WARNING: This is the _old_ Lustre wiki, and it is in the process of being retired. The information found here is all likely to be out of date. Please search the new wiki for more up to date information.

Change Log 1.6

From Obsolete Lustre Wiki
Revision as of 00:20, 22 January 2008 by Lollsolo (talk | contribs)
Jump to navigationJump to search



Changes from v1.6.4.1 to v1.6.4.2

Support for kernels: 2.6.5-7.286 (SLES 9), 2.6.9-55.0.9.EL (RHEL 4), 2.6.16.53-0.8 (SLES 10), 2.6.18-8.1.14.el5 (RHEL 5), 2.6.18.8 vanilla (kernel.org)

Client support for unpatched kernels: (se http://wiki.lustre.org/index.php?title=Patchless_Client) 2.6.16 - 2.6.22 vanilla (kernel.org)

Due to problems with nested symlinks and FMODE_EXEC (bug 12652), we do not recommend using patchless RHEL4 clients with kernels prior to 2.6.9-55EL (RHEL4U5).

Recommended e2fsprogs version: 1.40.4-cfs1

Note that reiserfs quotas are disabled on SLES 10 in this kernel.

RHEL 4 (patched) and RHEL 5/SLES 10 (patchless) clients behave differently on 'cd' to a removed cwd "./" (refer to Bugzilla 14399).

Severity: critical

Frequency: only for relatively new filesystems, when OSTs are in recovery

Bugzilla: 14631

Description: OST objects below id 20000 are deleted, causing data loss

Details: For relatively newly formatted OST filesystem(s), where there have not been at least 20000 objects created on an OST a bug in MDS->OST orphan recovery could cause those objects to be deleted if the OST was in recovery, but the MDS was not. Safety checks in the orphan recovery prevent this if more than 20000 objects were ever created on an OST. If the MDS was also in recovery the problem was not hit. Only in 1.6.4.1.


Severity: major

Frequency: rare, depends on device drivers and load

Bugzilla: 14529

Description: MDS or OSS nodes crash due to stack overflow

Details: Code changes in 1.6.4 increased the stack usage of some functions. In some cases, in conjunction with device drivers that use a lot of stack the MDS (or possibly OSS) service threads could overflow the stack. One change which was identified to consume additional stack has been reworked to avoid the extra stack usage.


Changes from v1.6.4 to v1.6.4.1

Support for networks: socklnd - any kernel supported by Lustre, qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1 and 1.2, viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x

Support for kernels: 2.6.5-7.286 (SLES 9), 2.6.9-55.0.9.EL (RHEL 4), 2.6.16.53-0.8 (SLES 10), 2.6.18-8.1.14.el5 (RHEL 5), 2.6.18.8 vanilla (kernel.org)

Client support for unpatched kernels: (see http://wiki.lustre.org/index.php?title=Patchless_Client) 2.6.16 - 2.6.22 vanilla (kernel.org)

Due to recently discovered recovery problems, we do not recommend using patchless RHEL 4 clients with this or any earlier release.

Recommended e2fsprogs version: 1.40.2-cfs1

Note that reiserfs quotas are disabled on SLES 10 in this kernel.

Severity: major

Bugzilla: 14433

Description: Oops on connection from 1.6.3 client

Frequency: always, on connection from 1.6.3 client

Details: Enable and accept the OBD_CONNECT_LRU_RESIZE flag only if LRU resizing is enabled at configure time. This fixes an oops caused by incorrectly accepting the LRU_RESIZE feature even if --enable-lru-resize is not specified.


Changes from v1.6.3 to v1.6.4

Support for networks: socklnd - any kernel supported by Lustre, qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1 and 1.2, viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x

Support for kernels: 2.6.5-7.286 (SLES 9), 2.6.9-55.0.9.EL (RHEL 4), 2.6.16.53-0.8 (SLES 10), 2.6.18-8.1.14.el5 (RHEL 5), 2.6.18.8 vanilla (kernel.org)

Client support for unpatched kernels: (see http://wiki.lustre.org/index.php?title=Patchless_Client) 2.6.16 - 2.6.22 vanilla (kernel.org)

Due to recently discovered recovery problems, we do not recommend using patchless RHEL 4 clients with this or any earlier release.

Recommended e2fsprogs version: 1.40.2-cfs1

Note that reiserfs quotas are disabled on SLES 10 in this kernel.

Severity: enhancement

Bugzilla: 11686

Description: Console message flood

Details: Make cdls ratelimiting more tunable by adding several tunable in procfs /proc/sys/lnet/console_{min,max}_delay_centisecs and /proc/sys/lnet/console_backoff.


Severity: enhancement

Bugzilla: 13521

Description: Update kernel patches for SLES10 2.6.16.53-0.8.

Details: Update which_patch & target file for SLES10 latest kernel.


Severity: enhancement

Bugzilla: 13128

Description: add --type and --size parameters to lfs find

Details: Enhance lfs find by adding filetype and filesize parameters. Also multiple OBDs can now be specified for the --obd option.


Severity: enhancement

Bugzilla: 11270

Description: eliminate client locks in face of contention

Details: file contention detection and lockless i/o implementation for contended files.


Severity: enhancement

Bugzilla: 12411

Description: Remove client patches from SLES 10 kernel.

Details: This causes SLES 10 clients to behave as patchless clients even on a Lustre-patched (server) kernel.


Severity: enhancement

Bugzilla: 2369

Description: use i_size_read and i_size_write in 2.6 port

Details: replace inode->i_size access with i_size_read/write()


Severity: enhancement

Bugzilla: 13454

Description: Add jbd statistics patch for RHEL5 and 2.6.18-vanilla.


Severity: enhancement

Bugzilla: 13518

Description: Kernel patches update for RHEL4 2.6.9-55.0.6.

Details: Modify vm-tunables-rhel4.patch.


Severity: enhancement

Bugzilla: 13452

Description: Kernel config for 2.6.18-vanilla.

Details: Modify targets/2.6-vanilla.target.in. Add config file kernel-2.6.18-2.6-vanilla-i686.config. Add config file kernel-2.6.18-2.6-vanilla-i686-smp.config. Add config file kernel-2.6.18-2.6-vanilla-x86_64.config. Add config file kernel-2.6.18-2.6-vanilla-x86_64-smp.config.


Severity: enhancement

Bugzilla: 13207

Description: adapt the lustre_config script to support the upgrade case

Details: Add "-u" option for lustre_config script to support upgrading 1.4 server targets to 1.6 in parallel.


Severity: critical

Frequency: always

Bugzilla: 13751

Description: Kernel patches update for RHEL5 2.6.18-8.1.14.el5.

Details: Modify target file & which_patch. A flaw was found in the IA32 system call emulation provided on AMD64 and Intel 64 platforms. An improperly validated 64-bit value could be stored in the %RAX register, which could trigger an out-of-bounds system call table access. An untrusted local user could exploit this flaw to run code in the kernel (ie a root privilege escalation). (CVE-2007-4573).


Severity: critical

Frequency: always

Bugzilla: 13748

Description: Update RHEL 4 kernel to fix local root privilege escalation.

Details: Update to the latest RHEL 4 kernel to fix the vulnerability described in CVE-2007-4573. This problem could allow untrusted local users to gain root access.


Severity: major

Frequency: occasional

Bugzilla: 14353

Description: excessive CPU consumption on client reduces IO performance

Details: in some cases the ldlm_poold thread is spending too much time trying to cancel locks, and is cancelling them too aggressively and this can severely impact IO performance. Disable the dynamic LRU resize code at build time. It can be re-enabled with configure --enable-lru-resize at build time.


Severity: major

Frequency: occasional

Bugzilla: 13917

Description: MDS hang or stay in waiting lock

Details: If client receive lock with CBPENDING flag ldlm need send lock cancel as separate rpc, to avoid situation when cancel request can't processed due all i/o threads stay in wait lock.


Severity: major

Frequency: occasional

Bugzilla: 11710

Description: improve handling recoverable errors Details: If request processed with error which can be recoverable on server request should be resend, otherwise page released from cache and marked as error.


Severity: normal

Bugzilla: 12302

Description: new userspace socklnd

Details: Old userspace tcpnal that resided in lnet/ulnds/socklnd replaced with new one - usocklnd.


Severity: normal

Frequency: occasional

Bugzilla: 13730

Description: Do not fail import if osc_interpret_create gets -EAGAIN

Details: If osc_interpret_create got -EAGAIN it immediately exits and wakeup oscc_waitq. After wakeup oscc_wait_for_objects call oscc_has_objects and see OSC has no objests and call oscc_internal_create to resend create request.


Severity: normal

Frequency: when removing large files

Bugzilla: 13181

Description: scheduling issue during removal of large Lustre files

Details: Don't take the BKL in fsfilt_ext3_setattr() for 2.6 kernels. It causes scheduling issues when removing large files (17TB in the present case).


Severity: normal

Frequency: always

Bugzilla: 13358

Description: 1.4.11 Can't handle directories with stripe set and extended ACLs

Details: Impossible (EPROTO is returned) to access a directory that has a non-default striping and ACLs.


Severity: normal

Frequency: only on ppc

Bugzilla: 12234

Description: /proc/fs/lustre/devices broken on ppc

Details: The patch as applied to 1.6.2 doesn't look correct for all arches. We should make sure the type of 'index' is loff_t and then cast explicitly as needed below. Do not assign an explicitly cast loff_t to an int.


Severity: normal

Frequency: only for rhel5

Bugzilla: 13616

Description: Kernel patches update for RHEL5 2.6.18-8.1.10.el5.

Details: Modify the target file & which_kernel.


Severity: normal

Frequency: if the uninit_groups feature is enabled on ldiskfs

Bugzilla: 13706

Description: e2fsck reports "invalid unused inodes count"

Details: If a new ldiskfs filesystem is created with the "uninit_groups" feature and only a single inode is created in a group then the "bg_unused_inodes" count is incorrectly updated. Creating a second inode in that group would update it correctly.


Severity: normal

Frequency: only if filesystem is inconsistent

Bugzilla: 11673

Description: handle "serious error: objid * already exists" more gracefully

Details: If LAST_ID value on disk is smaller than the objects existing in the O/0/d* directories, it indicates disk corruption and causes an LBUG(). If the object is 0-length, then we should use the existing object. This will help to avoid a full fsck in most cases.


Severity: normal

Frequency: rarely

Bugzilla: 13570

Description: To avoid grant space > avaible space when the disk is almost full. Without this patch you might see the error "grant XXXX > available" or some LBUG about grant, when the disk is almost full.

Details: In filter_check_grant, for non_grant cache write, we should check the left space by if (*left > ungranted + bytes), instead of (*left > ungranted), because only we are sure the left space is enough for another "bytes", then the ungrant space should be increase. In client, we should update cl_avail_grant only there is OBD_MD_FLGRANT in the reply.


Severity: normal

Frequency: when using O_DIRECT and quotas

Bugzilla: 13930

Description: Incorrect file ownership on O_DIRECT output files

Details: block usage reported by 'lfs quota' does not take into account files that have been written with O_DIRECT.


Severity: normal

Frequency: always

Bugzilla: 13976

Description: touch file failed when fs is not full

Details: OST in recovery should not be discarded by MDS in alloc_qos(), otherwise we can get ENOSP while fs is not full.


Severity: normal

Frequency: always

Bugzilla: 13805

Description: data checksumming impacts single node performance

Details: disable checksums by default since it impacts single node performance. It is still possible to enable checksums by default via "configure --enable-checksum", or at runtime via procfs.


Severity: minor

Frequency: when lov objid is destroyed

Bugzilla: 14222

Description: mds can't recreate lov objid file.

Details: if lov objid file is destroyed and ost with highest index connected first mds not get last objid number from ost. Also if mds get last id from ost his not tell osc about this and it's produce warning about wrong del orphan request.


Severity: minor

Frequency: rarely

Bugzilla: 12948

Description: buffer overruns could theoretically occur

Details: llapi_semantic_traverse() modifies the "path" argument by appending values to the end of the origin string, and a buffer overrun may occur. Adding buffer overrun check in liblustreapi.


Severity: minor

Bugzilla: 13732

Description: change order of libsysio includes

Details: '#include sysio.h' should always come before '#include xtio.h'


Changes from v1.6.2 to v1.6.3

Support for networks: socklnd - any kernel supported by Lustre, qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1 and 1.2, viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x

Support for kernels: 2.6.5-7.286 (SLES 9), 2.6.9-55.0.2.EL (RHEL 4), 2.6.16.46-0.14 (SLES 10), 2.6.18-8.1.8.el5 (RHEL 5), 2.6.18.8 vanilla (kernel.org)

Client support for unpatched kernels: (see http://wiki.lustre.org/index.php?title=Patchless_Client) 2.6.16 - 2.6.22 vanilla (kernel.org)

Due to recently discovered recovery problems, we do not recommend using patchless RHEL 4 clients with this or any earlier release.

Recommended e2fsprogs version: 1.40.2-cfs1

Note that reiserfs quotas are disabled on SLES 10 in this kernel.

Severity: enhancement

Bugzilla: 12192

Description: llapi_file_create() does not allow some changes

Details: add llapi_file_open() that allows specifying the file creation mode and open flags, and also returns an open file handle.


Severity: enhancement

Bugzilla: 12743

Description: df doesn't work properly if diskfs blocksize != 4K

Details: Choose biggest blocksize of OST's as the LOV's blocksize.


Severity: enhancement

Bugzilla: 11248

Description: merge and cleanup kernel patches.

Details: Remove mnt_lustre_list in vfs_intent-2.6-rhel4.patch.


Severity: enhancement

Bugzilla: 13039

Description: RedHat Update kernel for RHEL5

Details: Kernel config file for RHEL5.


Severity: enhancement

Bugzilla: 12446

Description: OSS needs mutliple precreate threads

Details: Add ability to start more than one create thread per OSS.


Severity: enhancement

Bugzilla: 13039

Description: RedHat Update kernel for RHEL5

Details: Modify the kernel config file more closer RHEL5.


Severity: enhancement

Bugzilla: 13360

Description: Build failure against Centos5 (RHEL5)

Details: Define PAGE_SIZE when it isn't present.


Severity: enhancement

Bugzilla: 11401

Description: client-side metadata stat-ahead during readdir(directory readahead)

Details: perform client-side metadata stat-ahead when the client detects readdir and sequential stat of dir entries therein


Severity: enhancement

Bugzilla: 11230

Description: Tune the kernel for good SCSI performance.

Details: Set the value of /sys/block/{dev}/queue/max_sectors_kb to the value of /sys/block/{dev}/queue/max_hw_sectors_kb in mount_lustre.


Severity: critical

Frequency: Always for filesystems larger than 2TB on 32-bit systems.

Bugzilla: 13547 , 13627

Description: Data corruption for OSTs that are formatted larger than 2TB on 32-bit servers.

Details: When generating the bio request for lustre file writes the sector number would overflow a temporary variable before being used for the IO. The data reads correctly from Lustre (which will overflow in a similar manner) but other file data or filesystem metadata may be corrupted in some cases.


Severity: major

Bugzilla: 13236

Description: TOE Kernel panic by ksocklnd

Details: offloaded sockets provide their own implementation of sendpage, can't call tcp_sendpage() directly


Severity: major

Bugzilla: 13482

Description: build error

Details: fix typos in gmlnd, ptllnd and viblnd


Severity: major

Bugzilla: 12932

Description: obd_health_check_timeout too short

Details: set obd_health_check_timeout as 1.5x of obd_timeout


Severity: major

Frequency: only with quota on the root user

Bugzilla: 12223

Description: mds_obd_create error creating tmp object

Details: When the user sets quota on root, llog will be affected and can't create files and write files.


Severity: normal

Bugzilla: 12782

Description: /proc/sys/lnet has non-sysctl entries

Details: Updating dump_kernel/daemon_file/debug_mb to use sysctl variables


Severity: normal

Bugzilla: 10778

Description: kibnal_shutdown() doesn't finish; lconf --cleanup hangs

Details: races between lnd_shutdown and peer creation prevent lnd_shutdown from finishing.


Severity: normal

Bugzilla: 13279

Description: open files rlimit 1024 reached while liblustre testing

Details: ulnds/socklnd must close open socket after unsuccessful 'say hello' attempt.


Severity: normal

Frequency: always on directories with default striping set

Bugzilla: 12836

Description: lfs find on -1 stripe looping in lsm_lmm_verify_common()

Details: Avoid lov_verify_lmm_common() on directory with -1 stripe count.


Severity: normal

Frequency: Always on ia64 patchless client, and possibly others.

Bugzilla: 12826

Description: Add EXPORT_SYMBOL check for node_to_cpumask symbol.

Details: This allows the patchless client to be loaded on architectures without this export.


Severity: normal

Frequency: rare

Bugzilla: 13142

Description: disorder of journal start and llog_add cause deadlock.

Details: in llog_origin_connect, journal start should happen before llog_add keep the same order as other functions to avoid the deadlock.


Severity: normal

Frequency: occasionally when using NFS

Bugzilla: 13030

Description: "ll_intent_file_open()) lock enqueue: err: -13" with nfs

Details: with NFS, the anon dentry's parent was set to itself in d_alloc_anon(), so in MDS, we use rec->ur_fid1 to find the corresponding dentry other than use rec->ur_name.


Severity: normal

Frequency: Occasionally with failover

Bugzilla: 12459

Description: Client eviction due to failover config

Details: after a connection loss, the lustre client should attempt to reconnect to the last active server first before trying the other potential connections.


Severity: normal

Frequency: only with liblustre clients on XT3

Bugzilla: 12418

Description: evictions taking too long

Details: allow llrd to evict clients directly on OSTs


Severity: normal

Bugzilla: 13125

Description: osts not allocated evenly to files

Details: change the condition to increase offset_idx


Severity: normal

Bugzilla: 13436

Description: Only those disconnect error should be returned by rq_status.

Details: In open/enqueue processs, Some errors, which will cause client disconnected, should be returned by rq_status, while other errors should still be returned by intent, then mdc or llite will detect them.


Severity: normal

Bugzilla: 13600

Description: "lfs find -obd UUID" prints directories

Details: "lfs find -obd UUID" will return all directory names instead of just file names. It is incorrect because the directories do not reside on the OSTs.


Severity: normal

Bugzilla: 13596

Description: MDS hang after unclean shutdown of lots of clients

Details: Never resend AST requests.


Severity: normal

Frequency: Always, for kernels after 2.6.16

Bugzilla: 13304

Description: Fix warning idr_remove called for id=.. which is not allocated. Details: Last kernels save old s_dev before kill super and not allow to restore from callback - restore it before call kill_anon_super.


Severity: minor

Bugzilla: 12186

Description: Fix errors in lfs documentation

Details: Fixes man pages


Severity: minor

Frequency: rare

Bugzilla: 12588

Description: when mds and osts use different quota unit(32bit and 64bit), quota will be released repeatly.

Details: void sending multiple quota reqs to mds, which will keep the status between the reqs.


Severity: cleanup

Bugzilla: 13532

Description: rewrite ext2-derived code in llite/dir.c and obdclass/uuid.c

Details: rewrite inherited code (uuid parsing code from ext2 utils and readdir code from ext3) from scratch preserving functionality.


Changes from v1.6.1 to v1.6.2

Support for kernels: 2.6.5-7.286 (SLES 9), 2.6.9-55.0.2.EL (RHEL 4), 2.6.16.46-0.14 (SLES 10), 2.6.18-8.1.8.el5 (RHEL 5), 2.6.18.8 vanilla (kernel.org)

Client support for unpatched kernels: (see http://wiki.lustre.org/index.php? title=Patchless_Client) 2.6.16 - 2.6.22 vanilla (kernel.org)

Due to recently discovered recovery problems, we do not recommend using patchless RHEL 4 clients with this or any earlier release.

Recommended e2fsprogs version: 1.39.cfs8

Note that reiserfs quotas are disabled on SLES 10 in this kernel.

Severity: enhancement

Bugzilla: 12786

Description: lfs setstripe enhancement

Details: Make lfs setstripe understand 'k', 'm' and 'g' for stripe size.


Severity: enhancement

Bugzilla: 12211

Description: randomly memory allocation failure util

Details: Make lustre randomly failed allocating memory for testing purpose.


Severity: enhancement

Bugzilla: 10786

Description: omit set fsid for export NFS

Details: fix set/restore device id for avoid EMFILE error and mark lustre fs as FS_REQUIRES_DEV for avoid problems with generate fsid.


Severity: enhancement

Bugzilla: 10595

Description: Error message improvement.

Details: Merging of two LCONSOLE_ERROR_MSG into one.


Severity: enhancement

Bugzilla: 12606

Description: don't use GFP_* in generic Lustre code.

Details: Use cfs_alloc_* functions and CFS_* flags for code portability.


Severity: enhancement

Bugzilla: 12333

Description: obdclass is limited by single OBD_ALLOC(idarray)

Details: replace OBD_ALLOC/OBD_FREE with OBD_VMALLOC/OBD_VFREE


Severity: enhancement

Bugzilla: 12415

Description: updated patchess for new RHEL4 kernel

Details: Fixed ext3-unlink-race.patch per Kalpak's comment.


Severity: enhancement

Bugzilla: 13006

Description: warnings with build patchless client with vanila 2.6.19 and up

Details: change old ctl_table style and replace ctl_table/ctl_table_header with cfs_sysctl_table_t/cfs_sysctl_table_header_t


Severity: enhancement

Bugzilla: 13093

Description: O_DIRECT bypasses client statistics.

Details: When running with O_DIRECT I/O, neither the client rpc_stats nor read_ahead_stats were updated. Copied stats section from osc_send_oap_rpc() into async_internal().


Severity: enhancement

Bugzilla: 13249

Description: Kernel patches for SLES9 2.6.5-7.286 kernel

Details: Update target/ChangeLog/which_patch .


Severity: enhancement

Bugzilla: 12955

Description: jbd statistics

Details: Port older jbd statistics patch for sles10


Severity: enhancement

Bugzilla: 13360

Description: Build failure against Centos5 (RHEL5)

Details: Use getpagesize() instead of PAGE_SIZE.


Severity: major

Frequency: after network failures

Bugzilla: 12769

Description: Add sync option to mount_lustre.c

Details: Client loses data written to lustre after a network interruption.


Severity: normal

Frequency: mds/oss recovery

Bugzilla: 10800

Description: llog ctxt is refrenced after it has been freed.

Details: llog ctxt refcount was added to avoide the race between ctxt free and llog recovery process. Each llog user must hold ctxt refcount before it access the llog. And the llog ctxt can only be freed when its refcount is zero.


Severity: normal

Frequency: only for SLES10

Bugzilla: 12771

Description: Update kernel patch for SLES10 SP1

Details: Add patch blkdev_tunables-2.6-sles10.patch to 2.6-sles10.series.


Severity: normal

Bugzilla: 11802

Description: lustre support for RHEL5

Details: Add support for RHEL5.


Severity: normal

Frequency: rare

Bugzilla: 11756

Description: umount blocks forever on error

Details: In result of wrong using obd_no_recov and obd_force flags client can hand if cancel or some other requests is lost.


Severity: normal

Frequency: Only for SLES

Bugzilla: 13177

Description: sanity_quota fail test_1

Details: There are multiple occurences of $TSTUSR in SLES's /etc/group file, which makes TSTID[2] inunique.


Severity: normal

Frequency: rare

Bugzilla: 9977

Description: lvbo_init failed for resource with missing objects.

Details: Fix returning error if we do stat for file with missing/corrupted objects and i_size set to all sum of size of all avaible objects. if we to truncate/write to missing object - it is recreated.


Severity: normal Frequency: When flocks are used. Bugzilla: 13103 Description: assertion failure in ldlm_cli_enquque_fini for non NULL lock. Details: Flock locks might destroy just granted lock if it could be merged with another existing flock, this is done in completion handler, so teach ldlm_cli_enquque_fini that this is a valid case for flock locks.


Severity: normal Frequency: Rare Bugzilla: 11974 Description: reply_lock_interpret crash due to race with it and lock cancel. Details: Do not replay locks that are being cancelled. Do not reference locks by their address during replay, just by their handle.


Severity: normal Frequency: only with deactivated OSTs Bugzilla: 11679 Description: lstripe command fails for valid OST index Details: The stripe offset is compared to 'lov->desc.ld_tgt_count' instead of lov->desc.ld_active_tgt_count.


Severity: minor Frequency: rare Bugzilla: 13147 Description: block reactivating mgc import until all deactivates complete Details: Fix race when failing back MDT/MGS to itself (testing)


Severity: minor Frequency: only for Cray XT3 Bugzilla: 11706 Description: peer credits not enough on many OST per OSS systems. Details: Use new lnet way to add credits as we need those for pings and ASTs


Severity: minor Frequency: only with liblustre Bugzilla: 12790 Description: Liblustre is not releasing flock locks on file close. Details: Release flock locks on file close.


Severity: minor Frequency: only for RHEL4 Bugzilla: 12839 Description: Update kernel patches for kernel-2.6.9-55.0.2.EL Details: Remove inode-nr_unused-2.6.9-rhel4.patch from 2.6-rhel4.series Update target file and kernel config.


Severity: minor Frequency: rare Bugzilla: 11327 Description: ASSERTION(export != NULL) failed in target_handle_connect Details: Assetion hit is result of rare race between disconnect and connet to same nid. target_handle_connect found old connect cockie and tried to reconnect, but can't find export for this cockie.


Severity: minor Frequency: rare Bugzilla: 13276 Description: Oops in read and write path when failing to allocate lock. Details: Check if lock allocation failed and return error back.


Changes from v1.6.0.1 to v1.6.1 Support for networks: socklnd - kernels up to 2.6.16, qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1 and 1.2 viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x Support for kernels: 2.6.5-7.283 (SLES 9), 2.6.9-55.EL (RHEL 4), 2.6.16.46-0.14 (SLES 10), 2.6.18.8 vanilla (kernel.org) Client support for unpatched kernels: (see http://wiki.lustre.org/index.php?title=Patchless_Client) 2.6.16 - 2.6.22 vanilla (kernel.org) Due to recently discovered recovery problems, we do not recommend using patchless RHEL 4 clients with this or any earlier release. Recommended e2fsprogs version: 1.39.cfs8 Note that reiserfs quotas are disabled on SLES 10 in this kernel. Starting with this release, the ldiskfs backing filesystem required by Lustre is now in its own package, lustre-ldiskfs. This package should be installed. It is versioned separately from Lustre and may be released separately in future. Severity: enhancement Bugzilla: 12194 Description: add optional extra BUILD_VERSION info Details: add a new environment variable (namely LUSTRE_VERS) which allows to override the lustre version.


Severity: enhancement Bugzilla: 11548 Description: Add LNET router traceability for debug purposes Details: If a checksum failure occurs with a router as part of the IO path, the NID of the last router that forwarded the bulk data is printed so it can be identified.


Severity: enhancement Bugzilla: 10997 Description: lfs setstripe use optional parameters instead of postional parameters.


Severity: enhancement Bugzilla: 10651 Description: Nanosecond timestamp support for ldiskfs Details: The on-disk ldiskfs filesystem has added support for nanosecond resolution timestamps. There is not yet support for this at the Lustre filesystem level.


Severity: enhancement Bugzilla: 10768 Description: 64-bit inode version Details: : Add a on-disk 64-bit inode version for ext3 to track changes made to the inode. This will be required for version-based recovery.


Severity: enhancement Bugzilla: 11563 Description: Add -o localflock option to simulate old noflock behaviour. Details: This will achieve local-only flock/fcntl locks coherentness.


Severity: enhancement Bugzilla: 11647 Description: update patchless client Details: Add support for patchless client with 2.6.20, 2.6.21 and RHEL 5


Severity: enhancement Bugzilla: 10589 Description: metadata RPC reduction (e.g. for rm performance) Details: decrease the amount of synchronous RPC between clients and servers by canceling conflicing lock before the operation on the client and packing thier handles into the main operation RPC to server.


Severity: enhancement Bugzilla: 12605 Description: add #ifdef HAVE_KERNEL_CONFIG_H Details: kernels from 2.6.19 not need include linux/config.h, but add include linux/autoconf.h in commpiler command line.


Severity: enhancement Bugzilla: 12764 Description: patchless client support for 2.6.22 kernel Details: 2.6.22 has only one visble change, SLAB_CTOR_* constants is removed. In this case we need drop using os depended interface to kmem_cache and use cfs_mem_cache API.


Severity: enhancement Bugzilla: 10968 Description: VFS operations stats tool. Details: Tool which collects stats by tracking value written in pid, ppid, gid and uses llstat to generate output to plot graph using plot-llstat Updated lustre/utils/Makefile.am Added lustre/utils/ltrack_stats.c


Severity: enhancement Bugzilla: 11039 Description: 2.6.18 server support (lustre 1.6.1) Details: Support for 2.6.18 kernels on the server side.


Severity: enhancement Bugzilla: 12678 Description: remove fs_prep_san_write operation and related patches Details: remove the ext3-san-jdike patches which are no longer useful.


Severity: enhancement Bugzilla: 4900 Description: Async OSC create to avoid the blocking unnecessarily. Details: If a OST has no remain object, system will block on the creating when need to create a new object on this OST. Now, ways use pre-created objects when available, instead of blocking on an empty osc while others are not empty. If we must block, we block for the shortest possible period of time.


Severity: enhancement Bugzilla: 11721 Description: Add printing inode info into message about error in writepage.


Severity: major Bugzilla: 11971 Description: Accessing a block bevice can re-enable I/O when Lustre is tearing down a device. Details: dev_clear_rdonly(bdev) must be called in kill_bdev() instead of blkdev_put().


Severity: major Frequency: only with mballoc3 code and deep extent trees Bugzilla: 12861 Description: ldiskfs_ext_search_right: bad header in inode: unexpected eh_depth Details: a wrong check of extent headers in ldiskfs_ext_search_right() can cause the filesystem to be remounted read-only.


Severity: normal Frequency: rare Bugzilla: 13129 Description: server LBUG when shutting down Details: Block umount forever until the mount refcount is zero rather than giving up after an arbitrary timeout.


Severity: normal Frequency: 2.6.18 servers only Bugzilla: 12546 Description: ll_kern_mount() doesn't release the module reference Details: The ldiskfs module reference count never drops down to 0 because ll_kern_mount() doesn't release the module reference.


Severity: normal Frequency: rare Bugzilla: 12470 Description: server LBUG when using old ost_num_threads parameter Details: Accept the old ost_num_threads parameter but warn that it is deprecated, and fix an off-by-one error that caused an LBUG.


Severity: normal Frequency: rare Bugzilla: 11722 Description: Transient SCSI error results in persistent IO issue Details: iobuf->dr_error is not reinitialized to 0 between two uses.


Severity: normal Frequency: sometimes when underlying device returns I/O errors Bugzilla: 11743 Description: OSTs not going read-only during write failures Details: OSTs are not remounted read-only when the journal commit threads get I/O errors because fsfilt_ext3 calls journal_start/stop() instead of the ext3 wrappers.


Severity: normal Frequency: SLES10 only Bugzilla: 12538 Description: sanity-quota.sh quotacheck failed: rc = -22 Details: Quotas cannot be enabled on SLES10.


Severity: normal Frequency: liblustre clients only Bugzilla: 12229 Description: getdirentries does not give error when run on compute nodes Details: getdirentries does not fail when the size specified as an argument is too small to contain at least one entry


Severity: normal Frequency: rare Bugzilla: 11315 Description: OST "spontaneously" evicts client; client has imp_pingable == 0 Details: Due to a race condition, liblustre clients were occasionally evicted incorrectly.


Severity: normal Frequency: during server recovery Bugzilla: 11203 Description: MDS failing to send precreate requests due to OSCC_FLAG_RECOVERING Details: request with rq_no_resend flag not awake l_wait_event if they get a timeout.


Severity: normal Frequency: rare Bugzilla: 11818 Description: MDS fails to start if a duplicate client export is detected Details: in some rare cases it was possible for a client to connect to an MDS multiple times. Upon recovery the MDS would detect this and fail during startup. Handle this more gracefully.


Severity: normal Frequency: rare Bugzilla: 12477 Description: Wrong request locking in request set processing Details: ptlrpc_check_set wrongly uses req->rq_lock for proctect add to imp_delayed_list, in this place should be used imp_lock.


Severity: normal Frequency: when reconnecting Bugzilla: 11662 Description: Grant leak when OSC reconnect to OST Details: When osc reconnect ost, OST(filter) should check whether it should grant more space to client by comparing fed_grant and cl_avail_grant, and return the granted space to client instead of "new granted" space, because client will call osc_init_grant to update the client grant space info.


Severity: normal Frequency: when client reconnects to OST Bugzilla: 11662 Description: Grant leak when OSC does a resend and replays bulk write Details: When osc reconnect to OST, OST(filter) should clear grant info of bulk write request, because the grant info while be sync between OSC and OST when reconnect, and we should ignore the grant info these of resend/replay write req.


Severity: normal Frequency: rare Bugzilla: 11662 Description: Grant space more than avaiable space sometimes. Details: When then OST is about to be full, if two bulk writing from different clients came to OST. Accord the avaliable space of the OST, the first req should be permitted, and the second one should be denied by ENOSPC. But if the seconde arrived before the first one is commited. The OST might wrongly permit second writing, which will cause grant space > avaiable space.


Severity: normal Frequency: when client is evicted Bugzilla: 12371 Description: Grant might be wrongly erased when osc is evicted by OST Details: when the import is evicted by server, it will fork another thread ptlrpc_invalidate_import_thread to invalidate the import, where the grant will be set to 0. While the original thread will update the grant it got when connecting. So if the former happened latter, the grant will be wrongly errased because of this race.


Severity: normal Frequency: rare Bugzilla: 12401 Description: Checking Stale with correct fid Details: ll_revalidate_it should uses de_inode instead of op_data.fid2 to check whether it is stale, because sometimes, we want the enqueue happened anyway, and op_data.fid2 will not be initialized.


Severity: normal Frequency: only with 2.4 kernel Bugzilla: 12134 Description: random memory corruption Details: size of struct ll_inode_info is to big for union inode.u and this can be cause of random memory corruption.


Severity: normal Frequency: rare Bugzilla: 10818 Description: Memory leak in recovery Details: Lov_mds_md was not free in an error handler in mds_create_object. It should also check obd_fail before fsfilt_start, otherwise if fsfilt_start return -EROFS,(failover mds during mds recovery). then the req will return with repmsg->transno = 0 and rc = EROFS. and we met hit the assert LASSERT(req->rq_reqmsg->transno == req->rq_repmsg->transno) in ptlrpc_replay_interpret. Fcc should be freed no matter whether fsfilt_commit success or not.


Severity: normal Frequency: rare Bugzilla: 11935 Description: Not check open intent error before release open handle Details: in some rare cases, the open intent error is not checked before release open handle, which may cause ASSERTION(open_req->rq_transno != 0), because it tries to release the failed open handle.


Severity: normal Frequency: rare Bugzilla: 12556 Description: Set cat log bitmap only after create log success. Details: in some rare cases, the cat log bitmap is set too early. and it should be set only after create log success.


Severity: normal Frequency: rare Bugzilla: 12086 Description: the cat log was not initialized in recovery Details: When mds(mgs) do recovery, the tgt_count might be zero, so the unlink log on mds will not be initialized until mds post recovery. And also in mds post recovery, the unlink log will initialization will be done asynchronausly, so there will be race between add unlink log and unlink log initialization.


Severity: normal Bugzilla: 12597 Description: brw_stats were being printed incorrectly Details: brw_stats were being printed as log2 but all of them were not recorded as log2. Also remove some code duplication arising from filter_tally_{read,write}.


Severity: normal Frequency: rare, only in recovery. Bugzilla: 11674 Description: ASSERTION(req->rq_type != LI_POISON) failed Details: imp_lock should be held while iterating over imp_sending_list for prevent destroy request after get timeout in ptlrpc_queue_wait.


Severity: normal Bugzilla: 12689 Description: replay-single.sh test 52 fails Details: A lock's skiplist need to be cleanup when it being unlinked from its resource list.


Severity: normal Frequency: always Bugzilla: 11737 Description: Short directio read returns full requested size rather than actual amount read. Details: Direct I/O operations should return actual amount of bytes transferred rather than requested size.


Severity: normal Bugzilla: 12646 Description: sanity.sh test_77h fails with "test_77h file compare failed" Details: test_77h uses a file which was messed by other test case.


Severity: normal Bugzilla: 12576 Description: Not Check whether lov_tgts is NULL in some lov functions Details: Checking whether lov_tgts is NULL in some functions.


Severity: normal Bugzilla: 11815 Description: replace obdo_alloc() with OBDO_ALLOC macro Details: nothing special is done in obdo_alloc() function, and for debugging purpose, it needs to be replaced with macros.


Severity: normal Bugzilla: 12784 Description: bad return value and errno from fcntl call Details: In liblustre API, errno should be a negative value if error happens.


Severity: normal Bugzilla: 11544 Description: ptlrpc_check_set() LBUG Details: In case of positive reply from server and failed client bulk callback after bulk transfer shouldn't LBUG, but process this request as erroneous.


Severity: normal Frequency: rare Bugzilla: 12696 Description: ASSERTION(imp->imp_conn_current) failed Details: an assertion failure is hit if a client node boots and attempts to mount a lustre filesystem faster than RECONNECT_INTERVAL seconds.


Severity: normal Frequency: only for i686 Bugzilla: 12695 Description: 1.4.11 RC1 build fails for RHEL 4, i686 Details: Fixed config variable for build.


Severity: normal Frequency: rare Bugzilla: 12415 Description: Updated patchess for new RHEL4 kernel Details: Updated patch inode-nr_unused-2.6.9-rhel4.patch Updated patch jbd-stats-2.6.9.patch Updated patch qsnet-rhel4-2.6.patch Updated patch quota-deadlock-on-pagelock-core.patch Updated patch vfs_intent-2.6-rhel4.patch Updated patch vfs_races-2.6-rhel4.patch Updated series file 2.6-rhel4-titech.series Updated series file 2.6-rhel4.series Updated kernel config files


Severity: normal Frequency: rare Bugzilla: 12374 Description: lquota slave complains LBUG when reconnecting with mds or failover in mds. Details: quota slave depends qctxt->lqc_import to send its quota request. This pointer will be invalid if mds did failover or broke its connect to osts, which leads to LBUG.


Severity: normal Frequency: when qunit size is too small(less than 20M) Bugzilla: 12588 Description: write is stopped by improper -EDQUOT Details: If the master is busy and qunit size is small enough(let's say 1M), the slave can not get quota from master on time, which will lead slave to trigger a -EQUOTA to client.


Severity: normal Frequency: rare Bugzilla: 12629 Description: Deadlock during metadata tests Details: in prune_dir_dentries(), shrink_dcache_parent() should not be called with the per-dentry lock held.


Severity: normal Frequency: SLES9 only Bugzilla: 12744 Description: Lustre patched kernel for SLES9 SP3 has NR_CPUS set to 8 Details: set CONFIG_NR_CPUS to 128 instead of 8.


Severity: normal Frequency: rare Bugzilla: 11324 Description: LDISKFS-fs error (device sdc): ldiskfs_free_blocks Details: a disk corruption can cause the mballoc code to assert on a double free or other extent corruptions. Handle these with ext3_error() instead of assertions.


Severity: normal Frequency: rare Bugzilla: 13063 Description: lfsck built against 1.4.x cannot run against 1.6.0 lustre Details: the definition for OBD_IOC_GETNAME changed in 1.6.0. One of the few external users of this ioctl number is lfsck's call to llapi_lov_get_uuids() and this caused lfsck to fail at startup. Add the old ioctl number to the handler so both old and new lfsck can work.


Severity: normal Bugzilla: 11301 Description: parallel lock callbacks Details: Instead of sending blocking and completion callbacks as separated requests, adding them to a set and sending in parallel.


Severity: normal Bugzilla: 12417 Description: Disable most debugging by default Details: To improve performance, disable most logging (for debug purposes) by default. VFSTRACE, RPCTRACE, and DLMTRACE are now off by default, and HA includes fewer messages.


Severity: normal Bugzilla: 11013 Description: hash tables for lists of nids, connections and uuids Details: Hash tables noticeably help when a lot of clients connect to a server, to faster identify duplicate connections or reconnects, also to faster find export to evict in manual eviction case.


Severity: normal Bugzilla: 11190 Description: Sometimes, when the server evict a client, and the client will not be evicted as soon as possible. Details: In enqueue req, the error was returned by intent, instead of rq_status which make ptlrpc layer not detect this error, and does not evict the client. So enqueue error should be returned by rq_status.


Severity: normal Frequency: only for SLES9 Bugzilla: 12543 Description: Routinely utilize latest Quadrics drivers in CFS releases Details: Update patch qsnet-suse-2.6.patch.


Severity: normal Frequency: only for sles10 Bugzilla: 12771 Description: Update patches for SLES 10 SP1 kernel. Details: Update the patch vfs_intent-2.6-sles10.patch.


Severity: normal Frequency: rare Bugzilla: 12543 Description: Routinely utilize latest Quadrics drivers in CFS releases Details: Update patch qsnet-rhel4-2.6.patch.


Severity: normal Frequency: rare Bugzilla: 12975 Description: Using wrong pointer in osc_brw_prep_request Details: Access to array[-1] can produce panic if kernel compiled with CONFIG_PAGE_ALLOC enabled


Severity: normal Frequency: only in recovery Bugzilla: 13148 Description: Mark OST as early accessible if his start SYNC. Details: osc_precreate return flag early accessible if oscc marked as OSCC_FLAG_SYNC_IN_PROGRESS.


Severity: normal Frequency: rare Bugzilla: 13196 Description: Sometimes precreate code can triger create object on wrong ost Details: Wrong protected or not not restored variables aftre precreate loop can produce creation object on wrong ost.


Severity: normal Frequency: oss recovery Bugzilla: 10800 Description: llog_commit_thread cleanup should sync with llog_commit_thread start Details: llog_commit_thread_count should be synced between llog_commit start and cleanup, so new llog_commit thread should not be started when llog_commit threads being stopped to avoid accessing some freed stuff.


Severity: minor Frequency: only with 10000 clients or more Bugzilla: 12364 Description: poor connect scaling with increasing client count Details: Don't run filter_grant_sanity_check for more than 100 exports to improve scaling for large numbers of clients.


Severity: minor Frequency: nfs export on patchless client Bugzilla: 11970 Description: connectathon hang when test nfs export over patchless client Details: Disconnected dentry cannot be found with lookup, so we do not need to unhash it or make it invalid


Severity: minor Frequency: rare Bugzilla: 11546 Description: open req refcounting wrong on reconnect Details: If reconnect happened between getting open reply from server and call to mdc_set_replay_data in ll_file_open, we will schedule replay for unreferenced request that we are about to free. Subsequent close will crash in variety of ways. Check that request is still eligible for replay in mdc_set_replay_data().


Severity: minor Frequency: rare Bugzilla: 11512 Description: disable writes to filesystem when reading health_check file Details: the default for reading the health_check proc file has changed to NOT do a journal transaction and write to disk, because this can cause reads of the /proc file to hang and block HA state checking on a healthy but otherwise heavily loaded system. It is possible to return to the previous behaviour during configure with --enable-health-write.


Severity: minor Frequency: rare Bugzilla: 11658 Description: log_commit_thread vs filter_destroy race leads to crash Details: Take import reference before releasing llog record semaphore


Severity: minor Frequency: only with huge numbers of clients Bugzilla: 11817 Description: Prevents from taking the superblock lock in llap_from_page for a soon died page. Details: using LL_ORIGIN_REMOVEPAGE origin flag instead of LL_ORIGIN_UNKNOW for llap_from_page call in ll_removepage() prevents from taking the superblock lock for a soon died page.


Severity: minor Bugzilla: 11706 Description: service threads may hog cpus when there are a lot of requests Details: Insert cond_resched to give other threads a chance to use some CPU


Severity: minor Frequency: always Bugzilla: 12747 Description: fix mal-formatted messages Details: fix some mal-formatted DEBUG_REQ and LCONSOLE_ERROR_MSG messages


Severity: minor Frequency: always in liblustre Bugzilla: 11737 Description: wrong IS_ERR implementation in liblustre.h Details: fix IS_ERR implementation in liblustre.h for right detect errors.


Severity: minor Frequency: always Bugzilla: 10419 Description: Correct condition for output debug message. Details: inode i_nlink equal zero is not enough for output message about disk corruption, i_ctime and i_mode should be also checked.


Severity: minor Frequency: always in patchless client Bugzilla: 12415 Description: add configure check for truncate_complete_page Details: improve checks for exported symbols. This allow run check without sources, but with Module.symvers shipped with kernel distribution. add check for truncate_complete_page used by patchless client.


Severity: minor Frequency: only run on patchless client. Bugzilla: 12858 Description: use do_facet on sanity.sh for test handling recoverables errors Details: use do_facet instead of direct use sysctl for set fail_loc on OST


Severity: minor Frequency: only at startup Bugzilla: 11778 Description: Delay client connections to MDT until fist MDT->OST connect Details: If a client tried to create a new file before the MDT had connected to any OSTs, the create would return EIO. Now the client will simply block until the MDT connects to the first OST and the create can succeed.


Severity: minor Frequency: at statup only Bugzilla: 12860 Description: mds_lov_synchronize race leads to various problems Details: simultaneous MDT->OST connections at startup can cause the sync to abort, leaving the OSC in a bad state.


Changes from v1.6.0 to v1.6.0.1 Severity: normal Frequency: on some architectures Bugzilla: 12404 Description: 1.6 client sometimes fails to mount from a 1.4 MDT Details: Uninitialized flags sometimes cause configuration commands to be skipped.


Severity: normal Frequency: patchless clients only Bugzilla: 12391 Description: missing __iget() symbol export Details: The __iget() symbol export is missing. To avoid the need for this on patchless clients the deathrow inode reaper is turned off, and we depend on the VM to clean up old inodes. This dependency was during via the fix for bug 12181.


Severity: normal Frequency: always Bugzilla: 12848 Description: sanity.sh fail: test_52b Details: The ll_inode_to_ext_flags() has a glitch which makes MDS return incorrect inode's flags to client.


Changes from v1.4.10 to v1.6.0 CONFIGURATION CHANGE. This version of Lustre WILL NOT INTEROPERATE with older versions automatically. In many cases a special upgrade step is needed. Please read the user documentation before upgrading any part of a 1.4.x system. WARNING: Lustre configuration and startup changes are required with this release. See https://mail.clusterfs.com/wikis/lustre/MountConf for details. Support for kernels: 2.4.21-47.0.1.EL (RHEL 3), 2.6.5-7.283 (SLES 9), 2.6.9-42.0.10.EL (RHEL 4), 2.6.12.6 vanilla (kernel.org), 2.6.16.27-0.9 (SLES10) Client support for unpatched kernels: (see https://mail.clusterfs.com/wikis/lustre/PatchlessClient) 2.6.16 - 2.6.19 vanilla (kernel.org), 2.6.9-42.0.8EL (RHEL 4) Recommended e2fsprogs version: 1.39.cfs6 Note that reiserfs quotas are disabled on SLES 10 in this kernel Severity: enhancement Bugzilla: 4900 Description: Async OSC create to avoid the blocking unnecessarily. Details: If a OST has no remain object, system will block on the creating when need to create a new object on this OST. Now, ways use pre-created objects when available, instead of blocking on an empty osc while others are not empty. If we must block, we block for the shortest possible period of time.


Severity: enhancement Bugzilla: 8007 Description: MountConf Details: Lustre configuration is now managed via mkfs and mount commands instead of lmc and lconf. New obd types (MGS, MGC) are added for dynamic configuration management. See https://mail.clusterfs.com/wikis/lustre/MountConf for details.


Severity: enhancement Bugzilla: 4482 Description: dynamic OST addition Details: OSTs can now be added to a live filesystem


Severity: enhancement Bugzilla: 9851 Description: startup order invariance Details: MDTs and OSTs can be started in any order. Clients only require the MDT to complete startup.


Severity: enhancement Bugzilla: 4899 Description: parallel, asynchronous orphan cleanup Details: orphan cleanup is now performed in separate threads for each OST, allowing parallel non-blocking operation.


Severity: enhancement Bugzilla: 9862 Description: optimized stripe assignment Details: stripe assignments are now made based on ost space available, ost previous usage, and OSS previous usage, in order to try to optimize storage space and networking resources.


Severity: enhancement Bugzilla: 4226 Description: Permanently set tunables Details: All writable /proc/fs/lustre tunables can now be permanently set on a per-server basis, at mkfs time or on a live system.


Severity: enhancement Bugzilla: 10547 Description: Lustre message v2 Details: Add lustre message format v2.


Severity: enhancement Bugzilla: 9866 Description: client OST exclusion list Details: Clients can be started with a list of OSTs that should be declared "inactive" for known non-responsive OSTs.


Severity: enhancement Bugzilla: 10088 Description: fine-grained SMP locking inside DLM Details: Improve DLM performance on SMP systems by removing the single per-namespace lock and replace it with per-resource locks.


Severity: enhancement Bugzilla: 9332 Description: don't hold multiple extent locks at one time Details: To avoid client eviction during large writes, locks are not held on multiple stripes at one time or for very large writes. Otherwise, clients can block waiting for a lock on a failed OST while holding locks on other OSTs and be evicted.


Severity: enhancement Bugzilla: 9293 Description: Multiple MD RPCs in flight. Details: Further unserialise some read-only MDT RPCs - learn about intents. To avoid overly-overloading MDT, introduce a limit on number of MDT RPCs in flight for a single client and add /proc controls to adjust this limit.


Severity: enhancement Bugzilla: 22484 Description: client read/write statistics Details: Add client read/write call usage stats for performance analysis of user processes. /proc/fs/lustre/llite/*/offset_stats shows non-sequential file access. extents_stats shows chunk size distribution. extents_stats_per_process show chunk size distribution per user process.


Severity: enhancement Bugzilla: 22485 Description: per-client statistics on server Details: Add ldlm and operations statistics for each client in /proc/fs/lustre/mds|obdfilter/*/exports/


Severity: enhancement Bugzilla: 22486 Description: improved MDT statistics Details: Add detailed MDT operations statistics in /proc/fs/lustre/mds/*/stats


Severity: enhancement Bugzilla: 10968 Description: VFS operations stats Details: Add client VFS call stats, trackable by pid, ppid, or gid /proc/fs/lustre/llite/*/stats_track_[pid|ppid|gid]


Severity: enhancement Bugzilla: 2258 Description: Dynamic service threads Details: Within a small range, start extra service threads automatically when the request queue builds up.


Severity: enhancement Bugzilla: 11229 Description: Easy OST removal Details: OSTs can be permanently deactivated with e.g. 'lctl conf_param lustre-OST0001.osc.active=0'


Severity: enhancement Bugzilla: 11335 Description: MGS proc entries Details: Added basic proc entries for the MGS showing what filesystems are served.


Severity: enhancement Bugzilla: 10998 Description: provide MGS failover Details: Added config lock reacquisition after MGS server failover.


Severity: enhancement Bugzilla: 11461 Description: add Linux 2.4 support Details: Added support for RHEL 2.4.21 kernel for 1.6 servers and clients


Severity: enhancement Bugzilla: 10902 Description: plain/inodebits lock performance improvement Details: Grouping plain/inodebits in granted list by their request modes and bits policy, thus improving the performance of search through the granted list.


Severity: enhancement Bugzilla: 11667 Description: Add "/proc/sys/lustre/debug_peer_on_timeout" Details: liblustre envirable: LIBLUSTRE_DEBUG_PEER_ON_TIMEOUT boolean to control whether to print peer debug info when a client's RPC times out.


Severity: enhancement Bugzilla: 11264 Description: Add uninit_groups feature to ldiskfs2 to speed up e2fsck Details: The uninit_groups feature works in conjunction with the kernel filesystem code (ldiskfs2 only) and e2fsprogs-1.39-cfs6 to speed up the pass1 processing of e2fsck. This is a read-only feature in ldiskfs2 only, so older kernels and current ldiskfs cannot mount filesystems that have had this feature enabled.


Severity: enhancement Bugzilla: 10816 Description: Improve multi-block allocation algorithm to avoid fragmentation Details: The mballoc3 code (ldiskfs2 only) adds new mechanisms to improve allocation locality and avoid filesystem fragmentation.


Severity: major Frequency: mixed-endian client/server environments Bugzilla: 11214 Description: mixed-endian crashes Details: The new msg_v2 system had some failures in mixed-endian environments.


Severity: major Frequency: when an incorrect nid is specified during startup Bugzilla: 10734 Description: ptlrpc connect to non-existant node causes kernel crash Details: LNET can't be re-entered from an event callback, which happened when we expire a message after the export has been cleaned up. Instead, hand the zombie cleanup off to another thread.


Severity: major Frequency: only if OST filesystem is corrupted Bugzilla: 9829 Description: client incorrectly hits assertion in ptlrpc_replay_req() Details: for a short time RPCs with bulk IO are in the replay list, but replay of bulk IOs is unimplemented. If the OST filesystem is corrupted due to disk cache incoherency and then replay is started it is possible to trip an assertion. Avoid putting committed RPCs into the replay list at all to avoid this issue.


Severity: major Frequency: liblustre (e.g. catamount) on a large cluster with >= 8 OSTs/OSS Bugzilla: 11684 Description: System hang on startup Details: This bug allowed the liblustre (e.g. catamount) client to return to the app before handling all startup RPCs. This could leave the node unresponsive to lustre network traffic and manifested as a server ptllnd timeout.


Severity: major Frequency: only for devices with external journals Bugzilla: 10719 Description: Set external device read-only also Details: During a commanded failover stop, we set the disk device read-only while the server shuts down. We now also set any external journal device read-only at the same time.


Severity: major Frequency: when setting specific ost indicies Bugzilla: 11149 Description: QOS code breaks on skipped indicies Details: Add checks for missing OST indicies in the QOS code, so OSTs created with --index need not be sequential.


Severity: normal Bugzilla: 12123 Description: ENOENT returned for valid filehandle during dbench. Details: Check if a directory has children when invalidating dentries associated with an inode during lock cancellation. This fixes an incorrect ENOENT sometimes seen for valid filehandles during testing with dbench.


Severity: normal Bugzilla: 11330 Description: a large application tries to do I/O to the same resource and dies in the middle of it. Details: Check the req->rq_arrival time after the call to ost_brw_lock_get(), but before we do anything about processing it & sending the BULK transfer request. This should help move old stale pending locks off the queue as quickly as obd_timeout.


Severity: minor Frequency: SFS test only (otherwise harmless) Bugzilla: 6062 Description: SPEC SFS validation failure on NFS v2 over lustre. Details: Changes the blocksize for regular files to be 2x RPC size, and not depend on stripe size.


Severity: minor Frequency: always Bugzilla: 6380 Description: Fix client-side osc byte counters Details: The osc read/write byte counters in /proc/fs/lustre/osc/*/stats are now working


Severity: minor Frequency: always as root on SLES Bugzilla: 10667 Description: Failure of copying files with lustre special EAs. Details: Client side always return success for setxattr call for lustre special xattr (currently only "trusted.lov").


Severity: minor Frequency: always Bugzilla: 10345 Description: Refcount LNET uuids Details: The global LNET uuid list grew linearly with every startup; refcount repeated list entries instead of always adding to the list.


Severity: minor Frequency: only for kernels with patches from Lustre below 1.4.3 Bugzilla: 11248 Description: Remove old rdonly API Details: Remove old rdonly API which unused from at least lustre 1.4.3


Severity: minor Frequency: when upgrading from 1.4 while trying to change parameters Bugzilla: 11692 Description: The wrong (new) MDC name was used when setting parameters for upgraded MDT's. Also allows changing of OSC (and MDC) parameters if --writeconf is specified at tunefs upgrade time.


Changes from v1.6.0 to v1.4.11 Support for networks: socklnd - kernels up to 2.6.16, qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1 viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x Severity: major Bugzilla: 12014 Description: ASSERTION failures when upgrading to the patchless zero-copy socklnd Details: This bug affects "rolling upgrades", causing an inconsistent protocol version negotiation and subsequent assertion failure during rolling upgrades after the first wave of upgrades.


Severity: major Bugzilla: 10916 Description: added LNET self test Details: landing b_self_test


Severity: major Bugzilla: 12316 Description: Add OFED1.2 support to o2iblnd Details: o2iblnd depends on OFED's modules, if out-tree OFED's modules are installed (other than kernel's in-tree infiniband), there could be some problem while insmod o2iblnd (mismatch CRC of ib_* symbols). If extra Module.symvers is supported in kernel (i.e, 2.6.17), this link provides solution: https://bugs.openfabrics.org/show_bug.cgi?id=355 if extra Module.symvers is not supported in kernel, we will have to run the script in bug 12316 to update $LINUX/module.symvers before building o2iblnd. More details about this are in bug 12316.


Severity: normal Bugzilla: 11680 Description: make panic on lbug configurable


Severity: minor Bugzilla: 13288 Description: Initialize cpumask before use


Severity: minor Bugzilla: 11223 Details: Change "dropped message" CERRORs to D_NETERROR so they are logged instead of creating "console chatter" when a lustre timeout races with normal RPC completion.


Severity: minor Details: lnet_clear_peer_table can wait forever if user forgets to clear a lazy portal.


Severity: minor Details: libcfs_id2str should check pid against LNET_PID_ANY.


Severity: minor Frequency: rare Bugzilla: 12227 Description: cfs_duration_{u,n}sec() wrongly calculate nanosecond part of struct timeval. Details: do_div() macro is used incorrectly.


Changes from v1.4.9 to v1.6.0 Support for networks: socklnd - kernels up to 2.6.16, qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1, viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x Severity: enhancement Bugzilla: 10316 Description: Fixed console chatter in case of -ETIMEDOUT.


Severity: enhancement Bugzilla: 11684 Description: Added D_NETTRACE for recording network packet history (initially only for ptllnd). Also a separate userspace ptllnd facility to gather history which should really be covered by D_NETTRACE too, if only CDEBUG recorded history in userspace.


Severity: enhancement Bugzilla: 11094 Description: Multiple instances for o2iblnd Details: Allow multiple instances of o2iblnd to enable networking over multiple HCAs and routing between them.


Severity: major Frequency: rare Bugzilla: 12458 Description: Assertion failure in kernel ptllnd caused by posting passive bulk buffers before connection establishment complete.


Severity: major Frequency: rare Bugzilla: 12455 Description: A race in kernel ptllnd between deleting a peer and posting new communications for it could hang communications - manifesting as "Unexpectedly long timeout" messages.


Severity: major Frequency: rare Bugzilla: 12432 Description: Kernel ptllnd lock ordering issue could hang a node.


Severity: major Frequency: rare Bugzilla: 12016 Description: node crash on socket teardown race


Severity: major Frequency: after Ptllnd timeouts and portals congestion Bugzilla: 11659 Description: Credit overflows Details: This was a bug in ptllnd connection establishment. The fix implements better peer stamps to disambiguate connection establishment and ensure both peers enter the credit flow state machine consistently.


Severity: major Frequency: rare Bugzilla: 11394 Description: kptllnd didn't propagate some network errors up to LNET Details: This bug was spotted while investigating 11394. The fix ensures network errors on sends and bulk transfers are propagated to LNET/lustre correctly.


Severity: major Frequency: rare Bugzilla: 11616 Description: o2iblnd handle early RDMA_CM_EVENT_DISCONNECTED. Details: If the fabric is lossy, an RDMA_CM_EVENT_DISCONNECTED callback can occur before a connection has actually been established. This caused an assertion failure previously.


Severity: major Bugzilla: 11201 Description: lnet deadlock in router_checker Details: turned ksnd_connd_lock, ksnd_reaper_lock, and ksock_net_t:ksnd_lock into BH locks to eliminate potential deadlock caused by ksocknal_data_ready() preempting code holding these locks.


Severity: major Bugzilla: 11126 Description: Millions of failed socklnd connection attempts cause a very slow FS Details: added a new route flag ksnr_scheduled to distinguish from ksnr_connecting, so that a peer connection request is only turned down for race concerns when an active connection to the same peer is under progress (instead of just being scheduled).


Severity: normal Frequency: rare Description: gmlnd ignored some transmit errors when finalizing lnet messages.


Severity: normal Frequency: rare Bugzilla: 11472 Description: Changed the default kqswlnd ntxmsg=512


Severity: minor Frequency: rare Description: Ptllnd didn't init kptllnd_data.kptl_idle_txs before it could be possibly accessed in kptllnd_shutdown. Ptllnd should init kptllnd_data.kptl_ptlid2str_lock before calling kptllnd_ptlid2str.


Severity: minor Frequency: rare Description: ptllnd logs a piece of incorrect debug info in kptllnd_peer_handle_hello.


Severity: minor Frequency: rare Description: the_lnet.ln_finalizing was not set when the current thread is about to complete messages. It only affects multi-threaded user space LNet.


Severity: minor Frequency: 'lctl peer_list' issued on a mx net Bugzilla: 12237 Description: Enable lctl's peer_list for MXLND


Changes from v1.4.9 to v1.4.10 Support for kernels: 2.4.21-47.0.1.EL (RHEL 3) 2.6.5-7.283 (SLES 9) 2.6.9-42.0.10.EL (RHEL 4) 2.6.12.6 vanilla (kernel.org) 2.6.16.27-0.9 (SLES 10) Recommended e2fsprogs version: 1.39.cfs5 Note that reiserfs quotas are disabled on SLES 10 in this kernel Severity: enhancement Bugzilla: 11667 Description: Add "/proc/sys/lustre/debug_peer_on_timeout" (liblustre envirable: LIBLUSTRE_DEBUG_PEER_ON_TIMEOUT) boolean to control whether to print peer debug info when a client's RPC times out.


Severity: enhancement Bugzilla: 11563 Description: Add -o localflock option to simulate old noflock behaviour. Details: This will achieve local-only flock/fcntl locks coherentness.


Severity: enhancement Bugzilla: 11264 Description: Add uninit_groups feature to ldiskfs2 to speed up e2fsck Details: The uninit_groups feature works in conjunction with the kernel filesystem code (ldiskfs2 only) and e2fsprogs-1.39-cfs6 to speed up the pass1 processing of e2fsck. This is a read-only feature in ldiskfs2 only, so older kernels and current ldiskfs cannot mount filesystems that have had this feature enabled.


Severity: enhancement Bugzilla: 10816 Description: Improve multi-block allocation algorithm to avoid fragmentation Details: The mballoc3 code (ldiskfs2 only) adds new mechanisms to improve allocation locality and avoid filesystem fragmentation.


Severity: critical Frequency: occasional, depends on client load and configuration Bugzilla: 12181 , 12203 Description: data loss for recently-modified files Details: In some cases it is possible that recently written or created files may not be written to disk in a timely manner (this should normally be within 30s unless client IO load is very high). The problem appears as zero-length files or files that are a multiple of 1MB in size after a client crash or client eviction that are missing data at the end of the file.


Severity: major Frequency: liblustre (e.g. catamount) on a large cluster with >= 8 OSTs/OSS Bugzilla: 11684 Description: System hang on startup Details: This bug allowed the liblustre (e.g. catamount) client to return to the app before handling all startup RPCs. This could leave the node unresponsive to lustre network traffic and manifested as a server ptllnd timeout.


Severity: major Frequency: rare Bugzilla: 10866 Description: proc file read during shutdown sometimes raced obd removal, causing node crash Details: Add lock to prevent obd access after proc file removal.


Severity: major Frequency: only if OST filesystem is corrupted Bugzilla: 9829 Description: client incorrectly hits assertion in ptlrpc_replay_req() Details: for a short time RPCs with bulk IO are in the replay list, but replay of bulk IOs is unimplemented. If the OST filesystem is corrupted due to disk cache incoherency and then replay is started it is possible to trip an assertion. Avoid putting committed RPCs into the replay list at all to avoid this issue.


Severity: major Frequency: always Bugzilla: 11710 Description: add support PG_writeback bit Details: add support for PG_writeback bit for Lustre, for more carefull work with page cache in 2.6 kernel. This also fix some deadlocks and remove hack for work O_SYNC with 2.6 kernel.


Severity: normal Frequency: frequent on thin XT3 nodes Bugzilla: 10802 Description: UUID collision on thin XT3 Linux nodes Details: UUIDs on Compute Node Linux XT3 nodes were not generated randomly, since we relied on an insufficiently-seeded PRNG.


Severity: normal Frequency: rare Bugzilla: 11693 Description: OSS hangs after "All ost request buffers busy" Details: A deadlock between quota and journal operations caused OSS hangs after printing "All ost request buffers busy."


Severity: normal Frequency: always Bugzilla: 10214 Description: make O_SYNC working on 2.6 kernels Details: 2.6 kernels use different method for mark pages for write, so need add a code to lustre for O_SYNC work.


Severity: normal Frequency: Only for files larger than 4GB on 32-bit clients. Bugzilla: 11237 Description: improperly doing page alignment of locks Details: Modify lustre core code to use CFS_PAGE_* defines instead of PAGE_*. Make CFS_PAGE_MASK a 64-bit mask.


Severity: normal Frequency: rarely Bugzilla: 11203 Description: RPCs being resent when they shouldn't be Details: Some RPCs that should not be resent are being resent. This can cause inconsistencies in the RPC state machine. Do not resend such requests.


Severity: normal Frequency: rare, only with NFS export Bugzilla: 11669 Description: Crash on NFS re-export node Details: under very unusual load conditions an assertion is hit in ll_intent_file_open()


Severity: normal Frequency: always Bugzilla: 10901 Description: large O_DIRECT requests fail under memory pressure/fragmentation Details: Large single O_DIRECT read and write calls can fail to allocate a sufficiently large buffer to process the request. In case of allocation failure the allocation is retried with a smaller buffer and broken into smaller requests.


Severity: normal Frequency: always Bugzilla: 11090 Description: versioning check is incomplete Details: Checking the version difference of client vs. server, report error if the gap is too big.


Severity: minor Frequency: always on liblustre builds Bugzilla: 11175 Description: Cleanup compiler warnings on liblustre


Severity: minor Frequency: always on liblustre builds on XT3 Bugzilla: 12146 Description: LC_CONFIG_CDEBUG don't run while build liblustre on XT3.


Severity: minor Frequency: always Bugzilla: 11110 Description: Failure to close file and release space on NFS Details: Put inode details into lock acquired in ll_intent_file_open. Use mdc_intent_lock in ll_intent_open to properly detect all kind of errors unhandled by mdc_enqueue.


Changes from v1.4.8 to v1.4.9 Support for kernels: 2.6.16.21-0.8 (SLES10), 2.6.9-42.0.3EL (RHEL 4), 2.6.5-7.276 (SLES 9), 2.4.21-47.0.1.EL (RHEL 3), 2.6.12.6 vanilla (kernel.org) Support for networks: socklnd - kernels up to 2.6.15 (I believe this is accurate, SLES10), qswlnd - Qsnet kernel modules 5.20 and later, openiblnd - IbGold 1.8.2, o2iblnd - OFED 1.1, viblnd - Voltaire ibhost 3.4.5 and later, ciblnd - Topspin 3.2.0, iiblnd - Infiniserv 3.3 + PathBits patch, gmlnd - GM 2.1.22 and later, mxlnd - MX 1.2.1 or later, ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x Recommended e2fsprogs version: 1.39.cfs2-0 The backwards-compatible /proc/sys/portals symlink has been removed in this release. Before upgrading, please ensure that you change any configuration scripts or /etc/sysctl.conf files that access /proc/sys/portals/* or sysctl portals.* to use the corresponding entry in /proc/sys/lnet or sysctl lnet.*. This change can be made in advance of the upgrade on any system running Lustre 1.4.6 or newer, since /proc/sys/lnet was added in that version. Note that reiserfs quotas are temporarily disabled on SLES 10 in this kernel. Severity: enhancement Bugzilla: 11245 Description: new ko2iblnd module parameter: ib_mtu Details: the default IB MTU of 2048 performs badly on 23108 Tavor HCAs. You can avoid this problem by setting the MTU to 1024 using this module parameter.

Severity: enhancement Bugzilla: 11118/11620 Description: ptllnd small request message buffer alignment fix Details: Set the PTL_MD_LOCAL_ALIGN8 option on small message receives. Round up small message size on sends in case this option is not supported. 11620 was a defect in the initial implementation which effectively asserted all peers had to be running the correct protocol version which was fixed by always NAK-ing such requests and handling any misalignments they introduce.

Severity: enhancement Bugzilla: 11250 Description: Patchless ZC(zero copy) socklnd Details: New protocol for socklnd, socklnd can support zero copy without kernel patch, it's compatible with old socklnd. Checksum is moved from tunables to modparams.

Severity: enhancement Bugzilla: 11234 Description: Dump XT3 portals traces on kptllnd timeout Details: Set the kptllnd module parameter "ptltrace_on_timeout=1" to dump Cray portals debug traces to a file. The kptllnd module parameter "ptltrace_basename", default "/tmp/lnet-ptltrace", is the basename of the dump file.

Severity: enhancement Bugzilla: 10316 Description: Allow /proc/sys/lnet/debug to be set symbolically Details: Allow debug and subsystem debug values to be read/set by name in addition to numerically, for ease of use.

Severity: critical Frequency: MDS failover only, very rarely Bugzilla: 11125 Description: "went back in time" messages on mds failover Details: The greatest transno may be lost when the current operation finishes with an error (transno==0) and the client's last_rcvd record is over-written. Save the greatest transno in the mds_last_transno for this case.

Severity: major on XT3 Bugzilla: none Description: libcfs overwrites /proc/sys/portals Details: libcfs created a symlink from /proc/sys/portals to /proc/sys/lnet for backwards compatibility. This is no longer required and makes the Cray portals /proc variables inaccessible.

Severity: major Frequency: infrequent Bugzilla: 11308 Description: kernel ptllnd fix bug in connection re-establishment Details: Kernel ptllnd could produce protocol errors e.g. illegal matchbits and/or violate the credit flow protocol when trying to re-establish a connection with a peer after an error or timeout.

Severity: major Frequency: Cray XT3 with more than 4000 clients and multiple jobs Bugzilla: 10906 Description: many clients connecting with IO in progress causes connect timeouts Details: Avoid synchronous journal commits to avoid delays caused by many clients connecting/disconnecting when bulk IO is in progress. Queue liblustre connect requests on OST_REQUEST_PORTAL instead of OST_IO_PORTAL to avoid delays behind potentially many pending slow IO requests.

Severity: major Frequency: rare Bugzilla: 10891 Description: handle->h_buffer_credits > 0, assertion failure Details: h_buffer_credits is zero after truncate, causing assertion failure. This patch extends the transaction or creates new one after truncate.

Severity: major Frequency: rarely, using CFS RAID5 patches in non-standard kernel series Bugzilla: 11313 Description: stale data returned from RAID cache Details: If only a small amount of IO is done to the RAID device before reading it again it is possible to get stale data from the RAID cache instead of reading it from disk.

Severity: major Frequency: always for 2.6.16.27-0.6 sles10 kernel Bugzilla: 11641 Description: lbuild failure Details: extra -0.6 in SLES10 kernel version confuses lbuild. lustre and Linux kernel calculate different kernel release strings if a localversion file is present in the kernel tarball. The fix deletes the localversion file.

Severity: minor Bugzilla: 11312 Description: OFED FMR API change Details: This changes parameter usage to reflect a change in ib_fmr_pool_map_phys() between OFED 1.0 and OFED 1.1. Note that FMR support is only used in experimental versions of the o2iblnd - this change does not affect standard usage at all.

Severity: minor Frequency: rarely Description: When kib(nal|lnd)_del_peer() is called upon a peer whose ibp_tx_queue is not empty, kib(nal|lnd)_destroy_peer()'s 'LASSERT(list_empty(&peer->ibp_tx_queue))' will fail.

Severity: minor Frequency: rarely Description: When ksocknal_del_peer() is called upon a peer whose ksnp_tx_queue is not empty, ksocknal_destroy_peer()'s 'LASSERT(list_empty(&peer->ksnp_tx_queue))' will fail.

Severity: minor Frequency: very rarely Bugzilla: 10727 Description: If ksocknal_lib_setup_sock() fails, a ref on peer is lost. If connd connects a route which has been closed by ksocknal_shutdown(), ksocknal_create_routes() may create new routes which hold references on the peer, causing shutdown process to wait for peer to disappear forever.

Severity: minor Frequency: always for specific kernels and striping counts Bugzilla: 11042 Description: client may get "Matching packet too big" without ACL support Details: Clients compiled without CONFIG_FS_POSIX_ACL get an error message when trying to access files in certain configurations. The clients should in fact be denied when mounting because they do not understand ACLs.

Severity: minor Frequency: always with random mmap IO to multi-striped file Bugzilla: 10919 Description: mmap write might be lost if we are writing to a 'hole' in stripe Details: Only if the hole is at the end of OST object so that kms is too small. Fix is to increase kms accordingly in ll_nopage.

Severity: minor Frequency: rare Bugzilla: 11040 Description: Creating too long symlink causes lustre errors Details: Check symlink and name lengths before sending requests to MDS.

Severity: minor Frequency: MDS failover only, very rarely Bugzilla: 11277 Description: clients may get ASSERTION(granted_lock != NULL) Details: When request was taking a long time, and a client was resending a getattr by name lock request. The were multiple lock requests with the same client lock handle and mds_getattr_name->fixup_handle_for_resent_request found one of the lock handles but later failed with ASSERTION(granted_lock != NULL).

Severity: minor Frequency: depends on hardware Bugzilla: 11540 Description: lustre write performance loss in the SLES10 kernel Details: the performance loss is caused by using of write barriers in the ext3 code. The SLES10 kernel turns barrier support on by default. The fix is to undo that change for ldiskfs.

Severity: normal Frequency: when ptlrpc is under heavy use and runs out of request buffer Bugzilla: 11318 Description: In lnet_match_blocked_msg(), md can be used without holding a ref on it.

Severity: normal Frequency: only in configurations with LNET routers Bugzilla: 10316 Description: routes automatically marked down and recovered Details: In configurations with LNET routers if a router fails routers now actively try to recover routes that are down, unless they are marked down by an administrator.

Severity: normal Frequency: occasionally with multiple writers to a single file Bugzilla: 11081 Description: shared writes to file may result in wrong size reported by stat() Details: Allow growing of kms when extent lock is cancelled

Severity: normal Frequency: rare, only if OST filesystem is inconsistent with MDS filesystem Bugzilla: 11211 Description: writes to a missing object would leak memory on the OST Details: If there is an inconsistency between the MDS and OST filesystems, such that the MDS references an object that doesn't exist, writes to that object will leak memory due to incorrect cleanup in the error handling path, eventually running out of memory on the OST.

Severity: normal Frequency: only if flock is enabled (not on by default) Bugzilla: 11415 Description: posix locks not released on fd closure on 2.6.9+ Details: We failed to add posix locks to list of inode locks on 2.6.9+ kernels, this caused such locks not to be released on fd close and then assertions on fs unmount about still used locks.

Severity: normal Frequency: NFS re-export or patchless client Bugzilla: 11179, 10796 Description: Crash on NFS re-export node (__d_move) Details: We do not want to hash the dentry is we don't have a lock. But if this dentry is later used in d_move, we'd hit uninitialised list head d_hash, so we just do this to init d_hash field but leave dentry unhashed.

Severity: normal Frequency: NFS re-export or patchless client Bugzilla: 11135 Description: NFS exports has problem with symbolic link Details: lustre client don`t propertly install dentry when re-exported to nfs or run patchless client.

Severity: normal Frequency: NFS re-export or patchless client Bugzilla: 10796 Description: Various nfs/patchless fixes. Details: fixes reuse disconected alias for lookup process - this fixes warning "find_exported_dentry: npd != pd", fix permission error with open files at nfs. fix apply umask when do revalidate.

Severity: normal Frequency: occasional Bugzilla: 11191 Description: Crash on NFS re-export node Details: calling clear_page on the wrong pointer triggered oops in generic_mapping_read().

Severity: normal Frequency: rarely, using O_DIRECT IO Bugzilla: 10903 Description: unaligned directio crashes client with LASSERT Details: check for unaligned buffers before trying any requests.

Changes from v1.4.7.1 to v1.4.8 Support for kernels: 2.6.9-42.0.3EL (RHEL 4) 2.6.5-7.276 (SLES 9) 2.4.21-47.0.1.EL (RHEL 3) 2.6.12.6 vanilla (kernel.org) Severity: enhancement Bugzilla: 10452 Description: Allow recovery/failover for liblustre clients. Details: liblustre clients were unaware of failover configurations until now.

Severity: enhancement Bugzilla: 10743 Description: user file locks should fail when not mounting with flock option Details: Set up an error-returning stub in ll_file_operations.lock field to prevent incorrect behaviour when client is mounted without flock option. Also, set up properly f_op->flock field for RHEL4 kernels.

Severity: enhancement Bugzilla: 4900 Description: Async OSC create to avoid the blocking unnecessarily. Details: If a OST has no remain object, system will block on the creating when need to create a new object on this OST. Now, ways use pre-created objects when available, instead of blocking on an empty osc while others are not empty. If we must block, we block for the shortest possible period of time.

Severity: enhancement Bugzilla: 10889 Description: Checksum enhancements Details: New checksum enhancements allow for resending RPCs that failed checksum checks.

Severity: enhancement Bugzilla: 7376 Description: Tunables on number of dirty pages in cacche Details: Allow to set limit on number of dirty pages cached.

Severity: major Frequency: quota enabled and large files being deleted Bugzilla: 10707 Description: releasing more than 4GB of quota at once hangs OST Details: If a user deletes more than 4GB of files on a single OST it will cause the OST to spin in an infinite loop. Release quota in < 4GB chunks, or use a 64-bit value for 1.4.7.1+.

Severity: major Frequency: rarely (truncate to non-zero file size after write under load) Bugzilla: 10730, 10687 Description: Files padded with zeros to next 4K multiple Details: With filesystems mounted using the "extents" option (2.6 kernels) it is possible that files that are truncated to a non-zero size immediately after being written are filled with zero bytes beyond the truncated size. No file data is lost.

Severity: major Frequency: extremely rare except on liblustre-based clients Bugzilla: 10480 Description: Lustre space not freed when files are deleted Details: Clean up open-unlinked files after client eviction. Previously the unlink was skipped and the files remained as orphans.

Severity: major Frequency: always Bugzilla: 11103 Description: Broke core dumps to lustre Details: Negative dentry may be unhashed if parent does not have UPDATE lock, but some callers, e.g. do_coredump, expect dentry to be hashed after successful create, hash it in ll_create_it.

Severity: minor Frequency: rare Bugzilla: 10845 Description: statfs data retrieved from /proc may be stale or zero Details: When reading per-device statfs data from /proc, in the {kbytes,files}_{total,free,avail} files, it may appear as zero or be out of date.

Severity: minor Frequency: systems with MD RAID1 external journal devices Bugzilla: 10832 Description: lconf's call to blkid is confused by RAID1 journal devices Details: Use the "blkid -l" flag to locate the MD RAID device instead of returning all block devices that match the journal UUID.

Severity: minor Frequency: always if "lfs find" used on a local file/directory Bugzilla: 10864 Description: "lfs find" segfaults if used on a local file/directory Details: The case where a directory component was not specified wasn't handled correctly. Handle this properly.

Severity: minor Frequency: always on ia64 Bugzilla: 10905 Description: "lfs df" loops on printing out MDS statfs information Details: The obd_ioctl_data was not initialized and in some systems this caused a failure during the ioctl that did not return an error. Initialize the struct and return an error on failure.

Severity: minor Frequency: SLES 9 only Bugzilla: 10667 Description: Error of copying files with lustre special EAs as root Details: Client side always return success for setxattr call for lustre special xattr (currently only "trusted.lov").

Severity: minor Frequency: liblustre clients only Bugzilla: 10883 Description: Race in 'instant cancel' lock handling could lead to such locks never to be granted in case of SMP MDS Details: Do not destroy not yet granted but cbpending locks in handle_enqueue

Severity: minor Frequency: replay/resend of open Bugzilla: 10991 Description: non null lock assetion failure in mds_intent_policy Details: Trying to replay/resend lockless open requests resulted in mds_open() returning 0 with no lock. Now it sets a flag if a lock is going to be returned.

Severity: normal Frequency: always, for aggregate stripe size over 4GB Bugzilla: 10725 Description: "lfs setstripe" fails assertion when setting 4GB+ stripe width Details: Using "lfs setstripe" to set stripe size * stripe count over 4GB will fail the kernel with "ASSERTION(lsm->lsm_xfersize != 0)"

Severity: normal Frequency: always on ppc64 Bugzilla: 10634 Description: the write to an ext3 filesystem mounted with mballoc got stuck Details: ext3_mb_generate_buddy() uses find_next_bit() which does not perform endianness conversion.

Severity: normal Frequency: rarely on clusters with both ia64+i386 clients Bugzilla: 10672 Description: ia64+i686 clients doing shared IO on the same file may LBUG Details: In rare cases when both ia64+i686 (or other mixed-PAGE_SIZE) clients are doing concurrent writes to the same file it is possible that the ia64 clients may LASSERT because the OST extent locks are not PAGE_SIZE aligned. Ensure that grown locks are always aligned on the request boundary.

Severity: normal Frequency: always Bugzilla: 7040 Description: Overwriting in use executable truncates on-disk binary image Details: If one node attempts to overwrite an executable in use by another node, we now correctly return ETXTBSY instead of truncating the file.

Severity: normal Frequency: always Bugzilla: 2707 Description: chmod on Lustre root is propagated to other clients Details: Re-validate root's dentry in ll_lookup_it to avoid having it invalid by the follow_mount time.

Severity: normal Frequency: rare Bugzilla: 10643 Description: client crash on unmount - lock still has references Details: In some error handling cases it was possible to leak a lock reference on a client while accessing a file. This was not harmful to the client during operation, but would cause the client to crash when the filesystem is unmounted.

Severity: normal Frequency: always Bugzilla: 10921 Description: ETXTBSY on mds though file not in use by client Details: ETXTBSY is no longer incorrectly returned when attempting to chmod or chown a directory that the user previously tried to execute or a currently-executing binary.

Severity: normal Frequency: rare Bugzilla: 10999 Description: OST failure "would be an LBUG" in waiting_locks_callback() Details: In some cases it was possible to send a blocking callback to a client doing a glimpse, even though that client didn't get a lock granted. When the glimpse lock is cancelled on the OST the freed lock is left on the waiting list and corrupted the list.

Changes from v1.4.7 to v1.4.7.1 Support for kernels: 2.6.9-42.0.2.EL (RHEL 4) 2.6.5-7.276 (SLES 9) 2.4.21-40.EL (RHEL 3) 2.6.12.6 vanilla (kernel.org) bug fix Severity: major Frequency: always on RHEL 3 Bugzilla: 10867 Description: Number of open files grows over time Details: The number of open files grows over time, whether or not Lustre is started. This was due to a filp leak introduced by one of our kernel patches.

Changes from v1.4.6 to v1.4.7 Support for kernels: 2.6.9-42.EL (RHEL 4) 2.6.5-7.267 (SLES 9) 2.4.21-40.EL (RHEL 3) 2.6.12.6 vanilla (kernel.org) Severity: enhancement Bugzilla: 3627 Description: add TCP zero-copy support to kernel Details: Add support to the kernel TCP stack to allow zero-copy bulk sends if the hardware supports scatter-gather and checksumming. This allows socklnd to do client-write and server-read more efficiently and reduce CPU utilization from skbuf copying.

Severity: enhancement Bugzilla: 9340 Description: allow number of MDS service threads to be changed at module load Details: It is now possible to change the number of MDS service threads running. Adding "options mds mds_num_threads={N}" to the MDS's /etc/modprobe.conf will set the number of threads for the next time Lustre is restarted (assuming the "mds" module is also reloaded at that time). The default number of threads will stay the same, 32 for most systems.

Severity: enhancement Bugzilla: 10193 (patchless) Description: Remove dependency on various unexported kernel interfaces. Details: No longer need reparent_to_init, exit_mm, exit_files, sock_getsockopt, filemap_populate, FMODE_EXEC, put_filp.

Severity: enhancement Bugzilla: 10420 Description: Support NFS exporting on 2.6 kernels. Details: Implement non-rawops metadata methods for NFS server to use without changing NFS server code.

Severity: enhancement Bugzilla: 9293, 9385 Description: MDS RPCs are serialised on client. This is unnecessary for some. Details: Do not serialize getattr (non-intent version) and statfs.

Severity: Enhancement Bugzilla: 10482 Description: Cache open file handles on client. Details: MDS now will return special lock along with openhandle, if requested and client is allowed to hold openhandle, even if unused, until such a lock is revoked. Helps NFS a lot, since NFS is opening closing files for every read/write openration.

Severity: Enhancement Bugzilla: 9291 Description: Cache open negative dentries on client when possible. Details: Guard negative dentries with UPDATE lock on parent dir, drop negative dentries on lock revocation.

Severity: enhancement Description: Include MPICH 1.2.6 Lustre ADIO interface patch Details: In lustre/contrib/ or /usr/share/lustre in RPM a patch for MPICH is included to add Lustre-specific ADIO interfaces. This is based closely on the UFS ADIO layer and only differs in file creation, in order to allow the OST striping to be set. This is user-contributed code and not supported by CFS.

Severity: enhancement Frequency: Always Bugzilla: 10248 Description: Allow fractional MB tunings for lustre in /proc/ filesystem. Details: Many of the /proc/ tunables can only be tuned at a megabyte granularity. Now, Fractional MB granularity is be supported, this is very useful for low memory system.

Severity: enhancement Bugzilla: 9292 Description: Getattr by fid Details: Getting a file attributes by its fid, obtaining UPDATE|LOOKUP locks, avoids extra getattr rpc requests to MDS, allows '/' to have locks and avoids getattr rpc requests for it on every stat.

Severity: enhancement Bugzilla: 10462 Description: add client O_DIRECT support for 2.6 kernels Details: It is now possible to do O_DIRECT reads and writes to files in the Lustre client mountpoint on 2.6 kernel clients.

Severity: enhancement Bugzilla: 10446 Description: parallel glimpse, setattr, statfs, punch, destroy requests Details: Sends glimpse, setattr, statfs, punch, destroy requests to OSTs in parallel, not waiting for response from every OST before sending a rpc to the next OST.

Severity: enhancement Bugzilla: 10318 Description: Bring 'lfs find' closer in line with regular Linux find. Details: lfs find util supports -atime, -mtime, -ctime, -maxdepth, -print, -print0 options and obtains all the needed info through the lustre ioctls.

Severity: enhancement Bugzilla: 6221 Description: support up to 1024 configured devices on one node Details: change obd_dev array from statically allocated to dynamically allocated structs as they are first used to reduce memory usage

Severity: enhancement Bugzilla: 2259 Description: clear OBD RPC statistics by writing to them Details: It is now possible to clear the OBD RPC statistics by writing to the "stats" file.

Severity: critical Frequency: Always, for 32-bit kernel without CONFIG_LBD and filesystem > 2TB Bugzilla: 6191 Description: filesystem corruption for non-standard kernels and very large OSTs Details: If a 32-bit kernel is compiled without CONFIG_LBD enabled and a filesystems larger than 2TB is mounted then the kernel will silently corrupt the start of the filesystem. CONFIG_LBD is enabled for all CFS-supported kernels, but the possibility of this happening with a modified kernel config exists.

Severity: major Frequency: rare Bugzilla: 5719, 9635, 9792, 9684 Description: OST (or MDS) trips assertions in (re)connection under heavy load Details: If a server is under heavy load and cannot reply to new connection requests before the client resends the (re)connect, the connection handling code can behave badly if two service threads are concurrently handing separate (re)connections from the same client. Add better locking to the connection handling code, and ensure that only a single connection will be processed for a given client UUID, even if the lock is dropped.

Severity: major Frequency: rare Bugzilla: 9326, 10402, 10897 Description: client crash in ptlrpcd_wake() thread when sending async RPC Details: It is possible that ptlrpcd_wake() dereferences a freed async RPC. In rare cases the ptlrpcd thread alread processed the RPC before ptlrpcd_wake() was called and the request was freed.

Severity: major Frequency: rare Bugzilla: 10300 Description: OST crash if filesystem is unformatted or corrupt Details: If an OST is started on a device that has never been formatted or if the filesystem is corrupt and cannot even mount then the error handling cleanup routines would dereference a NULL pointer.

Severity: major Frequency: rare (only with non-default dump_on_timeout debug enabled) Bugzilla: 10397 Description: waiting_locks_callback trips kernel BUG if client is evicted Details: Running with the dump_on_timeout debug flag turned on makes it possible that the waiting_locks_callback() can try to dump the Lustre kernel debug logs from an interrupt handler. Defer this log dumping to the expired_lock_main() thread.

Severity: major Frequency: only very large systems with liblustre clients Bugzilla: 7304 Description: slow eviction of liblustre clients with the "evict_by_nid" RPC Details: Use asynchronous set_info RPCs to send the "evict_by_nid" to all OSTs in parallel. This allows the eviction of stale liblustre clients to proceed much faster than if they were done in series, and also offers similar improvements for other set_info RPCs.

Severity: major Frequency: Always, for filesystems larger than 2TB Bugzilla: 6191 Description: ldiskfs crash at mount for filesystem larger than 2TB with mballoc Details: Kenrel kmalloc limits allocations to 128kB and this prevents filesystems larger than 2TB to be mounted with mballoc enabled.

Severity: major Frequency: during server recovery Bugzilla: 10479 Description: crash after server is denying duplicate export Details: If clients are resending connect requests to the server, the server refuses to allow a client to connect multiple times. Fixed a bug in the handling of this case.

Severity: minor Frequency: only if NFS exporting from client Bugzilla: 10258 Description: NULL pointer deref in ll_iocontrol() if chattr mknod file Details: If setting attributes on a file created under NFS that had never been opened it would be possible to oops the client if the file had no objects.

Severity: minor Frequency: always for liblustre Bugzilla: 10290 Description: liblustre client does MDS+OSTs setattr RPC for each write Details: When doing a write from a liblustre client, the client incorrectly issued an RPC to the MDS and each OST the file was striped over in order to update the timestamps. When writing with small chunks and many clients this could overwhelm the MDS with RPCs. In all cases it would slow down the write because these RPCs are unnecessary.

Severity: minor Frequency: Sometimes when using sys_sendfile Bugzilla: 7020 Description: "page not covered by a lock" warnings from ll_readpage Details: sendfile called ll_readpage without right page locks present. Now we introduced ll_file_sendfile that does necessary locking around call to generic_file_sendfile() much like we do in ll_file_read().

Severity: minor Frequency: rare (only users of deprecated and unsupported LDAP config) Bugzilla: 9337 Description: write_conf for zeroconf mount queried LDAP incorrectly for client Details: LDAP apparently contains 'lustreName' attributes instead of 'name'. A simple remapping of the name is sufficient.

Severity: minor Frequency: common Bugzilla: 10265 Description: excessive CPU usage during initial read phase on client Details: During the initial read phase on a client, it would agressively retry readahead on the file, consuming too much CPU and impacting performance (since 1.4.5.8). Improve the readahead algorithm to avoid this, and also improve some other common cases (read of small files in particular, where "small" is files smaller than /proc/fs/lustre/llite/*/max_read_ahead_whole_mb, 2MB by default).

Severity: minor Frequency: rare Bugzilla: 10450 Description: MDS crash when receiving packet with unknown intent. Details: Do not LBUG in unknown intent case, just return -EFAULT

Severity: minor Frequency: occasional, when OST network is overloaded/intermittent Bugzilla: 10416 Description: client evicted by OST after bulk IO timeout Details: If a client sends a bulk IO request (read or write) the OST may evict the client if it is unresposive to its data GET/PUT request. This is incorrect if the network is overloaded (takes too long to transfer the RPC data) or dropped the OST GET/PUT request. There is no need to evict the client at all, since the pinger and/or lock callbacks will handle this, and the client can restart the bulk request.

Severity: minor Frequency: Always when mmapping file with no objects Bugzilla: 10438 Description: client crashes when mmapping file with no objects Details: Check that we actually have objects in a file before doing any operations on objects in ll_vm_open, ll_vm_close and ll_glimpse_size.

Severity: minor Frequency: Rare Bugzilla: 10484 Description: Request leak when working with deleted CWD Details: Introduce advanced request refcount tracking for requests referenced from lustre intent.

Severity: minor Frequency: Always Bugzilla: 10510 Description: Remounting a client read-only wasn't possible with a zconf mount Details: It wasn't possible to remount a client read-only with llmount.

Severity: minor Frequency: Always Bugzilla: 9486 Description: extended inode attributes (immutable, append-only) work improperly when 2.4 and 2.6 kernels are used on client/server or vice versa Details: Introduce kernel-independent values for these flags.

Severity: minor Frequency: rare Bugzilla: 10150 Description: setattr vs write race when updating file timestamps Details: Client processes that update a file timestamp into the past right after writing to the file (e.g. tar) it is possible that the updated file modification time can be reset to the current time due to a race between processing the setattr and write RPC.

Severity: minor Frequency: rare Bugzilla: 10437 Description: Flush dirty partially truncated pages during truncate Details: Immediatelly flush partially truncated pages in filter_setattr, this way we completely avoid having any pages in page cache on OST and can retire ugly workarounds during writes to flush such pages.

Severity: minor Frequency: rare Bugzilla: 10409 Description: i_sem vs transaction deadlock in mds_obd_destroy during unlink. Details: protect inode from truncation within vfs_unlink() context just take a reference before calling vfs_unlink() and release it when parent's i_sem is free.

Severity: minor Frequency: always, if extents are used on OSTs Bugzilla: 10703 Description: index ei_leaf_hi (48-bit extension) is not zeroed in extent index Details: OSTs using the extents format would not zero the high 16 bits of the index physical block number. This is not a problem for any OST filesystems smaller than 16TB, and no kernels support ext3 filesystems larger than 16TB yet. This is fixed in 1.4.7 (all new/modified files) and can be fixed for existing filesystems with e2fsprogs-1.39-cfs1.

Severity: minor Frequency: rare Bugzilla: 9387 Description: import connection selection may be incorrect if timer wraps Details: Using a 32-bit jiffies timer with HZ=1000 may cause backup import connections to be ignored if the 32-bit jiffies counter wraps. Use a 64-bit jiffies counter.

Severity: minor Frequency: very large clusters immediately after boot Bugzilla: 10083 Description: LNET request buffers exhausted under heavy short-term load Details: If a large number of client requests are generated on a service that has previously never seen so many requests it is possible that the request buffer growth cannot keep up with the spike in demand. Instead of dropping incoming requests, they are held in the LND until the RPC service can accept more requests.

Severity: minor Frequency: Sometimes during replay Bugzilla: 9314 Description: Assertion failure in ll_local_open after replay. Details: If replay happened on an open request reply before we were able to set replay handler, reply will become not swabbed tripping the assertion in ll_local_open. Now we set the handler right after recognising of open request

Severity: minor Frequency: very rare Bugzilla: 10584 Description: kernel reports "badness in vsnprintf" Details: Reading from the "recovery_status" /proc file in small chunks may cause a negative length in lprocfs_obd_rd_recovery_status() call to vsnprintf() (which is otherwise harmless). Exit early if there is no more space in the output buffer.

Severity: minor Frequency: rare Bugzilla: 10641 Description: Client mtime is not the same on different clients after utimes Details: In some cases, the client was using the utimes() syscall on a file cached on another node. The clients now validate the ctime from the MDS + OSTs to determine which one is right.

Severity: minor Frequency: always Bugzilla: 10611 Description: Inability to activate failout mode Details: lconf script incorrectly assumed that in pythong string's numeric value is used in comparisons.

Severity: minor Frequency: always with multiple stripes per file Bugzilla: 10671 Description: Inefficient object allocation for mutli-stripe files Details: When selecting which OSTs to stripe files over, for files with a stripe count that divides evenly into the number of OSTs, the MDS is always picking the same starting OST for each file. Return the OST selection heuristic to the original design.

Severity: minor Frequency: rare Bugzilla: 10673 Description: mount failures may take full timeout to return an error Details: Under some heavy load conditions it is possible that a failed mount can wait for the full obd_timeout interval, possibly several minutes, before reporting an error. Instead return an error as soon as the status is known.

Severity: normal Frequency: rare Bugzilla: 10047 Description: NULL pointer deref in llap_from_page. Details: get_cache_page_nowait can return a page with NULL (or otherwise incorrect) mapping if the page was truncated/reclaimed while it was searched for. Check for this condition and skip such pages when doing readahead. Introduce extra check to llap_from_page() to verify page->mapping->host is non-NULL (so page is not anonymous).

Severity: normal Frequency: with certain MDS communication failures at client mount time Bugzilla: 10268 Description: NULL pointer deref after failed client mount Details: a client connection request may delayed by the network layer and not be sent until after the PTLRPC layer has timed out the request. If the client fails the mount immediately it will try to clean up before the network times out the request. Add a reference from the request import to the obd device and delay the cleanup until the network drops the request.

Severity: normal Frequency: occasionally during client (re)connect Bugzilla: 9387 Description: assertion failure during client (re)connect Details: processing a client connection request may be delayed by the client or server longer than the client connect timeout. This causes the client to resend the connection request. If the original connection request is replied in this interval, the client may trip an assertion failure in ptlrpc_connect_interpret() which thought it would be the only running connect process.

Severity: normal Frequency: only with obd_echo servers and clients that are rebooted Bugzilla: 10140 Description: kernel BUG accessing uninitialized data structure Details: When running an obd_echo server it did not start the ping_evictor thread, and when a client was evicted an uninitialized data structure was accessed. Start the ping_evictor in the RPC service startup instead of the OBD startup.

Severity: normal Frequency: very rare (synthetic metadata workload only) Bugzilla: 9974 Description: two racing renames might cause an MDS thread to deadlock Details: Running the "racer" program may cause one MDS thread to rename a file from being the source of a rename to being the target of a rename at exactly the same time that another thread is doing so, and the second thread has already enqueued these locks after doing a lookup of the target and is trying to relock them in order. Ensure that we don't try to re-lock the same resource.

Changes from v1.4.5 to v1.4.6 WIRE PROTOCOL CHANGE. This version of Lustre networking WILL NOT INTEROPERATE with older versions automatically. Please read the user documentation before upgrading any part of a live system. WARNING: Lustre networking configuration changes are required with this release. See https://bugzilla.clusterfs.com/show_bug.cgi?id=10052 for details. Support for kernels: 2.6.9-22.0.2.EL (RHEL 4) 2.6.5-7.244 (SLES 9) 2.6.12.6 vanilla (kernel.org) Severity: enhancement Bugzilla: 7981/8208 Description: Introduced Lustre Networking (LNET) Details: LNET is new networking infrastructure for Lustre, it includes a reorganized network configuration mode (see the user documentation for full details) as well as support for routing between different network fabrics. Lustre Networking Devices (LNDs) for the supported network fabrics have also been created for this new infrastructure.

Severity: enhancement Description: Introduced Access control lists Details: clients can set ACLs on files and directories in order to have more fine-grained permissions than the standard Unix UGO+RWX. The MDS must be started with the "-o acl" mount option.

Severity: enhancement Description: Introduced filesystem quotas Details: Administrators may now establish per-user quotas on the filesystem.

Severity: enhancement Bugzilla: 7982 Description: Configuration change for the XT3 The PTLLND is now used to run Lustre over Portals on the XT3 The configure option(s) --with-cray-portals are no longer used. Rather --with-portals=<path-to-portals-includes> is used to enable building on the XT3. In addition to enable XT3 specific features the option --enable-cray-xt3 must be used.

Severity: enhancement Bugzilla: 7116 Description: 2.6 OST async journal commit and locking fix to improve performance Details: The filter_direct_io()+filter_commitrw_write() journal commits for 2.6 kernels are now async as they already were in 2.4 kernels so that they can commit concurrently with the network bulk transfer. For block-allocated files the filter allocation semaphore is held to avoid filesystem fragmentation during allocation. BKL lock removed for 2.6 xattr operations where it is no longer needed.

Severity: enhancement Bugzilla: 7328 Description: specifying an (invalid) directory default stripe_size of -1 would reset the directory default striping Details: stripe_size -1 was used internally to signal directory stripe removal, now use "all default" to signal dir stripe removal as a directory striping of "all default" is not useful

Severity: enhancement Bugzilla: 7198 Description: doing an ls at the same time as file IO can be slow Details: enqueue and other "small" requests can be blocked behind many large IO requests. Create a new OST IO portal for non-IO requests so they can be processed faster.

Severity: enhancement Bugzilla: 6252 Description: Improve read-ahead algorithm to avoid excessive IO for random reads Details: Existing read-ahead algorithm is tuned for the case of streamlined sequential reads and behaves badly with applications doing random reads. Improve it by reading ahead at least read region, and avoiding excessive large RPC for small reads.

Severity: enhancement Bugzilla: 8330 Description: Creating more than 1000 files for a single job may cause a load imbalance on the OSTs if there are also a large number of OSTs. Details: qos_prep_create() uses an OST index reseed value that is an even multiple of the number of available OSTs so that if the reseed happens in the middle of the object allocation it will still utilize the OSTs as uniformly as possible.

Severity: enhancement Bugzilla: 7304 Description: improve by-nid export eviction on the MDS and OST Details: allow multiple exports with the same NID to be evicted at one time without re-searching the exports list.

Severity: enhancement Bugzilla: 7342 Description: bind OST threads to NUMA nodes to improve performance Details: all OST threads are uniformly bound to CPUs on a single NUMA node and do their allocations there to localize memory access

Severity: enhancement Bugzilla: 7979 Description: llmount can determine client NID directly from Myrinet (GM) Details: the client NID code from gmnalnid was moved directly into llmount, removing the need to use this or specifying the client NID explicitly when mounting GM clients with zeroconf

Severity: enhancement Bugzilla: 9445 Description: remove cleanup logs Details: replace lconf-generated cleanup logs with lustre internal cleanup routines. Eliminates the need for client-cleanup and mds-cleanup logs.

Severity: enhancement Bugzilla: 8592 Description: add support for EAs (user and system) on lustre filesystems Details: it is now possible to store extended attributes in the Lustre client filesystem, and with the user_xattr mount option it is possible to allow users to store EAs on their files also

Severity: enhancement Bugzilla: 7293 Description: Add possibility (config option) to show minimal available OST free space. Details: When compiled with --enable-mindf configure option, statfs(2) (and so, df) will return least minimal free space available from all OSTs as amount of free space on FS, instead of summary of free spaces of all OSTs.

Severity: enhancement Bugzilla: 7311 Description: do not expand extent locks acquired on OST-side Details: Modify ldlm_extent_policy() to not expand local locks, acquired by server: they are not cached anyway.

Severity: enhancement Frequency: if MDS is started with down OST Bugzilla: 9439,5706 Description: Allow startup/shutdown of an MDS without depending on the availability of the OSTs. Details: Asynchronously call mds_lov_synchronize during MDS startup. Add appropriate locking and lov-osc refcounts for safe cleaning. Add osc abort_inflight calls in case the synchronize never started.

Severity: enhancement Bugzilla: 7417 Description: Ability to exchange lustre version between client and servers and issue warnings at client side if client is too old. Also for liblustre clients there is ability to refuse connection of too old clients. Details: New 'version' field is added to connect data structure that is filled with version info. That info is later checked by server and by client.

Severity: enhancement Bugzilla: 9528 Description: allow liblustre clients to delegate truncate locking to OST Details: To avoid overhead of locking, liblustre client instructs OST to take extent lock in ost_punch() on client's behalf. New connection flag is added to handle backward compatibility.

Severity: enhancement Bugzilla: 4928, 7341, 9758 Description: allow number of OST service threads to be specified Details: a module parameter allows the number of OST service threads to be specified via "options ost ost_num_threads={N}" in the OSS's /etc/modules.conf or /etc/modprobe.conf.

Severity: enhancement Frequency: if client is started with failover MDS Bugzilla: 9818 Description: Allow multiple MDS hostnames in the mount command Details: Try to read the configuration from all specified MDS hostnames during a client mount in case the "primary" MDS is down.

Severity: enhancement Bugzilla: 9297 Description: Stop sending data to evicted clients as soon as possible. Details: Check if the client we are about to send or are sending data to was evicted already. (Check is done every second of waiting, for which l_wait_event interface was extended to allow checking of exit condition at specified intervals).

Severity: enhancement Bugzilla: 9477, 9557, 9870 Description: Verify that the MDS configuration logs are updated when xml is Details: Check if the .xml configuration logs are newer than the config logs stored on the MDS and report an error if this is the case. Request --write-conf, or allow starting with --old_conf.

Severity: enhancement Bugzilla: 6034 Description: Handle symlinks in the path when checking if Lustre is mounted. Details: Resolve intermediate symlinks when checking if a client has mounted a filesystem to avoid duplicate client mounts.

Severity: enhancement Bugzilla: 9578 Description: Support for specifying external journal device at mount Details: If an OST or MDS device is formatted with an external journal device, this device major/minor is stored in the ext3 superblock and may not be valid for failover. Allow detecting and specifying the external journal at mount time.

Severity: enhancement Bugzilla: 9461 Description: Implement 'lfs df' to report actual free space on per-OST basis Details: Add sub-command 'df' on 'lfs' to report the disk space usage of MDS/OSDs. Usage: lfs df [-i][-h]. Command Options: '-i' to report usage of objects; '-h' to report in human readable format.

Severity: major Frequency: rare Bugzilla: 7407 Description: Running on many-way SMP OSTs can trigger oops in llcd_send() Details: A race between allocating a new llcd and re-getting the llcd_lock allowed another thread to grab newly-allocated llcd.

Severity: major Frequency: rare Bugzilla: 7359 Description: Fix for potential infinite loop processing records in an llog. Details: If an llog record is corrupted/zeroed, it is possible to loop forever in llog_process(). Validate the llog record length and skip the remainder of the block on error.

Severity: major Frequency: rare Bugzilla: 8322 Description: OST or MDS may oops in ping_evictor_main() Details: ping_evictor_main() drops obd_dev_lock if deleting a stale export but doesn't restart at beginning of obd_exports_timed list afterward.

Severity: major Frequency: rare, only with supplementary groups enabled on SMP 2.6 kernels Bugzilla: 7273 Description: MDS may oops in groups_free() Details: in rare race conditions a newly allocated group_info struct is freed again, and this can be NULL. The 2.4 compatibility code for groups_free() checked for a NULL pointer, but 2.6 did not.

Severity: major Frequency: rare Bugzilla: 5047 Description: data loss during non-page-aligned writes to a single file from both multiple nodes and multiple threads on one node at same time Details: updates to KMS and lsm weren't protected by common lock. Resulting inconsistency led to false short-reads, that were cached and later used by ->prepare_write() to fill in partially written page, leading to data loss.

Severity: major Frequency: when mmap is used/binaries executed from Lustre Bugzilla: 9482 Description: Unmmap pages before throwing them away from read cache. Details: llap_shrink cache now attempts to unmap pages before discarding them (if unmapping failed - do not discard). SLES9 kernel has extra checks that trigger if this unmapping is not done first.

Severity: major Frequency: rare Bugzilla: 6146, 9635, 9895 Description: servers crash with bad pointer in target_handle_connect() Details: In rare cases when a client is reconnecting it was possible that the connection request was the last reference for that export. We would temporarily drop the export reference and get a new one, but this may have been the last reference and the export was just destroyed. Get new reference before dropping old one.

Severity: major Frequency: rare, unless heavy write-truncate concurrency is continuous Bugzilla: 4180, 6984, 7171, 9963, 9331 Description: OST becomes very slow and/or deadlocked during object unlink Details: filter_destroy() was holding onto the parent directory lock while truncating+unlinking objects. For very large objects this may block other threads for a long time and slow overall OST responsiveness. It may also be possible to get a lock ordering deadlock in this case, or run out of journal credits because of the combined truncate+unlink. Solution is to do object truncate first in one transaction without parent lock, and then do the final unlink in a new transaction with the parent lock. This reduces the lock hold time dramatically.

Severity: major Frequency: rare, 2.4 kernels only Bugzilla: 9967 Description: MDS or OST cleanup may trip kernel BUG when dropping kernel lock Details: mds_cleanup() and filter_cleanup() need to drop the kernel lock before unmounting their filesystem in order to avoid deadlock. The kernel_locked() function in 2.4 kernels only checks whether the kernel lock is held, not whether it is this process that is holding it as 2.6 kernels do.

Severity: major Frequency: rare Bugzilla: 9635 Description: MDS or OST may oops/LBUG if a client is connecting multiple times Details: The client ptlrpc code may be trying to reconnect to a down server before a previous connection attempt has timed out. Increase the reconnect interval to be longer than the connection timeout interval to avoid sending duplicate connections to servers.

Severity: major Frequency: rare, 2.6 OSTs only Bugzilla: 10076 Description: OST may deadlock under high load on fragmented files Details: If there was a heavy load and highly-fragmented OST filesystems it was possible to have all the OST threads deadlock waiting on allocation of biovecs, because the biovecs were not released until the entire RPC IO was completed. Instead, release biovecs as soon as they are complete to ensure forward IO progress.

Severity: major Frequency: rare Bugzilla: 10235 Description: Mounting an MDS with pending unlinked files may cause oops Details: target_finish_recovery() calls mds_postrecov() which returned the number of orphans unlinked. mds_lov_connect->mds_postsetup() considers this an error and immediately begins cleaning up the lov, just after starting the mds_lov process

Severity: minor Frequency: rare Bugzilla: 8320 Description: lconf incorrectly determined whether two IP networks could talk Details: In some more complicated routing and multiple-network configurations, lconf will avoid trying to make a network connection to a disjoint part of the IP space. It was doing the math incorrectly for one set of cases.

Severity: minor Frequency: occasional (liblustre only) Bugzilla: 6363 Description: liblustre could not open files whose last component is a symlink Details: sysio_path_walk() would incorrectly pass the open intent to intermediate path components.

Severity: minor Frequency: rare (liblustre only with non-standard tuning) Bugzilla: 7201 (7350) Description: Tuning the MDC DLM LRU size to zero triggers client LASSERT Details: llu_lookup_finish_locks() tries to set lock data on a lock after it has been released, only do this for referenced locks

Severity: minor Frequency: common for large clusters running liblustre clients Bugzilla: 7198 Description: doing an ls when liblustre clients are running is slow Details: sending a glimpse AST to a liblustre client waits for every AST to time out, as liblustre clients will not respond. Since they cannot cache data we refresh the OST lock LVB from disk instead.

Severity: minor Frequency: rare (only HPUX clients mounting unsupported re-exported NFS vol) Bugzilla: 5781 Description: an HPUX NFS client would get -EACCESS when ftruncate()ing a newly created file with mode 000 Details: the Linux NFS server relies on an MDS_OPEN_OWNEROVERRIDE hack to allow an ftruncate() as a non-root user to a file with mode 000. Lustre now respects this flag to disable mode checks when truncating a file owned by the user

Severity: minor Frequency: liblustre-only, when liblustre client dies unexpectedly or becomes busy Bugzilla: 7313 Description: Revoking locks from clients that went dead or catatonic might take a lot of time. Details: New lock flags FL_CANCEL_ON_BLOCK used by liblustre makes cancellation of such locks instant on servers without waiting for any reply from clients. Clients drops these locks when cancel notification from server is received without replying.

Severity: minor Frequency: liblustre-only, when liblustre client dies or becomes busy Bugzilla: 7311 Description: Doing ls on Linux clients can take a long time with active liblustre clients Details: Liblustre client cannot handle ASTs in timely manner, so avoid granting such locks to it in the first place if possible. Locks are taken by proxy on the OST during the read or write and dropped immediately afterward. Add connect flags handling, do not grant locks to liblustre clients for glimpse ASTs.

Severity: minor Frequency: common for liblustre clients doing little filesystem IO Bugzilla: 9352, 7313 Description: server may evict liblustre clients accessing contended locks Details: if a client is granted a lock or receives a completion AST with a blocking AST already set it would not reply to the AST for LDLM_FL_CANCEL_ON_BLOCK locks. It now replies to such ASTs.

Severity: minor Frequency: lfs setstripe, only systems with more than 160 OSTs Bugzilla: 9440 Description: unable to set striping with a starting offset beyond OST 160 Details: llapi_create_file() incorrectly limited the starting stripe index to the maximum single-file stripe count.

Severity: minor Frequency: LDAP users only Bugzilla: 6163 Description: lconf did not handle in-kernel recovery with LDAP properly Details: lconf/LustreDB get_refs() is searching the wrong namespace

Severity: minor Frequency: if client is started with down MDS Bugzilla: 7184 Description: if client is started with down MDS mount hangs in ptlrpc_queue_wait Details: Having an LWI_INTR() wait event (interruptible, but no timeout) will wait indefinitely in ptlrpc_queue_wait->l_wait_event() after ptlrpc_import_delayed_req() because we didn't check if the request was interrupted, and we also didn't break out of the event loop if there was no timeout

Severity: minor Frequency: always, if lconf --abort_recovery used Bugzilla: 7047 Description: lconf --abort_recovery fails with 'Operation not supported' Details: lconf was attempting to abort recovery on the MDT device and not the MDS device

Severity: minor Frequency: rare Bugzilla: 6034 Description: lconf didn't resolve symlinks before checking to see whether a given mountpoint was already in use

Severity: minor Frequency: when migrating failover services Bugzilla: 6395, 9514 Description: When migrating a subset of services from a node (e.g. failback from a failover service node) the remaining services would time out and evict clients. Details: lconf --force (implied by --failover) sets the global obd_timeout to 5 seconds in order to quickly disconnect, but this caused other RPCs to time out too quickly. Do not change the global obd_timeout for force cleanup, only set it for DISCONNECT RPCs.

Severity: minor Frequency: occasional (Cray XT3 only) Bugzilla: 7305 Description: root not authorized to access files in CRAY_PORTALS environment Details: The client process capabilities were not honoured on the MDS in a CRAY_PORTALS/CRAY_XT3 environment. If the file had previously been accessed by an authorized user then root was able to access the file on the local client also. The root user capabilities are now allowed on the MDS, as this environment has secure UID.

Severity: minor Frequency: occasional Bugzilla: 6449 Description: ldiskfs "too long searching" message happens too often Details: A debugging message (otherwise harmless) prints too often on the OST console. This has been reduced to only happen when there are fragmentation problems on the filesystem.

Severity: minor Frequency: rare Bugzilla: 9598 Description: Division by zero in statfs when all OSCs are inactive Details: lov_get_stripecnt() returns zero due to incorrect order of checks, lov_statfs divides by value returned by lov_get_stripecnt().

Severity: minor Frequency: common Bugzilla: 9489, 3273 Description: First write from each client to each OST was only 4kB in size, to initialize client writeback cache, which caused sub-optimal RPCs and poor layout on disk for the first writen file. Details: Clients now request an initial cache grant at (re)connect time and so that they can start streaming writes to the cache right away and always do full-sized RPCs if there is enough data. If the OST is rebooted the client also re-establishes its grant so that client cached writes will be honoured under the grant.

Severity: minor Frequency: common Bugzilla: 7198 Description: Slow ls (and stat(2) syscall) on files residing on IO-loaded OSTs Details: Now I/O RPCs go to different portal number and (presumably) fast lock requests (and glimses) and other RPCs get their own service threads pool that should be able to service those RPCs immediatelly.

Severity: minor Frequency: rare, liblustre only. Bugzilla: 9296, 9581 Description: Two simultaneous writes from liblustre at offset within same page might proceed at the same time overwriting eachother with stale data. Details: I/O lock withing llu_file_prwv was released too early, before data actually was hitting the wire. Extended lock-holding time until server acknowledges receiving data.

Severity: minor Frequency: extremely rare. Never observed in practice. Bugzilla: 9652 Description: avoid generating lustre_handle cookie of 0. Details: class_handle_hash() generates handle cookies by incrementing global counter, and can hit 0 occasionaly (this is unlikely, but not impossible, because initial value of cookie counter is selected randonly). Value of 0 is used as a sentinel meaning "unassigned handle" --- avoid it. Also coalesce two critical sections in this function into one.

Severity: minor Frequency: rare, normally only when NFS exporting is done from client Bugzilla: 9301 Description: 'bad disk LOV MAGIC: 0x00000000' error when chown'ing files without objects Details: Make mds_get_md() recognise empty md case and set lmm size to 0.

Severity: minor Frequency: always, if srand() is called before liblustre initialization Bugzilla: 9794 Description: Liblustre uses system PRNG disturbing its usage by user application Details: Introduce internal to lustre fast and high-quality PRNG for lustre usage and make liblustre and some other places in generic lustre code to use it.

Severity: minor Frequency: rare Bugzilla: 9309 Description: lconf can hit an error exception but still return success. Details: The lconf command catches the Command error exception at the top level script context and will exit with the associated exit status, but doesn't ensure that this exit status is non-zero.

Severity: minor Frequency: rare Bugzilla: 9493 Description: failure of ptlrpc thread startup can cause oops Details: Starting a ptlrpc service thread can fail if there are a large number of threads or the server memory is very fragmented. Handle this without oopsing.

Severity: minor Frequency: always, only if liblustre and non-default acceptor port was used Bugzilla: 9933 Description: liblustre cannot connect to servers with non-default acceptor port Details: tcpnal_set_default_params() was not called and was therefore ignoring the environment varaible TCPNAL_PORT, as well as other TCPNAL_ environment variables

Severity: minor Frequency: rare Bugzilla: 9923 Description: two objects could be created on the same OST for a single file Details: If an OST is down, in some cases it was possible to create two objects on a single OST for a single file. No problems other than potential performance impact and spurious error messages.

Severity: minor Frequency: rare Bugzilla: 5681, 9562 Description: Client may oops in ll_unhash_aliases Details: Client dcache may become inconsistent in race condition. In some cases "getcwd" can fail if the current directory is modified.

Severity: minor Frequency: always Bugzilla: 9942 Description: Inode refcounting problems in NFS export code Details: link_raw functions used to call d_instantiate without obtaining extra inode reference first.

Severity: minor Frequency: rare Bugzilla: 9942, 9903 Description: Referencing freed requests leading to crash, memleaks with NFS. Details: We used to require that call to ll_revalidate_it was always followed by ll_lookup_it. Also with revalidate_special() it is possible to call ll_revalidate_it() twice for the same dentry even if first occurence returned success. This fix changes semantic between DISP_ENQ_COMPLETE disposition flag to mean there is extra reference on a request referred from the intent. ll_intent_release() then releases such a request.

Severity: minor Frequency: rare, normally benchmark loads only Bugzilla: 1443 Description: unlinked inodes were kept in memory on the client Details: If a client is repeatedly creating and unlinking files it can accumulate a lot of stale inodes in the inode slab cache. If there is no other client load running this can cause the client node to run out of memory. Instead flush old inodes from client cache that have the same inode number as a new inode.

Severity: minor Frequency: SLES9 2.6.5 kernel and long filenames only Bugzilla: 9969, 10379 Description: utime reports stale NFS file handle Details: SLES9 uses out-of-dentry names in some cases, which confused the lustre dentry revalidation. Change it to always use the in-dentry qstr.

Severity: minor Frequency: echo_client brw_test command Bugzilla: 9919 Description: fix echo_client to work with OST preallocated code Details: OST preallocation code (5137) didn't take echo_client IO path into account: echo_client calls filter methods outside of any OST thread and, hence, there is no per-thread preallocated pages and buffers to use. Solution: hijack pga pages for IO. As a byproduct, this avoids unnecessary data copying.

Severity: minor Frequency: rare Bugzilla: 3555, 5962, 6025, 6155, 6296, 9574 Description: Client can oops in mdc_commit_close() after open replay Details: It was possible for the MDS to return an open request with no transaction number in mds_finish_transno() if the client was evicted, but without actually returning an error. Clients would later try to replay that open and may trip an assertion Simplify the client close codepath, and always return an error from the MDS in case the open is not successful.

Changes from v1.4.4 to v1.4.5 Severity: enhancement Frequency: occasional, if non-standard max_dirty_mb used Bugzilla: 7138 Description: Client will block write RPCs if not enough grant Details: If a client has max_dirty_mb smaller than max_rpcs_in_flight, then the client will block writes while waiting for another RPC to complete instead of consuming its dirty limit. With change we get improved performance when max_dirty_mb is small.

Severity: enhancement Bugzilla: 3389, 6253 Description: Add support for supplementary groups on the MDS. Details: The MDS has an upcall /proc/fs/lustre/mds/{mds}/group_upcall (set to /usr/sbin/l_getgroups if enabled) which will do MDS-side lookups for user supplementary groups into a cache.

Severity: enhancement Bugzilla: 6902 Description: Add ability to evict clients by NID from MDS. Details: By echoing "nid:$NID" string into /proc/fs/lustre/mds/.../evict_client client with nid that equals to $NID would be instantly evicted from this MDS and from all active OSTs connected to it.

Severity: major Frequency: rare Bugzilla: 7264 Description: Mounting an ldiskfs file system with mballoc may crash OST node. Details: ldiskfs mballoc code may reference an uninitialized buddy struct at startup during orphan unlinking. Instead, skip buddy update before setup, as it will be regenerated after recovery is complete.

Severity: minor Frequency: rare Bugzilla: 7039 Description: If an OST is inactive, its locks might reference stale inodes. Details: lov_change_cbdata() must iterate over all namespaces, even if they are inactive to clear inode references from the lock.

Severity: minor Bugzilla: 7278 Description: O_CREAT|O_EXCL open flags in liblustre always return -EEXIST Details: Make libsysio to not enforce O_EXCL by clearing the flag, for liblustre O_EXCL is enforced by MDS.

Severity: minor Bugzilla: 6455 Description: readdir never returns NULL in liblustre. Details: Corrected llu_iop_getdirentries logic, to return offset of next dentry in struct dirent.

Severity: minor Bugzilla: 7137 Frequency: liblustre only, depends on application IO pattern Description: liblustre clients evicted if not contacting servers Details: Don't put liblustre clients into the ping_evictor list, so they will not be evicted by the pinger ever.

Severity: minor Bugzilla: 7198 Description: Do not query file size twice, somewhat slowing stat(2) calls. Details: lookup_it_finish() used to query file size from OSTs that was not needed.

Severity: minor Bugzilla: 6237 Description: service threads change working directory to that of init Details: Starting lustre service threads may pin the working directory of the parent thread, making that filesystem busy. Threads now change to the working directory of init to avoid this.

Severity: minor Bugzilla: 6827 Frequency: during shutdown only Description: shutdown with a failed MDS or OST can cause unmount to hang Details: Don't resend DISCONNECT messages in ptlrpc_disconnect_import() if server is down.

Severity: minor Bugzilla: 7331 Frequency: 2.6 only Description: chmod/chown may include an extra supplementary group Details: ll{,u}_mdc_pack_op_data() does not properly initialize the supplementary group and if none is specified this is used.

Severity: minor Bugzilla: 5479 (6816) Frequency: rare Description: Racing open + rm can assert client in mdc_set_open_replay_data() Details: If lookup is in progress on a file that is unlinked we might try to revalidate the inode and fail in revalidate after lookup is complete and ll_file_open() enqueues the open again but it_open_error() was not checking DISP_OPEN_OPEN errors correctly.

Severity: minor Frequency: always, if lconf --abort_recovery used Bugzilla: 7047 Description: lconf --abort_recovery fails with 'Operation not supported' Details: lconf was attempting to abort recovery on the MDT device and not the MDS device

Changes from v1.4.3 to v1.4.4 Severity: enhancement Bugzilla: 7015 Description: Addition of lconf --service command line option Details: lconf now accepts a '--service <arg>' option, which is shorthand for 'lconf --group <arg> --select <arg>=<hostname>'

Severity: enhancement Bugzilla: 6101 Description: Failover mode is now the default for OSTs. Details: By default, OSTs will now run in failover mode. To return to the old behaviour, add '--failout' to the lmc line for OSTs.

Severity: enhancement Bugzilla: 1693 Description: Health checks are now provided for MDS and OSTs Details: Additional detailed health check information on MSD and OSTs is now provided through the procfs health_check value.

Severity: critical Bugzilla: 6866 Frequency: rare, only 2.6 kernels Description: Unusual file access patterns on the MDS may result in inode data being lost in very rare circumstances. Details: Bad interaction between the ea-in-inode patch and the "no-read" code in the 2.6 kernel caused the inode and/or EA data not to be read from disk, causing single-file corruption.

Severity: critical Bugzilla: 6998 Frequency: rare, only 2.6 filesystems using extents Description: Heavy concurrent write and delete load may cause data corruption. Details: It was possible under high-load situations to have an extent metadata block in the block device cache from a just-unlinked file overwrite a newly-allocated data block. We now unmap any metadata buffers that alias just-allocated data blocks.

Severity: major Frequency: rare (only unsupported configurations with a node running as an OST and a client) Bugzilla: 6514, 5137 Description: Mounting a Lustre file system on a node running as an OST could lead to deadlocks Details: OSTs now preallocates memory needed to write out data at startup, instead of when needed, to avoid having to allocate memory in possibly low memory situations. Specifically, if the file system is mounted on on OST, memory pressure could force it to try to write out data, which it needed to allocate memory to do. Due to the low memory, it would be unable to do so and the node would become unresponsive.

Severity: major Bugzilla: 6302 Frequency: rare Description: Network or server problems during mount may cause partially mounted clients instead of returning an error. Details: The config llog parsing code may overwrite the error return code during mount error handling, returning success instead of an error.

Severity: minor Frequency: occasional, depends on IO load Bugzilla: 4466 Description: Disk fragmentation on the OSTs could eventually cause slowdowns after numerous create/delete cycles Details: The ext3 inode allocation policy would not allocate new inodes very well on the OSTs because there are no new directories being created. Instead we look for groups with free space if the parent directories are nearly full.

Severity: minor Bugzilla: 6422 Frequency: rare Description: MDS can fail to allocate large reply buffers Details: After long uptimes the MDS can fail to allocate large reply buffers (e.g. zconf client mount config records) due to memory fragmentation or consumption by the buffer cache. Preallocate some large reply buffers so that these replies can be sent even under memory pressure.

Severity: minor Bugzilla: 6266 Frequency: rare (liblustre) Description: fsx running with liblustre complained that using truncate() to extend the file doesn't work. This patch corrects that issue. Details: This is the liblustre equivalent of the fix for bug 6196. Fixes ATTR_SIZE and lsm use in llu_setattr_raw.

Severity: minor Bugzilla: 7241 Frequency: filesystems with default stripe_count larger than 77 Description: lconf+mke2fs fail when formatting filesystem with > 77 stripes Details: lconf specifies an inode size of 4096 bytes when the default stripe_count is larger than 77. This conflicts with the default inode density of 1 per 4096 bytes. Allocate smaller inodes in this case to avoid pinning too much memory for large EAs.

Changes from v1.4.2 to v1.4.3 Severity: enhancement Bugzilla: 5902 Description: New debugging infrastructure for tracking down data corruption Details: The I/O checksum code was replaced to: (a) control it at runtime, (b) cover more of the client-side code path, and (c) try to narrow down where problems occurred

Severity: enhancement Bugzilla: 6296 Description: Default groups are now added by lconf Details: You can now run lconf --group <servicename> without having to manually add groups with lmc.

Severity: enhancement Description: The default stripe count has been changed to 1 Details: The interpretation of the default stripe count (0, to lfs or lmc) has been changed to mean striping across a single OST, rather than all available. For general usage we have found a stripe count of 1 or 2 works best.

Severity: enhancement Description: Add support for compiling against Cray portals. Details: Conditional compiling for some areas that are different on Cray Portals.

Severity: enhancement Bugzilla: 6931 Description: Initial enabling of flock support for clients Details: Implements fcntl advisory locking and file status functions. This feature is provided as an optional mount flag (default off), and is NOT CURRENTLY SUPPORTED. Not all types of record locking are implemented yet, and those that are are not guaranteed to be completely correct in production environments. mount -t lustre -o [flock|noflock] ...

Severity: major Frequency: occasional during --force or --failover shutdown under load Bugzilla: 5949, 4834 Description: Server oops/LBUG if stopped with --force or --failover under load Details: a collection of import/export refcount and cleanup ordering issues fixed for safer force cleanup

Severity: major Frequency: only filesystems larger than 120 OSTs Bugzilla: 5990, 6223 Description: lfs getstripe would oops on a very large filesystem Details: lov_getconfig used kfree on vmalloc'd memory

Severity: major Frequency: rare Bugzilla: 6200 Description: A bug in MDS/OSS recovery could cause the OSS to fail an assertion Details: There's little harm in aborting MDS/OSS recovery and letting it try again, so I removed the LASSERT and return an error instead.

Severity: major Frequency: rare Bugzilla: 3819, 4364, 4397, 6313 Description: Racing close and eviction MDS could cause assertion in mds_close Details: It was possible to get multiple mfd references during close and client eviction, leading to one thread referencing a freed mfd. Severity:: enhancement Bugzilla: 3262, 6359 Description: Attempts to reconnect to servers are now more aggressive. Details: This builds on the enhanced upcall-less recovery that was added in 1.4.2. When trying to reconnect to servers, clients will now try each server in the failover group every 10 seconds. By default, clients would previously try one server every 25 seconds.

Severity: major Frequency: rare Bugzilla: 6371 Description: After recovery, certain operations trigger a failed assertion on a client. Details: Failing over an mds, using lconf -d --failover, while a client was doing a readdir() call would cause the client to LBUG after recovery completed and the readdir() was resent.

Severity: major Frequency: occasional Bugzilla: 6412 Description: Nodes with an elan id of 0 trigger a failed assertion

Severity: major Frequency: Only if a default stripe is set on the filesystem root. Bugzilla: 6367 Description: Setting a default stripe on the filesystem root prevented the filesystem from being remounted. Details: The client was sending extra request flags in the root getattr request and did not allocate a reply buffer for the dir EA.

Severity: major Frequency: occasional, higher if lots of files are accessed by one client Bugzilla: 6159, 6097 Description: Client trips assertion regarding lsm mismatch/magic Details: While revalidating inodes the VFS looks up inodes with ifind() and in rare cases can find an inode that is being freed. The ll_test_inode() code will free the lsm during ifind() when it finds an existing inode and then the VFS later attaches this free lsm to a new inode.

Severity: major Frequency: rare Bugzilla: 6422, 7030 Description: MDS deadlock between mkdir and client eviction Details: Creating a new file via mkdir or mknod (starting a transaction and getting the ns lock) can deadlock with client eviction (gets ns lock and trying to finish a synchronous transaction).

Severity: major Frequency: occasional Bugzilla: 6409, 6834 Description: Creating files with an explicit stripe count may lead to a failed assertion on the MDS Details: If some OSTs are full or unavailable, creating files may trigger a failed assertion on the MDS. Now, Lustre will try to use other servers or return an error to the client.

Severity: major Frequency: occasional Bugzilla: 6198 Description: OSTs running 2.4 kernels but with extents enabled might trip an assertion in the ext3 JBD (journaling) layer. Details: The b_committed_data struct is protected by the big kernel lock in 2.4 kernels, serializing journal_commit_transaction() and ext3_get_block_handle->ext3_new_block->find_next_usable_block() access to this struct. In 2.6 kernels there is finer grained locking to improve SMP performance of the JBD layer.

Severity: minor Frequency: rare (extremely heavy IO load with hundreds of clients) Bugzilla: 6172 Description: Client is evicted, gets IO error writing to file Details: lock ordering changes for bug 5492 reintroduced bug 3267 and caused clients to be evicted for AST timeouts. The fixes in bug 5192 mean we no longer need to have such short AST timeouts so ldlm_timeout has been increased.

Severity: minor Frequency: only filesystems exporting via NFS to Solaris 10 clients Bugzilla: 6242, 6243 Description: reading from files that had been truncated to a non-zero size but never opened returned no data Details: ll_file_read() reads zeros from no-object files to EOF

Severity: minor Frequency: always when accessing e.g. tty/console device nodes Bugzilla: 3790 Description: tty and some other devices nodes cannot be used on lustre Details: file's private_data field is used by device data and lustre values in there got lost. New field was added to struct file to store fs-specific private data.

Severity: minor Frequency: when exporting Lustre via NFS Bugzilla: 5275 Description: NFSD failed occasionally when looking up a path component Details: NFSD is looking up ".." which was broken in ext3 directories that had grown large enough to become hashed.

Severity: minor Frequency: Clusters with multiple interfaces not on the same subnet Bugzilla: 5541 Description: Nodes will repeatedly try to reconnect to an interface which it cannot reach and report an error to the log. Details: Extra peer list entries will be created by lconf with some peers unreachable. lconf now validates the peer before adding it.

Severity: minor Frequency: occasional Description: While starting a server, the fsfilt_ext3 module could not be loaded. Details: CFS's improved ext3 filesystem is named ldiskfs for 2.6 kernels. Previously, lconf would still use the ext3 name when trying to load modules. Now, it will correctly use ext3 on 2.4 and ldiskfs on 2.6.

Severity: minor Frequency: occasional Bugzilla: 6469 Description: Multiple concurrent overlapping read+write on multiple SMP nodes caused lock timeout during readahead (since 1.4.2). Details: Processes doing readahead might match a lock that hasn't been granted yet if there are overlapping and conflicting lock requests. The readahead process waits on ungranted lock (original lock is CBPENDING), while OST waits for that process to cancel CBPENDING read lock and eventually evicts client.

Severity: minor Bugzilla: 6147 Description: Changes the "SCSI I/O Stats" kernel patch to default to "enabled"

Changes from v1.4.1 to v1.4.2 Note: Lustre 1.4.2 uses a network protocol incompatible with previous versions of Lustre. Please update all servers and clients to version 1.4.2 or later at the same time. You must also update the configuration logs.

If you get AttributeErrors when running lconf, see the Knowledge Base.

Severity: Enhancement Description: Upcalls are no longer needed for clients to recover to failover servers. (3262)

Severity: Enhancement Description: When creating new directories, inherit the parent's custom striping settings if present. (3048)

Severity: Enhancement Description: Servers are now more enthusiastic about evicting unresponsive clients, which increases the likliness of successful recovery. (5921)

Severity: Enhancement Description: Quadrics Elan drivers are now included in our kernel for the RHEL 3 2.4 and SLES 9 2.6 kernels.

Severity: Enhancement Description: Changes to the network protocols were made to increase interoperability with future versions of Lustre. This reduces the need to upgrade whole clusters at a time. (6007)

Severity: Enhancement Description: Protocol changes to support quota were added in this release. Actual quota functionality will be present in a future release.

Severity: Enhancement Description: Mixed endian and word size environments are now supported.

Severity: Enhancement Description: Change the default MDS formatting parameters to create more inodes (1 per 4 kB, instead of 1 per 8 kB).

Severity: Enhancement Description: If you know recovery will not succeed, you can now run "lconf --abort-recovery <config.xml>" instead of waiting for recovery to timeout. (6017)

Severity: Enhancement Description: Another limit on the number of OSTs was removed. (3026)

Severity: Enhancement Description: Improved lustre status init script.

Severity: Enhancement Description: With large configurations, lconf performance is much improved. (6204)

Severity: Enhancement Description: Increased the maximum number of obd devices to 520. (6242)

Severity: Major Frequency: Only on clients using zconf mounting and the unsupported SLES 2.4 kernel Description: The zero-copy TCP patch was causing data corruption, and has been removed. (5902)

Severity: Major Frequency: Occasional Description: Under load, incorrect locking could lead to client hangs and watchdog timeouts on servers. (6077)

Severity: Major Frequency: Rare Description: A race condition could lead to failed assertions on a client. (5666)

Severity: Major Frequency: Rare Description: Disk I/O errors in 2.6 would usually lead to a server panic. (6046)

Severity: Major Frequency: Occasional Description: The fix for 4908 (in 1.4.1 RC1) was not quite complete, and could lead to a failed assertion requiring a reboot. (5653)

Severity: Major Frequency: Occasional Description: Avoid lock ordering deadlock issue with write/truncate. (6203,5654)

Severity: Major Frequency: Rare Description: Some setattr calls on striped files could lead to a server panic. (4554)

Severity: Major Frequency: Rare Description: A locking error path could lead to a failed assertion. (6149, 6148)

Severity: Major Frequency: Rare (Only on clusters with ~200 servers) Description: Clients on filesystems with a large number of servers are unable to create files. (5707)

Severity: Major Frequency: Rare (Only on big-endian clients with a large number of servers) Description: Big-endian clients on filesystems with a large number of servers could oops when mounting. (5861)

Severity: Minor Frequency: Rare (Only when exporting Lustre over NFS to HP-UX clients) Description: HP-UX clients would get an error opening a file with O_TRUNC. (5781)

Severity: Minor Frequency: Occasional Description: In certain cases the Lustre software watchdog could be easily triggered, causing an unnecessary number of messages to be printed to the log files. (5515)

Severity: Minor Frequency: Occasional Description: Renaming one directory over another would leak an inode, causing errors if e2fsck was run. (5953)

Severity: Major Frequency: Occasional (only on 2.6 systems) Description: A subtle change from Linux 2.4 to 2.6 could lead to client threads hanging indefinitely. It would only happen if a timeout occurred in just the right place, but would affect all threads attempting to do I/O -- to any file system -- until the node was rebooted. (5981)

Severity: Minor Frequency: Occasional Description: Display the correct file size in create+truncate+fstat case. (6196)

Severity: Minor Frequency: Rare Description: Correctly handle dentries for mountpoints. (5907)

Severity: Minor Frequency: Rare Description: A race condition could lead to extraneous error messages about lvbo_update. (6170)

Severity: Minor Frequency: Rare (Solaris 10 NFS clients) Description: Correctly handle reads of files with no objects. (6243, 6264)

Severity: Minor Frequency: Rare (only after administrative deactivation of a client/server connection) Description: lctl recover will also mark a device active if deactivate was used. (5933)

Severity: Minor Frequency: Rare Description: Configurations for clients with different nettypes are now properly stored on the MDS. (5619)

Severity: Minor Frequency: Rare Description: Configurations for filesystems not available from an MDS are no longer stored on that MDS. This speeds up the reformat/write_conf process. (5617)

Severity: Minor Frequency: Rare Description: lconf now creates multiple connections when routed OSTs are used. (5201)

Severity: Minor Description: Init scripts are now turned off by default; run chkconfig --on lustre and chkconfig --on lustrefs to turn them on.

Severity: Minor Frequency: Occasional Description: Some modules that were autoloaded are now removed when Lustre is shut down using lconf.

Severity: Minor Frequency: Rare Description: Limit stripes per file to 160 (the maximum EA size). (6093)

Changes from v1.4.1 RC1 to v1.4.1 Final (If you are upgrading from v1.4.0, please also read the changes for v1.4.0 to v1.4.1 RC1) Severity: Enhancement Description: Support has been added for the RHEL 4 kernel on i686. (5773)

Severity: Enhancement Description: Improved error messages have been added in some situations, including at service startup, during recovery, for socket errors, and when incompatible (Lustre 1.4.2+) configuration logs are encountered. (5898, 5864)

Severity: Enhancement Description: mount.lustre now accepts common mount arguments that the client VFS handles for us, such as nodev, nosuid, and noexec. (5637)

Severity: Major Frequency: Common, when serving NFS from a lustre client Description: When serving NFS from a Lustre client, heavy NFS operations could cause a failed assertion on the Lustre client. Note that although we have not yet made significant improvements to NFS performance, some people do it anyway. (4655, 5760)

Severity: Major Frequency: Rare Description: A 2.6-specific race condition could produce crashes (in "ll_unhash_aliases") under load (5687, 5210)

Severity: Major Frequency: Rare Description: If a client tries to mount when some OSTs are down, the OST may think it is already connected, and the client will be unable to mount. (5317)

Severity: Major Frequency: Rare Description: A number of client deadlocks have been fixed; these were most often on 2.6, but could in some rare cases affect 2.4. (5492, 5624, 5654, 5672)

Severity: Major Frequency: Rare Description: An incorrect error path in the lock manager could lead to out-of-sync clients, and long delays while waiting on invalid locks. These delays would affect only certain files, and would never go away until the node was rebooted. (5779)

Severity: Major Frequency: Rare Description: Occasionally the MDS would grant locks to clients that had been evicted, eventually causing the MDS to lock up. (5683)

Severity: Major Frequency: Rare Description: Creating a file whose name begins with . in an unlinked directory could cause an oops. (5548)

Severity: Major Frequency: Rare, only on 2.6 Description: There was a tiny window in the I/O path where, if a thread doing I/O received an interrupt from the disk subsystem to complete a previous I/O, the OSSwould deadlock. (5811)

Severity: Major Frequency: Rare, only on servers with extents enabled Description: When corruption is encountered on an ext3 filesystem using extents, errors are now returned instead of causing a panic. (5733)

Severity: Major Frequency: Only on servers with extents enabled Description: Directories are no longer created using extents to ensure compatibility with all versions of e2fsck. (5909, 5936)

Severity: Major Frequency: Common, only on 64-bit servers with mballoc enabled Description: Fixed 64-bit alignment access, and other mballoc fixes. The code will automatically repair the file system. (5733, 5638)

Severity: Minor in 2.4, Major in 2.6 Frequency: Rare Description: SUID bug (5695) kernel version 43: fix remove_suid bugs in both 2.4 and 2.6. In 2.4 it would cause a minor loss of functionality; in 2.6 it would ASSERT. (5695)

Severity: Minor Frequency: Common, only on SuSE Description: The init scripts now work on SuSE Linux. (5702)

Severity: Minor Frequency: Common, only on 64 bit systems Description: lconf and lmc will now look in /usr/lib64 for Python libraries. (5800)

Severity: Minor Frequency: Common if you tried to fail-back, rare otherwise Description: Many fixes when running lconf --force or lconf --failover were made. (3607, 3651, 4797, 5203, 4834)

Severity: Minor Frequency: Rare Description: Files occasionally have mtime in the future. (4829, 5669)

Severity: Minor Frequency: Rare Description: Some internal timers did not handle wrapping time values leading to stalled recovery. (5882)

Severity: Minor Frequency: Rare Description: When trying to open a file whose parent directory doesn't exist, fix a memory leak and add a negative lookup. (5154)

Changes from v1.4.0 to v1.4.1 RC1 (release candidate; not certified for production use) Severity: enhancement Description: proper mmap locking has been landed again, with considerable improvements from the initial attempt in v1.2.7. This will correct a class of errors which could normally manifest themselves in two ways:


running a binary on node A, then overwriting it on node B, would not cause node A to download a fresh copy. At best, subsequent executions would run the old binary; at worst, the executable would crash, likely with "bus error" if the binary had a stripe count greater than 1, and was large enough that it would be spread across multiple OSTs, then a "bus error" crash was common

Although we have made every effort to thoroughly test this new version, because there were serious problems with the previous mmap code, we are releasing this 1.4.1 release candidate in the hopes that users with test systems can thoroughly stress-test this build before we certify it for production use.

Severity: major Frequency: rare Description: after a backend disk failure which caused some objects to be lost, it was possible to crash an OSS while trying to read data from that object. (5265)

Severity: major Frequency: rare Description: some confusion with lists and locks could lead to an unfortunate list corruption, with the effect of making a server evict the same client, for the same lock, in an infinite loop. (4908)

Severity: minor Frequency: rare Description: an unlikely error at just the right time could leak a Lustre DLM lock on the client, and cause an assertion at shutdown. This was fixed by cleaning up the lock properly after the server indicates an error. (4238)

Severity: major Frequency: common Description: we have received many reports of the VM failing to do its job of discarding unused pages from the page cache, under memory pressure. As a workaround, we try to alleviate this pressure by setting a maximum amount of memory that Lustre will allow to be used by pages in the page cache under Lustre's control. (4699)

Severity: major Frequency: very rare Description: an unlikely error at just the right time could leave a page dirty and locked; this page would never be unlocked, and could cause a deadlock or failure to unmount the file system. (3677)

Severity: major Frequency: common Description: if a user attempted to open() a symlink, that request would be incorrectly saved for later replay during recovery. This replayed request would cause an assertion on the MDS. (3440)

Severity: major Frequency: very rare Description: if an Elan server disappeared from the network fabric in the middle of a zero-copy bulk read, the client would cleanup improperly, and trigger an assertion in the Elan driver. (4012)

Severity: minor Frequency: common Description: fix some small memory leaks in the RPC handling error paths.(5406)

Severity: major Frequency: very rare Description: if some Lustre threads start, but others fail, then a list could be left corrupted. (5160)

Severity: major Frequency: common Description: an off-by-one error in the readahead code could cause it to readahead an extra page, not covered by a lock, which would then stick around in the page cache for a long time. (5388)

Severity: minor Frequency: very rare Description: if multiple processes attempt to manipulate OBD objects (like running multiple "lconf" instances at once), incorrect locking could cause a crash on that node. (5260)

Severity: major Frequency: very rare Description: a race condition in the sync() path left the MDs open to a theoretical crash. (5458)

Severity: major Frequency: common Description: the new multi-block ext3 allocator (mballoc) would try to allocate too many contiguous pages, which could often fail on systems with fragmented memory. Poor error checking in this case would cause a crash. Both have been fixed. (5504)

Severity: major Frequency: always Description: patches were added to the SLES9 2.6 series to address problems in the block device and scsi disk layers. Both had I/O size limits which were too low, and caused serious performance degradation. (5482)

Severity: major Frequency: common Description: the ordering of two inode semaphores changed between Linux 2.4 and 2.6, but it was not documented anywhere. As a result, Lustre still unconditionally took them in the wrong order, which could cause a deadlock if two processes on the same node tried to simultaneously truncate the same file. (5654)

Severity: minor Frequency: common Description: configurations including multiple TCP devices would cause lconf to try to start multiple acceptors, unless you specified different ports for each. (5277)

Severity: major Frequency: very rare Description: a lookup failure in MDS getattr could cause an MDS crash by not handing the error correctly. (5635)

Severity: minor Frequency: common Description: now we return the same kinds of errors that mount(8) does, at least, from our lustre mount handler. Better errors are coming. (5168)

Severity: minor Frequency: common Description: the ppc64/x86_64 spec files were fixed to use %{_libdir} instead of /usr/lib (5389)

Severity: major Frequency: common Description: some kernels would block for memory during readahead in low-memory situations, instead of just failing. This was fixed with a kernel patch to expose a different allocation API. (5383)

Severity: enhancement Description: at some point we lost the ability to do a Lustre ping from userspace; this has been replaced as liblustreapi:llapi_ping, which uses a /proc file on the backend. This has the side effect of fixing "lfs check" to return an error instead of block when the MDS is down. (5628)

Changes from v1.2.8 to v1.4.0 Severity: Enhancement Description: prototype InfiniBand NALs were added to the tree

Severity: Enhancement Description: support for ext3 disk extents and the optimized multi-block allocator were added, to improve I/O performance

Severity: Enhancement Description: the OSS now performes direct I/O reads, as it has always done for writes, bypassing the poorly-performing page cache (4048)

Severity: Enhancement Description: the logical object volume (LOV) was rewritten more sensibly; many bugs were fixed in the process, and the subsystem will be easier to maintain and extend.

Severity: minor Frequency: small, temporary memory leak is guaranteed; crash is extremely rare Description: OST read/write RPC replies did not contain a "last committed" transaction number, so they were being pinned in memory on the client side for longer than necessary. In one extreme case, consisting of an I/O pattern with absolutely no other RPCs, many thousands were pinned in this way until memory was exhausted. (4966)

Severity: minor Frequency: always Description: the kernel primitive that we used in the software watchdog thread caused it to run as uninterruptible, thus artificially increasing the load on the system to a minimum of 1.00 at all times. (5246)

Severity: minor Frequency: rare Description: an acute memory shortage at startup could cause an assertion in at least one place, which we now handle gracefully. (5176)

Severity: minor Frequency: rare Description: failing to allocate memory in one particular spot in the RPC transmit path would cause an assertion (5119)

Severity: minor Frequency: rare Description: on Portals router nodes, dumping the internal state via /proc/sys/portals/routes could cause the system to oops if the routing table was changing at that instant (4827)

Severity: Enhancement Description: Some fixes were made to the flock/lockf code, but it's still disabled (pending 5135)

Changes from v1.2.7 to v1.2.8 Severity: major Frequency: very common Description: a defect in the 1.2.7 networking code caused small messages (stat, create, etc.) to move very slowly over TCP/IP.

Severity: minor Frequency: common Description: users should notice a more accurate "mtime" during and after file writes

Severity: minor Frequency: rare Description: an issue was fixed in which the signals sent by "strace" could cause a Lustre RPC to abort too soon

Severity: minor Frequency: rare Description: if an asynchronous write fails (because a server disk has failed, for example), we now do our best to tell the application that issued the write (although it may not always be possible)

Severity: major Frequency: common Description: Lustre 1.2.7 contained a partial fix for problems which, in certain cases, prevented binaries from being executed properly when stored in Lustre. This introduced different problems, so this code has been removed from 1.2.8 -- mmap support has reverted to the same state as in 1.2.6. A proper fix will appear in an early 1.4.x release.

Severity: severe Frequency: rare Description: An issue was fixed which could cause a page to be incorrectly partially zeroed on the server (resulting in data loss of between 1 and PAGE_SIZE-1 bytes). This was extremely rare, and most likely when using large-page (IA64) clients to write to small-page (IA32, x86-64) servers.

Severity: minor Frequency: common Description: Mounting Lustre could result in significantly-degraded NFS read performance on the same node, because Lustre disables kernel readahead in favour of its own. We now do this in a way that does not impact other file systems.

allocate qswnal tx descriptors singly to avoid fragmentation (4504) don't LBUG on obdo_alloc() failure, use OBD_SLAB_ALLOC() (4800) fix NULL dereference in /proc/sys/portals/routes (4827) allow failed mdc_close() operations to be interrupted (4561) stop precreate on OST before MDS would time out on it (4778) discard client grant for sub-page writes on large-page clients (4520) don't free dentries not owned by NFS code, check generation (4806) fix lsm leak if mds_create_objects() fails (4801) limit debug_daemon file size, always print CERROR messages (4789) use transno after validating reply (3892) process timed out requests if import state changes (3754) update mtime on OST during writes, return in glimpse (4829) add mkfsoptions to LDAP (4679) fix socknal refcount leak preventing cleanup on failed socket (4805) add software watchdogs to catch hung threads quickly (4941) make lustrefs init script start after nfs is mounted fix CWARN/ERROR duplication (4930) support for sles 9 %post scripts support for building 2.6 kernel-source packages support for sles km_* packages Changes from v1.2.6 to v1.2.7 avoid deadlock during client->OST recovery handling

avoid allocating new objects on OSTs that are full

use privileged source ports for client->{MDS,OST} connections deny non-priviledged connections at server by default

Note: Because the servers will reject connections from non-privileged ports by default, it is necessary to update the clients before, or at the same time as the servers. It is not possible to update only the servers unless you specifically disable this security feature.

rate-limit console error and warning messages

handle mmap()ed regions coherently, by using the Lustre DLM. This will correct the "Bus error" symptom occasionally seen when running modified binaries from Lustre.

ignore -ENOENT errors in osc_destroy (3639) notify osc create thread that OSC is being cleaned up (4600) add nettype argument for llmount in #5d in conf-sanity.sh (3936) reconstruct ost_handle() like mds_handle() (4657) create a new thread to do import eviction to avoid deadlock (3969) let lconf resolve symlinked-to devices (4629) allow more than 32,000 subdirectories in a single directory (3244) fix i_blocks count for O_DIRECT writes (3751) OST returns ENOSPC from object create when no space left (4539) don't send truncate RPC if file size isn't changing (4410) limit OSC precreate to 1/2 of value OST considers bogus (4778) rate limit CERROR/CWARN console message to avoid overload (4519) GETFILEINFO dir ioctl returns LOV EA + MDS stat in 1 call (3327) Changes from v1.2.5 to v1.2.6 avoid crash during MDS cleanup with OST shut down (2775) fix loi_list_lock/oig_lock inversion on interrupted IO (4136) don't use bad inodes on the MDS (3744) dynamic object preallocation to improve recovery speed (4236) don't hold spinlock over lock dumping or change debug flags (4401) don't zero obd_dev when it is force cleaned (3651) print grants to console if they go negative (4431) "lctl deactivate" will stop automatic recovery attempts (3406) look for existing locks in ldlm_handle_enqueue() (3764) don't resolve lock handle twice in recovery avoiding race (4401) Changes from v1.2.4 to v1.2.5 MDS->OST orphan recovery fixes reduce lock hold times that may have caused timeouts under load VFS fixes to avoid using invalid dentries don't close LustreDB during write_conf until it is done (3860) fix typo in lconf for_each_profile (3821) allow dumping logs from multiple threads at one time (3820) don't allow multiple threads in OSC recovery(3812) fix debug_size parameters (3864) fix mds_postrecov to initialize import for llog ctxt (3121) replace config semaphore with spinlock (3306) be sure to send a reply for a CANCEL rpc with bad export (3863) don't allow enqueue to complete on a destroyed export (3822) down write_lock before checking llog header bitmap (3825) recover from lock replay timeout (3764) up llog sem before sending rpc (3652) reduce ns lock hold times when setting kms (3267) change a dlm LBUG to LASSERTF, to maybe learn something (4228) fix NULL deref and obd_dev leak on setup error (3312) replace some LBUG about llog ops with error handling (3841) don't match INVALID dentries from d_lookup and spin (3784) hold dcache_lock while marking dentries INVALID and hashing (4255) miscellania add libwrap support for the TCP acceptor (3996) add /proc/sys/portals/routes for non-root route listing (3994) allow setting MDS UUID in .xml (2580) print the stack of a process that LBUGs (4228) Changes from v1.2.3 to v1.2.4 improved IO performance client recovery fixes lower overhead for Lustre debugging logs init scripts for starting Lustre don't cleanup request in ll_file_open() on failed MDS open (3430) make sure to unset replay flag from failed open requests (3440) if default stripe count is 0, use OST count for inode size (3636) update parent mtime/ctime on client for create/unlink (2611) drop dentry ref in ext3_add_link from open_connect_dentry (3266) free recovery state on server during a forced cleanup (3571) unregister_reply for resent reqs (3063) loop back devices mounting and status check on 2.6 (3563) fix resource-creation race that can provoke i_size == 0 (3513) don't try to use bad inodes returned from MDS/OST fs lookup (3688) more debugging for page-accounting assertion (3746) return -ENOENT instead of asserting if ost getattr+unlink race (3558) avoid deadlock after precreation failure (3758) fix race and lock order deadlock in orphan handling (3450, 3750) add validity checks when grabbing inodes from l_ast_data (3599) miscellania add /proc/.../recovery_status to obdfilter (3428) lightweight CDEBUG infrastructure, debug daemon (3668) change default OSC RPC parameters to be better on small clusters turn off OST read cache for files smaller than 32MB install man pages and include them in rpms (3100) add new init script for (un)mounting lustre filesystems (2593) run chkconfig in %post for init scripts (3701) drop scimac NAL (unmaintained) Changes from v1.2.2 to v1.2.3 recoverable OST fixes other recovery fixes scheduling hang in newer kernels fixed clean kiobufs before and after use (3485) strip trailing '/'s before comparing paths with /proc/mounts (3486) remove assertions to work around "in-flight rpcs" recovery bug (3063) change init script to fail more clearly if not run as root (1528) allow clients to reconnect during replay (1742) fix ns_lock/i_sem lock ordering deadlock for kms update (3477) don't do DNS lookups on NIDs too small for IP addresses (3442) re-awaken ptlrpcd if new requests arrive during check_set (3554) fix cond_resched (3554) only evict unfinished clients after recovery (3515) allow bulk resend, prevent data loss (3570) dynamic ptlrpc request buffer allocation (2102) don't allow unlinking open directory if it isn't empty (2904) set MDS/OST threads to umask 0 to not clobber client modes (3359) remove extraneous obd dereference causing LASSERT failure (3334) don't use get_cycles() when creating temp. files on the mds (3156) hold i_sem when setting i_size in ll_extent_lock() (3564) miscellania servers can dump a log evicting a client - lustre.dump_on_timeout=1 fix ksocknal_fmb_callback() error messages (2918) Changes from v1.2.1 to v1.2.2 Linux 2.6 SuSE kernel support is significantly improved More recovery fixes don't copy lvb into (possibly NULL) reply on error (2983) don't deref dentry after dput, don't free lvb on error (2922) use the kms to determine writeback rpc length (2947) increment oti_logcookies when osc is inactive (2948) update client's i_blocks count via lvb messages (2543) handle intent open/close of special files properly (1557) mount MDS with errors=remount-ro, like obdfilter (2009) initialize lock handle to avoid ASSERT on error cleanup (3057) don't use cancelling-locks' kms values (2947) use highest lock extent for kms, not last one (2925) don't dereference ERR_PTR() dentry in error handling path (3107) fix thread race in portals_debug_dumplog() (3122) create lprocfs device entries at setup instead of at attach (1519) common AST error handler, don't evict client on completion race (3145) zero nameidata in detach_mnt in 2.6 (3118) verify d_inode after revalidate_special is valid in 2.6 (3116) use lustre_put_super() to handle zconf unmounts in 2.6 (3064) initialize RPC timeout timer earlier for 2.6 (3219) don't dereference NULL reply buffer if mdc_close was never sent (2410) print nal/nid for unknown nid (3258) additional checks for oscc recovery before doing precreate (3284) fix ll_extent_lock() error return code for 64-bit systems (3043) don't crash in mdc_close for bad permissions on open (3285) zero i_rdev for non-device files (3147) clear page->private before handing to FS, better assertion (3119) fix incorrect decref of invalidated dentry (2350) don't hold journal transaction open across create RPC (3313) update atime on MDS at close time (3265) close LDAP connection when recovering to avoid server load (3315) update iopen-2.6 patch with fixes from 2399,2517,2904 (3301) don't leak open file on MDS after open resend (3325) serialize filter_precreate and filter_destroy_precreated (3329) loop device shouldn't call sync_dev() for nul device (3092) clear page cache after eviction (2766) resynchronize MDS->OST in background (2824) refuse to mount the same filesystem twice on same mountpoint (3394) allow llmount to create routes for mounting behind routers (3320) push lock cancellation to blocking thread for glimpse ASTs (3409) don't call osc_set_data_with_check() for TEST_LOCK matches (3159) fix rare problem with rename on htree directories (3417) miscellania allow default OST striping configuration per directory (1414) fix compilation for qswnal for 2.6 kernels (3125) increase maximum number of MDS request buffers for large systems change liblustreapi to be useful for external progs like lfsck (3098) increase local configuration timeout for slow disks (3353) allow configuring ldlm AST timeout - lustre.ldlm_timeout=<seconds> Changes from v1.2 to v1.2.1 improved support for Linux 2.6.x fixes for glimpse AST timeouts / incorrectly 0-sized files (2818) don't overwrite extent policy data in reply if lock was blocked (2901) drop filter export grants atomically with removal from device (2663) del obd_self_export from work_list in class_disconnect_exports (2908) don't LBUG if MDS recovery times out during orphan cleanup (2530) swab reply message in mdc_close, other PPC fixes (2464) fix destroying of named logs (2325) overwrite old logs when running lconf --write_conf (2264) bump LLOG_CHUNKSIZE to 8k to allow for more OSTs (2306) fix race in target_handle_connect (2898) mds_reint_create() should take same inode create lock (2926) correct journal credits calculated for CANCEL_UNLINK_LOG (2931) don't close files for self_export to avoid uninitialized obd (2936) allow MDS with the same name as client node (2939) hold dentry reference for closed log files for unlink (2325) reserve space for all logs during transactions (2059) don't evict page beyond end of stripe extent (2925) don't oops on a deleted current working directory (2399) handle hard links to targets without a parent properly (2517) don't dereference NULL lock when racing during eviction (2867) don't grow lock extents when there are lots of conflicting locks (2919) Changes from v1.0.4 to v1.2 ENOSPC is properly handled, to avoid data loss when disks become full (974) protocol optimizations allow for faster stat() calls while other nodes are writing to a file (1021) reads no longer exclude all writes from the same file (1021) orphan handling to avoid leaking space on client/server crashes fewer journal credits needed for writes, to improve parallelism (2370) fixes for running a small-page-size MDS with large-page-size clients (2777) dozes of less user-visible bugs, detailed below lfsck support in lustre kernel code (2349) ptlrpcd can be blocked, stopping all progress (2477) takes i_sem instead of DLM locks internally on obdfilter (2720) recovery for initial connections (2355) fixes for mds_cleanup_orphans (1934) abort_recovery crashes MDS in b_eq (mds_unlink_orphan) (2584) block all file creations until orphan recovery completes (1901) client remove rq_connection from request struct (2423) conf-sanity test_5, proper cleanup in umount log not availale (2640) recovery timer race (2670) mdc_close recovey bug (2532) ptlrpc cleanup bug (2710) mds timeout on local locks (2588) namespace lock held during RPCs (2431) handle interrupted sync write properly (2503) don't try to handle a message that hasn't been replied to (2699) client assert failure during cleanup after abort recovery (2701) leak mdc device after failed mount (2712) ptlrpc_check_set allows timedout requests to complete (2714) wait for inflight reqs when ptlrpcd finishes (2710) make sure unregistered services are removed from the srv_list reset bulk XID's when resending them (caught by 1138 test) unregister_bulk after timeout handle write after unfinished setstripe, stripe-only getstripe (2388) readahead locks pages, leaves pending causing memory pressure (2673) increase OST request buffers to 4096 on large machines (2729) fix up permission of existing directories in simple_mkdir (2661) init deleted item, add assertions ptlrpc_abort_inflight() (2725) don't assign transno to errored transactions (2742) don't delete objects on OST if given a bogus objid from MDS (2751) if rq_no_resend, then timeout request after recovery (2432) fix MDS llog_logid record size, 64-bit array alignment (2733) don't call usermode_helper from ptlrpcd, DEFAULT upcall (2773) put magic in mount.lustre data, check for bad/NULL mount data (2529) MDS recovery shouldn't delete objects that it has given out (2730) don't unlock pages twice when trigger_group_io returns error (2814) don't deref NULL rq_repmsg if ldlm_handle_enqueue failed (2822) don't write pages to disk if there was an error (1450) don't ping imports that have recovery disabled (2676) take buffered bytes into account when balancing socknal conn (2817) hold a DLM lock over readdir always, use truncate_inode_pages (2706) reconnect unlink llog connection after MDS reconnects to OST (2816) remove little-endian swabbing of llog records (1987) set/limit i_blksize to LL_MAX_BLKSIZE on client (2884) retry reposting request buffers if they fail (1191) grow extent at grant time to avoid granting a revoked lock (2809) lock revoke doesn't evict page if covered by a second lock (2765) disable VM readahead to avoid reading outside lock extents (2805) return LL_SUPER_MAGIC from statfs for the filesystem type (1972) updated kernel patches for hp-2.4.20 kernel (2681) Changes from v1.0.3 to v1.0.4 fix truncated write corruption (2366) zero end of page at obdfilter for partial page writes (2648) fix for failed assertion in iopen_connect_dentry (1792, 2517) don't flag the ptlrpcd thread with PF_MEMALLOC (2636) ensure len(uuid) < 37 in lmc (1171) don't leave stale dentries around after renames (bug 2428) fix timeouts when evicting a client with a single lock held (2642) set deadline for the initial HELLO message to drain (2634) print out dotted-quad IP addresses in the socknal (2302) additional debugging for MDS client eviction problem (2443) fix mkfsoptions support for osts (2603, 2604) Changes from v1.0.2 to v1.0.3 added kernel patch series for vanilla 2.6.0 and vanilla 2.4.24 fix object leak when renaming a file to itself (2429) fix "lfs find --obd" (2510) add a /proc tunable to disable the obdfilter's read cache (2591) disable nagle in the socknal under 0conf to improve MDS performance (2578) fix several bugs in the kernel-source RPM (2516) add --disable-doc to avoid PDF generation (2421) add --ptldebug and --subsystem to lmc (1719) don't take the new-inode lock after a failed creation (2362) allocate memory with _NOFS in the DLM to avoid deadlock (1933) when a client is evicted, wake threads waiting for locks (2460) recalculate the rpcd timeout after resend (2494) call vfs_rmdir when removing "pending" directories in recovery (2368) lmc now creates a default one-stripe lov (2454) expand procfs space to handle large clusters (2326) stop LDAP rpm packages from altering slapd.conf (2301) choose MDS inode size based on stripe count (2572) avoid format warnings on ia64 updated documentation Changes from v1.0.1 to v1.0.2 change default debug level to reasonable production setting reduce client side cache size to reduce cache flush time reduce max RPCs in flight to avoid unnecessary file fragmentation make TCP zerocopy and pinger support enabled by default (2476) sync writes completed after process exits caused crashes (2319) better file I/O statistics gathering in /proc don't take unnecessary, deadlock-inducing bug in readpage (2383) another kernel patch to fix zero-copy TCP function export don't take duplicate lock when processing re-sent getattr (2420) MDS/OST recovery case which requires object creation asserted (2425) move lfs from /usr/sbin to /usr/bin in packages fix race between mds_client_add and mds_client_free (2417) use kmalloc instead of slabs in portals (2430) don't create duplicate records when a failover MDS is present (2442) remove unnecessary mount age check (2332) don't remove directory inodes from locks prematurely (2451) don't break if MDS service name is the same as hostname (2103) fix races in client write RPC generation when cache full (2482) Changes from v1.0 to v1.0.1 some users reported problems building the kernel or Lustre, with an error about "UTS_RELEASE". This problem was caused by building an SMP kernel with a non-SMP /boot/kernel.h, or vice versa. The kernel source RPM supplied with v1.0.1 should correct this issue. many changes which reduce the likelihood of memory allocation failures fix a category of lock inversions in the MDS getattr/reint paths fix three other rare lock inversion or i_sem/journal inversion bugs fix NULL dereference crash in certain OST startup failure cases fix a race condition in the lock manager which could allow delinquent clients to avoid eviction protect MDS inode fsdata with stronger locking, to prevent an assertion during MDS_CLOSE operations avoid cancelling a lock which was never granted, which causes an assertion, after a lock match failure fix two rare exit paths which could leak an internal lock reference fencepost error in MDS/OST orphan recovery lstripe now fails when the requested offset > OST count ensure that all kernel patch series have a complete list.h better error messages when a client is rejected during recovery changes to the log format, to allow zero-conf configurations with more than 100 OSTs fix gcc 2.96 compilation problem in xattr kernel patch x86-64 compile warning fixes small update to the lfs documentation