Date: Tue, 11 May 2010 23:26:07 +0200 From: =?iso-8859-1?Q?Cl=E9ment_Moulin?= <cmoulin@simplerezo.com> To: <freebsd-fs@freebsd.org> Subject: Very bad ZFS performance on fresh FreeBSD 8 installation Message-ID: <00e201caf150$91d3b950$b57b2bf0$@com>
next in thread | raw e-mail | index | archive | help
Hi
We have recently added 3 new disks to one of our storage servers =
(Opteron
DualCore 2.2 GHz, 2048 MB RAM).
We made a ZFS pool storage of this 3 disks (2 TB each) attached to a =
PCIX
SATA RAID controllers (3ware 9550SX-16ML), and made a fresh installation =
of
FreeBSD 8/amd64.
Disk performance other the ZFS storage is very bad (about 8-9 MB read or
write...).
And when machine has low FREE memory (lot of INACTIVE memory used), it's
even worst (about 2MB/s)...
~$ uname -a
FreeBSD ---.simplerezo.com 8.0-RELEASE-p2 FreeBSD 8.0-RELEASE-p2 #0: Wed =
Apr
28 23:07:37 CEST 2010
root@---.simplerezo.com:/usr/obj/usr/src/sys/KERNEL amd64
# NOTE: tried with -RELEASE, running -STABLE (same results)
~$ zpool list
NAME SIZE USED AVAIL CAP HEALTH ALTROOT
tank 5,44T 1,26T 4,18T 23% ONLINE -
~$ zpool status
pool: tank
state: ONLINE
scrub: none requested
config:
NAME STATE READ WRITE CKSUM
tank ONLINE 0 0 0
raidz1 ONLINE 0 0 0
da0p2 ONLINE 0 0 0
da1p2 ONLINE 0 0 0
da2p2 ONLINE 0 0 0
errors: No known data errors
~$ tw_cli /c0 show all
/c0 Driver Version =3D 3.70.05.001
/c0 Model =3D 9550SX-16ML
/c0 Available Memory =3D 224MB
/c0 Firmware Version =3D FE9X 3.08.00.029
/c0 Bios Version =3D BE9X 3.10.00.003
/c0 Boot Loader Version =3D BL9X 3.01.00.006
/c0 Serial Number =3D L021603A6120017
/c0 PCB Version =3D Rev 032
/c0 PCHIP Version =3D 1.60
/c0 ACHIP Version =3D 1.70
/c0 Number of Ports =3D 16
/c0 Number of Drives =3D 13
/c0 Number of Units =3D 7
/c0 Total Optimal Units =3D 7
/c0 Not Optimal Units =3D 0
/c0 JBOD Export Policy =3D off
/c0 Disk Spinup Policy =3D 1
/c0 Spinup Stagger Time Policy (sec) =3D 1
/c0 Auto-Carving Policy =3D off
/c0 Auto-Carving Size =3D 2048 GB
/c0 Auto-Rebuild Policy =3D on
/c0 Rebuild Rate =3D 1
/c0 Verify Rate =3D 1
/c0 Controller Bus Type =3D PCIX
/c0 Controller Bus Width =3D 64 bits
/c0 Controller Bus Speed =3D 133 Mhz
Unit UnitType Status %RCmpl %V/I/M Stripe Size(GB) Cache
AVrfy
-------------------------------------------------------------------------=
---
--
u0 SINGLE OK - - - 1862.63 ON =
OFF
u1 SINGLE OK - - - 1862.63 ON =
OFF
u2 SINGLE OK - - - 1862.63 ON =
OFF
u3 RAID-5 OK - - 64K 931.303 ON =
OFF
u4 RAID-5 OK - - 64K 931.303 ON =
OFF
u5 RAID-5 OK - - 64K 1396.96 ON =
OFF
u6 SINGLE OK - - - 1862.63 ON =
OFF
Port Status Unit Size Blocks Serial
---------------------------------------------------------------
p0 OK u0 1.82 TB 3907029168 S1UYJ1BZ102991
p1 OK u1 1.82 TB 3907029168 JK1170YAHU3KVP
p2 OK u2 1.82 TB 3907029168 S1UYJ1LZ110057
p3 OK u4 465.76 GB 976773168 KRVN33ZAHEKHXD
p4 OK u4 465.76 GB 976773168 KRVN33ZAHE54XD
p5 OK u4 465.76 GB 976773168 KRVN33ZAHDZPMD
p6 OK u5 698.63 GB 1465149168 3QD08DVE
p7 OK u5 698.63 GB 1465149168 3QD09JMS
p8 OK u5 698.63 GB 1465149168 3QD09758
p9 NOT-PRESENT - - - -
p10 NOT-PRESENT - - - -
p11 OK u3 465.76 GB 976773168 KRVN33ZAHG0DED
p12 OK u3 465.76 GB 976773168 KRVN33ZAHAJ4ZD
p13 OK u3 465.76 GB 976773168 KRVN33ZAH80K6D
p14 OK u6 1.82 TB 3907029168 JK1120YAG2K1DP
p15 NOT-PRESENT - - - -
Name OnlineState BBUReady Status Volt Temp Hours =
LastCapTest
-------------------------------------------------------------------------=
--
bbu On Yes OK OK OK 255 =
03-Oct-2009
~$ diskinfo -c -t /dev/da0
/dev/da0
512 # sectorsize
1999988850688 # mediasize in bytes (1.8T)
3906228224 # mediasize in sectors
243151 # Cylinders according to firmware.
255 # Heads according to firmware.
63 # Sectors according to firmware.
BZ102991D7FFC800F1DE # Disk ident.
I/O command overhead:
time to read 10MB block 0.109465 sec =3D 0.005
msec/sector
time to read 20480 sectors 3.105226 sec =3D 0.152
msec/sector
calculated command overhead =3D 0.146
msec/sector
Seek times:
Full stroke: 250 iter in 5.754512 sec =3D 23.018 msec
Half stroke: 250 iter in 4.829476 sec =3D 19.318 msec
Quarter stroke: 500 iter in 9.630453 sec =3D 19.261 msec
Short forward: 400 iter in 5.849457 sec =3D 14.624 msec
Short backward: 400 iter in 4.123671 sec =3D 10.309 msec
Seq outer: 2048 iter in 0.222291 sec =3D 0.109 msec
Seq inner: 2048 iter in 0.229290 sec =3D 0.112 msec
Transfer rates:
outside: 102400 kbytes in 1.024872 sec =3D 99915 =
kbytes/sec
middle: 102400 kbytes in 1.220958 sec =3D 83869 =
kbytes/sec
inside: 102400 kbytes in 2.315101 sec =3D 44231 =
kbytes/sec
~$ diskinfo -c -t /dev/da1
/dev/da1
512 # sectorsize
1999988850688 # mediasize in bytes (1.8T)
3906228224 # mediasize in sectors
243151 # Cylinders according to firmware.
255 # Heads according to firmware.
63 # Sectors according to firmware.
YAHU3KVPD7FFCD0054FA # Disk ident.
I/O command overhead:
time to read 10MB block 0.111094 sec =3D 0.005
msec/sector
time to read 20480 sectors 4.501331 sec =3D 0.220
msec/sector
calculated command overhead =3D 0.214
msec/sector
Seek times:
Full stroke: 250 iter in 5.741269 sec =3D 22.965 msec
Half stroke: 250 iter in 3.777884 sec =3D 15.112 msec
Quarter stroke: 500 iter in 6.487416 sec =3D 12.975 msec
Short forward: 400 iter in 3.129467 sec =3D 7.824 msec
Short backward: 400 iter in 2.411493 sec =3D 6.029 msec
Seq outer: 2048 iter in 0.419405 sec =3D 0.205 msec
Seq inner: 2048 iter in 0.425003 sec =3D 0.208 msec
Transfer rates:
outside: 102400 kbytes in 0.808851 sec =3D 126599 =
kbytes/sec
middle: 102400 kbytes in 1.716277 sec =3D 59664 =
kbytes/sec
inside: 102400 kbytes in 1.985879 sec =3D 51564 =
kbytes/sec
# NOTE: da2 not showed (same h/w as da1)
~$ dd if=3D/dev/zero of=3Dtest1G bs=3D1M count=3D1024
1024+0 records in
1024+0 records out
1073741824 bytes transferred in 133.956339 secs (8015610 bytes/sec)
# gstat and zpool iostat reports same values
# The same test done on the same machine (da6 is the similar disk as =
da1),
on an UFS partition (results is about 80 MB/s):
~$ dd if=3D/dev/zero of=3Dtest1G bs=3D1M count=3D1024
1024+0 records in
1024+0 records out
1073741824 bytes transferred in 12.543317 secs (85602701 bytes/sec)
~$ cat /boot/loader.conf
zfs_load=3D"YES"
vfs.root.mountfrom=3D"zfs:tank/root"
vfs.zfs.arc_max=3D"64M"
vm.kmem_size=3D"1024M"
vm.swap_enabled=3D"0"
~$ sysctl vfs.zfs kstat.zfs
vfs.zfs.l2c_only_size: 0
vfs.zfs.mfu_ghost_data_lsize: 0
vfs.zfs.mfu_ghost_metadata_lsize: 0
vfs.zfs.mfu_ghost_size: 0
vfs.zfs.mfu_data_lsize: 0
vfs.zfs.mfu_metadata_lsize: 0
vfs.zfs.mfu_size: 114688
vfs.zfs.mru_ghost_data_lsize: 0
vfs.zfs.mru_ghost_metadata_lsize: 0
vfs.zfs.mru_ghost_size: 0
vfs.zfs.mru_data_lsize: 512
vfs.zfs.mru_metadata_lsize: 0
vfs.zfs.mru_size: 59429376
vfs.zfs.anon_data_lsize: 0
vfs.zfs.anon_metadata_lsize: 0
vfs.zfs.anon_size: 1656320
vfs.zfs.l2arc_noprefetch: 0
vfs.zfs.l2arc_feed_secs_shift: 1
vfs.zfs.l2arc_feed_secs: 1
vfs.zfs.l2arc_headroom: 128
vfs.zfs.l2arc_write_boost: 67108864
vfs.zfs.l2arc_write_max: 67108864
vfs.zfs.arc_meta_limit: 16777216
vfs.zfs.arc_meta_used: 107541232
vfs.zfs.mdcomp_disable: 0
vfs.zfs.arc_min: 33554432
vfs.zfs.arc_max: 67108864
vfs.zfs.zfetch.array_rd_sz: 1048576
vfs.zfs.zfetch.block_cap: 256
vfs.zfs.zfetch.min_sec_reap: 2
vfs.zfs.zfetch.max_streams: 8
vfs.zfs.prefetch_disable: 1
vfs.zfs.recover: 0
vfs.zfs.txg.synctime: 5
vfs.zfs.txg.timeout: 30
vfs.zfs.scrub_limit: 10
vfs.zfs.vdev.cache.bshift: 16
vfs.zfs.vdev.cache.size: 10485760
vfs.zfs.vdev.cache.max: 16384
vfs.zfs.vdev.aggregation_limit: 131072
vfs.zfs.vdev.ramp_rate: 2
vfs.zfs.vdev.time_shift: 6
vfs.zfs.vdev.min_pending: 4
vfs.zfs.vdev.max_pending: 35
vfs.zfs.cache_flush_disable: 0
vfs.zfs.zil_disable: 0
vfs.zfs.version.zpl: 3
vfs.zfs.version.vdev_boot: 1
vfs.zfs.version.spa: 13
vfs.zfs.version.dmu_backup_stream: 1
vfs.zfs.version.dmu_backup_header: 2
vfs.zfs.version.acl: 1
vfs.zfs.debug: 0
vfs.zfs.super_owner: 0
kstat.zfs.misc.arcstats.hits: 677531
kstat.zfs.misc.arcstats.misses: 805411
kstat.zfs.misc.arcstats.demand_data_hits: 524276
kstat.zfs.misc.arcstats.demand_data_misses: 570927
kstat.zfs.misc.arcstats.demand_metadata_hits: 153255
kstat.zfs.misc.arcstats.demand_metadata_misses: 234484
kstat.zfs.misc.arcstats.prefetch_data_hits: 0
kstat.zfs.misc.arcstats.prefetch_data_misses: 0
kstat.zfs.misc.arcstats.prefetch_metadata_hits: 0
kstat.zfs.misc.arcstats.prefetch_metadata_misses: 0
kstat.zfs.misc.arcstats.mru_hits: 634920
kstat.zfs.misc.arcstats.mru_ghost_hits: 4103
kstat.zfs.misc.arcstats.mfu_hits: 42611
kstat.zfs.misc.arcstats.mfu_ghost_hits: 5985
kstat.zfs.misc.arcstats.allocated: 1132742
kstat.zfs.misc.arcstats.deleted: 839033
kstat.zfs.misc.arcstats.stolen: 378817
kstat.zfs.misc.arcstats.recycle_miss: 751590
kstat.zfs.misc.arcstats.mutex_miss: 457
kstat.zfs.misc.arcstats.evict_skip: 713728
kstat.zfs.misc.arcstats.hash_elements: 3639
kstat.zfs.misc.arcstats.hash_elements_max: 6958
kstat.zfs.misc.arcstats.hash_collisions: 146864
kstat.zfs.misc.arcstats.hash_chains: 195
kstat.zfs.misc.arcstats.hash_chain_max: 4
kstat.zfs.misc.arcstats.p: 33554432
kstat.zfs.misc.arcstats.c: 33554432
kstat.zfs.misc.arcstats.c_min: 33554432
kstat.zfs.misc.arcstats.c_max: 67108864
kstat.zfs.misc.arcstats.size: 107823344
kstat.zfs.misc.arcstats.hdr_size: 764608
kstat.zfs.misc.arcstats.l2_hits: 0
kstat.zfs.misc.arcstats.l2_misses: 0
kstat.zfs.misc.arcstats.l2_feeds: 0
kstat.zfs.misc.arcstats.l2_rw_clash: 0
kstat.zfs.misc.arcstats.l2_writes_sent: 0
kstat.zfs.misc.arcstats.l2_writes_done: 0
kstat.zfs.misc.arcstats.l2_writes_error: 0
kstat.zfs.misc.arcstats.l2_writes_hdr_miss: 0
kstat.zfs.misc.arcstats.l2_evict_lock_retry: 0
kstat.zfs.misc.arcstats.l2_evict_reading: 0
kstat.zfs.misc.arcstats.l2_free_on_write: 0
kstat.zfs.misc.arcstats.l2_abort_lowmem: 0
kstat.zfs.misc.arcstats.l2_cksum_bad: 0
kstat.zfs.misc.arcstats.l2_io_error: 0
kstat.zfs.misc.arcstats.l2_size: 0
kstat.zfs.misc.arcstats.l2_hdr_size: 0
kstat.zfs.misc.arcstats.memory_throttle_count: 0
kstat.zfs.misc.arcstats.l2_write_trylock_fail: 0
kstat.zfs.misc.arcstats.l2_write_passed_headroom: 0
kstat.zfs.misc.arcstats.l2_write_spa_mismatch: 0
kstat.zfs.misc.arcstats.l2_write_in_l2: 0
kstat.zfs.misc.arcstats.l2_write_io_in_progress: 0
kstat.zfs.misc.arcstats.l2_write_not_cacheable: 0
kstat.zfs.misc.arcstats.l2_write_full: 0
kstat.zfs.misc.arcstats.l2_write_buffer_iter: 0
kstat.zfs.misc.arcstats.l2_write_pios: 0
kstat.zfs.misc.arcstats.l2_write_bytes_written: 0
kstat.zfs.misc.arcstats.l2_write_buffer_bytes_scanned: 0
kstat.zfs.misc.arcstats.l2_write_buffer_list_iter: 0
kstat.zfs.misc.arcstats.l2_write_buffer_list_null_iter: 0
kstat.zfs.misc.vdev_cache_stats.delegations: 3113
kstat.zfs.misc.vdev_cache_stats.hits: 342284
kstat.zfs.misc.vdev_cache_stats.misses: 50877
...
--
Cl=E9ment Moulin SimpleRezo
www.simplerezo.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?00e201caf150$91d3b950$b57b2bf0$>