Facebook
Twitter
Hello everyone,
I configured a NAS on a dedicated server with Plesk (Debian).
This dedicated hosts a website, the purpose of the NAS-HA is to put the site files there to allow the addition of an additional instance behind a LoadBalancer.
No problem to configure the NAS (nfs).
I then copied the site files and then changed the pointing of the domain to this space.
The website works but the display of a page takes 1 minute (!) instead of a few millisecond when the storage is on the SSD.
One php page with only "echo 'OK';" take 2 seconds to be displayed (!).
I don't understand this performance. In state, the use of the NAS is impossible.
Nothing in the web logs.
Anyone have an idea of the problem? or how to improve this.
For information, NAS configuration with NFS:
#sudo mount -t nfs IP_HA-NAS:/NFS_PATH /var/www/vhosts/mydomain.com/public
NAS Performance:
/bin/dd if=/dev/zero of=speedtest bs=1M count=300 conv=fdatasync
300+0 records in
300+0 records out
314572800 bytes (315 MB, 300 MiB) copied, 5.4138 s, 58.1 MB/s
fio --name=rand-write --ioengine=libaio --iodepth=32 --rw=randwrite --invalidate=1 --bsrange=4k:4k,4k:4k --size=512m --runtime=120 --timebased --do_verify=1 --direct=1 --group_reporting --numjobs=1_
rand-write: (g=0): rw=randwrite, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=libaio, iodepth=32
fio-3.25
Starting 1 process
rand-write: Laying out IO file (1 file / 512MiB)
Jobs: 1 (f=1): [w(1)][100.0%][w=10.7MiB/s][w=2748 IOPS][eta 00m:00s]
rand-write: (groupid=0, jobs=1): err= 0: pid=168930: Sat Jul 29 21:27:31 2023
write: IOPS=2746, BW=10.7MiB/s (11.2MB/s)(1288MiB/120011msec); 0 zone resets
slat (nsec): min=1776, max=3567.4k, avg=9004.97, stdev=10353.93
clat (usec): min=10723, max=43593, avg=11637.62, stdev=561.72
lat (usec): min=10756, max=43600, avg=11646.82, stdev=561.44
clat percentiles (usec):
| 1.00th=[10945], 5.00th=[11076], 10.00th=[11207], 20.00th=[11338],
| 30.00th=[11469], 40.00th=[11469], 50.00th=[11600], 60.00th=[11600],
| 70.00th=[11731], 80.00th=[11863], 90.00th=[12125], 95.00th=[12256],
| 99.00th=[12780], 99.50th=[13829], 99.90th=[17957], 99.95th=[19792],
| 99.99th=[27132]
bw ( KiB/s): min= 9532, max=11233, per=100.00%, avg=10995.37, stdev=162.55, samples=237
iops : min= 2383, max= 2808, avg=2748.56, stdev=40.61, samples=237
lat (msec) : 20=99.96%, 50=0.04%
cpu : usr=1.11%, sys=2.54%, ctx=140200, majf=0, minf=8
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=100.0%, >=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=0.1%, 64=0.0%, >=64=0.0%
issued rwts: total=0,329626,0,0 short=0,0,0,0 dropped=0,0,0,0
latency : target=0, window=0, percentile=100.00%, depth=32
Run status group 0 (all jobs):
WRITE: bw=10.7MiB/s (11.2MB/s), 10.7MiB/s-10.7MiB/s (11.2MB/s-11.2MB/s), io=1288MiB (1350MB), run=120011-120011msec
Thank you in advance for your help.
I configured a NAS on a dedicated server with Plesk (Debian).
This dedicated hosts a website, the purpose of the NAS-HA is to put the site files there to allow the addition of an additional instance behind a LoadBalancer.
No problem to configure the NAS (nfs).
I then copied the site files and then changed the pointing of the domain to this space.
The website works but the display of a page takes 1 minute (!) instead of a few millisecond when the storage is on the SSD.
One php page with only "echo 'OK';" take 2 seconds to be displayed (!).
I don't understand this performance. In state, the use of the NAS is impossible.
Nothing in the web logs.
Anyone have an idea of the problem? or how to improve this.
For information, NAS configuration with NFS:
#sudo mount -t nfs IP_HA-NAS:/NFS_PATH /var/www/vhosts/mydomain.com/public
NAS Performance:
/bin/dd if=/dev/zero of=speedtest bs=1M count=300 conv=fdatasync
300+0 records in
300+0 records out
314572800 bytes (315 MB, 300 MiB) copied, 5.4138 s, 58.1 MB/s
fio --name=rand-write --ioengine=libaio --iodepth=32 --rw=randwrite --invalidate=1 --bsrange=4k:4k,4k:4k --size=512m --runtime=120 --timebased --do_verify=1 --direct=1 --group_reporting --numjobs=1_
rand-write: (g=0): rw=randwrite, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=libaio, iodepth=32
fio-3.25
Starting 1 process
rand-write: Laying out IO file (1 file / 512MiB)
Jobs: 1 (f=1): [w(1)][100.0%][w=10.7MiB/s][w=2748 IOPS][eta 00m:00s]
rand-write: (groupid=0, jobs=1): err= 0: pid=168930: Sat Jul 29 21:27:31 2023
write: IOPS=2746, BW=10.7MiB/s (11.2MB/s)(1288MiB/120011msec); 0 zone resets
slat (nsec): min=1776, max=3567.4k, avg=9004.97, stdev=10353.93
clat (usec): min=10723, max=43593, avg=11637.62, stdev=561.72
lat (usec): min=10756, max=43600, avg=11646.82, stdev=561.44
clat percentiles (usec):
| 1.00th=[10945], 5.00th=[11076], 10.00th=[11207], 20.00th=[11338],
| 30.00th=[11469], 40.00th=[11469], 50.00th=[11600], 60.00th=[11600],
| 70.00th=[11731], 80.00th=[11863], 90.00th=[12125], 95.00th=[12256],
| 99.00th=[12780], 99.50th=[13829], 99.90th=[17957], 99.95th=[19792],
| 99.99th=[27132]
bw ( KiB/s): min= 9532, max=11233, per=100.00%, avg=10995.37, stdev=162.55, samples=237
iops : min= 2383, max= 2808, avg=2748.56, stdev=40.61, samples=237
lat (msec) : 20=99.96%, 50=0.04%
cpu : usr=1.11%, sys=2.54%, ctx=140200, majf=0, minf=8
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=100.0%, >=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=0.1%, 64=0.0%, >=64=0.0%
issued rwts: total=0,329626,0,0 short=0,0,0,0 dropped=0,0,0,0
latency : target=0, window=0, percentile=100.00%, depth=32
Run status group 0 (all jobs):
WRITE: bw=10.7MiB/s (11.2MB/s), 10.7MiB/s-10.7MiB/s (11.2MB/s-11.2MB/s), io=1288MiB (1350MB), run=120011-120011msec
Thank you in advance for your help.