before
connection is established.
- Show peer NID in all error messages on pathrecord/CM failures.
- Simplified kibnal_{peer_connect_failed,connreq_done} params.
- Fixed bug that would make ibc_connreq allocation failure LBUG.
- --connref in kibnal_connreq_done() moved to caller.
- Removed --connref race in established connection CM_IDLE callback.
eeb [Thu, 31 Mar 2005 10:33:38 +0000 (10:33 +0000)]
* Fix for 5998: LASSERT(kibnal_peer_active(peer))
eeb [Thu, 31 Mar 2005 10:29:47 +0000 (10:29 +0000)]
* Fixed bad LASSERT in qswnal (= instead of ==)
nathan [Wed, 30 Mar 2005 21:58:08 +0000 (21:58 +0000)]
Branch b1_4
think-o
nathan [Wed, 30 Mar 2005 21:10:23 +0000 (21:10 +0000)]
Branch b1_4
b=5951
Try to confine test 24 effects to test 24
jacob [Wed, 30 Mar 2005 19:55:13 +0000 (19:55 +0000)]
we build this file on all rhel 2.6 as well
brian [Wed, 30 Mar 2005 19:40:10 +0000 (19:40 +0000)]
Replace /usr/sbin and /usr/bin filelists with wildcards.
eeb [Wed, 30 Mar 2005 18:06:51 +0000 (18:06 +0000)]
* Removed '-Wall' from ranal build
eeb [Wed, 30 Mar 2005 18:06:03 +0000 (18:06 +0000)]
* Fixed trailing ';' on #define PORTALS_CFG_VERSION
eeb [Wed, 30 Mar 2005 18:05:07 +0000 (18:05 +0000)]
* Changed --with-iib to allow a path to the installed Infinicon headers
jacob [Wed, 30 Mar 2005 17:08:43 +0000 (17:08 +0000)]
all aboard! next stop, testing your build before submitting requests to buffalo!
eeb [Wed, 30 Mar 2005 14:03:28 +0000 (14:03 +0000)]
* llmount fix
- vibnal needs IP address as well as NID (assuming NID == IP
could lead to ARP failures; e.g. bug 5858).
adilger [Wed, 30 Mar 2005 11:06:27 +0000 (11:06 +0000)]
Branch: b1_4
Define $UPCALL=DEFAULT for instanity.sh, test breaks otherwise (it assumes
that "--lustre-upcall $UPCALL" will work, instead we eat the next parameter
--ptldebug as the upcall).
jacob [Wed, 30 Mar 2005 08:31:21 +0000 (08:31 +0000)]
b=6011
r=adilger
* bump portals ioctl version to work around not checking the
portals_cfg version number anywhere
* print error messages when there are errors in lctl
* some typo fixes ect.
adilger [Wed, 30 Mar 2005 08:05:09 +0000 (08:05 +0000)]
Branch: b1_4
Update ChangeLog with a message about incompatible 1.4.2 release.
adilger [Wed, 30 Mar 2005 07:59:30 +0000 (07:59 +0000)]
Branch: b1_4
Remove unused variable.
adilger [Wed, 30 Mar 2005 07:39:31 +0000 (07:39 +0000)]
Branch: b1_4
Clean up both llog contexts in osc and obdfilter, even if one has an error.
Equivalent to changes in lov_llog_cleanup() and mds_llog_cleanup().
b=4834
r=nathan
adilger [Wed, 30 Mar 2005 04:55:21 +0000 (04:55 +0000)]
Branch: b1_4
For some reason having an inline ll_set_rdonly() with HAVE_OLD_DEV_SET_RDONLY
is causing gcc to miscompile and way overstep the array bounds (2 == 1792
in some cases it seems). Move this code to a function.
Add some more 64-bit sanity checks (it was do_div() on BGL that broke things
previously).
adilger [Wed, 30 Mar 2005 02:42:53 +0000 (02:42 +0000)]
Branch: b_cray
Remove l_getgroups from RPM build, as this is not present in any branch
except HEAD. We need some sort of simple configure test to determine if
this should be included in the RPM or not.
adilger [Wed, 30 Mar 2005 01:03:26 +0000 (01:03 +0000)]
Branch: b_cray
Quiet liblustre compile warning.
adilger [Wed, 30 Mar 2005 00:32:33 +0000 (00:32 +0000)]
Branch: b1_4 (merge from b_cray)
Remove useless fcb_cache_count atomic.
jacob [Tue, 29 Mar 2005 22:38:21 +0000 (22:38 +0000)]
b=5981
r=oleg
fix for this patch from oleg.
this fixes oopses when running replay-single in UML for me, and
recovery-small for andreas somewhere
nkj [Tue, 29 Mar 2005 21:05:01 +0000 (21:05 +0000)]
* added uml-vanilla-2.4.24.config for lustre/uml setups
adilger [Tue, 29 Mar 2005 20:33:39 +0000 (20:33 +0000)]
Branch: b1_4
Use ldlm_type_t when storing lock type.
adilger [Tue, 29 Mar 2005 20:09:03 +0000 (20:09 +0000)]
Branch: b1_4
Ignore backup series files.
jacob [Tue, 29 Mar 2005 19:05:20 +0000 (19:05 +0000)]
Fix quotes
jacob [Tue, 29 Mar 2005 18:53:37 +0000 (18:53 +0000)]
didn't mean for this to go in
jacob [Tue, 29 Mar 2005 18:51:56 +0000 (18:51 +0000)]
b=3262
r=adilger,green
Store backup servers in the config logs on the mds, and try them
round-robin style when recovering
ported from b_cray, originally by eric mei.
adilger [Tue, 29 Mar 2005 13:03:33 +0000 (13:03 +0000)]
Branch: b1_4
Don't re-add a lock being destroyed to the waiting locks list.
Debugging (that doesn't panic system) in case this happens again.
b=5653
r=phil
buffalo-pull [Tue, 29 Mar 2005 09:08:01 +0000 (09:08 +0000)]
Enable SMFS build.
Include /usr/sbin/l_getgroups in the RPM.
yury [Tue, 29 Mar 2005 08:45:22 +0000 (08:45 +0000)]
- update from HEAD.
buffalo-pull [Tue, 29 Mar 2005 08:14:23 +0000 (08:14 +0000)]
Need to include smfs_api.h in the distributed sources (i.e. make dist).
buffalo-pull [Tue, 29 Mar 2005 08:09:33 +0000 (08:09 +0000)]
HEAD is now at 1.7.0. Mostly cosmetic for building RPMS and so forth.
buffalo-pull [Tue, 29 Mar 2005 07:49:57 +0000 (07:49 +0000)]
Fix needed so make dist works again.
alex [Tue, 29 Mar 2005 07:09:20 +0000 (07:09 +0000)]
get rid of old wrong patch
jacob [Tue, 29 Mar 2005 06:41:04 +0000 (06:41 +0000)]
update wiretest for MDS_SET_INFO. without the noise, this amounts to:
- LASSERTF(MDS_LAST_OPC == 46, " found %lld\n",
+ LASSERTF(MDS_SET_INFO == 46, " found %lld\n",
+ (long long)MDS_SET_INFO);
+ LASSERTF(MDS_LAST_OPC == 47, " found %lld\n",
jacob [Tue, 29 Mar 2005 06:34:29 +0000 (06:34 +0000)]
r=adilger
r=phil
include the version of the actual compiler we were compiled with.
adilger [Tue, 29 Mar 2005 06:32:09 +0000 (06:32 +0000)]
Branch: b1_4
Ignore writemany binary.
adilger [Tue, 29 Mar 2005 06:24:00 +0000 (06:24 +0000)]
Branch: b1_4
Remove scripts duplicated in build/
r=jacob
green [Tue, 29 Mar 2005 06:00:51 +0000 (06:00 +0000)]
b1_4_quotaoff needs same portals as b1_4 too
jacob [Tue, 29 Mar 2005 05:27:18 +0000 (05:27 +0000)]
r=phil
remove unused files.
jacob [Tue, 29 Mar 2005 05:02:16 +0000 (05:02 +0000)]
Clean out this change in my tree; don't install the liblustre file.
jacob [Tue, 29 Mar 2005 04:55:56 +0000 (04:55 +0000)]
r=phil
these haven't been used in years and years.
phil [Tue, 29 Mar 2005 04:34:02 +0000 (04:34 +0000)]
b=4952
A plurality of Makefiles led me astray; super.c isn't compiled into 2.6 builds
at all, so lustre_remount_fs needs to be in llite_lib.c
lwang [Tue, 29 Mar 2005 03:15:08 +0000 (03:15 +0000)]
Update lwizard man page on how to use multinet
zhaoqiang [Tue, 29 Mar 2005 03:00:34 +0000 (03:00 +0000)]
Changelog:
- fill lib_qry_user()
- define ptl_netid_t
lwang [Tue, 29 Mar 2005 02:59:37 +0000 (02:59 +0000)]
lwizard supports multi-net
nathan [Mon, 28 Mar 2005 23:05:35 +0000 (23:05 +0000)]
try to clean up all lov/mds llogs, even if first on fails
phil [Mon, 28 Mar 2005 20:28:11 +0000 (20:28 +0000)]
b=4952
r=adilger
Protocol change! This commit breaks wire protocol compatibility.
connect messages now exchange another buffer, which currently contains only
flags. This is used to implement read-only mounting, but will be used to fix
other issues as well.
The flags are exchanged with the MDT and OST, but currently only the MDT pays
any attention to them. The places that check the disk are carefuly to check
the export for its read-only status. Having this flag in the export gives us
the opportunity to also set it when the client doesn't request it, to force
read-only mounts as a security policy.
This commit also adds remount_fs method, which can make use of mdc_set_info to
change the rw/ro status at remount-time. And osc_set_info should follow.
wangchao [Mon, 28 Mar 2005 06:22:02 +0000 (06:22 +0000)]
the basic code/patch for remote permission, including the fix for
defects 36-40 (because b_hd_acl was always not ready on b_hd_remote_uid,
the fix of the defects were on local).
d = 36-40
adilger [Sat, 26 Mar 2005 08:27:13 +0000 (08:27 +0000)]
Branch: b1_4
Fix regression caught by e2fsck - we weren't unlinking empty directories
if they were renamed-over by another directory. This is impossible to
do with a shell, as it will move the source dir INTO the target instead
of OVER the target.
b=5953
adilger [Sat, 26 Mar 2005 06:36:41 +0000 (06:36 +0000)]
Branch: b1_4
Quiet grant messages until we have CONNECT messages to fix bug 3273.
b=5983
phil [Sat, 26 Mar 2005 05:23:00 +0000 (05:23 +0000)]
changelog entry for 5981
phil [Sat, 26 Mar 2005 05:08:16 +0000 (05:08 +0000)]
land b_release_1_4_1 onto b1_4
phil [Sat, 26 Mar 2005 04:38:54 +0000 (04:38 +0000)]
b=5654
r=adilger
The last little bits of cleanup for bug 5654 (from Andreas's review):
- save_valid isn't needed in ll_setattr_raw, because either the function exits
early or ia_valid gets cleared regardless
- protect i_size updates in ll_nopage and ll_ap_refresh_count
- change ll_page_matches to only match outgoing locks for real reads;
readaheads no longer match locks which are in the process of being
cancelled anyways
phil [Sat, 26 Mar 2005 04:13:11 +0000 (04:13 +0000)]
b=5981
r=adilger
SetPageDirty in 2.6 is a hangman's noose made of time bombs, with which to
shoot yourself in the foot. It doesn't adjust page lists or counters, which
we now believe was almost certainly responsible for the two weeks of
mysterious "negative nr_dirty" hangs at NERSC and NOAA.
As an extra precaution, I also move the clear_page_dirty_for_io compat function
into the 2.4-only part. If configure happened to ever enable it in 2.6
somehow, it would be a similar disaster (assuming that the compile didn't
fail).
adilger [Sat, 26 Mar 2005 01:40:44 +0000 (01:40 +0000)]
Branch: b_cray
Fix liblustre test compilation because kmap is not defined (nor should it
be) for user-space NALs.
b=5878
r=gcc
adilger [Fri, 25 Mar 2005 22:51:03 +0000 (22:51 +0000)]
Branch: b1_4
The compatibility macro for cpu_online() had reversed parameters.
b=5929
r=fergal (original patch)
nathan [Fri, 25 Mar 2005 22:16:41 +0000 (22:16 +0000)]
b=5903
minor fix for 5903