Whamcloud - gitweb
fs/lustre-release.git
8 years agoLU-427 test: Test failure on test suite lfsck
yangsheng [Thu, 4 Aug 2011 03:36:23 +0000 (11:36 +0800)]
LU-427 test: Test failure on test suite lfsck

- Reset $MDSDB & $OSTDB in generate_db(). Else they will
  stale if user redefine $SHARED_DIRECTORY.
- Add a function check_shared_dir() to ensure
  $SHARED_DIRECTORY is shared among tests nodes.

Change-Id: Idf2a3d75e46c4cf768419adfea627511c24c495c
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1180
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-883 ldiskfs: drop unused diagnostic information
Fan Yong [Tue, 31 Jan 2012 07:26:31 +0000 (15:26 +0800)]
LU-883 ldiskfs: drop unused diagnostic information

The debug informatin was introduced for diagnosing readonly
issues for bug 16680. It is unused any longer and makes the
console output some noisy. So drop.

Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Change-Id: If950654d6517f317809bb0de1446e2377a524c77
Reviewed-on: http://review.whamcloud.com/2068
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Bobi Jam <bobijam@whamcloud.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-971 mdt: fix open resent issue with last_xid
Mikhail Pershin [Mon, 9 Jan 2012 13:46:10 +0000 (17:46 +0400)]
LU-971 mdt: fix open resent issue with last_xid

req_xid_is_last() compares xid with one in client data,
but in master it is not updated in case of open without create.
Patch updates export lcd with last xid, transno and rc for open
requests.

Signed-off-by: Mikhail Pershin <tappro@whamcloud.com>
Change-Id: I9e769fecc1e93c7a556d4b9eeadc80a70369e901
Reviewed-on: http://review.whamcloud.com/1930
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Reviewed-by: Li Wei <liwei@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1049 script: lc_net doesn't parse output correctly
Minh Diep [Tue, 31 Jan 2012 00:39:43 +0000 (16:39 -0800)]
LU-1049 script: lc_net doesn't parse output correctly

Port the second fix from bz=23234
The output of ping contains two ip addresses. The regex
matching picks up both addresses. The fix is to add
-m 1 to stop at the first match
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: Ie145e710844d80587bf6826822c8db941a4a3bae
Reviewed-on: http://review.whamcloud.com/2057
Reviewed-by: Cliff White <cliffw@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-601 mdd: cleanup error messages and code style
Andreas Dilger [Wed, 9 Nov 2011 20:06:30 +0000 (13:06 -0700)]
LU-601 mdd: cleanup error messages and code style

While looking at LU-601, I added comment blocks for several of
the functions in the PENDING directory cleanup path, along with
fixes to the code style and error messages.  No functional changes
should be introduced by this code change.

The error message that was formerly printed by the 1.8 MDS in
mds_unlink_orphan() and checked by replay-single.sh test_37 no
longer exists in the 2.x MDS code.  Re-add a message if there
is an error cleaning up directory orphans, and change test_37
to match the resulting error message (similar to the 1.8 code).

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ic97843e49643041513f3b2fc6a40f2be63ffddca
Reviewed-on: http://review.whamcloud.com/1679
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1091 fix the tag matching code in configure
Brian J. Murrell [Fri, 10 Feb 2012 20:27:04 +0000 (15:27 -0500)]
LU-1091 fix the tag matching code in configure

Signed-off-by: Brian J. Murrell <brian@whamcloud.com>
Change-Id: I24dd4d0929364a2012afe725586626328ea584c0
Reviewed-on: http://review.whamcloud.com/2131
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1095 mgs: remove message from console
Christopher J. Morrone [Fri, 10 Feb 2012 23:24:06 +0000 (15:24 -0800)]
LU-1095 mgs: remove message from console

There is no good reason for a sysadmin to see this message
on the console.  Most of the time this will be a fluke
due to the vagarities of lnet networks (server decides
client is disconnected, but client doesn't know that yet,
messages arriving out of order, etc.).

Signed-off-by: Christopher J. Morrone <morrone2@llnl.gov>
Change-Id: I0c18734f82a9c89a5e940ce4e2c602614e89ce26
Reviewed-on: http://review.whamcloud.com/2133
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-709 build: LC_XATTR_ACL & LC_POSIX_ACL_XATTR_H cleanup
yangsheng [Tue, 6 Dec 2011 21:24:59 +0000 (05:24 +0800)]
LU-709 build: LC_XATTR_ACL & LC_POSIX_ACL_XATTR_H cleanup

xattr_acl.h removed since 2.6.13 and posix_acl_xattr.h
exist since 2.6.11. So just use posix_acl_xattr.h for now.
And removed relate codes.

Change-Id: Ibefd4db87fa79ec9ee6365d48c83abd0dda0e063
Signed-off-by: yangsheng <ys@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1916
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1077 distribute missing file in build/autoconf
Brian J. Murrell [Tue, 7 Feb 2012 22:15:53 +0000 (17:15 -0500)]
LU-1077 distribute missing file in build/autoconf

In landing 0d5cf708f60c1ed9233fd12f4326851ab412ef6a for ticket
LU-723 a defect was introduced where
build/autoconf/lustre-build-ldiskfs.m4 is missing from the
distribution tarball.

Signed-off-by: Brian J. Murrell <brian@whamcloud.com>
Change-Id: I34a1d7ad20229fb531eb4e76182647e708b300d4
Reviewed-on: http://review.whamcloud.com/2115
Tested-by: Hudson
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Prakash Surya <surya1@llnl.gov>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1029 build: build ofed 1.5.4 with qlgc_vnic failed
Minh Diep [Tue, 7 Feb 2012 15:53:09 +0000 (07:53 -0800)]
LU-1029 build: build ofed 1.5.4 with qlgc_vnic failed

Ofed failed to include proper header files to support
qlgc_vnic. Since we are not using ib on vnic in the lab,
we'll remove it

Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: Ibce110b44940fda5f13abab890f3e9176f55b9d2
Reviewed-on: http://review.whamcloud.com/2110
Tested-by: Hudson
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Reviewed-by: Michael MacDonald <mjmac@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-915 tests: MKFSOPTS fix for test suite
James Simmons [Thu, 12 Jan 2012 15:00:06 +0000 (10:00 -0500)]
LU-915 tests: MKFSOPTS fix for test suite

While testing LU-80 I had to provide my own MKFSOPT string
for the mkfsoptions in local.sh. In the conf-sanity test
the MKFSOPT provided were totally replaced by a new MKFSOPT
that contained only lazy_itable_init. This prevented me from
running any conf-sanity test bacause I couldn't format the
MDS. This patch instead appends lazy_itable_init to the
mkfsoptions string if it already exist.

Change-Id: If30d2a692431dcdb3631fc9c1e77da5ff2792881
Signed-off-by: James Simmons <uja.ornl@gmail.com>
Reviewed-on: http://review.whamcloud.com/1830
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: Cliff White <cliffw@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoRevert "LU-1013 obdclass: lu_object_find miss to unlink object from LRU"
Oleg Drokin [Wed, 15 Feb 2012 18:41:03 +0000 (13:41 -0500)]
Revert "LU-1013 obdclass: lu_object_find miss to unlink object from LRU"

Reverting because in fact it overlaps with LU-1017

This reverts commit b9ccecd1453c5c76fe135048c39f149c241650c6.

Signed-off-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-966 mdd: revert commit and use original patch
Mikhail Pershin [Wed, 15 Feb 2012 08:39:53 +0000 (12:39 +0400)]
LU-966 mdd: revert commit and use original patch

Use original patch which replaces LASSERT with CERROR in MDD,
because checking object exists in MDT ruins VBR recovery.
It happens too early but VBR should check that too before reply
to the client.

Signed-off-by: Mikhail Pershin <tappro@whamcloud.com>
Change-Id: If31586c9d1cc86c4c8059a7227c231acdc82a0f1
Reviewed-on: http://review.whamcloud.com/2148
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Bobi Jam <bobijam@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Tested-by: Yu Jian <yujian@whamcloud.com>
8 years agoLU-889 recovery: rework extend_recovery_timer()
Jinshan Xiong [Wed, 25 Jan 2012 06:15:59 +0000 (22:15 -0800)]
LU-889 recovery: rework extend_recovery_timer()

Commit 8da33c6cc5192303fcd18f45892e1f115004e662 is buggy where
the time used to rearm the timer is wrong. In this patch, I
will reset all changes and use the same scheme as 2.1 release.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: Icd887687262644e1a1cfffd6f34eacc5bc418f84
Reviewed-on: http://review.whamcloud.com/1722
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Mike Pershin <tappro@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1059 clio: to not try to discard freeing pages
Jinshan Xiong [Tue, 31 Jan 2012 21:30:21 +0000 (13:30 -0800)]
LU-1059 clio: to not try to discard freeing pages

This is a bug imported in LU-948. We should check if we have owned
the page successfully before trying to discard it.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: I30631be98f1fcc1b98abe727c8c6984b918bfffd
Reviewed-on: http://review.whamcloud.com/2073
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-969 debug: reduce stack usage
Hongchao Zhang [Thu, 5 Jan 2012 21:28:51 +0000 (05:28 +0800)]
LU-969 debug: reduce stack usage

in ptlrpc_main, move struct lu_env to heap to save stack
in mdt_open.c, declare functions non-static to prevent inlining

Change-Id: I73c703c79b0539dc40036a5f9b131507adaff662
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Hongchao Zhang <hongchao.zhang@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/2070
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-1042 obdfilter: initialize new object timestamp
Andreas Dilger [Fri, 27 Jan 2012 21:12:06 +0000 (14:12 -0700)]
LU-1042 obdfilter: initialize new object timestamp

Initialize newly-created objects with a/m/ctime = 0, so that however
clients modify the timestamp it will be updated the first time.  The
fsfilt_ext3_setattr() code will special case ctime = 0 for new files
and reset them to the ext4 s_mkfs_time stored in the superblock.

In LU-221 (commit 414251797ed178eec5d431e1f5aa4a889d2b159f) the
timestamps were initialized to (INT_MIN + 24 * 3600) (1901-12-14),
but the use of unsigned on-disk timestamps caused these negative
numbers to be transformed into large positive numbers (debugfs
reports them to be "Tue Jan 19 20:14:08 2038").  Add a fix so that
files with this exact timestamp have the timestamp reset to 0.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I22f2cd443402c0c524bafaf37c80cad7b6d00c1e
Reviewed-on: http://review.whamcloud.com/2036
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-797 tests: skip ost-pools.sh 23b when SLOW=no
Andreas Dilger [Fri, 3 Feb 2012 22:27:40 +0000 (15:27 -0700)]
LU-797 tests: skip ost-pools.sh 23b when SLOW=no

Running test_23b can take over 30 minutes, and should not be run on a
large LUN inside a VM.  Print out some of the constants that determine
whether the test is run or not, for debugging purposes.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I7491002276e36994be4baf30a731576c8ced7530
Reviewed-on: http://review.whamcloud.com/2091
Tested-by: Hudson
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-963 build: update Lustre ChangeLog
Niu Yawei [Tue, 14 Feb 2012 02:21:57 +0000 (18:21 -0800)]
LU-963 build: update Lustre ChangeLog

Update the recommended e2fsprogs version to 1.41.90.wc4 for 2.2.

Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: I5516a0c228cca4aa36c68cc299d0127c9c6f5325
Reviewed-on: http://review.whamcloud.com/2140
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1055 remove improper assert in osd_declare_object_destroy
Niu Yawei [Fri, 3 Feb 2012 07:44:24 +0000 (23:44 -0800)]
LU-1055 remove improper assert in osd_declare_object_destroy

After recovery, orphan cleanup could race with the client unlink on
close, so the LASSERT on lu_object_is_dying() should be moved from
declare stage into the real destroy function.

Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: Ibc4ad0613d907ab98b653d5a64ce54e1f018dcb2
Reviewed-on: http://review.whamcloud.com/2083
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 tests: modprobe exportfs for fsfilt_ldiskfs
Andreas Dilger [Mon, 23 Jan 2012 22:17:55 +0000 (15:17 -0700)]
LU-506 tests: modprobe exportfs for fsfilt_ldiskfs

When trying to load fsfilt_ldiskfs.ko from the build tree, it fails
to load due to the missing exportfs_decode_fh() symbol in RHEL6
kernels.  Force loading of the exportfs.ko module if ldiskfs is used.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Iecb13155b69ffc3a227e3df770ca590277cd500c
Reviewed-on: http://review.whamcloud.com/2014
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
8 years agoLU-1051 osd: improve quota credits calculation
Niu Yawei [Thu, 2 Feb 2012 14:32:02 +0000 (06:32 -0800)]
LU-1051 osd: improve quota credits calculation

Instead of reserving constant LDISKFS_QUOTA_INIT_BLOCKS for all kinds
of transactions, this patch tracks how many/which uid/gids are
affected in each declare function, then calculates the total quota
credits according to the affected uid/gids in osd_trans_start().

This patch also includes following credits improvement:
- For object creation, reserve less credits for the '.' and '..'
  insertion, and don't reserve for file creation;
- Only reserve the credits for oi insertion for normal fids;
- Limit the credits to j_max_transaction_buffers in the
  osd_trans_start();

Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: Ifbcc26b670c4965f22cc96ae7db16154927f32a4
Reviewed-on: http://review.whamcloud.com/2082
Tested-by: Hudson
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-985 lprocfs: verify user buffer access
Bobi Jam [Fri, 13 Jan 2012 05:46:07 +0000 (13:46 +0800)]
LU-985 lprocfs: verify user buffer access

In lprocfs_xxx_evict_client(), need verify user's buffer when access
it.

Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I702e22f8d432edce200c6d91a0af8a1eac792008
Reviewed-on: http://review.whamcloud.com/1961
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Liang Zhen <liang@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1061 agl: cl_locks_prune() waits for the last user
Fan Yong [Thu, 2 Feb 2012 11:17:41 +0000 (19:17 +0800)]
LU-1061 agl: cl_locks_prune() waits for the last user

The AGL sponsor holds user reference count on the cl_lock before
triggering AGL RPC. The user reference count on the cl_lock will
be released by AGL RPC reply upcall. Such AGL mechanism conflict
with cl_locks_prune(), which requires no lock is in active using
when the last iput() called.

So the cl_locks_prune() should wait for the last user reference
count to be released by the enqueue reply upcall.

Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Change-Id: I8998c0a247448b1b6c6e99995c9d956b1666279b
Reviewed-on: http://review.whamcloud.com/2079
Tested-by: Hudson
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1017 handle -EAGAIN properly in lu_object_find_try()
Niu Yawei [Tue, 31 Jan 2012 06:06:47 +0000 (22:06 -0800)]
LU-1017 handle -EAGAIN properly in lu_object_find_try()

htable_lookup() could return -EAGAIN for dying object, we should
handle it properly in lu_object_find_try().

Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: I616928cb983d4f64a64f25b7d296b6c9bd18e4ea
Reviewed-on: http://review.whamcloud.com/2066
Tested-by: Hudson
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-874 ptlrpc: handle in-flight hqreq correctly
Jinshan Xiong [Wed, 25 Jan 2012 19:27:55 +0000 (11:27 -0800)]
LU-874 ptlrpc: handle in-flight hqreq correctly

If there are in-flight requests pending, we shouldn't timeout the
covering dlm locks; neither should we remove the requests from export
exp_hp_rpcs list until the requests are handled.

In this patch, the following things are improved:
1. leave IO rpcs in export's hp list until they are handled;
2. using interval tree to find rpc overlapped locks;
3. refresh the lock again after IO rpcs are finished to leave a time
   window for clients to cancel covering dlm locks;
4. rework repbody in ost_handler.c so as to not modify original obdo
5. cleanup the code.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: I33e2d113d7929a56389741c06dffb5efb6bf28a3
Reviewed-on: http://review.whamcloud.com/1918
Tested-by: Hudson
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: <alexander_boyko@xyratex.com>
8 years agoLU-874 osc: prioritize writeback pages
Jinshan Xiong [Tue, 10 Jan 2012 07:34:06 +0000 (23:34 -0800)]
LU-874 osc: prioritize writeback pages

When a lock is being canceled, we should prioritize those covering
pages which have already been submitted by page writeback daemon;
otherwise, this client may be evicted because there is no active IO
for that lock for a long time.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: If14eff6361f55d2b2eeb2db7146789dda4c32060
Reviewed-on: http://review.whamcloud.com/1938
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1067 obdecho: Recheck client env ctx for echo md client.
wangdi [Sat, 4 Feb 2012 08:12:48 +0000 (00:12 -0800)]
LU-1067 obdecho: Recheck client env ctx for echo md client.

During echo md test, if there are real clients being mounted
at the same time, the cl env it gotten from the cache might
contain the wrong context, so we need recheck the ctx and
refill the env forcedly.

Signed-off-by: Wang Di <di.wang@whamcloud.com>
Change-Id: Iddbceee80966b5ca9284c886731386a97d089d53
Reviewed-on: http://review.whamcloud.com/2092
Tested-by: Hudson
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1073 llite: no CERROR on unknown flock type
Alexander Zarochentsev [Sat, 11 Feb 2012 07:19:31 +0000 (11:19 +0400)]
LU-1073 llite: no CERROR on unknown flock type

Xyratex-bug-id: MRP-215

Signed-off-by: Alexander Zarochentsev <alexander_zarochentsev@xyratex.com>
Change-Id: I435c3282bc87750f6ebd19e618a1ee8e229834d2
Reviewed-on: http://review.whamcloud.com/2109
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1013 obdclass: lu_object_find miss to unlink object from LRU
Fan Yong [Sat, 11 Feb 2012 01:26:29 +0000 (09:26 +0800)]
LU-1013 obdclass: lu_object_find miss to unlink object from LRU

There is race condition between lu_object_find and lu_object_put.
For the case of two threads trying to find some object with the
same FID concurrently, and the object is not allocated in memory
yet, if the first thread adds the object into LRU list before the
second thread re-searching object hash table for inserting the
new object created by itself, then the second thread will find
the object created by the first thread. Under such case, the
second thread should unlink the object from LRU.

Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Change-Id: Iadec96c27d5285f8b859b0060a6f611e87585789
Reviewed-on: http://review.whamcloud.com/2134
Tested-by: Hudson
Reviewed-by: Bobi Jam <bobijam@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-687 ldiskfs: resolve section dynlocks mismatch
Andreas Dilger [Thu, 26 Jan 2012 10:06:30 +0000 (03:06 -0700)]
LU-687 ldiskfs: resolve section dynlocks mismatch

Fix __init/__exit section mismatch.

  WARNING: lustre-2.1.0/ldiskfs/ldiskfs/ldiskfs.o(.init.text+0x1bc):
  Section mismatch in reference from the function init_module() to the
  function .exit.text:dynlock_cache_exit().  An __init init_module()
  function references a function __exit dynlock_cache_exit().

  This is often seen when error handling in the init function uses
  functionality in the exit path.  The fix is often to remove the
  __exit annotation of dynlock_cache_exit() so it may be used outside
  an exit section.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ie0bdde7f78c18bca1127151175cf56bfa6ad500c
Reviewed-on: http://review.whamcloud.com/2019
Tested-by: Hudson
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1046 ldlm: hold ldlm_cb_set_arg until the last user exit
Fan Yong [Tue, 31 Jan 2012 05:51:41 +0000 (13:51 +0800)]
LU-1046 ldlm: hold ldlm_cb_set_arg until the last user exit

There is race condition between ldlm_cb_interpret() and
ldlm_run_ast_work() when test/release "ldlm_cb_set_arg":
ldlm_run_ast_work() can exit before ldlm_cb_interpret()
processing "ldlm_cb_set_arg::waitq", then causes invalid
memory accessing.

Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Change-Id: Idfb3f41739e02a79fe4310ecbc7bb842e75a82d8
Reviewed-on: http://review.whamcloud.com/2065
Tested-by: Hudson
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-993 osd: code cleanup for directory nlink count
Niu Yawei [Mon, 16 Jan 2012 06:52:12 +0000 (22:52 -0800)]
LU-993 osd: code cleanup for directory nlink count

- LDISKFS_LINK_MAX is ldiskfs unique, we should not handle it in the mdd
  layer. It's moved down to the osd layer in this patch.

- Remove the declared operation count assertion in OSD_EXEC_OP(), since
  the undo operations are not declared, if there some operation failed,
  the undo operation will trigger the assertion unnecessarily.

- Restore the sub-directory count to 70000 for the sanity test_51b, and
  add test_51ba for testing unlink > LDISKFS_LINK_MAX sub-directories.

Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: Id02e7d2ac3a7664a55566b1de783f0a73162339b
Reviewed-on: http://review.whamcloud.com/1971
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-928 llite: fix comment for lustre_client_ocd
Andreas Dilger [Thu, 15 Dec 2011 08:24:33 +0000 (01:24 -0700)]
LU-928 llite: fix comment for lustre_client_ocd

ll_ocd_update() was renamed to cl_ocd_update() before 2.0.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I834935d2dc9ef0edebbd5badb4bc54283a325730
Reviewed-on: http://review.whamcloud.com/1868
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1053 build: allow deleted/chmod in commit-msg
Andreas Dilger [Sun, 29 Jan 2012 07:20:45 +0000 (00:20 -0700)]
LU-1053 build: allow deleted/chmod in commit-msg

Allow files that were deleted or chmod when verifying a commit
message that contains a diff generated with "commit -v".  The
checks added for excluding the diff were previously too strict.
Add a test case for each of these situations, as well as a case
for a commit message that contains "diff" at the start of a line
in the middle of a commit message.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I74fe98682342e445da7fe64fd42e91df4564500c
Reviewed-on: http://review.whamcloud.com/2053
Reviewed-by: Bruce Korb <bruce_korb@xyratex.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1025 checksum: add final bit inversion for crc32c
Alexander.Boyko [Fri, 3 Feb 2012 07:20:01 +0000 (11:20 +0400)]
LU-1025 checksum: add final bit inversion for crc32c

The linux kernel implementations of crc32c perform final bit
inversion after loop calculation of checksum.

Signed-off-by: Alexander Boyko <alexander_boyko@xyratex.com>
Change-Id: I5fa6af60c51f6f86f394f3cc71aa2672be614f7b
Reviewed-on: http://review.whamcloud.com/2018
Tested-by: Hudson
Reviewed-by: Shuichi Ihara <sihara@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-817 lustre-iokit: sgpdd-survey is encountering r/w errors on arrays using 2TB...
Shuichi Ihara [Mon, 7 Nov 2011 09:45:33 +0000 (18:45 +0900)]
LU-817 lustre-iokit: sgpdd-survey is encountering r/w errors on arrays using 2TB drives

There are two fix/improvements in sgpdd-survey.
(1) adding --lba option to sg_readcap for large LUNs.
(2) support configurable boundadry block size between
concurrent regions per device.

Signed-off-by: Shuichi Ihara <sihara@ddn.com>
Change-Id: Ib3cdb051cf55e096919ad63a42640aaacfe511c4
Reviewed-on: http://review.whamcloud.com/1658
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Cliff White <cliffw@whamcloud.com>
Reviewed-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-746 test: obdfilter-survey FAIL hndls expected >8, have 2
Lai Siyao [Fri, 4 Nov 2011 15:08:25 +0000 (08:08 -0700)]
LU-746 test: obdfilter-survey FAIL hndls expected >8, have 2

obdfilter-survey.sh checks jbd proc stats after survey, but it
doesn't take obd cleanup time into account, so the stats collected
may not reflect the data of test. To fix this, save run time of
survey test, and collect stats of (run_time/4) ago.

Signed-off-by: Lai Siyao <laisiyao@whamcloud.com>
Change-Id: I597a6279353c203b50b1c2b17543bd34d86d8806
Reviewed-on: http://review.whamcloud.com/1645
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Liang Zhen <liang@whamcloud.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
8 years agoLU-1023 utils: Time counting fix for obdfilter-survey
wangdi [Tue, 24 Jan 2012 03:56:09 +0000 (19:56 -0800)]
LU-1023 utils: Time counting fix for obdfilter-survey

1. Assigning the start and end time of test_brw so it
   can get correct time usage.
2. In mds_survey, it adds a new output line for threas utils,
   (Total: total xxxx threads X sec ...), and we should skip
   this line in get_stats(obdfilter-survey), so it can get
   correct min/max time.

Signed-off-by: Wang Di <di.wang@whamcloud.com>
Change-Id: I58c13bde299c254ed10e1405bfed3e1dce4ef216
Reviewed-on: http://review.whamcloud.com/1999
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-874 ldlm: prioritize LDLM_CANCEL requests
Jinshan Xiong [Thu, 22 Dec 2011 00:33:51 +0000 (16:33 -0800)]
LU-874 ldlm: prioritize LDLM_CANCEL requests

If a lock canceling request has already reached server, there is no
reason of evicting the client when the waiting list times out.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: I1a300916b4b3b592ca565ffc06cb3658d699d7a0
Reviewed-on: http://review.whamcloud.com/1900
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-980 llog: cleanup return value in llog_client_create
Hongchao Zhang [Thu, 12 Jan 2012 13:29:00 +0000 (21:29 +0800)]
LU-980 llog: cleanup return value in llog_client_create

in llog_client_create, the newly allocated llog_handle is
return by parameter res, but it doesn't be cleaned up
if the following operations failed and the corresponding
llog_handle is already freed.

Signed-off-by: Hongchao Zhang <hongchao.zhang@whamcloud.com>
Change-Id: I8b59dfde91da2c20881f29e8ff46a0a93f0ee1b2
Reviewed-on: http://review.whamcloud.com/1958
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Reviewed-by: Bobi Jam <bobijam@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-998 acl: declare acl operation for setattr
Lai Siyao [Wed, 18 Jan 2012 07:46:24 +0000 (15:46 +0800)]
LU-998 acl: declare acl operation for setattr

Setattr on ATTR_MODE may set acl if acl is enabled, and it should be
declared in advance.

Signed-off-by: Lai Siyao <laisiyao@whamcloud.com>
Change-Id: Id9c94c5498f8fee0a79986bb424444f658c98e60
Reviewed-on: http://review.whamcloud.com/1984
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Li Wei <liwei@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-1048 ldiskfs: fix dynlock cache entry freeing
Oleg Drokin [Sat, 28 Jan 2012 01:26:53 +0000 (20:26 -0500)]
LU-1048 ldiskfs: fix dynlock cache entry freeing

Update to rhel6.2 broke dynlocks patch and the last hunk was
ignored by quilt/patch.
This commit rediffs the proper patch against 2.6.32-220.el6

Change-Id: If9020458d07c7c2dc714b3e38587f66c4846f806
Signed-off-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/2034
Tested-by: Hudson
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-797 tests: speed up ost-pools tests
Andreas Dilger [Thu, 26 Jan 2012 12:39:06 +0000 (05:39 -0700)]
LU-797 tests: speed up ost-pools tests

The test time of the ost-pools subtests is unreasonably long.

test_14 fills an OST to 90% full, regardless of the OST size.
Skip the test if the amount of data to be written is too large
to run in a practical time.

test_18 creates 3x3x30000 files to compare performance with/without
pools enabled.  Instead of creating a fixed number of files, use
createmany to run for a specific (short) time to measure performance.

test_23 tried to fill all OSTs 100% full.  Split this test into two:
- test_23a to test quota with a file in a pool
- test_23b to test OOS with a file striped over pool

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ib851939a210ab68f52da1ac777781c2a922c500c
Reviewed-on: http://review.whamcloud.com/2028
Tested-by: Hudson
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-972 ldlm: reduce server log message everytime client connect
Minh Diep [Tue, 10 Jan 2012 21:16:17 +0000 (13:16 -0800)]
LU-972 ldlm: reduce server log message everytime client connect

Changed to D_HA to reduce the messages
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: Ief4507ef484369b6a7aafb7ce9b1f1e0b1f0967e
Reviewed-on: http://review.whamcloud.com/1944
Tested-by: Hudson
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Mikhail Pershin <tappro@whamcloud.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoTag 2.1.55 2.1.55 v2_1_55_0
Oleg Drokin [Wed, 25 Jan 2012 14:49:22 +0000 (09:49 -0500)]
Tag 2.1.55

Change-Id: I7f6bf0b88a7dc5c5a2eb08ccff090c2a17dfce22
Signed-off-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-898 ptlrpc: fix ptlrpc request race.
Alexander.Boyko [Fri, 6 Jan 2012 06:38:00 +0000 (10:38 +0400)]
LU-898 ptlrpc: fix ptlrpc request race.

Allow request reorder from export, only if request has been
added to the list.

Race condition with req error handle at ptlrpc_server_handle_req_in().
1. req is added to rq_export->exp_queued_rpc by ptlrpc_hpreq_init()
2. ptlrpc_server_request_add() returns error ( ost_validate_obdo() whith
one of this condition !(fid_seq_is_rsvd(oa->o_seq) ||
fid_seq_is_idif(oa->o_seq))
3. ptlrpc_server_drop_request(req) drops request (disconnect export),
but req is in rq_export->exp_queued_rpc
4. ldlm_server_blocking_ast handle rq_export->exp_queued_rpc and fail
because req->rq_export is NULL.
Fix allows request reorder from export only if request has been added to
the list. So workaround is not need for situation when request from export
was processed before ptlrpc_server_request_add.

Signed-off-by: Alexander Boyko <alexander_boyko@xyratex.com>
Reviewed-by: Vitaly Fertman <vitaly_fertman@xyratex.com>
Reviewed-by: Denis Kondratenko <denis_kondratenko@xyratex.com>
Reviewed-by: Andrew Perepechko <Andrew_Perepechko@xyratex.com>
Xyratex-bug-id: MRP-284
Change-Id: I5f763b3c4f19b6af5f803b50b43a5570dab3dc76
Reviewed-on: http://review.whamcloud.com/1799
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andrew Perepechko <andrew_perepechko@xyratex.com>
Reviewed-by: Denis Kondratenko <Denis_Kondratenko@xyratex.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-931 mdd: store lu_fid instead of pointer in md_capainfo
Hongchao Zhang [Tue, 17 Jan 2012 04:10:25 +0000 (12:10 +0800)]
LU-931 mdd: store lu_fid instead of pointer in md_capainfo

in md_capainfo, mc_fid contains at most 5 pointers to lu_fid,
and if the corresponding lu_fid is freed, the pointer isn't notified
about it, then the pointer will point to freed memory!

Signed-off-by: Hongchao Zhang <hongchao.zhang@whamcloud.com>
Change-Id: I00088cbfeb145ceac0477467a8b2436f6cf1e530
Reviewed-on: http://review.whamcloud.com/1979
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Mikhail Pershin <tappro@whamcloud.com>
Reviewed-by: wangdi <di.wang@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-919 obdclass: remove hard coded 0x5a5a5a
Niu Yawei [Wed, 11 Jan 2012 03:59:10 +0000 (19:59 -0800)]
LU-919 obdclass: remove hard coded 0x5a5a5a

We assert atomic_t value with hard coded 0x5a5a5a in several places,
which could result in false assertion failure when the reference count
getting very large in some extreme case.

The hard coded 0x5a5a5a should be replaced by LI_POISON.

Signed-off-by: Bruno Faccini <bruno.faccini@bull.net>
Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: Idc271621017d071b3e2dce5d0ec6fb854127a955
Reviewed-on: http://review.whamcloud.com/1953
Reviewed-by: Lai Siyao <laisiyao@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-814 test: automate NFS over lustre testing
Minh Diep [Thu, 5 Jan 2012 16:55:48 +0000 (08:55 -0800)]
LU-814 test: automate NFS over lustre testing

Provide setup nfs within auster framework

Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: Icfd61bf6772807a344576b92b5268a83a7b79e4b
Reviewed-on: http://review.whamcloud.com/1664
Reviewed-by: Wei Liu <sarah@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-879 tests: Add test for checking rename_stats
wangdi [Sat, 14 Jan 2012 07:15:46 +0000 (23:15 -0800)]
LU-879 tests: Add test for checking rename_stats

Add 133d in sanity for checking rename_stats.

Signed-off-by: Di Wang <di.wang@whamcloud.com>
Change-Id: If9a57b9ac458fdf729c19f597d6197f410966e91
Reviewed-on: http://review.whamcloud.com/1970
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
8 years agoLU-169 lov: add basic infrastructure for layout lock
Johann Lombardi [Tue, 10 Jan 2012 16:41:26 +0000 (17:41 +0100)]
LU-169 lov: add basic infrastructure for layout lock

This patch adds some basic infrastructure to support the layout lock
in a near future. This includes defining a new inode lock bit to lock
the file layout (namely MDS_INODELOCK_LAYOUT) as well as a new lookup
intent (IT_LAYOUT).

Signed-off-by: Jacques-Charles Lafoucriere <jacques-charles.lafoucriere@cea.fr>
Change-Id: Ibf1c3c166b5def4654684febbcf3a99ea7e482eb
Signed-off-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1854
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-781 kernel: kernel update [RHEL6.2 2.6.32-220]
yangsheng [Thu, 5 Jan 2012 10:30:42 +0000 (18:30 +0800)]
LU-781 kernel: kernel update [RHEL6.2 2.6.32-220]

Add support for RHEL6.2. The version is 2.6.32-220.el6.

Change-Id: Icc03a2f5d8b377aa1b1180ae09056989bbc84a9d
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1892
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-948 clio: add a callback to cl_page_gang_lookup()
Jinshan Xiong [Thu, 12 Jan 2012 00:03:41 +0000 (16:03 -0800)]
LU-948 clio: add a callback to cl_page_gang_lookup()

Add a callback to cl_page_gang_lookup() so that it will be easier to
fix this issue and be helpful for new IO engine.

If a read lock is being canceled, we used to grab page lock and then
check if they are covered by another lock, otherwise they will be
discarded. This is unnecessary because we can do this w/o grabbing
page lock.

With the above fix, when a read-ahead page is in IO during recovery,
and one of covering locks is being canceled by early cancel for
recovery, it will detect that this page is being covered by another
one, and then this page will be skipped w/o trying to grab page lock.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: I22a3ea0790f5c0e01c12c29208b6d60c38058f12
Reviewed-on: http://review.whamcloud.com/1955
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-459 debug: quiet overly verbose debug messages
Andreas Dilger [Fri, 16 Dec 2011 02:20:28 +0000 (19:20 -0700)]
LU-459 debug: quiet overly verbose debug messages

Some debugging messages are being printed to the console, but
do not provide any particular value.  Turn these into kernel
debug messages.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Id8b0624b281ce67501d0d81cd0e89cc020cd669a
Reviewed-on: http://review.whamcloud.com/1876
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-412 tests: Fix test script lookup in auster
Li Wei [Mon, 11 Jul 2011 05:23:33 +0000 (13:23 +0800)]
LU-412 tests: Fix test script lookup in auster

When asked to run "lfsck", auster found "/usr/sbin/lfsck" instead of
"$LUSTRE/tests/lfsck.sh".  This patch restricts auster to look for test
scripts in only $LUSTRE/tests.

Change-Id: Iea521d06cdf1cea1a9bd80224f847275732d3447
Signed-off-by: Li Wei <liwei@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1078
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-966 mdd: mdd object may not be exist
Bobi Jam [Mon, 9 Jan 2012 10:23:41 +0000 (18:23 +0800)]
LU-966 mdd: mdd object may not be exist

If MDT device has been checked with fsck, some mdd objects
could be removed, so that recovery replay could act on non-existing
objects.

Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: If3a3b72ee70ab2513978ed968c9598ddde11c085
Reviewed-on: http://review.whamcloud.com/1928
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Reviewed-by: Mikhail Pershin <tappro@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-807 utils: remove old service tags support
Andreas Dilger [Mon, 31 Oct 2011 19:17:01 +0000 (13:17 -0600)]
LU-807 utils: remove old service tags support

Remove obsolete and unused service tags infrastructure from the
build system and mount utilities.  This reverts the changes from:

    14765d2816bafa2a08879ece0e33bf8c97f84948
    805392ae4c4a4295d0f027234c83a670dfdc2268

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I1f2bd75dfd285fa1cebb5cb8eb4772cf2fc9ad7a
Reviewed-on: http://review.whamcloud.com/1634
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-812 synchronize_rcu no longer a define
Wally Wang [Fri, 13 Jan 2012 00:12:54 +0000 (16:12 -0800)]
LU-812 synchronize_rcu no longer a define

synchronize_kernel() in old kernel(pre 2.6.12) is no longer supported
and synchronize_rcu is no longer a define after 2.6.33. Remove the no
longer used old code.

Change-Id: Iac668efc35d82e6218b1924eca009f92d19a0c7a
Signed-off-by: Wally Wang <wang@cray.com>
Reviewed-on: http://review.whamcloud.com/1952
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-883 build: allow blank after signoff, email fix
Andreas Dilger [Thu, 15 Dec 2011 07:16:20 +0000 (00:16 -0700)]
LU-883 build: allow blank after signoff, email fix

Allow blank lines after the signoff section, since there will usually
be a blank line between the signoff and the checkpatch.pl output.

Improve the EMAILPAT regex to detect bad email addresses that do not
have a full name (at least 2 parts) and a full domain (also with
at least 2 parts).

Allow a generic "{Organization}-bug-id:" line in the signoff section
to allow linking the patch commit into arbitrary bug databases for
ease of tracking patches.

Add test cases for all of these changes.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Iaf14f6c985d3dd4837064d29071bd9acd8031d67
Reviewed-on: http://review.whamcloud.com/1867
Reviewed-by: <bruce.korb@gmail.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Bobi Jam <bobijam@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-80 utils: Large stripe support
James Simmons [Tue, 10 Jan 2012 13:59:23 +0000 (08:59 -0500)]
LU-80 utils: Large stripe support

Currently a file can be stripped across OSTs up to a limit of
160 stripes due to the ldiskfs xattr size limit of 4096 bytes.
This limit will be increased to 2000 stripes or more by increasing
the maximum xattr size for the MDT.

During testing, issues emerged with clients that are not expecting
more than 160 stripes. This patch allows clients to interoperate with
servers that do not support large xattrs, and also servers with
support with at least 2000 stripes, though it is intended not to have
any hard upper limit.

Change-Id: Idbaeb98919aea6b4cd375b881ed87661034d9394
Signed-off-by: James Simmons <uja.ornl@gmail.com>
Reviewed-on: http://review.whamcloud.com/1194
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Yu Jian <yujian@whamcloud.com>
8 years agoLU-960 utils: bad stripe count report, and validate stripe size
Minh Diep [Fri, 6 Jan 2012 01:40:57 +0000 (17:40 -0800)]
LU-960 utils: bad stripe count report, and validate stripe size

Need to use %d to print -1 instead of %u
Need to check for -1 in input for stripe size

Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: Ia9593497764f1d3c0110ad22d70b5da8f7b07a21
Reviewed-on: http://review.whamcloud.com/1922
Tested-by: Hudson
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Richard Henwood <rhenwood@whamcloud.com>
8 years agoLU-233 test: Remove taring of log files in gather logs.
Chris Gearing [Tue, 4 Oct 2011 17:31:59 +0000 (18:31 +0100)]
LU-233 test: Remove taring of log files in gather logs.

gather_logs in test-framework zips the logs for no apparent purpose
just adding to the file storage. In fact it creates multiple bz2
files which contain one another. This change removes all the bz2
stuff

Change made to remove Russian dolls whilst keeping behaviour of
recovery-*-scale tests

Signed-off-by: Chris Gearing <chris@whamcloud.com>
Change-Id: I76a15a44395c0bdf4ee01e9240b64bdcdf8b25ed
Reviewed-on: http://review.whamcloud.com/1398
Tested-by: Hudson
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-822 osd: use bitmask to calculate seq hash
Liang Zhen [Tue, 10 Jan 2012 17:18:52 +0000 (01:18 +0800)]
LU-822 osd: use bitmask to calculate seq hash

We are using mod to hash seq to different OI files, which is not
allowed on 32-bit arch because seq is 64-bit. It can be resolved
by limit oi_count to power2 and use bitmask to calculate seq hash.
This patch also renamed modparameter osd_oi_num to osd_oi_count.

Signed-off-by: Liang Zhen <liang@whamcloud.com>
Change-Id: I61c1fac65a33c78b5b5196d2b2d6fd5519deffda
Reviewed-on: http://review.whamcloud.com/1941
Tested-by: Hudson
Reviewed-by: Mikhail Pershin <tappro@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-867 gss: adapt to 2.6.32 kernel changes cache_detail
Bobi Jam [Mon, 19 Dec 2011 01:35:27 +0000 (09:35 +0800)]
LU-867 gss: adapt to 2.6.32 kernel changes cache_detail

2.6.32 kernel changes cache_detail's member cache_request to
cache_upcall.

Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I3ddec24e88fd271c8e88e2c649be52542651b8cc
Reviewed-on: http://review.whamcloud.com/1885
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-874 ldlm: Fix ldlm_bl_* thread creation
Christopher J. Morrone [Thu, 5 Jan 2012 19:49:50 +0000 (11:49 -0800)]
LU-874 ldlm: Fix ldlm_bl_* thread creation

Always create a new ldlm_bl_ thread when all threads
are busy, not just after returning from sleep.

Change-Id: I2fa99a0f09a42e1333589fc7bc2a6eebef4924b6
Signed-off-by: Christopher J. Morrone <morrone2@llnl.gov>
Reviewed-on: http://review.whamcloud.com/1926
Tested-by: Hudson
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
8 years agoLU-976 tests: skip MMP test for non-ldiskfs backfs
Andreas Dilger [Mon, 9 Jan 2012 19:04:54 +0000 (12:04 -0700)]
LU-976 tests: skip MMP test for non-ldiskfs backfs

Skip the Multi-Mount Protection tests for non-ldiskfs backing
filesystems.  MMP is currently only implemented for ldiskfs,
so until that changes this test cannot pass for any other FSTYPE.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I4dc9936fa6f34b4dc4cc465a6352daae2198788f
Reviewed-on: http://review.whamcloud.com/1934
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-987 build: Fail to create ldisk rpms
James Simmons [Fri, 13 Jan 2012 16:11:29 +0000 (11:11 -0500)]
LU-987 build: Fail to create ldisk rpms

The autoMakefile.am in ldsikfs does not define the
BUILD_SERVER flag so make rpms fails. This patch
simply set the flag to true since ldiskfs will most
likely be used only on servers

Signed-off-by: James Simmons <uja.ornl@gmail.com>
Change-Id: I51e31d1ce0fd1d7e8639426852af1888a9a93f4f
Reviewed-on: http://review.whamcloud.com/1964
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-590 tests: obdfilter-survey.sh fails test 2a.
Andriy Skulysh [Thu, 5 Jan 2012 13:04:14 +0000 (15:04 +0200)]
LU-590 tests: obdfilter-survey.sh fails test 2a.

obdfilter-survey.sh fails to connect during test 2a.
Interruption to and restart of test leads to a panic.
This patch sets correct target for netdisk case, allows to
handle signals in test scripts, sets correct parameters for
obdfilter-survey cleanup.

Xyratex-bug-id: MRP-118
Change-Id: I057610ba51e9a9afb704b4467b8600fd61652a71
Signed-off-by: Andriy Skulysh <Andriy_Skulysh@xyratex.com>
Reviewed-by: Alexey Lyashkov <alexey_lyashkov@xyratex.com>
Reviewed-on: http://review.whamcloud.com/1288
Tested-by: Hudson
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-952 quota: follow locking order of quota code
Niu Yawei [Fri, 6 Jan 2012 09:18:35 +0000 (01:18 -0800)]
LU-952 quota: follow locking order of quota code

The locking order of quota code is: i_mutex > dqonoff_sem >
journal_lock > dqptr_sem > dquot->dq_lock > dqio_mutex, so we
should call the ll_vfs_dq_init() after journal started to avoid
deadlock.

Signed-off-by: Niu Yawei <niu@whamcloud.com>
Change-Id: Ia88a2eb8c9dc3827afd4828e0160ee376a1f041e
Reviewed-on: http://review.whamcloud.com/1923
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Hudson
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoRevert "LU-633 iokit: mdt-survey script for MD echo client test"
Oleg Drokin [Fri, 13 Jan 2012 22:27:45 +0000 (17:27 -0500)]
Revert "LU-633 iokit: mdt-survey script for MD echo client test"

Broke build somehow, even though passed gerrit, so reverting meanwhile.

This reverts commit 4f5fc8f9f0a93274c7b7ba7ab79d7a338cd0dfb8.

Signed-off-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-633 iokit: mdt-survey script for MD echo client test
Minh Diep [Wed, 7 Dec 2011 00:38:54 +0000 (16:38 -0800)]
LU-633 iokit: mdt-survey script for MD echo client test

Create a mdt-survey script to run echo client for MD

Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: I2d75de5c28b70a3b8474ed8512389d850c77e638
Reviewed-on: http://review.whamcloud.com/1803
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: wangdi <di.wang@whamcloud.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 tests: check lustre.conf for modprobe
Andreas Dilger [Fri, 16 Dec 2011 02:24:57 +0000 (19:24 -0700)]
LU-506 tests: check lustre.conf for modprobe

The newer userspace modprobe requires that the /etc/modprobe.d/
files end in ".conf", so that there is no confusion between config
files that are supposed to be parsed, and files that are left
after editing (e.g. lustre.conf.orig or lustre.conf~).

Add a check for /etc/modprobe.d/lustre.conf to get lnet module
parameters during testing.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: Ie408f5334b2570f13e225038488df06ff7b524c4
Reviewed-on: http://review.whamcloud.com/1877
Tested-by: Hudson
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-954 build: make lbuild to build lustre-iokit
Minh Diep [Fri, 30 Dec 2011 00:43:44 +0000 (16:43 -0800)]
LU-954 build: make lbuild to build lustre-iokit

Add additional codes in lbuild to build lustre-iokit rpm.
It should be noarch because it's independent of any arch.
Add info to Changelog and change iokit version to 1.3.0

Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: I8b3c0bbaf348c350155d7c50e9ffcb4ec92fe1ff
Reviewed-on: http://review.whamcloud.com/1907
Tested-by: Hudson
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Michael MacDonald <mjmac@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agonew tag 2.1.54 2.1.54 v2_1_54_0
Oleg Drokin [Wed, 11 Jan 2012 18:00:36 +0000 (13:00 -0500)]
new tag 2.1.54

Change-Id: I62f089d9c945452336b7d22b2b0bca06890ebe7f
Signed-off-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-868 ptlrpc: Fix the timeout for waiting next replay
wangdi [Mon, 21 Nov 2011 06:57:03 +0000 (22:57 -0800)]
LU-868 ptlrpc: Fix the timeout for waiting next replay

During recovery, when setting the timeout for waiting the next
replay, it should consider netlatency(added into timeout) and
early reply as well, so if server sends the early reply for
the request, the client might extend the timeout according to
current estimate service time.

Signed-off-by: Wang di <di.wang@whamcloud.com>
Change-Id: I23ebf1dc3f525f78573890be26474b2c79c65a6d
Reviewed-on: http://review.whamcloud.com/1716
Tested-by: Hudson
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 kernel: FC15 - Introduce simple_setattr().
yangsheng [Wed, 31 Aug 2011 15:52:28 +0000 (23:52 +0800)]
LU-506 kernel: FC15 - Introduce simple_setattr().

Since 2.6.35: simple_setattr() has be introduced to
replace inode_setattr().
kernel-commit: 7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f

Signed-off-by: Yang Sheng <ys@whamcloud.com>
Change-Id: I0e002f20fa4bafb18e0c7d3c55924800265658f6
Reviewed-on: http://review.whamcloud.com/1863
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 kernel: Add config check for sb_any_quota_loaded
yangsheng [Tue, 10 Jan 2012 18:59:11 +0000 (02:59 +0800)]
LU-506 kernel: Add config check for sb_any_quota_loaded

Add config check for sb_any_quota_loaded() since
OFED just backport DQUOT_USAGE_ENABLED.

Signed-off-by: yangsheng <ys@whamcloud.com>
Change-Id: I2f5fe42408bed1be7110944e7a47e0af16d896db
Reviewed-on: http://review.whamcloud.com/1943
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Michael MacDonald <mjmac@whamcloud.com>
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-884 osc: async osc_check_rpcs()
Jinshan Xiong [Wed, 4 Jan 2012 18:28:29 +0000 (10:28 -0800)]
LU-884 osc: async osc_check_rpcs()

Add a new "async" parameter to osc_check_rpcs(); if it is called with
async, it will compose a fake ptlrpc_request so that RPCs will be
composed and issued in ptlrpcd context.

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: I1c2f8ae43da8146428c474f17ddf3dc23a2df9ef
Reviewed-on: http://review.whamcloud.com/1825
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-925 agl: async glimpse lock process in CLIO stack
Fan Yong [Fri, 6 Jan 2012 06:49:42 +0000 (14:49 +0800)]
LU-925 agl: async glimpse lock process in CLIO stack

Adjust CLIO lock state machine for supporting:
1. unuse lock in non-hold state.
2. re-enqueue non-granted glimpse lock.

Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Change-Id: I9de8939a398d7b4c7062e6c5859bca06deddd089
Reviewed-on: http://review.whamcloud.com/1243
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Tested-by: Hudson
Reviewed-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-962 ptlrpc: feature to run callback in ptlrpcd context
Jinshan Xiong [Wed, 4 Jan 2012 07:56:22 +0000 (23:56 -0800)]
LU-962 ptlrpc: feature to run callback in ptlrpcd context

In this patch, a feature is added to run a callback in ptlrpc
context. We need a ptlrpc work for this purpose. There are three
functions exported:
  1. ptlrpc_alloc_work() to allocate work;
  2. ptlrpc_run_work() to run an allocated work, this function can
     be executed many times;
  3. ptlrpc_destroy_work() to destroy the work;

Signed-off-by: Jinshan Xiong <jinshan.xiong@whamcloud.com>
Change-Id: I2bce5a17003855468eab9075fb50ed02d7bcc208
Reviewed-on: http://review.whamcloud.com/1917
Reviewed-by: Johann Lombardi <johann@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 kernel: FC15 - small changes
yangsheng [Thu, 5 Jan 2012 17:14:34 +0000 (01:14 +0800)]
LU-506 kernel: FC15 - small changes

   -- stacktrace_ops.{warning(), warning_symbol()} removed.
   -- sk_sleep() helper added.
   -- quota_on() 4 parameter change to use 'struct path'.
   -- fs_struct.lock change to use spin_lock.
   -- other trivial changes.

Change-Id: Ic9bf47454b19c1cfc3e41cd3aebbabb074f6110f
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1864
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Lai Siyao <laisiyao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 kernel: FC15 - reiserfs remove & cleanup
yangsheng [Wed, 4 Jan 2012 11:22:04 +0000 (19:22 +0800)]
LU-506 kernel: FC15 - reiserfs remove & cleanup

 -- Remove reiserfs support entirely.
 -- Change to don't use PATCHLEVEL, since kernel has
    forward to version 3.1.

Signed-off-by: yangsheng <ys@whamcloud.com>
Change-Id: I86d185ba522b5c9fc5e16bfe1d34be8720573e58
Reviewed-on: http://review.whamcloud.com/1915
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-822 osd: multiple Object Index files
Liang Zhen [Thu, 8 Dec 2011 16:48:29 +0000 (00:48 +0800)]
LU-822 osd: multiple Object Index files

Single OI container could be performance bottleneck on server side,
because many service threads may content on the same OI htree-tree
even OI htree can support parallel operations but there are
still a lot of spinlock contentions and cacheline contentions.
Also, parallel operations of OI htree can't scale very well if
there are hundreds or thousands threads, it is because limitation
of dynlock. Instead of fix scalability of dynlock, the long term
solution is more straightforward, we can simply support multiple OI
containers and hash service threads to different OIs by lu_fid::f_seq.
We need to make sure this feature can support single OI created
by 2.1 or earlier versions, also, user can specify number of OIs by
modparameter osd_oi_num on creating new filesystem, this parameter
will be ignored if OSD is loading on existed filesystem.

Signed-off-by: Liang Zhen <liang@whamcloud.com>
Change-Id: Iaa5ef9e43b80301150608802e40b4ef506467457
Reviewed-on: http://review.whamcloud.com/1822
Tested-by: Hudson
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-879 mds: Add a few rename stats under /proc
wangdi [Fri, 16 Dec 2011 01:19:31 +0000 (17:19 -0800)]
LU-879 mds: Add a few rename stats under /proc

1. Add samedir_rename in /proc/fs/lustre/mds/lustre-MDT0000/stats
to collect stats of same dir rename.
2. Add crossdir_rename in /proc/fs/lustre/mds/lustre-MDT0000/stats
to collect stats of cross dir rename.
3. Add /proc/fs/lustre/mds/lustre-MDT0000/rename_stats(YAML format)
to collect stats of rename stats happened on different size
directories.
The size of directories under which files are being removed.
With these patches, it will find out how many renames take place
in the same directory compared to how many renames are between
So during DNE implementation, we can know how rename may be
affected by DNE remote directories and large striped directories.

Signed-off-by: Wang Di <di.wang@whamcloud.com>
Change-Id: I4452ce196802c5724607455e0a9b4b372b06f159
Reviewed-on: http://review.whamcloud.com/1878
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-169 lov: add generation number to LOV EA
Johann Lombardi [Thu, 15 Dec 2011 00:00:00 +0000 (01:00 +0100)]
LU-169 lov: add generation number to LOV EA

This patch shrinks lov_mds_md_v*::lmm_stripe_count to 16 bits and use
the remaining 16 bits to store a generation number for the layout.
This generation will be used in conjunction the layout lock to allow
clients to detect when the file layout has changed.
The layout generation starts at 0 and will be bumped each time the
file layout is altered.
For backward compatibility, the layout generation is set to 0 when the
layout is sent to a client that does not support
OBD_CONNECT_LAYOUTLOCK.

This patch also stores OBD_INCOMPAT_LMM_VER in the MDS last_rcvd file
to prevent older versions of Lustre that cannot deal with a 16-bit
lmm_stripe from mounting the filesystem and exporting layouts to older
clients without setting the layout to 0.  This flag will be set in the
last_rcvd file only once we start modifying file layouts, but at least
the current version should not be confused by a 16-bit stripe count
and a non-zero generation.

Signed-off-by: Jacques-Charles Lafoucriere <jacques-charles.lafoucriere@cea.fr>
Change-Id: Ic40083227057eba565287d1a10890875b8a96c13
Signed-off-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1866
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-593 obdclass: echo client for MDS stack
wangdi [Wed, 16 Nov 2011 22:55:23 +0000 (14:55 -0800)]
LU-593 obdclass: echo client for MDS stack

1. Add interfaces and tools for exercising a local MDT
   device for performance reasons, in a similar manner
   to obdfilter-survey.
2. add test_create, test_mkdir, test_lookup, test_destroy,
   test_rmdir, test_setxattr, test_md_getattr in lctl for
   md echo client test.

Signed-off-by: Wang di <di.wang@whamcloud.com>
Change-Id: Ibf774a567820ff36b3624e44371c63a9428d82a5
Reviewed-on: http://review.whamcloud.com/1287
Tested-by: Hudson
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-955 build: fix bad lustre-backend-fs dependency
Minh Diep [Thu, 5 Jan 2012 17:12:29 +0000 (09:12 -0800)]
LU-955 build: fix bad lustre-backend-fs dependency

Fix an incorrect RPM package dependency if Lustre RPMs are built
with "make rpms" with client only

Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Change-Id: Ib8691a37fc230cc63b7aca48bc5146a67e10a2f0
Reviewed-on: http://review.whamcloud.com/1576
Reviewed-by: Brian J. Murrell <brian@whamcloud.com>
Tested-by: Hudson
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-909 osd: changes to osd api
Alex Zhuravlev [Fri, 6 Jan 2012 05:01:40 +0000 (13:01 +0800)]
LU-909 osd: changes to osd api

the main purpose of the patch is to get declare methods in the API
and to teach osd-based devices to use that

- new declaration methods for each changing method
- explicit destroy method:
  ->do_ref_del() never destroy object
- methods to access data in 0-copy manner:
  no actual implementation in this patch
- mdd/fld use new methods to create/declare/start transactions
- specific method to change/access version are removed:
  use xattr methods
- ldiskfs osd tracks all declarations and asserts if caller
  is trying to call changing method w/o proper declaration

Change-Id: I473c0c2950c1920abb2fef1dac465c08f35522ea
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Signed-off-by: Hongchao Zhang <hongchao.zhang@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1669
Tested-by: Hudson
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-847 quota: move lmv/mdc/osc/lov quota code out of lquota
Johann Lombardi [Fri, 30 Sep 2011 13:12:59 +0000 (06:12 -0700)]
LU-847 quota: move lmv/mdc/osc/lov quota code out of lquota

All quota code was initially put into a separate kernel module since
quota might be released under a different license. That's not relevant
any more and we can now move the client-side quota code back to the
regular lustre modules.

This removes useless indirections and makes the code easier to read
and to maintain.

Change-Id: If898a46db9158edb8e4eaf855f1ed98db97330f0
Signed-off-by: Niu Yawei <niu@whamcloud.com>
Signed-off-by: Johann Lombardi <johann@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1613
Tested-by: Hudson
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-80 tests: large xattr support
Yu Jian [Fri, 30 Dec 2011 06:28:44 +0000 (14:28 +0800)]
LU-80 tests: large xattr support

This patch adds and updates some test cases to verify the
large xattr feature. To enable this feature, the "-O large_xattr"
option needs to be set on the filesystem either with --mkfsoptions
at format time or via tune2fs.

Signed-off-by: Yu Jian <yujian@whamcloud.com>
Change-Id: Ie62e6e2194fdaa7239ec4e1451a4e696888dca8c
Reviewed-on: http://review.whamcloud.com/1880
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-80 lov: large stripe count support
Alexander Boyko [Fri, 30 Dec 2011 06:24:10 +0000 (14:24 +0800)]
LU-80 lov: large stripe count support

Currently a file can be stripped across OSTs up to a limit of
160 stripes. This patch expands that limit to 2000 and it is
possible to go even to larger stripe counts.

Signed-off-by: Alexander Boyko <alexander_boyko@xyratex.com>
Change-Id: I42e1aad35dd056faac23a0d5b025e0a23fc4ec2f
Reviewed-on: http://review.whamcloud.com/1111
Reviewed-by: Yu Jian <yujian@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-80 ldiskfs: large EA support
James Simmons [Fri, 30 Dec 2011 06:02:25 +0000 (14:02 +0800)]
LU-80 ldiskfs: large EA support

This patch implements the large EA support in ext4. If the size of
an EA value is larger than the blocksize, then the EA value would
not be saved in the external EA block, instead it would be saved
in an external EA inode. So, the patch also helps support a larger
number of EAs.

Signed-off-by: James Simmons <uja.ornl@gmail.com>
Change-Id: Ic08921cf13483c9b28560c987773d7aa36c62fac
Reviewed-on: http://review.whamcloud.com/1708
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
8 years agoLU-250 lnet: Router random shuffling support
James Simmons [Wed, 28 Dec 2011 16:00:56 +0000 (11:00 -0500)]
LU-250 lnet: Router random shuffling support

This is the last of the router improvements that where
developed at ORNL. This feature allows routes to be
randomly placed. Our results show a 20 percent
improvement with random shuffling.

Signed-off-by: James Simmons <uja.ornl@gmail.com>
Change-Id: I6862febebd6797fb35c003646f6d90f5d5d2b014
Reviewed-on: http://review.whamcloud.com/249
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Isaac Huang <Isaac_Huang@xyratex.com>
Reviewed-by: Liang Zhen <liang@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 kernel: FC15 - file_operations relate changes.
yangsheng [Wed, 4 Jan 2012 15:23:16 +0000 (23:23 +0800)]
LU-506 kernel: FC15 - file_operations relate changes.

   -- file_operations.ioctl() has been removed.
   -- file_operations.fsync() changes need 2 arguments.

Change-Id: I7776593497dd988fbf860221e2dcea61c6c4870f
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1862
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
8 years agoLU-925 agl: trigger async glimpse lock when statahead
Fan Yong [Fri, 16 Dec 2011 07:34:25 +0000 (15:34 +0800)]
LU-925 agl: trigger async glimpse lock when statahead

Client will send async glimpse lock RPCs to OSTs for file size
attribute before stat files to accelerate traversing large dir.

Signed-off-by: Fan Yong <yong.fan@whamcloud.com>
Change-Id: I9bf850abdd3c02c8470ddfcd91a3dc3ef7819c6d
Reviewed-on: http://review.whamcloud.com/1692
Reviewed-by: Lai Siyao <laisiyao@whamcloud.com>
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-506 kernel: FC15 - vfsmount.mnt_count doesn't use atomic_t
yangsheng [Fri, 2 Sep 2011 02:20:02 +0000 (10:20 +0800)]
LU-506 kernel: FC15 - vfsmount.mnt_count doesn't use atomic_t

vfsmount.mnt_count use pre-cpu variable instead of atomic_t.

Change-Id: I5eba5a67839719e03d0b44be6312b452bf4dcb98
Signed-off-by: Yang Sheng <ys@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/1845
Tested-by: Hudson
Reviewed-by: Lai Siyao <laisiyao@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: Maloo <whamcloud.maloo@gmail.com>
8 years agoLU-639 obdclass: wait obd cleanup before mount
Bobi Jam [Tue, 20 Dec 2011 09:59:07 +0000 (17:59 +0800)]
LU-639 obdclass: wait obd cleanup before mount

Obd device cleanup is executed by obd zombie thread, and umount thread
can return successfully before obd zomebie finishes its job. In some
cases, especially in test cases, a test may starts before last tests
finishes obd cleanup, this patch makes mount thread wait for obd
zombie finishes its job.

Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I881be5de18960867c36e8c4e4180c0c594d88a01
Reviewed-on: http://review.whamcloud.com/1896
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Niu Yawei <niu@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-176 obdclass: disable mb_cache by default
Liang Zhen [Tue, 29 Mar 2011 03:37:28 +0000 (11:37 +0800)]
LU-176 obdclass: disable mb_cache by default

We are supposed to disable mb_cache by default (bug 22771),
but we never did because it's not in default mount option.
This patch will add "no_mbcache" to default mount option.

Change-Id: I13c9db8e98ad305d26d887d8bd069eff92c20763
Signed-off-by: Liang Zhen <liang@whamcloud.com>
Reviewed-on: http://review.whamcloud.com/373
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
8 years agoLU-748 test: shorten the runtime of sanity subtest_220
Hongchao Zhang [Mon, 12 Dec 2011 18:28:08 +0000 (02:28 +0800)]
LU-748 test: shorten the runtime of sanity subtest_220

in sanity.sh, test_220 tries to exhaust all of the inodes on the OSTs
in order to verify that when it returns -ENOSPC to inode precreate
request, but there is still free blocks, then the MDS continues to use
these precreated inodes on the OSTs.

Signed-off-by: Hongchao Zhang <hongchao.zhang@whamcloud.com>
Change-Id: Icaad07311125f362f0efb26da76534c7dca27b6a
Reviewed-on: http://review.whamcloud.com/1676
Tested-by: Hudson
Tested-by: Maloo <whamcloud.maloo@gmail.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Fan Yong <yong.fan@whamcloud.com>