zpool - low speed write (moved from freebsd-stable)

[Alex V. Petrov]

Hi All!

$ dd if=/dev/random of=/tank/test bs=3M count=1000
1000+0 records in
1000+0 records out
3145728000 bytes transferred in 298.153293 secs (10550707 bytes/sec)

What, i think, very-very low :-(

FreeBSD alex.super 8.1-STABLE FreeBSD 8.1-STABLE #76: Mon Aug  2 20:19:09 
KRAST 2010     alex at alex.super:/usr/obj/usr/src/sys/ALEX  amd64

real memory  = 4294967296 (4096 MB)
avail memory = 4098732032 (3908 MB)


zpool status -v
  pool: tank
 state: ONLINE
 scrub: scrub completed after 7h12m with 0 errors on Tue Aug  3 04:54:14 2010
config:

        NAME        STATE     READ WRITE CKSUM
        tank        ONLINE       0     0     0
          ada4      ONLINE       0     0     0
          ada2      ONLINE       0     0     0
          ada3      ONLINE       0     0     0

errors: No known data errors

zpool history
History for 'tank':
2009-07-16.19:46:24 zpool create tank ad12
2009-12-13.14:58:46 zpool add tank ad8
2010-04-24.01:59:41 zpool upgrade tank
2010-05-09.02:16:34 zpool add tank ada3
2010-05-25.17:57:12 zpool scrub tank
2010-06-27.16:02:45 zpool scrub tank
2010-08-02.21:41:53 zpool scrub tank

ada2 at ahcich2 bus 0 scbus2 target 0 lun 0
ada2: <WDC WD10EADS-00M2B0 01.00A01> ATA-8 SATA 2.x device
ada2: 300.000MB/s transfers (SATA 2.x, UDMA6, PIO 8192bytes)
ada2: Command Queueing enabled
ada2: 953869MB (1953525168 512 byte sectors: 16H 63S/T 16383C)
ada3 at ahcich3 bus 0 scbus3 target 0 lun 0
ada3: <WDC WD10EADS-00L5B1 01.01A01> ATA-8 SATA 2.x device
ada3: 300.000MB/s transfers (SATA 2.x, UDMA6, PIO 8192bytes)
ada3: Command Queueing enabled
ada3: 953869MB (1953525168 512 byte sectors: 16H 63S/T 16383C)
ada4 at ahcich4 bus 0 scbus4 target 0 lun 0
ada4: <WDC WD10EADS-00M2B0 01.00A01> ATA-8 SATA 2.x device
ada4: 300.000MB/s transfers (SATA 2.x, UDMA6, PIO 8192bytes)
ada4: Command Queueing enabled

smartd daily output:
Checking health of /dev/ada2: OK
Checking health of /dev/ada3: OK
Checking health of /dev/ada4: OK

/boot/loader.conf:
ahci_load="YES"
sem_load="YES"
snd_hda_load="YES"
nvidia_load="YES"
linux_load="YES"
wlan_xauth_load="YES"
vboxdrv_load="YES"
atapicam_load="YES"
coretemp_load="YES"
aio_load="YES"

****************************************
Next without "ahci_load="YES""

zpool destroy tank

zpool create tank ad8 ad10 ad12

dd if=/dev/zero of=/tank/test.zero bs=3M count=1000
1000+0 records in
1000+0 records out
3145728000 bytes transferred in 83.219741 secs (37800262 bytes/sec)

zpool offline tank ad10
cannot offline ad10: no valid replicas

zpool destroy tank

zpool create tank ad8 ad12

dd if=/dev/zero of=/tank/test.zero bs=3M count=1000
1000+0 records in
1000+0 records out
3145728000 bytes transferred in 126.873102 secs (24794286 bytes/sec)

dd if=/dev/zero of=/tank/test.zero bs=64k count=1000000
1000000+0 records in
1000000+0 records out
65536000000 bytes transferred in 1735.680273 secs (37758106 bytes/sec)

zpool destroy tank

zpool create tank ad8

dd if=/dev/zero of=/tank/test.zero bs=3M count=1000
1000+0 records in
1000+0 records out
3145728000 bytes transferred in 39.550739 secs (79536517 bytes/sec)

dd if=/dev/zero of=/tank/test.zero bs=64k count=100000
100000+0 records in
100000+0 records out
6553600000 bytes transferred in 90.810344 secs (72167990 bytes/sec)

1-disk zpool faster multy-disks?

****************************************

zpool destroy tank

At one time 3 dd

dd if=/dev/zero of=/dev/ad8 bs=64k count=1000000
1000000+0 records in
1000000+0 records out
65536000000 bytes transferred in 605.173955 secs (108292830 bytes/sec)

dd if=/dev/zero of=/dev/ad10 bs=64k count=1000000
1000000+0 records in
1000000+0 records out
65536000000 bytes transferred in 759.946393 secs (86237662 bytes/sec)

dd if=/dev/zero of=/dev/ad12 bs=64k count=1000000
1000000+0 records in
1000000+0 records out
65536000000 bytes transferred in 605.139062 secs (108299074 bytes/sec)


Disks   ad4   ad6   ad8  ad10  ad12   da0   da1
KB/t   0,00 16,00 64,00 64,00 64,00  0,00  0,00
tps       0     1  1667  1329  1646     0     0
MB/s   0,00  0,02   104 83,04   103  0,00  0,00
%busy     0     0    93    94    93     0     0

ie this problem is not the controller


-----
Alex V. Petrov