- Aug 03, 2007
-
-
Johann Lombardi authored
b=11802 i=adilger i=kalpak Severity : normal Bugzilla : 11802 Description: lustre support for RHEL5 Details : Add support for RHEL5.
-
Yang Sheng authored
b=12839 i=shadow i=adilger Remove inode-nr_unused-2.6.9-rhel4.patch from 2.6-rhel4.series. It was include in kernel-2.6.9-55.0.2.EL. Update target & kernel config.
-
Alexey Lyashkov authored
b=13196 i=green i=nathan
-
Oleg Drokin authored
r=wangdi,adilger,huangwei Release flock locks in liblustre on file close
-
Oleg Drokin authored
r=adilger Obtain necessary amount of peer credits for exery export per oss and for every possible AST per MDS.
-
- Aug 02, 2007
-
-
mjmac authored
b=12839 Reverting this commit, as it breaks sles9 builds.
-
Elena Gryaznova authored
i=Nathan Perform sync not after but before OBD_FAIL_MDS_REINT_NET_REP to be sure that client get the mds reply and kbytesfree was correctly updated.
-
milind authored
r=adilger, deen Description: When running with O_DIRECT I/O, neither the client rpc_stats nor read_ahead_stats were updated. Copied the stats section from osc_send_oap_rpc() into async_internal().
-
Yang Sheng authored
b=12839 i=shadow i=adilger Remove inode-nr_unused-2.6.9-rhel4.patch from 2.6-rhel4.series.
-
Liu Ying authored
b=13006 i=shadow, deen Description: warnings with build patchless client with vanila 2.6.19 and up Details : change the old ctl_table style and replace ctl_table/ctl_table_header with cfs_sysctl_table_t/cfs_sysctl_table_header_t
-
Yang Sheng authored
b=12415 r=kalpak Fixed the ext3-unlink-race.patch. It should be against the ext3.
-
Liu Ying authored
b=12333 i=green, nathan Description: obdclass is limited by single OBD_ALLOC(idarray) Details : replace OBD_ALLOC/OBD_FREE with OBD_VMALLOC/OBD_VFREE
-
Johann Lombardi authored
b=11802 i=green i=scjody attachment 11752 / rely on AUTOCONF_INCLUDED instead of HAVE_KERNEL_CONFIG_H
-
Bobi Jam authored
b=12606 i=shadow, nikita Description: don't use GFP_* in generic Lustre code. Details : Use cfs_alloc_* functions and CFS_* flags for code portability.
-
- Aug 01, 2007
-
-
Nathan Rutman authored
i=brian always df
-
Vitaly Fertman authored
b=12916 i=green i=shadow handling of zero connect flags in self export for ELC code
-
- Jul 31, 2007
-
-
Nathan Rutman authored
i=green i=adilger Fix for 12860 - only notify if not stopping/cleaned.
-
Elena Gryaznova authored
i=Adilger i=Brian Add skip() function to print the skipped tests. Skip test_99b if /tmp has wrong w permissions.
-
Alexey Lyashkov authored
b=13148 i=green i=adilger
-
- Jul 30, 2007
- Jul 27, 2007
-
-
Nathan Rutman authored
i=adilger i=johann Block umount forever until the mount refcount is zero rather than giving up after an arbitrary timeout.
-
Nathan Rutman authored
b=13145 i=brian set conf_param on MGS
-
Nathan Rutman authored
escaped quotes was wrong
-
- Jul 26, 2007
-
-
milind authored
r=adilger, nathan Description: Error Message improvement patch (error_07.patch)
-
Elena Gryaznova authored
i=Nathan Correct replay-dual, replay-single ALWAYS_EXCEPT list.
-
Elena Gryaznova authored
i=Adilger i=Nathan Correct recovery-small ALWAYS_EXCEPT list
-
Liu Ying authored
b=12769 i=green,wangdi Add sync option to mount_lustre.c
-
Elena Gryaznova authored
i=Nathan i=Brian Check /proc/mounts instead of mtab.
-
Alexey Lyashkov authored
as FS_REQUIRES_DEV for avoid problems with generate fsid. b=10786,9303 i=green i=adilger
-
Jinshan Xiong authored
-
Yang Sheng authored
b=12771 i=adilger i=shadow Add patch blkdev_tunables-2.6-sles10.patch to 2.6-sles10.series.
-
Jinshan Xiong authored
b=12864 r=wangdi,nathan Fixed a deadlock issue for LPROCFS.
-
Bobi Jam authored
b=12211 i=adilger i=green fix LTS AutoBuild error.
-
Bobi Jam authored
b=12211 i=adilger i=green Description: randomly memory allocation failure util Details : Make lustre randomly failed allocating memory for testing purpose.
-
Wang Di authored
land 10800(adding llog ctxt refcount) to b1_6. b=10800 i=green i=shadow
-
Brian J. Murrell authored
r=mjmac r=yujian If anything inside the "while read; do ... done" loop (or it's callees) reads from stdin (a very common thing to do) it will consume input meant for the read since it's reading from stdin with ${CSV_FILE} being redirected to stdin. Read on another file descriptor to avoid this.
-
- Jul 25, 2007
-
-
deen authored
i=adilger i=green b=12786
-
Nathan Rutman authored
i=brian add ONLY, debugsave fix iozone test size remove some test output
-
scjody authored
Add 1.6.2 to changelogs
-