Hi,
I got a HP StorageWorks P2000 G3 and AW595B controller. Tested out on a single 10G link (Jumbo enabled), and have ~1Gbit only
In storage I have 24*600G 10K SAS disks (HP) ant two vdisks are configured to store virtual harddisks.
fio test show it has 1.59Gbit/s, instead of 10G
Read test more worst 0,03832 Gbit/s
Where would be the bottleneck of this setup? Because this speed more than disappointed
What is the max speed of P2000 on each iSCSI ports in this setup?
I got a HP StorageWorks P2000 G3 and AW595B controller. Tested out on a single 10G link (Jumbo enabled), and have ~1Gbit only
In storage I have 24*600G 10K SAS disks (HP) ant two vdisks are configured to store virtual harddisks.
fio test show it has 1.59Gbit/s, instead of 10G
Code:
fio --name=randwrite --ioengine=libaio --rw=randwrite --bs=4k --numjobs=1 --size=1G --runtime=60 --time_based --filename=/dev/sdi
randwrite: (g=0): rw=randwrite, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=libaio, iodepth=1
fio-3.33
Starting 1 process
Jobs: 1 (f=1): [w(1)][100.0%][eta 00m:00s]
randwrite: (groupid=0, jobs=1): err= 0: pid=690003: Sat Mar 8 11:11:09 2025
write: IOPS=50.9k, BW=199MiB/s (208MB/s)(12.0GiB/61848msec); 0 zone resets
slat (nsec): min=1932, max=690434, avg=3497.99, stdev=2738.21
clat (nsec): min=635, max=370714, avg=797.13, stdev=930.61
lat (usec): min=2, max=694, avg= 4.30, stdev= 2.94
clat percentiles (nsec):
| 1.00th=[ 644], 5.00th=[ 644], 10.00th=[ 652], 20.00th=[ 652],
| 30.00th=[ 660], 40.00th=[ 708], 50.00th=[ 844], 60.00th=[ 852],
| 70.00th=[ 852], 80.00th=[ 860], 90.00th=[ 868], 95.00th=[ 884],
| 99.00th=[ 1800], 99.50th=[ 1848], 99.90th=[ 6304], 99.95th=[11456],
| 99.99th=[12736]
bw ( KiB/s): min=12696, max=1007632, per=100.00%, avg=629145.00, stdev=291490.32, samples=40
iops : min= 3174, max=251908, avg=157286.35, stdev=72872.53, samples=40
lat (nsec) : 750=45.03%, 1000=52.07%
lat (usec) : 2=2.70%, 4=0.04%, 10=0.07%, 20=0.08%, 50=0.01%
lat (usec) : 100=0.01%, 250=0.01%, 500=0.01%
cpu : usr=6.80%, sys=35.58%, ctx=4147, majf=4, minf=108
IO depths : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
issued rwts: total=0,3145729,0,0 short=0,0,0,0 dropped=0,0,0,0
latency : target=0, window=0, percentile=100.00%, depth=1
Run status group 0 (all jobs):
WRITE: bw=199MiB/s (208MB/s), 199MiB/s-199MiB/s (208MB/s-208MB/s), io=12.0GiB (12.9GB), run=61848-61848msec
Disk stats (read/write):
sdi: ios=16/12297, merge=0/3133431, ticks=308/675452, in_queue=675760, util=69.04%Read test more worst 0,03832 Gbit/s
Code:
fio --name=randread --ioengine=libaio --rw=randread --bs=4k --size=1G --numjobs=1 --runtime=60 --time_based --filename=/dev/sdi
randread: (g=0): rw=randread, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=libaio, iodepth=1
fio-3.33
Starting 1 process
Jobs: 1 (f=1): [r(1)][100.0%][r=5244KiB/s][r=1311 IOPS][eta 00m:00s]
randread: (groupid=0, jobs=1): err= 0: pid=703107: Sat Mar 8 11:27:27 2025
read: IOPS=1227, BW=4908KiB/s (5026kB/s)(288MiB/60003msec)
slat (usec): min=160, max=16338, avg=806.38, stdev=1336.86
clat (nsec): min=1314, max=412638, avg=4932.30, stdev=3440.78
lat (usec): min=163, max=16344, avg=811.31, stdev=1337.37
clat percentiles (nsec):
| 1.00th=[ 2672], 5.00th=[ 2928], 10.00th=[ 3088], 20.00th=[ 3344],
| 30.00th=[ 3696], 40.00th=[ 4192], 50.00th=[ 4640], 60.00th=[ 5088],
| 70.00th=[ 5984], 80.00th=[ 6496], 90.00th=[ 6688], 95.00th=[ 6944],
| 99.00th=[ 8768], 99.50th=[14784], 99.90th=[25472], 99.95th=[29568],
| 99.99th=[69120]
bw ( KiB/s): min= 1360, max= 5848, per=100.00%, avg=4916.30, stdev=666.02, samples=119
iops : min= 340, max= 1462, avg=1229.08, stdev=166.50, samples=119
lat (usec) : 2=0.18%, 4=36.15%, 10=62.89%, 20=0.51%, 50=0.26%
lat (usec) : 100=0.01%, 250=0.01%, 500=0.01%
cpu : usr=1.38%, sys=4.83%, ctx=73661, majf=0, minf=22
IO depths : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
issued rwts: total=73631,0,0,0 short=0,0,0,0 dropped=0,0,0,0
latency : target=0, window=0, percentile=100.00%, depth=1
Run status group 0 (all jobs):
READ: bw=4908KiB/s (5026kB/s), 4908KiB/s-4908KiB/s (5026kB/s-5026kB/s), io=288MiB (302MB), run=60003-60003msec
Disk stats (read/write):
sdi: ios=73534/0, merge=0/0, ticks=56773/0, in_queue=56773, util=94.57%Where would be the bottleneck of this setup? Because this speed more than disappointed
What is the max speed of P2000 on each iSCSI ports in this setup?
Last edited: