#
a584ef65 |
| 09-Mar-2007 |
johansen <none@none> |
6452589 zl_lock still held excessively long
|
#
d63d470b |
| 16-Feb-2007 |
gw25295 <none@none> |
6513020 zio pipeline went out to lunch
|
#
893a6d32 |
| 22-Jan-2007 |
ahrens <none@none> |
6514331 in-memory delete queue is not needed
|
#
67bd71c6 |
| 04-Nov-2006 |
perrin <none@none> |
6341569 zio_alloc_blk() vdev distribution performs badly 6428639 large writes to zvol synchs too much, better cut down a little 6444692 Need to flush disk write cache for dmu_sync buffers 6465634 zvo
6341569 zio_alloc_blk() vdev distribution performs badly 6428639 large writes to zvol synchs too much, better cut down a little 6444692 Need to flush disk write cache for dmu_sync buffers 6465634 zvol: dmu_sync() should be issued in parallel 6468731 lwb_state_t can be nuked 6470042 parallel dmu_sync() isn't being used 6471679 stash blocksize in zvol_state_t rather than reading in every zvol_log_write 6472230 ZIL vdev management is inefficient 6473775 zil_commit changes in snv_48 make it hot for O_DSYNC workloads 6478388 ZIL replay takes too long causing issues while booting 6486390 zil_commit could push more transactions 6486496 zil_replay() useful debug
show more ...
|
#
416e0cd8 |
| 26-Oct-2006 |
ek110237 <none@none> |
6485204 more tuneable tweakin
|
#
5ad82045 |
| 04-Oct-2006 |
nd150628 <none@none> |
6463348 ZFS code could be more portable
|
#
b19a79ec |
| 29-Aug-2006 |
perrin <none@none> |
6413510 zfs: writing to ZFS filesystem slows down fsync() on other files in the same FS 6453172 ztest turns into a sloth due to massive arc_min_prefetch_lifespan
|
#
13506d1e |
| 19-Jul-2006 |
maybee <none@none> |
6447377 ZFS prefetch is inconsistant
|
#
c5c6ffa0 |
| 20-Jun-2006 |
maybee <none@none> |
6416482 filebench oltp workload hangs in zfs 6440499 zil should avoid txg_wait_synced() and use dmu_sync() to issue parallel IOs when fsyncing
|
#
1d452cf5 |
| 15-Jun-2006 |
ahrens <none@none> |
PSARC 2006/388 snapshot -r 6373978 want to take lots of snapshots quickly ('zfs snapshot -r')
|
#
b4d654b0 |
| 20-Apr-2006 |
perrin <none@none> |
6413731 pathologically slower fsync on 32 bit systems
|
#
d80c45e0 |
| 14-Apr-2006 |
bonwick <none@none> |
6410711 intent log blocks don't get invited to pool parties
|
#
104e2ed7 |
| 23-Mar-2006 |
perrin <none@none> |
6343608 ZFS file range locking 6365101 zfs: copying from NFS to ZFS makes ksh response very sluggish 6393003 System hung -- out of memory (kernel va) due to zil's itx_t's 6393671 deadlock between dnl
6343608 ZFS file range locking 6365101 zfs: copying from NFS to ZFS makes ksh response very sluggish 6393003 System hung -- out of memory (kernel va) due to zil's itx_t's 6393671 deadlock between dnlc_reduce_cache() and zfs_zget() 6399298 system seems to be spinning in dnlc_reduce_cache()
show more ...
|
#
436b2950 |
| 20-Mar-2006 |
perrin <none@none> |
6393443 Remove remaining txg_wait_synced() from zfs unmount path.
|
#
ea8dc4b6 |
| 04-Mar-2006 |
eschrock <none@none> |
PSARC 2006/077 zpool clear PSARC 2006/139 FMA for ZFS 6284889 arc should replace the znode cache 6333006 DMU & DSL should not panic upon I/O error 6333092 concurrent reads to a file not scaling with
PSARC 2006/077 zpool clear PSARC 2006/139 FMA for ZFS 6284889 arc should replace the znode cache 6333006 DMU & DSL should not panic upon I/O error 6333092 concurrent reads to a file not scaling with number of readers 6338081 ZFS/FMA phase 1 6338386 need persistent error log 6341326 i/o error causes arc buf hash table corruption 6341639 zfs backup/restore should compute/verify checksum of backup stream 6348002 out of space due to changing properties 6354724 inaccurate error message from zfs restore 6354872 dmu_sync() blows predictive accounting 6355416 zpool scrubbing consumes all memory, system hung 6363995 df should only load libzfs when it encounters a ZFS filesystem 6366320 zfs backup/restore doesn't like signals 6368892 mount -m support needed for legacy mounts 6368902 boot archive fstat support needed for ZFS Mountroot 6369424 BFU complains when bfu'ing a ZFS root filesystem 6374062 mountroot support needed for ZFS 6376356 dirtying dbuf obj=43 lvl=0 blkid=0 but not tx_held 6378391 unused members of dmu_objset_stats_t 6378392 clean up zfs_cmd_t structure 6378685 buf_init should allocate its hash table more carefully 6378976 ziltest should be a first class citizen 6381086 zdb segfaults if there is a spa deferred-free bplist 6381203 deadlock due to i/o while assigning (tc_lock held) 6381209 freed space is not immediately available 6381344 'zpool clear' 6381345 FAULTED devices should really be UNAVAIL 6381346 import should mark devices as persistently unavailable 6383272 recursive mutex_enter() during log replay with zfs root 6386326 origin property is not displayed 6386354 libzfs does too much in its _init section, calls exit(1) 6386624 zpool should not complain about non-existent devices from libdiskmgt 6386910 spa needs to be i/o error hardened 6387735 need a mechanism to inject faults into ZFS 6387736 internal ZFS utilities should be placed in an ON-private package 6389928 libzfs should ship a lint library 6390609 malformed vdev config panics on zpool_create() 6390677 version number checking makes upgrades challenging 6390713 ztest hangs in zil_suspend() 6391873 metadata compression should be turned back on 6392113 ztest sometimes reports leaked blocks because ZIL isn't resilvered 6393004 minor memory leak in unique_insert()
show more ...
|
#
fe9cf88c |
| 23-Feb-2006 |
perrin <none@none> |
6381994 zfs_putpage() serializes I/O unnecessarily 6388739 threads can wait past transaction being committed in zil_commit
|
#
13f5297e |
| 01-Feb-2006 |
perrin <none@none> |
6377670 zil_replay() does unnecessary txg_wait_synced(), slowing down mount
|
#
22ac5be4 |
| 17-Dec-2005 |
perrin <none@none> |
6354547 sticky log buf size 6356050 zl_lock held excessively long 6356243 zfs_putpage: should do a synchronous write when B_ASYNC is not set 6358233 ZVOL doesn't honour O_DSYNC semantics
|
#
fa9e4066 |
| 31-Oct-2005 |
ahrens <none@none> |
PSARC 2002/240 ZFS 6338653 Integrate ZFS PSARC 2004/652 - DKIOCFLUSH 5096886 Write caching disks need mechanism to flush cache to physical media
|