Changes from version 2.1.5 to version 2.1.6
Server support for kernels:
2.6.18-348.6.1.el5 (RHEL5)
2.6.32-358.11.1.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-348.6.1.el5 (RHEL5)
2.6.32-358.11.1.el6 (RHEL6)
Recommended e2fsprogs version:
1.42.7.wc1
Issues fixes between 2.1.5 and 2.1.6
Release Notes - Lustre - Version Lustre 2.1.6
** Bug
* [LU-1233] - Test failure on test suite parallel-scale, subtest test_compilebench,no space left
* [LU-1291] - Test failure on test suite replay-single 44c
* [LU-2136] - Test failure on test suite posix, subtest test_1
* [LU-2368] - OSTs stuck in perpetual recovery
* [LU-2458] - Device MGC already exists, won't add
* [LU-2598] - obdfilter-survey LBUG ASSERTION( iobuf->dr_npages < iobuf->dr_max_pages ) failed
* [LU-2797] - GPF in osc_send_oap_rpc
* [LU-2888] - After downgrade from 2.4 to 2.1.4, hit (osd_handler.c:2343:osd_index_try()) ASSERTION( dt_object_exists(dt) ) failed
* [LU-2901] - Duplicate filename on the same ldiskfs directory on MDS
* [LU-2904] - parallel-scale-nfsv3: FAIL: setup nfs failed!
* [LU-3029] - Directory listings are unreliable
* [LU-3044] - LSeek SEEK_CUR gives incorrect value after write when file is open with O_APPEND
* [LU-3187] - Interop 2.3.64<->2.3/2.1: sanity test_180a: lustre-OST0000: client sent bad object 0x2ce2:2: rc = -EPROTO
* [LU-3219] - FIEMAP does not sync data or return cached pages
* [LU-3279] - Interop 2.3.0 <-> 2.4 failure on test suite lustre-rsync-test test_7: Failure in replication; differences found
* [LU-3376] - b2_1 copyrights need to be updated
* [LU-3401] - 2.1.5<->2.4.0 interop: sanity test 27z: FAIL: parent SEQ mismatch
** Improvement
* [LU-1468] - Support Compat RDMA for O2IB
* [LU-3378] - Kernel update [RHEL5.9 2.6.18-348.6.1.el5]
* [LU-3461] - Kernel update [RHEL6.4 2.6.32-358.11.1.el6]
Changes from version 2.1.4 to version 2.1.5
Server support for kernels:
2.6.18-348.1.1.el5 (RHEL5)
2.6.32-279.19.1.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-348.1.1.el5 (RHEL5)
2.6.32-279.19.1.el6 (RHEL6)
Recommended e2fsprogs version:
1.42.6.wc2
Issues fixes between 2.1.4 and 2.1.5
Release Notes - Lustre - Version Lustre 2.1.5
LU-582 | 1.8<->2.1 interop: sanity test_132: FAIL: some glimpse RPC is expected |
LU-588 | IO hangs from MMP |
LU-676 | Select machinefile option for mpirun via a variable |
LU-971 | Re-sent open requests cause mod_count leakages |
LU-1018 | Test failure on test suite parallel-scale, subtest test_compilebench |
LU-1189 | restore_lustre_params() needs run on active server nodes |
LU-1331 | changelogs: RNMTO record not always after RNMFRM |
LU-1448 | Disabled OSC can cause NULL pointer dereference when reading import |
LU-1484 | Test failure on test suite recovery-small, subtest test_57 |
LU-1486 | stat must fail: command not found |
LU-1571 | It should not update last xid for replay open. |
LU-1666 | hdr->coh_page_guard contention (single shared file performance) |
LU-1714 | crash upon loading libcfs module |
LU-1727 | lprocfs_counter_add() could be called in interrupt context |
LU-1770 | LU-1575 Introducing OBD_CONNECT_FLOCK_OWNER flag |
LU-1887 | Shrinking cur_grant_byte LBUG |
LU-2072 | Leak of s_mb_prealloc_table in ldiskfs |
LU-2183 | LU-718 quota support with DNE |
LU-2309 | Uninteroperable conf_params not documented |
LU-2517 | Kernel update [RHEL5.8 2.6.18-308.24.1.el5] |
LU-2526 | Interop 2.1.3<->2.4 Failure on test suite sanity-quota test_9: write 4.5G file failure, expect success |
LU-2550 | sanity test 122 hung |
LU-2555 | Null pointer deref in ldiskfs_ext_calc_credits_for_insert |
LU-2591 | race between mount/umount and lov_notify |
LU-2592 | replay-vbr test 0c: error: set_param: /proc/{fs,sys}/{lnet,lustre}/*/lustre-MDT0000/sync_permission: Found no match |
LU-2598 | obdfilter-survey LBUG ASSERTION( iobuf->dr_npages < iobuf->dr_max_pages ) failed |
LU-2601 | Kernel update [RHEL5.9 2.6.18-348.1.1.el5] |
LU-2620 | Failure on test suite replay-ost-single test_6: test_6 failed with 1 |
LU-2634 | LU-1366 short symlinks on MDT with "extents" have EXT4_EXTENTS_FL set |
LU-2638 | LU-2627 corruption of MDT ".." entry in some ldiskfs directories |
LU-2657 | Shouldn't deleting objects in mds_lov_update_objids() |
LU-2694 | lfsck in e2fsprogs is out of date |
LU-2769 | Kernel update [RHEL6.3 2.6.32-279.22.1.el6] |
LU-2775 | Interop 2.1.4<->2.4 failure on test suite lustre-initialization-1: ASSERTION( fid_seq_is_mdt(loi->loi_oi.oi_seq) ) failed |
LU-2824 | recovery-mds-scale test_failover_ost: tar: etc/localtime: Cannot open: Input/output error |
LU-2857 | 2.1.4<->2.4.0 interop: sanity test_76: FAIL: inode slab grew from 11183 to 12183 |
LU-2861 | 2.1.4<->2.4.0 interop: conf-sanity test 24a: mount.lustre: /dev/loop1 has no index assigned |
LU-2864 | 2.1.4<->2.4.0 interop: replay-dual test_16: FAIL: post-failover df: 1 |
LU-2922 | update lustre-ldiskfs.spec.in e2fsprogs Requires: line |
LU-2928 | Update b2_1 copyrights before release |
Changes from version 2.1.3 to version 2.1.4
Server support for kernels:
2.6.18-308.20.1.el5 (RHEL5)
2.6.32-279.14.1.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-308.20.1.el5 (RHEL5)
2.6.32-279.14.1.el6 (RHEL6)
Recommended e2fsprogs version:
1.42.3.wc3
Issues fixes between 2.1.3 and 2.1.4
Release Notes - Lustre - Version Lustre 2.1.4
Bug
- [LU-549] - Add xattr list/value cache on client
- [LU-691] - sanity test_133c defect
- [LU-748] - sanity test 220 must be placed in SLOW set
- [LU-797] - Test failure on test suite ost-pools, subtest test_14, test_18, test_23
- [LU-921] - generate warnings in case of discarding dirty pages
- [LU-974] - Lustre does not ignore umask when default ACL with mask is set
- [LU-1057] - low performance maybe related to quota
- [LU-1075] - cannot run racer.sh by auster since there is a dir with the same name racer
- [LU-1115] - software raid6 related BUG in fs/bio.c:222 when raid chunk > 64k
- [LU-1203] - When upgrading from Lustre 1.8 to 2.1, if the parameter root_squash is set, Lustre throws an error and denies mounting the filesystem. It's necessary to completely delete the parameter
- [LU-1283] - 2.2.0 fails to build from source
- [LU-1342] - Test failure on sanity-quota test_29
- [LU-1363] - SELinux and stateahead hang
- [LU-1438] - quota_chk_acq_common() still haven't managed to acquire quota
- [LU-1484] - Test failure on test suite recovery-small, subtest test_57
- [LU-1517] - no retry for the bulk operation
- [LU-1518] - Missing/bad operations in mdd_{obf,dot_lustre}_obj_op causing LBUGs
- [LU-1526] - interop 1.8,2.1 -> 2.4 "mkfs.lustre FATAL: The target index must be specified with --index"
- [LU-1544] - lfs catinfo command crashes
- [LU-1548] - Test failure on test suite mds-survey, subtest test_1
- [LU-1585] - Incorrect timestamp calculation in lst stat command
- [LU-1592] - ASSERTION(cfs_atomic_read(&imp->imp_refcount) == 0) failed: value: -1
- [LU-1597] - Reads and Writes failing with -13 (-EACCES)
- [LU-1606] - lustre_idl.h does not compile in user-space
- [LU-1632] - FID sequence numbers not working properly with filesystems formatted using 1.8?
- [LU-1648] - MDS Crash
- [LU-1650] - crash of lustre clients in osc_req_attr_set() routine
- [LU-1688] - recovery-small: test_58 failed with 1
- [LU-1693] - filter_do_bio() and osd_do_bio() should set bi_rw before calling bio_add_page()
- [LU-1716] - Race in setting connection flags and using them on 2.x client connect
- [LU-1720] - Quota doesn't work over 4TB on single OST
- [LU-1749] - llog_lvfs_create()) error looking up logfile
- [LU-1762] - mmp.sh gets wrong MMP update interval
- [LU-1779] - "skip" inside a test does not report SKIP in Maloo
- [LU-1782] - Ignore sb_has_quota_active() in OFED's header
- [LU-1923] - filefrag with large fiemap buffer crashes client
- [LU-2170] - osc_extent_merge()) ASSERTION( cur->oe_osclock == victim->oe_osclock) while running racer
- [LU-2237] - Customer Entered incorrect parameter when enabling quotas. System is down.
- [LU-2304] - Test failure sanityn test_16: dual-mount fsx data read error
- [LU-2309] - Uninteroperable conf_params not documented
- [LU-2371] - client quota interoperability with 2.4
- [LU-2405] - Interop 2.3<->2.4 Failure on test suite sanity, test_17g: symlink not NULL terminated stringof length 60
- [LU-2448] - No prepare-commit-msg and commit-msg files on b2_1
- [LU-2463] - posix test_1: mkfifo.3 and umask.2 failed
- [LU-2505] - lfsck: BUG: soft lockup - CPU#0 stuck for 67s! [umount:22194]
Improvement
- [LU-32] - always keep buffer_head reference on root node of iam_container
- [LU-847] - Merge some quota patches from Orion to 2.2
- [LU-1479] - SRP module enabled by lbuild
- [LU-1833] - Don't update mtab if it is symlink
- [LU-2372] - Kernel update [RHEL5.8 2.6.18-308.20.1.el5]
- [LU-2373] - Kernel update [RHEL6.3 2.6.32-279.14.1.el6]
- [LU-2420] - Have POSIX testing automated on b2_1
New Feature
- [LU-1842] - Quota enforcement landing
Story
- [LU-2007] - racy reconnect in target_handle_connect()
Task
- [LU-2483] - b2_1 copyrights need to be updated before release
Technical task
- [LU-1789] - Lightweight connection support
Changes from version 2.1.2 to version 2.1.3
Server support for kernels:
2.6.18-308.11.1.el5 (RHEL5)
2.6.32-279.2.1.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-308.11.1.el5 (RHEL5)
2.6.32-279.2.1.el6 (RHEL6)
Recommended e2fsprogs version:
1.42.3.wc1
Issues fixes between 2.1.2 and 2.1.3
Release Notes - Lustre - Version Lustre 2.1.3
- Bug
- LU-948 - Client recovery hang
- LU-958 - tests: debug_mb set incorrectly for smp or vm
- LU-969 - 2.1 client stack overruns
- LU-1059 - vvp_page_unmap()) ASSERTION(PageLocked(vmpage))
- LU-1129 - filter_handle_precreate()) ASSERTION(diff >= 0) failed
- LU-1194 - llog_recov_thread_stop+0x1ae/0x1b0 asserting
- LU-1203 - When upgrading from Lustre 1.8 to 2.1, if the parameter root_squash is set, Lustre throws an error and denies mounting the filesystem. It's necessary to completely delete the parameter
- LU-1216 - LBUG: ASSERTION(lli->lli_sai == NULL) failed using robinhood tool
- LU-1249 - lctl set_param debug_mb=10 gives Invalid argument
- LU-1282 - Lustre 2.1 client memory usage at mount is excessive
- LU-1378 - ASSERTION(range_is_sane(&seq->lcs_space)) failed
- LU-1418 - (osc_lock.c:1099:osc_lock_enqueue_wait()) DEADLOCK POSSIBLE! - too many
- LU-1423 - 16K pagesize clients error during ls
- LU-1428 - MDT servrice threads spinning in cfs_hash_for_each_relax()
- LU-1432 - Race condition between lprocfs_exp_setup() and lprocfs_free_per_client_stats() causes LBUG
- LU-1442 - File corrupt with 1MiB-aligned 4k regions of zeros
- LU-1471 - parallel-scale-nfsv3/v4: FAIL: setup nfs failed!
- LU-1484 - Test failure on test suite recovery-small, subtest test_57
- LU-1493 - assertion in dqacq_completion() (count < *hardlimit) failed
- LU-1522 - ASSERTION(cfs_atomic_read(&obd->obd_req_replay_clients) == 0) failed
- LU-1540 - e2fsck remove too many symlinks
- LU-1576 - client sluggish after running lpurge
- LU-1585 - Incorrect timestamp calculation in lst stat command
- LU-1625 - Test failure on test suite parallel-scale-nfsv4, subtest test_metabench
- LU-1626 - GPF in osc_create
- LU-1689 - Test failure on test suite mmp, subtest test_8
- LU-1703 - b2_1 can't pass acc-sm test
- Improvement
- LU-575 - lfs find fixes
- LU-857 - Lustre client tolerates enforced SELinux.
- LU-1158 - nanosecond timestamp support for Lustre
- LU-1164 - ko2iblnd schedulers
- LU-1477 - Kernel update [RHEL6.3 2.6.32-279.2.1.el6]
- LU-1511 - Kernel update [RHEL5.8 2.6.18-308.11.1.el5]
- LU-1620 - Asymmetric router failure parameters should be tunable
Changes from version 2.1.1 to version 2.1.2
Server support for kernels:
2.6.18-308.4.1.el5 (RHEL5)
2.6.32-220.17.1.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-308.4.1.el5 (RHEL5)
2.6.32-220.17.1.el6 (RHEL6)
Recommended e2fsprogs version:
1.42.3.wc1
Issues fixes between 2.1.1 and 2.1.2
Release Notes - Lustre - Version Lustre 2.1.2
Bug
- LU-78 - kiblnd_check_conns can deadlock
- LU-81 - Some JBD2 journaling deadlock at BULL
- LU-106 - unable to handle kernel paging request in lprocfs_stats_collect()
- LU-425 - SANITYN sanity_mount_check_clients fails if $MOUNT is a substring of $MOUNT2
- LU-427 - Test failure on test suite lfsck
- LU-499 - grant_rate and cancel_rate are static when an OST is idle
- LU-532 - 2.1 does not filter extended attributes list based on permissions, showing entire list at all times
- LU-542 - Missing XATTR changelog record
- LU-543 - Missing UNLINK record on overwritting rename
- LU-573 - conf-sanity test_22: @@@@@@ FAIL: test_22 failed with 41
- LU-577 - REPLAY_SINGLE test_70b failed due to $MOUNT not pass on to rundbench
- LU-617 - LBUG: (mdt_recovery.c:787:mdt_last_rcvd_update()) ASSERTION(req_is_replay(req)) failed
- LU-620 - "Bad page state" reported after unlink
- LU-629 - _debug_req() never prints out opcode/flags/status
- LU-630 - mount failure after MGS connection lost and file system is unmounted
- LU-646 - clarification of lustre fsync behavior
- LU-651 - Strange error message "is it ok to have flags 0x... and 0x... in the same brw?"
- LU-685 - Wide busy lock in kiblnd_pool_alloc_node
- LU-690 - conf-sanity test_21a: @@@@@@ FAIL: can't put import for lustre-OST0000-osc(ost) into FULL state
- LU-717 - ext4 mmp block uses incorrect utsname field for nodename
- LU-759 - mdc_enqueue() should clear rq_replay when mdc_enter_request() fails
- LU-780 - improve parallel-scale to support hyperion run
- LU-805 - lfs quota should show quota allocation rather than used
- LU-874 - Client eviction on lock callback timeout
- LU-882 - Quota code causes run away ll_ost_io thread
- LU-931 - fsstress - LBUG (lustre_idl.h:766:lu_fid_eq()) ASSERTION(fid_is_igif(f0) || fid_ver(f0) == 0)
- LU-935 - Crash lquota:dquot_create_oqaq+0x28f/0x510
- LU-952 - Hung thread with HIGH OSS load
- LU-960 - Bad stripe count reported by lfs getstripe when default stripe count set to -1
- LU-974 - Lustre does not ignore umask when default ACL with mask is set
- LU-980 - incompatbile error handling
- LU-983 - On a 1.8.6 client/host, tar is performing 10K reads, and the RPCs are typically one page in size for small files==tar is slow for small files using 1.8.6 vs 1.8.5
- LU-985 - buffer overflow resulting in stack corruption
- LU-1014 - MGS with sys.timeout is ignored and if sys.timeout is changed its not synced across the file system.
- LU-1017 - MDS oops when running racer test
- LU-1029 - EL6 kernel 2.6.32-220.el6 fails to build with OFA OFED 1.5.4
- LU-1049 - lc_net does not parse unexpected output from pdsh well
- LU-1050 - configure broken on centos6.2 with OFED-1.5.4
- LU-1084 - Console messages from sec stuff MUST GO
- LU-1092 - NULL pointer dereference in filter_export_stats_init()
- LU-1098 - Object doesn't exist!
- LU-1100 - metabench failed on NFSv3/v4 over Lustre
- LU-1102 - NULL pointer dereference in capa_encrypt_id+0x8b/0x3e0
- LU-1109 - NFS server not responding when running parallel-scale test_iorsff
- LU-1125 - crash in lc_watchdog_del_pending during tgt_recov
- LU-1128 - Two ll_ost_io threads apprently stuck in shrinker code
- LU-1134 - nfs tests bypass lustre setup
- LU-1137 - flock owner incorrectly handled on the server side
- LU-1166 - recovery never finished
- LU-1205 - sanityn.sh test_18 mmap_sanity sometimes takes thousands of seconds to run
- LU-1206 - Executing unwriteable, recently touched file returns ETXTBSY (Text file busy)
- LU-1212 - On MDS startup upon client connection mdt_xx threads Consume All Available CPU
- LU-1217 - ASSERTION(cfs_atomic_read(&lock->cll_ref) > 1 || olock->ols_hold == 0) failed
- LU-1218 - Recovery timer display in proc always displays 0
- LU-1245 - general protection fault in lprocfs_fops_read
- LU-1247 - After recovery 7 of 16 OST were deactivated by MDS.
- LU-1274 - Client threads block for sometime before being evicted and can never reconnect afterward
- LU-1280 - kernel BUG at .../lustre-2.1.0/lustre/lvfs/fsfilt-ldiskfs.c:978
- LU-1282 - Lustre 2.1 client memory usage at mount is excessive
- LU-1308 - 2.2 clients unable to mount upgraded MDT
- LU-1312 - crash at boot time in isci driver with 2.6.18-308.1.1
- LU-1319 - MDT getattr stats not getting updated
- LU-1320 - EIO on read shortly after file written
- LU-1345 - Handle none integer values in sanity 215 test
- LU-1350 - Parent doesn't exist!
- LU-1361 - Lustre kernel rpm does not provide kernel ABI (kabi) information
- LU-1366 - getting "dirdata length set incorrectly" running e2fsck
- LU-1398 - Problem building fsfilt on 2.1.x branch
- LU-1424 - Kernel update RHEL6.2 2.6.32-220.17.1.el6
Improvement
- LU-143 - hash function of ldlm_namespace and lu_site is not good enough
- LU-447 - add lctl --net XXX push
- LU-459 - silence excess 2.x error messages
- LU-554 - add gnilnd awareness to LNet
- LU-663 - Some architectures do not have NUMA features anymore
- LU-680 - superblock <-> mount point mapping
- LU-734 - improve recovery-*-scale tests to put debug logs into $LOGDIR
- LU-814 - automate NFSv3/v4 over Lustre Testing
- LU-879 - Detail rename operation in stats file
- LU-989 - Move client's import destruction from disconnect to cleanup phase
- LU-1095 - Console message cleanup
- LU-1241 - Kernel update RHEL6.2 2.6.32-220.7.1.el6
- LU-1358 - update to the latest redhat and centos kernels: kernel-2.6.32-220.13.1.el6
- LU-1374 - Kernel update RHEL5.8 2.6.18-308.4.1.el5
Task
Technical task
- LU-570 - find connection uuid by peer nid
Changes from version 2.1.0 to version 2.1.1
Server support for kernels:
2.6.18-274.12.1.el5 (RHEL5)
2.6.32-220.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-274.12.1.el5 (RHEL5)
2.6.32-220.el6 (RHEL6)
2.6.32.36-0.5 (SLES11)
Recommended e2fsprogs version:
1.41.90.wc4
Issues fixes between 2.1.0 and 2.1.1
Release Notes - Lustre - Version Lustre 2.1.1
Bug
LU-110 - Allow the use of a 2.0 MDS on a filesystem with a 1.8 disk format
LU-322 - Fix for ost pool test in test suite
LU-357 - Racer test defect
LU-417 - block usage is reported as zero by stat call for tens of seconds after creating a file
LU-488 - LustreError: 4564:0:(connection.c:100:ptlrpc_connection_put()) ASSERTION(!cfs_hlist_unhashed(&conn->c_hash)) failed
LU-508 - Kernel panic on ...BUILD/BUILD/lustre-ldiskfs-3.3.0/ldiskfs/extents.c:1920
LU-513 - cfs_wait_event_interruptible_exclusive is not exclusive
LU-601 - kernel BUG at fs/jbd2/transaction.c:1030
LU-613 - Lustre-Client dead-lock during binary exec() over Lustre FS
LU-687 - Application is OOM-killed during page-fault resolution on its binary over Lustre when there is plenty of memory available
LU-721 - Parallel writes to same file results in a file of zeroes
LU-745 - ost-pools test 23 hung
LU-753 - kernel:LustreError: 4998:0:(filter_io_26.c:791:filter_commitrw_write()) LBUG
LU-760 - Test failure on test suite sanity, subtest test_180a
LU-762 - Hyperion - mdtest failure
LU-769 - Test failure on test suite conf-sanity, subtest test_23a
LU-774 - Test failure on test suite replay-ost-single, subtest test_7
LU-791 - sanity 27q hang
LU-797 - Test failure on test suite ost-pools, subtest test_14, test_18, test_23
LU-820 - Annoying "format at cl_io.c:1551:cl_req_page_add doesn't end in newline"
LU-843 - Several minor issues
LU-919 - Multiple wrong LBUGs checking cfs_atomic_t vars/fields with inacurate poison value of 0x5a5a5a
LU-955 - Lustre-modules 2.1 client rpm wrongly requires lustre-backend-fs
LU-966 - post-fsck MDS LBUG during recovery due to missing FID
LU-987 - Fail to create ldisk rpms RHEL5
LU-1040 - Test failure on test suite conf-sanity
LU-1042 - 1.8 clients show wrong dates with 2.1 servers
LU-1091 - tag matching not quite working
LU-1127 - need performance-sanity to work on Hyperion
Improvement
LU-781 - Kernel update RHEL6.2 2.6.32-220.el6
LU-786 - new rhel5 kernel support 2.6.18-274.12.1.el5
LU-792 - lbuild-rhel5 should use redhat's SRPM repo
version 2.1.0
Support for networks:
socklnd -any kernel supported by Lustre,
qswlnd - Qsnet kernel modules 5.20 and later,
openiblnd - IbGold 1.8.2,
o2iblnd - OFED 1.3, 1.4.1, 1.4.2, 1.5.1, 1.5.2 and 1.5.3.1
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 1.2.10 or later,
ptllnd - Portals 3.3 / UNICOS/lc 1.5.x, 2.0.x
Server support for kernels:
2.6.18-238.19.1.el5 (RHEL5)
2.6.32-131.6.1.el6 (RHEL6)
Client support for unpatched kernels:
2.6.18-238.19.1.el5 (RHEL5)
2.6.32-131.6.1.el6 (RHEL6)
2.6.32.36-0.5 (SLES11)
Recommended e2fsprogs version:
1.41.90.wc3
Issues fixes between 2.0 and 2.1
Issue Type | Key | Summary |
---|---|---|
Bug | LU-8 | Use non-blocking connect in ksocklnd |
Bug | LU-13 | Frequent Client Evictions |
Improvement | LU-16 | Allow objects larger than 2TB in size |
Bug | LU-22 | ldlm_resource::lr_lvb_data is protected by wrong lock |
Bug | LU-25 | Blocking network request in ldlm shrinker |
Bug | LU-39 | ASSERTION(atomic_read(&client_stat->nid_exp_ref_count) == 0) failed: count 1 |
Bug | LU-46 | test-framework does not pick module parameters |
Improvement | LU-47 | lbuild should use the ustar format to allow path names greater than 99 |
Bug | LU-48 | fix to enable use of automake 1.11 |
Bug | LU-51 | various debian packaging fixes enhancements |
Bug | LU-52 | drop texlive-latex-recommended from the build dependencies for debian |
Bug | LU-57 | Allow OSTs to be created with no primary node, only failnodes |
Bug | LU-65 | Interop testing results for 1.8.5.54 clients with Lustre 2.0.59 servers |
Bug | LU-67 | write_disjoint: data corruption |
Bug | LU-68 | write_disjoint: invalid file size |
Bug | LU-69 | write_disjoint rank 4, loop 8029: filesize = 110592. Should be zero after truncate |
Bug | LU-71 | metabench failures |
New Feature | LU-73 | RHEL6 kernel support |
Bug | LU-77 | cl_page.c::cl_page_own0() assertion in echoclient |
Bug | LU-83 | wrong mount option cause system panic on MDS |
Bug | LU-85 | Deb meta-data is incorrect |
Bug | LU-86 | auster cleanups |
Bug | LU-91 | Impossible to use quotas on RHEL6.0 |
Bug | LU-94 | llite_lloop should not be part of the client build |
Bug | LU-98 | 'make rpms' does not work if the '--without-lustre-iokit' configure option is specified |
Bug | LU-102 | EXPORT_SYMBOL of static function breaks compile |
Improvement | LU-103 | Add test-groups |
Bug | LU-104 | Lustre grants flock exclusive locks on two file descriptors for the same file |
Improvement | LU-105 | Add -D logdir option to Auster so that the whole logdir can be passed - enables parent process to share log directory with Auster |
Bug | LU-109 | Tree cleanup for 2.1 |
Bug | LU-111 | mount_lustre::parse_options() does not pass force* options down |
Bug | LU-113 | Dependency issues with RHEL installation - lustre-ldiskfs |
Bug | LU-114 | WARNING: at fs/namei.c:1332 lookup_one_len+0xf1/0x110() |
Bug | LU-115 | need to see patch output from debian builds |
Bug | LU-116 | fix mmp test 10 to allow e2fsck run on mounted filesystem with -n option |
Bug | LU-118 | clear_inode: BUG_ON(inode->i_data.nrpages) |
Bug | LU-119 | Merge goof on master? |
Bug | LU-120 | bug in creating debian patches |
Bug | LU-121 | yaml.sh and test-framework sometimes attaches the full qualified node name to its output files and sometimes just the first element. |
Bug | LU-122 | Revert bug 21122 since it causes deadlock |
Bug | LU-127 | lustre modules on rhel should require their kernel |
Bug | LU-128 | OSSs frequent crashes due to LBUG/ASSERTION(last_rcvd>=le64_to_cpu(lcd->lcd_last_transno)) failed in recovery |
Bug | LU-130 | Kernel crash on lustre 2.0 client (page fault in ll_file_read, NULL pointer dereference) |
Task | LU-136 | test e2fsprogs-1.42.wc1 against 32TB+ ldiskfs filesystems |
New Feature | LU-139 | starting 2.6.38 DCACHE_LUSTRE_INVALID conflicts with DCACHE_OP_REVALIDATE |
Improvement | LU-140 | kill iopen |
Bug | LU-144 | xattr fixes |
Bug | LU-152 | replay single always times out during one of the tests when running on Toro |
Improvement | LU-155 | some dcache cleanups |
Bug | LU-157 | metabench failed on parallel-scale test |
Bug | LU-158 | Lock test of connectathon failed |
Bug | LU-160 | Test failure on test suite sanity, subtest test_155a |
Bug | LU-161 | connectathon test on NFS v3 client failed |
Bug | LU-162 | CentOS5 cannot load fsfilt_ldiskfs due to unknown symbols used ldiskfs_discard_preallocations |
Bug | LU-163 | compilebench fail on NFS v4 client |
Bug | LU-166 | MDR assert of wire dat for ATTR_BY_FID case |
Bug | LU-167 | Test failure on test suite sanityn |
Bug | LU-168 | Test failure on test suite sanityn, subtest test_40b |
Bug | LU-170 | OSCC_FLAG_LOW is always set and oscc_grow_count will never grow |
Bug | LU-172 | Test failure on test suite sanity, subtest test_27z |
Bug | LU-175 | mdt_lproc.c:255: error: the frame size of 1040 bytes is larger than 1024 bytes |
Bug | LU-177 | lbuild fixes for matrix build jobs |
Bug | LU-182 | RHEL6 support is broken |
Bug | LU-183 | error: get_param: /proc/(fs,sys)/(lnet,lustre)/osd/*MDT0000/kbytesfree: Found no match |
Bug | LU-184 | Test failure on test suite insanity, subtest test_0 |
Bug | LU-185 | LBUG: (cl_page.c:1362:cl_page_completion()) !(pg->cp_flags & CPF_READ_COMPLETED) ASSERTION(0) failed |
Bug | LU-186 | recovery-mds-scale (FLAVOR=OSS): (filter.c:151:filter_finish_transno()) LBUG |
Improvement | LU-188 | Reduce startup messages |
Bug | LU-189 | RHEL6 MMP patch misses fix from bug 22117 |
Bug | LU-196 | Set debug_mb size for every node |
Bug | LU-197 | Fix sanity-benchmark.sh to remove files after fsx |
Bug | LU-198 | Exit with error if NFSCLIENT is set, but no nfs export found |
Bug | LU-201 | unregistered bulk after reply unregistered causes "ptlrpc_set_wait" to hang |
Bug | LU-202 | Test failure on test suite sanity-quota |
Bug | LU-203 | parallel-scale test_statahead: FAIL: Failed to mount lustre on /tmp/mntpt/lustre0 |
Bug | LU-206 | Memory corruption due to MMP (1.8.5) |
Bug | LU-210 | back out debian per-commit patching build process |
Bug | LU-211 | lu_ref revisited on 2.1 |
Bug | LU-212 | reject connection request for bad obd_connect_data->ocd_brw_size |
Bug | LU-213 | using direct io for quota test to avoid cache problem |
Bug | LU-221 | sanityN.sh test_4 failed |
Bug | LU-225 | --with-ldiskfs-inkernel checks wrong file |
Improvement | LU-228 | kernel update to rhel5 2.6.18-238.9.1 |
Bug | LU-231 | sanity test_170: FAIL: expected 248 bad lines, but got 249 |
Bug | LU-234 | OOM killer causes node hang |
Bug | LU-235 | fix sanity test 36g to work with remote OSS |
Bug | LU-239 | Lustre Header (include/lprocfs_status.h) is not ISO C99 complaint |
Bug | LU-240 | sanity 171: test_171() races with background multiop |
Improvement | LU-243 | async lov_sync() operation |
Bug | LU-245 | port patch of bug22820 to 2.0 (too many default ACLs break directory access on new directories) |
Bug | LU-246 | port of bug 18779 (conf-sanity test_34c: touch: setting times of `/mnt/lustre/f34c': Input/output error) |
Bug | LU-248 | port bug24194 to master (Still seeing inconsistencies in OST allocation) |
Improvement | LU-255 | use ext4 features by default for newly formatted filesystems |
Bug | LU-257 | lustre.spec.in utilises undefined macro krequires |
Bug | LU-259 | Wrong option in ext4-force_over_16tb-rhel6.patch |
Bug | LU-260 | Add regression test case of bug22177 ("Test open-unlinked dir") |
Bug | LU-271 | NFS4 over lustre open permission check failed |
Bug | LU-273 | the patch export-show_task-2.6.18-vanilla.patch of rhel5 has some issues in lustre 2.0.59.0 and above |
Bug | LU-274 | Client delayed file status (cache meta-data) causing job failures |
Bug | LU-275 | I/O errors when lustre uses multipath devices |
Bug | LU-279 | Test failure on test suite sanity, subtest test_17k |
Improvement | LU-283 | Fix trailing white space characters in sanity.sh |
Bug | LU-284 | lustre-module got dependency issue when installing RHEL6 |
Bug | LU-285 | Test failure on test suite sanity, subtest test_180a |
Bug | LU-286 | racer: general protection fault: 0000 1 SMP RIP: __wake_up_common+60} |
Improvement | LU-288 | In tree single node testing uses installed lustre binaries by default, not in tree binaries. |
Improvement | LU-291 | echo client to use obd_brw_async |
Bug | LU-292 | Test failure on test suite recovery-small |
Bug | LU-298 | autoconf dpkg test needs improvment |
Bug | LU-299 | Uninitialized variable in shrinker test makes it fail incorrectly |
Bug | LU-300 | Oops in cl_page_put() during execve()/page-fault on a binary mapped from a Lustre-filesystem and executed by a parallel application |
Bug | LU-301 | build support for sles11 client |
Bug | LU-303 | lbuild fix for downloading ofed bugfix release |
Bug | LU-304 | Cray-specific licenses are not appropriate in community GPL release |
Bug | LU-305 | utime() fails with EINTR : not conform to POSIX standard |
Bug | LU-307 | Test failure on test suite parallel-scale ior |
Bug | LU-309 | sanity test_27z does not work on loop device |
Bug | LU-313 | lfsck.sh test is not actually running lfsck |
Bug | LU-314 | lctl set_param debug=0 generates a CWARN |
Bug | LU-316 | system hang when running lustre-rsync-test test_5b |
Bug | LU-321 | Don't assume file system name for some test in the lustre test suite |
Bug | LU-325 | port bug23206 to master (performance-sanity test_8: @@@@@@ FAIL: test_8 failed with 1) |
Bug | LU-326 | port bug22688 to master (recovery-small.sh: FAIL: test_18b test_18b failed with 2) |
Bug | LU-327 | port bug18896 to master(replay-single test_61d: @@@@@@ FAIL: cannot restart mds on Cray xt3) |
Bug | LU-328 | OSS pseudo-hang due to (struct filter_obd *)->fo_llog_list_lock deadlock upon OSTs warm restart/recovery |
Bug | LU-333 | Lustre client procfs stats: read_bytes does not record the number of bytes transfered from the fs. |
Bug | LU-336 | Function module_loaded in test-framework.sh returns false positives |
Bug | LU-337 | Processes stuck in sync_page on lustre client |
Bug | LU-339 | add configure check for MS_HAS_NEW_AOPS to support new aops |
Bug | LU-342 | port bug19494 to master ("lfs find" hangs when searching for an OST index) |
Bug | LU-346 | Test failure on test suite conf-sanity |
Bug | LU-349 | port bug21847 to master (obdfilter-survey: Syntax error in some locales) |
Bug | LU-350 | port bug24050 to master("lustre_start" caused client nodes failed to mount.) |
New Feature | LU-351 | Kernel update RHEL6 U1 2.6.32-131.0.15 |
Bug | LU-356 | port bug23049 to master(various t-f.sh patches) |
Improvement | LU-363 | Reduce the cached Kernel build artifacts to ease the use of disc space consumption. |
Bug | LU-367 | lfsck 1.41.90.wc2: illegal flag specified to DB->open |
Bug | LU-371 | Hyperion MDS failed on loading sptlrpc for ENOMEM |
Bug | LU-374 | port bug24426 to master(repeated "lctl dk" will overwrite the logs created by previous call" |
Bug | LU-376 | Client hangs when listing big directory with ls -la |
Bug | LU-386 | Test failure on test suite replay-single |
Bug | LU-387 | Test failure on test suite mmp |
Bug | LU-388 | Lustre's kernel-ib RPM conflicts with EL5's openib RPM |
Bug | LU-394 | LND failure casued by discontiguous KIOV pages |
Bug | LU-395 | obd_zombie_barrier is not barrier actually |
Bug | LU-397 | lustre 2.0 client can not mount to lustre 2.1 server |
Bug | LU-399 | mkfs.lustre: The resize maximum must be greater than the filesystem size. |
New Feature | LU-402 | Add support for RHEL6 kernel2.6.32-131.2.1.el6 |
New Feature | LU-403 | Add support for RHEL5 kernel 2.6.18-238.12.1.el5 |
Bug | LU-404 | Test failure on test suite mmp |
Bug | LU-405 | NFS4 reexport fails with ll_find_alias()) ASSERTION(last_discon == NULL) |
Bug | LU-419 | Running 1.8.6WC the mkfs.lustre failed to format a 22.94TB LUN, Size of device too big to be expressed in 32 bits using a block size of 4096 |
Bug | LU-421 | include lustre/BUILDING in dist tarball |
Bug | LU-426 | replay-single test_0b failed with quota enabled on the RHEL5/i686 |
Bug | LU-429 | Debug message cleanup in filter_connect() |
Bug | LU-435 | unknow error in page fault when running sanity test_30c |
Bug | LU-442 | Client LBUG - (osc_request.c:3087:osc_set_lock_data_with_check()) ASSERTION(lock->l_ast_data == NULL lock->l_ast_data == data) failed |
Bug | LU-451 | Test failure on test suite parallel-scale |
Improvement | LU-455 | autogen.sh preparation produces automake chatter |
Bug | LU-456 | statfs reports truncated blocks as freed while they are not |
Bug | LU-464 | Test failure on test suite obdfilter-survey |
Bug | LU-467 | Test failure on test suite liblustre |
Improvement | LU-469 | Lustre .config should be rebased on RHEL 6.1 from current kernel |
Bug | LU-471 | mkfs.lustre ext4 extended options passed via --mkfsoptions are ignored |
Improvement | LU-473 | Improve error message when 2.x client tries to mount 1.8 server |
Improvement | LU-476 | sanity 60a: run-llog.sh: SKIP: no MGS available, skipping llog test |
Bug | LU-477 | Oops: RIP: ldiskfs:ldiskfs_clear_inode+0x81/0xb0 |
Bug | LU-480 | Test failure on test suite sanityn: LBUG/LASSERT detected |
Bug | LU-481 | sanity test_119d fails (ASSERTION((struct cl_page *)vmpage->private != slice->cpl_page) failed) |
Bug | LU-487 | procfs stats file incorrectly records brw_read and brw_write values |
Bug | LU-491 | conf-sanity/50g fails on a local setup |
Bug | LU-492 | Test failure on sanity-quota test_29 |
Bug | LU-502 | ll_ost_io threads can be killed with OOM killer |
Improvement | LU-528 | Update RHEL5 kernel to 2.6.18-238.19.1 security update |
Bug | LU-530 | group qoutas not enforced |
Bug | LU-533 | lustre_types.h is missing, and replacement posix-types.h not included in user-space |
Bug | LU-539 | small size for RMF_CONNECT_DATA caused out of bound memory crash |
Bug | LU-544 | 1.8<->2.1 interop: conf-sanity test 56: mkfs.lustre FAIL: Journal size too big for filesystem. |
Bug | LU-559 | 1.8<->2.1 interop: LBUG: ASSERTION(diff >= 0) failed: lustre-OST0000: 1 - 33 = -32 |
Bug | LU-560 | negative dentries not cached after open, even with MDS_INODELOCK_UPDATE on parent |
Improvement | LU-585 | Bad error message "This is reconstruct open:" |
Bug | LU-592 | 1.8<->2.1 interop: sanity-quota test_25: FAIL: quota_usr inode quota usage transfer from quota_usr to quota_2usr failed: ||||||||||\ |
Bug | LU-594 | 1.8<->2.1 interop: sanity test_27y: FAIL: files created on deactivated OSTs instead of degraded OST |
Bug | LU-598 | Memory crash in racer test when open the object just deleted by other |
Bug | LU-599 | 1.8<->2.1 interop: Oops: RIP: mdt:mdt_identity_parse_downcall+0x4dc/0x5d0 |
Bug | LU-622 | Oops: RIP: libcfs:libcfs_debug_vmsg2+0x40b/0x9f0 |
Bug | LU-627 | LBUG: (lproc_llite.c:852:lprocfs_register_mountpoint()) ASSERTION(obd != NULL) failed |
Bug | LU-647 | e2fsprogs build failed |
Bug | LU-650 | recovery-double-scale: (llite_lib.c:1591:ll_update_inode()) LBUG |
Bug | LU-653 | recovery-mds-scale (FLAVOR=OSS): dbench write failed on handle 11108 (Cannot send after transport endpoint shutdown) |
Bug | LU-662 | 1.8<- >2.1 interop: LBUG: ASSERTION(!range_is_exhausted(&seq- >lcs_space)) failed |