- Apr 21, 2008
-
-
Eric Mei authored
change at_max according to AT status. b=13659 r=nathan r=rread r=grev
-
Andrew Perepechko authored
b=15218 i=johann i=tianzy additional admin quota file update
-
- Apr 18, 2008
-
-
Elena Gryaznova authored
i=Adilger force test_20a and test_20b to do write on the correct ost
-
Alexey Lyashkov authored
__u64 as usingied long long type. b=15517 i=johan i=deen
-
Alexey Lyashkov authored
callback. b=15210 i=green i=deen
-
bwzhou authored
b=15521 r=adilger, shadow correct the initialization of lc_min of struct lprocfs_counter
-
- Apr 17, 2008
-
-
Alexey Lyashkov authored
b=15412 i=johann i=deen
-
Alexey Lyashkov authored
i=nikita i=johann
-
- Apr 16, 2008
-
-
Yury Umanets authored
r=shadow,adilger - remove @ns from list using list_del_init() to make sure that consequnet list_empty() will really work right on removed listy_head.
-
Brian J. Murrell authored
i=cliffw i=wangyb Allow a kernel target to specify a delimiter between the version and the "flavor" (i.e. "smp") - specifically this allows RH kernels to be <version>smp and SLES10 kernels to be <version>-smp. - maintaining the vendors versioning specification means that when software is trying to determine a vendors kernel using patterns (like OFED does), it properly detects the SLES10 kernel. This all lays the ground work for bug 15316.
-
Elena Gryaznova authored
i=Nathan.Rutman skip test_37 for client only testing
-
Elena Gryaznova authored
i=Adilger allow both "cfs" and "sun" e2fsck
-
Elena Gryaznova authored
i=Yury.Umanets i=Alexey.Lyashkov force test_69 to fail if directio write failed
-
Yury Umanets authored
r=grev - fixes using check_runas_id(). Adds check for used runas id in test_72.
-
- Apr 15, 2008
-
-
Eric Mei authored
fix AT time calculation in AT_OFF mode. b=3055 r=nathan r=rread
-
Yang Sheng authored
b=12652 i=shadow, johann Add FMODE_EXEC flag to SLES10 SP1.
-
- Apr 14, 2008
- Apr 11, 2008
-
-
Eric Mei authored
Do not skip at_check_timed in AT_OFF mode, early replies might still be sent out until affected RPCs will drain eventually. b=15341 r=nathan r=rread
-
- Apr 10, 2008
-
-
deen authored
individual file sync to eliminate dangerous inode locking with I_LOCK that can lead to a deadlock. b=15188 i=green i=shadow
-
Vitaly Fertman authored
b=14661 i=green i=shadow -- remove BL_AST lock from lru once we mark the lock as a such; -- do not place BL_AST lock into lru even if the lock is matched and put later; => no BL_AST locks in lru at all; -- CANCELING locks are not so numerous, but to avoid its traversal by another thread another time, drop them from the unused list once come them across.
-
Alexey Lyashkov authored
b=15483 i=green i=johann
-
Yang Sheng authored
b=13397 i=johann i=shadow Split the export journal-api part as a separate patch.
-
- Apr 09, 2008
-
-
Elena Gryaznova authored
i=Yury.Umanets force test_66b to use FSNAME
-
Elena Gryaznova authored
i=Oleg.Drokin load crc16 module if it exists
-
- Apr 07, 2008
-
-
Yang Sheng authored
b=15152 Fixed previous lost part.
-
- Apr 04, 2008
-
-
Johann Lombardi authored
b=14751 i=green i=bzzz reset the time reference between calls to fsfilt_check_slow to prevent useless slow brw_start/direct_io/... messages.
-
tianzy authored
Add a new item(lq_lock) in struct lustre_qunit which protects every single qunit and qunit_hash_lock only protects qunit hash. It will improve parellelism. i=johann i=andrew
-
- Apr 03, 2008
-
-
Terry Rutledge authored
-
Bobi Jam authored
b=15288 i=wangdi, shadow fix stride_len assertion. when current ra window is consumed, and 2 consequent read requires to enlarge the read ahead window, and the enlargement action met window_start 0, window_len 80, because the latest read consumes the whole window content, stride_offset is 80, so the left of current ra window is 0, and the assertion of stride_len should be ">= 0" rather than "> 0"
-
Oleg Drokin authored
b=14257 Do not include LdLM_FLOCK locks into ldlm_pool sanity calculations.
-
Bobi Jam authored
b=14134 i=shadow, nathan change non-fatal error messages about contacting MGS.
-
Bobi Jam authored
b=13375 i=shadow, panda Descriptoin: make lov_create() will not stuck in obd_statfs_rqset() Details : If an OST is down the MDS will hang indefinitely in obd_statfs_rqset() waiting for the statfs data. While for MDS QOS usage of statfs, it should not stuck in waiting.
-
- Apr 02, 2008
-
-
Terry Rutledge authored
-
Johann Lombardi authored
b=14855 i=shadow i=adilger On SLES10/PPC, fs.h includes idr.h which requires BITS_PER_LONG to be defined. Add a hack in mkfs_lustre.c to work around this compile issue.
-
- Apr 01, 2008
-
-
Elena Gryaznova authored
i=Adilger load crc16
-
- Mar 31, 2008
-
-
Robert Read authored
Change #if to #ifdef to make gcc 3.x happy. b=15327 i=oleg i=walter
-
Jinshan Xiong authored
Remove specialized patch for titech, as Scjody suggested.
-
- Mar 28, 2008
-
-
deen authored
removal in bug 13499. b=13499
-
- Mar 27, 2008
-
-
Oleg Drokin authored
r=shadow,nikita Implement readv/writev (aio_read/aio_write) to greatly help NFS writes speed on 2.6 kernels.
-