Whamcloud - gitweb
adilger [Wed, 14 May 2008 21:44:41 +0000 (21:44 +0000)]
Branch b_release_1_6_5
Add more missing ChangeLog entries from b1_6.
deen [Wed, 14 May 2008 21:20:53 +0000 (21:20 +0000)]
Refactor start to encapsulate facet specific data.
b=12375
i=deen
i=grev
adilger [Wed, 14 May 2008 21:08:28 +0000 (21:08 +0000)]
Branch b_release_1_6_5
Add missing ChangeLog entry for minor fix.
b=15212
adilger [Tue, 13 May 2008 23:19:28 +0000 (23:19 +0000)]
Branch b_release_1_6_5
Minor typo fixes in ChangeLog.
adilger [Tue, 13 May 2008 23:03:02 +0000 (23:03 +0000)]
Branch b_release_1_6_5
Description: MDS may lose file striping (and hence file data) in some cases
Details : If there are additional extended attributes stored on the MDS,
in particular ACLs, SELinux, or user attributes (if user_xattr
is specified for the client mount options) then there is a risk
of attribute loss. Additionally, the Lustre file striping
needs to be larger than default (e.g. striped over all OSTs),
and an additional attribute must be stored initially in the
inode and then increase in size enough to be moved to the
external attribute block (e.g. ACL growing in size) for file
data to be lost.
i=kalpak.shah
b=15777
adilger [Tue, 13 May 2008 21:40:47 +0000 (21:40 +0000)]
file ext3-ea-expand-lose-block.patch was added on branch b_release_1_6_5 on 2008-05-13 23:01:58 +0000
adilger [Tue, 13 May 2008 21:40:44 +0000 (21:40 +0000)]
Branch b_release_1_6_5
Description: MDS may lose file striping (and hence file data) in some cases
Details : If there are additional extended attributes stored on the MDS,
in particular ACLs, SELinux, or user attributes (if user_xattr
is specified for the client mount options) then there is a risk
of attribute loss. Additionally, the Lustre file striping
needs to be larger than default (e.g. striped over all OSTs),
and an additional attribute must be stored initially in the
inode and then increase in size enough to be moved to the
external attribute block (e.g. ACL growing in size) for file
data to be lost.
i=kalpak.shah
b=15777
grev [Tue, 13 May 2008 18:42:05 +0000 (18:42 +0000)]
b=15745
i=Adilger
ignore rm error if TMP is on NFS
adilger [Tue, 13 May 2008 05:10:52 +0000 (05:10 +0000)]
Branch b_release_1_6_5
b=15759
Description: MDS or OSS service threads fail startup with -24 (-EMFILE)
Details : During startup under recovery, it is possible for service
thread startup to fail in ptlrpc_start_threads() if one
of the threads begins processing a request and then starts
an additional thread. This causes ptlrpc_start_threads()
to try and start 1 too many threads and get an error.
i=robert.read
i=oleg.drokin
adilger [Mon, 12 May 2008 18:52:50 +0000 (18:52 +0000)]
Branch b_release_1_6_5
Description: MDT cannot be unmounted, reporting "Mount still busy"
Details : Mountpoint references were being leaked during open reply
reconstruction after an MDS restart. Drop mountpoint reference
in reconstruct_open() and free dentry reference also.
i=oleg.drokin
b=13380
bwzhou [Sun, 11 May 2008 11:02:45 +0000 (11:02 +0000)]
Branch b_release_1_6_5
b=15521
r=adilger, grev
the test case for bug 15521
walter [Fri, 9 May 2008 19:35:57 +0000 (19:35 +0000)]
b=15732
i=adilger
land attachment 16772 - fixes for misc new catamount build warnings
which are getting treated as errors
stinson1947 [Fri, 9 May 2008 16:34:35 +0000 (16:34 +0000)]
Added OFED 1.3 support statement.
adilger [Fri, 9 May 2008 09:12:12 +0000 (09:12 +0000)]
Branch b_release_1_6_5
Reinitialize optind to 0 on each lfs_* call, in case lfs is being used
interactively. Most lfs_* functions do this already, but a few (find,
setstripe, quotachown) do not.
b=15212
i=rupesh (kalpak original patch)
i=johann
grev [Fri, 9 May 2008 07:58:33 +0000 (07:58 +0000)]
b=15660
i=Adilger
disable LIBLUSTRE test for NETTYPE != tcp
adilger [Thu, 8 May 2008 18:30:21 +0000 (18:30 +0000)]
Branch b_release_1_6_5
Fix compile warning for XT3.
b=15732
i=robert.read
brian [Thu, 8 May 2008 14:01:15 +0000 (14:01 +0000)]
b=15316
i=cliffw
i=wangyb
Forgot that b_release_* branches branch all modules and erroneously
omitted the lnet portion of the patch.
brian [Wed, 7 May 2008 21:30:40 +0000 (21:30 +0000)]
b=15316
i=cliffw
i=wangyb
Build OFED 1.3's kernel-ib and kernel-ib-devel with our patched lustre
server kernel for RHEL 4 and 5 and SLES 10. SLES 9 is not supported by
OFED 1.3.
Since OFED 1.3 provides a newer open-iscsi stack, prefer those modules
from the kernel-ib over those provided by the vendor kernels.
Additionally, build Lustre with o2iblnd support.
adilger [Wed, 7 May 2008 20:41:16 +0000 (20:41 +0000)]
Branch: b_release_1_6_5
Prefix the XID in requestor messages with "x" to match changes on the server
side.
b=13537
walter [Wed, 7 May 2008 18:54:15 +0000 (18:54 +0000)]
b=14091
i=he.huang
i=adilger
fix for build errors on Cray catamount builds
walter [Wed, 7 May 2008 18:52:37 +0000 (18:52 +0000)]
b=14091
i=he.huang
i=adilger
fix for user-tcpip.c build errors on Cray catamount builds
isaac [Mon, 5 May 2008 20:27:41 +0000 (20:27 +0000)]
b=15712
i=adilger, i=liangzhen:
Backout patch of b13983, checking and updating ksnp_proto and
adding conn to ksnp_conns should always happen atomically, keep
extra reference count of socket during establishing of connection.
johann [Fri, 2 May 2008 20:24:28 +0000 (20:24 +0000)]
Branch b_release_1_6_5
b=15517
i=johann
i=umka
Fix compile warnings on i686.
johann [Fri, 2 May 2008 19:40:15 +0000 (19:40 +0000)]
Branch b_release_1_6_5
b=15069
i=rread
i=wangdi
remove LASSERT in ptlrpc_invalidate_import() since ping req can be queued even
imp_invalid is set. See also bug 15716.
johann [Fri, 2 May 2008 19:18:00 +0000 (19:18 +0000)]
Branch b_release_1_6_5
b=15069
i=rread
i=wangdi
Skip the "sleep until imp_inflight == 0" part when invalidating an mgc import
which is already invalid.
johann [Fri, 2 May 2008 18:45:35 +0000 (18:45 +0000)]
Branch b_release_1_6_5
b=13904
i=johann
i=tianzy
Quota data should not be stored in a 32-bit variable. Use __u64 instead.
deen [Wed, 30 Apr 2008 20:57:42 +0000 (20:57 +0000)]
Don't disable LIBLUSTRE_POSIX_ACL if --disable-liblustre given and
don't build wiretest with build utils.
b=15642
i=adilger
i=shadow
fanyong [Wed, 30 Apr 2008 17:27:50 +0000 (17:27 +0000)]
Branch b_release_1_6_5
b=15691
i=huanghua
i=tappro
1) Prevent "ll_sa_wrong" from being increased repeatedly when hit ratio is low.
2) Remount client before sanity 123a to eliminate previous test effect.
ericm [Wed, 30 Apr 2008 17:19:03 +0000 (17:19 +0000)]
branch: b_release_1_6_5
set msghdr flags right before rpc sent out.
b=15487
r=rread
r=shadow
bobijam [Wed, 30 Apr 2008 01:49:30 +0000 (01:49 +0000)]
Branch b_release_1_6_5
b=14995
i=wangdi, rread
send activate event only for evicted imports.
walter [Tue, 29 Apr 2008 22:45:31 +0000 (22:45 +0000)]
b=13539
i=johann
i=adilger
fix for configure: WARNING: linux/random.h: present but cannot be compiled
walter [Tue, 29 Apr 2008 16:28:52 +0000 (16:28 +0000)]
b=15689
i=johann
i=alexey.lyashkov
fix error building lustre/liblustre/tests for Cray XT3 catamount
fanyong [Tue, 29 Apr 2008 09:40:48 +0000 (09:40 +0000)]
Branch b_release_1_6_5
b=15406
Add ChangeLog entry.
anserper [Mon, 28 Apr 2008 21:28:49 +0000 (21:28 +0000)]
Branch b_release_1_6_5
b=15441
i=johann
i=tianzy
removed quota accounting from quota files to avoid deadlocks
brian [Mon, 28 Apr 2008 19:43:35 +0000 (19:43 +0000)]
b=15316,13969
ChangeLog entries.
johann [Mon, 28 Apr 2008 16:15:07 +0000 (16:15 +0000)]
Branch b_release_1_6_5
b=14036
Fix changelog entry (was under the 1.6.0 section whereas it has been
fixed in 1.6.5).
bobijam [Mon, 28 Apr 2008 02:06:05 +0000 (02:06 +0000)]
Branch b_release_1_6_5
b=14803
i=johann, adilger
Description: Don't update lov_desc members until making sure they are valid
Details : When updating lov_desc members via proc fs, need fix their
validities before doing the real update.
cvs2svn [Sun, 27 Apr 2008 01:54:17 +0000 (01:54 +0000)]
This commit was manufactured by cvs2svn to create branch 'b_release_1_6_5'.
stinson1947 [Sun, 27 Apr 2008 01:54:16 +0000 (01:54 +0000)]
Added date for 1.6.5 release.
stinson1947 [Sun, 27 Apr 2008 01:53:11 +0000 (01:53 +0000)]
Added date for the 1.6.5 release.
stinson1947 [Sun, 27 Apr 2008 01:51:13 +0000 (01:51 +0000)]
Changed version numbers for 1.6.5.
stinson1947 [Sun, 27 Apr 2008 01:48:47 +0000 (01:48 +0000)]
Added date for the 1.6.5 release.
fanyong [Sat, 26 Apr 2008 14:30:54 +0000 (14:30 +0000)]
Branch b1_6
b=15658
i=huanghua
i=tappro
Support directory read ahead under patchless client mode.
When "ls" a dentry, the system trigger more than once "revalidate" or
"lookup", for "getattr", for "getxattr", and maybe for others.
Under patchless client mode, the operation intent is not accurate,
it maybe misguide the statahead thread. For example:
The "revalidate" call for "getattr" and "getxattr" of a dentry maybe
have the same operation intent -- "IT_GETATTR".
In fact, one dentry should has only one chance to interact with the
statahead thread, otherwise the statahead windows will be confused.
deen [Sat, 26 Apr 2008 12:39:55 +0000 (12:39 +0000)]
It is be possible to send the lock handle along with each read
or write request because the client is already doing a lock match
itself so there isn't any reason the OST should have to re-do that
search.
b=15198
i=adilger
i=shadow
walter [Sat, 26 Apr 2008 02:25:09 +0000 (02:25 +0000)]
b=15277
i=adilger
i=rread
fixes error linking lustre/liblustre/tests/echo_test during catamount
build of b1_6 for Cray XT3 systems
walter [Sat, 26 Apr 2008 02:23:43 +0000 (02:23 +0000)]
b=15277
i=adilger
i=rread
fixes error linking lustre/liblustre/tests/echo_test
during catamount build of b1_6 for Cray XT3 systems
adilger [Sat, 26 Apr 2008 00:10:33 +0000 (00:10 +0000)]
Branch b1_6
Clarify instructions.
adilger [Sat, 26 Apr 2008 00:08:57 +0000 (00:08 +0000)]
Branch b1_6
Fix line wrap.
adilger [Fri, 25 Apr 2008 23:22:02 +0000 (23:22 +0000)]
Branch b1_6
Minor cleanup.
brian [Fri, 25 Apr 2008 22:48:33 +0000 (22:48 +0000)]
b=15316
i=cliffw
i=wangyb
Build OFED 1.3's kernel-ib and kernel-ib-devel with our patched lustre
server kernel for RHEL 4 and 5 and SLES 10. SLES 9 is not supported by
OFED 1.3.
Since OFED 1.3 provides a newer open-iscsi stack, prefer those modules
from the kernel-ib over those provided by the vendor kernels.
Additionally, build Lustre with o2iblnd support.
brian [Fri, 25 Apr 2008 21:51:22 +0000 (21:51 +0000)]
b=15316
i=cliffw
i=wangyb
Build OFED 1.3's kernel-ib and kernel-ib-devel with our patched lustre
server kernel for RHEL 4 and 5 and SLES 10. SLES 9 is not supported by
OFED 1.3.
Since OFED 1.3 provides a newer open-iscsi stack, prefer those modules
from the kernel-ib over those provided by the vendor kernels.
Additionally, build Lustre with o2iblnd support.
brian [Fri, 25 Apr 2008 21:51:07 +0000 (21:51 +0000)]
b=15316
i=cliffw
i=wangyb
Build OFED 1.3's kernel-ib and kernel-ib-devel with our patched lustre
server kernel for RHEL 4 and 5 and SLES 10. SLES 9 is not supported by
OFED 1.3.
Since OFED 1.3 provides a newer open-iscsi stack, prefer those modules
from the kernel-ib over those provided by the vendor kernels.
Additionally, build Lustre with o2iblnd support.
walter [Fri, 25 Apr 2008 19:32:13 +0000 (19:32 +0000)]
b=14609
i=grev
fix for test_16 failure due to trying to create mntpt dir on Read-Only fs.
walter [Fri, 25 Apr 2008 19:31:09 +0000 (19:31 +0000)]
b=14609
i=grev
fix for test_16 failure due to trying to create mntpt dir on Read-Only fs.
walter [Fri, 25 Apr 2008 19:23:10 +0000 (19:23 +0000)]
b=15670
i=adilger
i=johann
land attachment 16523
fixes this compile warning (which is treated as an error -Werror on XT3's):
during lustrefs-1.6-ss builds:
lustrefs-1.6-ss/lustre/mds/mds_lov.c: In function `mds_lov_read_objids':
mds_lov.c:198: warning: int format, different type arg (arg 10)
walter [Fri, 25 Apr 2008 19:22:30 +0000 (19:22 +0000)]
b=15670
i=adilger
i=johann
land attachment 16523
fixes this compile warning (which is treated as an error -Werror on XT3's):
during lustrefs-1.6-ss builds:
lustrefs-1.6-ss/lustre/mds/mds_lov.c: In function `mds_lov_read_objids':
mds_lov.c:198: warning: int format, different type arg (arg 10)
johann [Fri, 25 Apr 2008 17:42:29 +0000 (17:42 +0000)]
Branch b1_6
b=14909
i=tianzy
use cancel_lru_locks instead of "sync; sleep 1; sync" in sanity-quota.sh.
johann [Fri, 25 Apr 2008 14:45:45 +0000 (14:45 +0000)]
Branch HEAD
b=14410
i=bzzz
i=kalpak
Force q->max_phys_segments to MAX_PHYS_SEGMENTS on SLES10 to be
sure that 1MB requests are not fragmented by the block layer.
johann [Fri, 25 Apr 2008 14:38:30 +0000 (14:38 +0000)]
Branch b1_6
b=14410
i=bzzz
i=kalpak
Force q->max_phys_segments to MAX_PHYS_SEGMENTS on SLES10 to be
sure that 1MB requests are not fragmented by the block layer.
walter [Fri, 25 Apr 2008 14:01:16 +0000 (14:01 +0000)]
b=13539
i=adilger
i=rread
add linux/random.h to AC_CHECK_HEADERS
add #if defined(HAVE_LINUX_RANDOM_H) to lustre/lvfs/prng.c
walter [Fri, 25 Apr 2008 14:00:05 +0000 (14:00 +0000)]
b=13539
i=adilger
i=rread
add linux/random.h to AC_CHECK_HEADERS
add #if defined(HAVE_LINUX_RANDOM_H) to lustre/lvfs/prng.c
mattwu [Fri, 25 Apr 2008 08:58:07 +0000 (08:58 +0000)]
windows porting: add private lnet tag to b_winnt_port branch
pravins [Thu, 24 Apr 2008 13:05:15 +0000 (13:05 +0000)]
add iam tag for umds cleanup branch, required for dynlock changes.
shadow [Thu, 24 Apr 2008 11:54:19 +0000 (11:54 +0000)]
don't put request into delay list while invalidate in flight.
normalize imp_infligh calculation.
b=15069
i=johann
i=rread
shadow [Thu, 24 Apr 2008 11:14:25 +0000 (11:14 +0000)]
don't put request into delay list while invalidate in flight.
restore generation check.
b=15069
i=johan
i=rread
shadow [Thu, 24 Apr 2008 08:48:03 +0000 (08:48 +0000)]
fix typo
shadow [Thu, 24 Apr 2008 08:28:16 +0000 (08:28 +0000)]
use more correctly detect RHEL/SLES kernels.
b=15511
i=Yang Sheng
yangsheng [Thu, 24 Apr 2008 08:23:14 +0000 (08:23 +0000)]
Branch HEAD
b=15240
i=adilger
Remove the RHEL4 comment in ChangeLog.
shadow [Thu, 24 Apr 2008 08:18:23 +0000 (08:18 +0000)]
use right detect for RHEL/SLES kernels.
b=15511
i=Yang Sheng
yangsheng [Thu, 24 Apr 2008 08:15:57 +0000 (08:15 +0000)]
Branch b1_6
b=15416
i=shadow, johann
Update kernel for SLES9 2.6.5-7.311.
yangsheng [Thu, 24 Apr 2008 08:08:48 +0000 (08:08 +0000)]
Branch b1_6
b=15240
i=shadow, green
Update to RHEL4 latest kernel.
shadow [Thu, 24 Apr 2008 07:07:59 +0000 (07:07 +0000)]
use generic CFS_LIST_HEAD macro instead of LIST_HEAD.
b=14929
i=zam
shadow [Thu, 24 Apr 2008 06:48:33 +0000 (06:48 +0000)]
use generic LIST_HEAD macros instead of linux specific.
b=14929
i=zam
green [Thu, 24 Apr 2008 05:58:37 +0000 (05:58 +0000)]
b=14712
r=vitaly,shadow
Do not free request that we do not have refcount on on open error
fanyong [Thu, 24 Apr 2008 04:41:11 +0000 (04:41 +0000)]
Branch b1_6
b=15406
i=huanghua
i=tappro
i=vitaly
Back port dir_SA fixes from HEAD (b1_8_dir_ra) to b1_6.
adilger [Thu, 24 Apr 2008 02:44:05 +0000 (02:44 +0000)]
Branch HEAD
Document the maximum filesystem name length.
b=15486
adilger [Thu, 24 Apr 2008 02:43:04 +0000 (02:43 +0000)]
Branch b1_6
Document the maximum filesysyem name length.
b=15486
bobijam [Thu, 24 Apr 2008 01:18:19 +0000 (01:18 +0000)]
Branch HEAD
b=15191
i=wangdi, shadow
during liblustre test during
mgc_llog_init() (lustre/mgc/libmgc.c)
llog_initiator_connect(ctxt)
while in liblustre lib, it is defined as an empty function only return 0, while
in kernel lib, it set the context's loc_imp. And this context's loc_imp is
required after in llog_client_create().
This fix defines llog_initiator_connect() in both lib (kernel version and
liblustre version)
ericm [Wed, 23 Apr 2008 18:00:48 +0000 (18:00 +0000)]
branch: b1_6
reset AT flag on reconnects.
a=nathan (original author)
b=15487
r=rread
r=ericm
yangsheng [Wed, 23 Apr 2008 13:26:03 +0000 (13:26 +0000)]
Branch HEAD
b=14714
i=adilger, johann
Fixed previous error.
yangsheng [Wed, 23 Apr 2008 13:24:40 +0000 (13:24 +0000)]
Branch b1_6
b=14714
i=adilger, johann
Fixed previous error.
yangsheng [Wed, 23 Apr 2008 03:52:19 +0000 (03:52 +0000)]
Branch HEAD
b=14576
i=shadow, nikita
Add own nr_free_buffer_pages() function when it wasn't exported.
isaac [Tue, 22 Apr 2008 20:03:46 +0000 (20:03 +0000)]
- removed trailing spaces.
grev [Tue, 22 Apr 2008 18:41:56 +0000 (18:41 +0000)]
b=15348
i=Scjody
check the .dat file correctness;
use the correct threads and regions values;
skip the first line of summary file in the format check
shadow [Tue, 22 Apr 2008 11:42:40 +0000 (11:42 +0000)]
not swab ost objects for directory because it's not exist.
b=14856
i=green
i=johan
shadow [Tue, 22 Apr 2008 11:39:53 +0000 (11:39 +0000)]
not swab ost objects for directory because it's not exist.
b=14856
i=green
i=johan
deen [Tue, 22 Apr 2008 08:18:45 +0000 (08:18 +0000)]
Set proper locale when generating wiretest.c.
b=15566
deen [Tue, 22 Apr 2008 07:53:33 +0000 (07:53 +0000)]
Update wirecheck.c/wirehdr.c and regenerate wiretest.c
b=15566
i=adilger
i=shadow
grev [Mon, 21 Apr 2008 19:42:37 +0000 (19:42 +0000)]
b=15273
i=Adilger
skip test_37 if CLIENTMODSONLY is set
grev [Mon, 21 Apr 2008 18:05:49 +0000 (18:05 +0000)]
b=15273
i=Adilger
skip test_37 if CLIENTMODSONLY is set
ericm [Mon, 21 Apr 2008 17:11:38 +0000 (17:11 +0000)]
branch: b1_6
change at_max according to AT status.
b=13659
r=nathan
r=rread
r=grev
anserper [Mon, 21 Apr 2008 11:20:39 +0000 (11:20 +0000)]
Branch b1_6
b=15218
i=johann
i=tianzy
additional admin quota file update
grev [Fri, 18 Apr 2008 10:35:14 +0000 (10:35 +0000)]
b=15612
i=Adilger
force test_20a and test_20b to do write on the correct ost
grev [Fri, 18 Apr 2008 10:32:52 +0000 (10:32 +0000)]
b=15612
i=Adilger
force test_20a and test_20b to do write on the correct ost
shadow [Fri, 18 Apr 2008 10:20:04 +0000 (10:20 +0000)]
fix warining with build on sles10/rhel5.
b=15517
i=johan
i=deen
shadow [Fri, 18 Apr 2008 10:05:16 +0000 (10:05 +0000)]
attach obd_cksum.h to build
shadow [Fri, 18 Apr 2008 09:45:38 +0000 (09:45 +0000)]
Fix warnings with compile liblustre at sles10/rhel5 which have
__u64 as usingied long long type.
b=15517
i=johan
i=deen
shadow [Fri, 18 Apr 2008 09:45:32 +0000 (09:45 +0000)]
Fix warnings with compile liblustre at sles10/rhel5 which have
__u64 as usingied long long type.
b=15517
i=johan
i=deen
shadow [Fri, 18 Apr 2008 07:16:30 +0000 (07:16 +0000)]
removing callback before disconnect import is open race with processing
callback.
b=15210
i=green
i=deen
shadow [Fri, 18 Apr 2008 06:53:17 +0000 (06:53 +0000)]
use one place for syscall.h
sys/syscall.h exist at all os'es instead of <syscall.h> which exist only
at linux.
b=14929
i=nikita