<div dir="auto">Could you please share fio command line used for this test?<div dir="auto">Additionally, can you tell me the time needed to extract the kernel source?</div></div><div class="gmail_extra"><br><div class="gmail_quote">Il 2 nov 2017 11:24 PM, "Ramon Selga" <<a href="mailto:ramon.selga@gmail.com">ramon.selga@gmail.com</a>> ha scritto:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<div class="m_5627811959350600145moz-cite-prefix">Hi,<br>
<br>
Just for your reference we got some similar values in a customer
setup with three nodes single Xeon and 4x8TB HDD each with a
double 10GbE backbone.<br>
<br>
We did a simple benchmark with fio tool on a virtual disk (virtio)
of a 1TiB of size, XFS formatted directly no partitions no LVM,
inside a VM (debian stretch, dual core 4GB RAM) deployed in a
gluster volume disperse 3 redundancy 1 distributed 2, sharding
enabled.<br>
<br>
We run a sequential write test 10GB file in 1024k blocks, a random
read test with 4k blocks and a random write test also with 4k
blocks several times with results very similar to the following:<br>
<br>
<font size="-1"><tt>writefile: (g=0): rw=write,
bs=1M-1M/1M-1M/1M-1M, ioengine=libaio, iodepth=200</tt><tt><br>
</tt><tt>fio-2.16</tt><tt><br>
</tt><tt>Starting 1 process</tt><tt><br>
</tt><tt><br>
</tt><tt>writefile: (groupid=0, jobs=1): err= 0: pid=11515: Thu
Nov 2 16:50:05 2017</tt><tt><br>
</tt><tt> write: io=10240MB, bw=473868KB/s, iops=462, runt=
22128msec</tt><tt><br>
</tt><tt> slat (usec): min=20, max=98830, avg=1972.11,
stdev=6612.81</tt><tt><br>
</tt><tt> clat (msec): min=150, max=2979, avg=428.49,
stdev=189.96</tt><tt><br>
</tt><tt> lat (msec): min=151, max=2979, avg=430.47,
stdev=189.90</tt><tt><br>
</tt><tt> clat percentiles (msec):</tt><tt><br>
</tt><tt> | 1.00th=[ 204], 5.00th=[ 249], 10.00th=[
273], 20.00th=[ 293],</tt><tt><br>
</tt><tt> | 30.00th=[ 306], 40.00th=[ 318], 50.00th=[
351], 60.00th=[ 502],</tt><tt><br>
</tt><tt> | 70.00th=[ 545], 80.00th=[ 578], 90.00th=[
603], 95.00th=[ 627],</tt><tt><br>
</tt><tt> | 99.00th=[ 717], 99.50th=[ 775], 99.90th=[
2966], 99.95th=[ 2966],</tt><tt><br>
</tt><tt> | 99.99th=[ 2966]</tt><tt><br>
</tt><tt> lat (msec) : 250=5.09%, 500=54.65%, 750=39.64%,
1000=0.31%, 2000=0.07%</tt><tt><br>
</tt><tt> lat (msec) : >=2000=0.24%</tt><tt><br>
</tt><tt> cpu : usr=7.81%, sys=1.48%, ctx=1221,
majf=0, minf=11</tt><tt><br>
</tt><tt> IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%,
16=0.2%, 32=0.3%, >=64=99.4%</tt><tt><br>
</tt><tt> submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%,
32=0.0%, 64=0.0%, >=64=0.0%</tt><tt><br>
</tt><tt> complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%,
32=0.0%, 64=0.0%, >=64=0.1%</tt><tt><br>
</tt><tt> issued : total=r=0/w=10240/d=0,
short=r=0/w=0/d=0, drop=r=0/w=0/d=0</tt><tt><br>
</tt><tt> latency : target=0, window=0,
percentile=100.00%, depth=200</tt><tt><br>
</tt><tt><br>
</tt><tt>Run status group 0 (all jobs):</tt><tt><br>
</tt><tt> WRITE: io=10240MB, aggrb=473868KB/s, minb=473868KB/s,
maxb=473868KB/s, mint=22128msec, maxt=22128msec</tt><tt><br>
</tt><tt><br>
</tt><tt>Disk stats (read/write):</tt><tt><br>
</tt><tt> vdg: ios=0/10243, merge=0/0, ticks=0/2745892,
in_queue=2745884, util=99.18</tt></font><br>
<br>
<font size="-1"><tt>benchmark: (g=0): rw=randread,
bs=4K-4K/4K-4K/4K-4K, ioengine=libaio, iodepth=128</tt><tt><br>
</tt><tt>...</tt><tt><br>
</tt><tt>fio-2.16</tt><tt><br>
</tt><tt>Starting 4 processes</tt><tt><br>
</tt><tt><br>
</tt><tt>benchmark: (groupid=0, jobs=4): err= 0: pid=11529: Thu
Nov 2 16:52:40 2017</tt><tt><br>
</tt><tt> read : io=1123.9MB, bw=38347KB/s, iops=9586, runt=
30011msec</tt><tt><br>
</tt><tt> slat (usec): min=1, max=228886, avg=415.40,
stdev=3975.72</tt><tt><br>
</tt><tt> clat (usec): min=482, max=328648, avg=52664.65,
stdev=30216.00</tt><tt><br>
</tt><tt> lat (msec): min=9, max=527, avg=53.08, stdev=30.38</tt><tt><br>
</tt><tt> clat percentiles (msec):</tt><tt><br>
</tt><tt> | 1.00th=[ 12], 5.00th=[ 22], 10.00th=[
23], 20.00th=[ 25],</tt><tt><br>
</tt><tt> | 30.00th=[ 33], 40.00th=[ 38], 50.00th=[
47], 60.00th=[ 55],</tt><tt><br>
</tt><tt> | 70.00th=[ 64], 80.00th=[ 76], 90.00th=[
95], 95.00th=[ 111],</tt><tt><br>
</tt><tt> | 99.00th=[ 151], 99.50th=[ 163], 99.90th=[
192], 99.95th=[ 196],</tt><tt><br>
</tt><tt> | 99.99th=[ 210]</tt><tt><br>
</tt><tt> lat (usec) : 500=0.01%, 750=0.01%, 1000=0.01%</tt><tt><br>
</tt><tt> lat (msec) : 10=0.03%, 20=3.59%, 50=52.41%,
100=36.01%, 250=7.96%</tt><tt><br>
</tt><tt> lat (msec) : 500=0.01%</tt><tt><br>
</tt><tt> cpu : usr=0.29%, sys=1.10%, ctx=10157,
majf=0, minf=549</tt><tt><br>
</tt><tt> IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%,
16=0.1%, 32=0.1%, >=64=99.9%</tt><tt><br>
</tt><tt> submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%,
32=0.0%, 64=0.0%, >=64=0.0%</tt><tt><br>
</tt><tt> complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%,
32=0.0%, 64=0.0%, >=64=0.1%</tt><tt><br>
</tt><tt> issued : total=r=287705/w=0/d=0,
short=r=0/w=0/d=0, drop=r=0/w=0/d=0</tt><tt><br>
</tt><tt> latency : target=0, window=0,
percentile=100.00%, depth=128</tt><tt><br>
</tt><tt><br>
</tt><tt>Run status group 0 (all jobs):</tt><tt><br>
</tt><tt> READ: io=1123.9MB, aggrb=38346KB/s, minb=38346KB/s,
maxb=38346KB/s, mint=30011msec, maxt=30011msec</tt><tt><br>
</tt><tt><br>
</tt><tt>Disk stats (read/write):</tt><tt><br>
</tt><tt> vdg: ios=286499/2, merge=0/0, ticks=3707064/64,
in_queue=3708680, util=99.83%<br>
<br>
benchmark: (g=0): rw=randwrite, bs=4K-4K/4K-4K/4K-4K,
ioengine=libaio, iodepth=128<br>
...<br>
fio-2.16<br>
Starting 4 processes<br>
<br>
benchmark: (groupid=0, jobs=4): err= 0: pid=11545: Thu Nov 2
16:55:54 2017<br>
write: io=422464KB, bw=14079KB/s, iops=3519, runt= 30006msec<br>
slat (usec): min=1, max=230620, avg=1130.75, stdev=6744.31<br>
clat (usec): min=643, max=540987, avg=143999.57,
stdev=66693.45<br>
lat (msec): min=8, max=541, avg=145.13, stdev=67.01<br>
clat percentiles (msec):<br>
| 1.00th=[ 34], 5.00th=[ 75], 10.00th=[ 87],
20.00th=[ 100],<br>
| 30.00th=[ 109], 40.00th=[ 116], 50.00th=[ 123],
60.00th=[ 135],<br>
| 70.00th=[ 151], 80.00th=[ 182], 90.00th=[ 241],
95.00th=[ 289],<br>
| 99.00th=[ 359], 99.50th=[ 416], 99.90th=[ 465],
99.95th=[ 490],<br>
| 99.99th=[ 529]<br>
lat (usec) : 750=0.01%, 1000=0.01%<br>
lat (msec) : 2=0.01%, 4=0.01%, 10=0.01%, 20=0.05%,
50=1.80%<br>
lat (msec) : 100=18.07%, 250=71.25%, 500=8.80%, 750=0.02%<br>
cpu : usr=0.29%, sys=1.28%, ctx=115493, majf=0,
minf=33<br>
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%,
32=0.1%, >=64=99.8%<br>
submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%,
64=0.0%, >=64=0.0%<br>
complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%,
64=0.0%, >=64=0.1%<br>
issued : total=r=0/w=105616/d=0, short=r=0/w=0/d=0,
drop=r=0/w=0/d=0<br>
latency : target=0, window=0, percentile=100.00%,
depth=128<br>
<br>
Run status group 0 (all jobs):<br>
WRITE: io=422464KB, aggrb=14079KB/s, minb=14079KB/s,
maxb=14079KB/s, mint=30006msec, maxt=30006msec<br>
<br>
Disk stats (read/write):<br>
vdg: ios=0/105235, merge=0/0, ticks=0/3727048,
in_queue=3734796, util=99.81%<br>
<br>
<br>
</tt></font><font face="Futura Bk BT">Basically we got
sequential write around 470MBps, random read 4k 9500IOPS and
random write 4k 3500IOPS.<br>
<br>
Hope it helps!<br>
<br>
</font><br>
El 01/11/17 a les 12:03, Shyam Ranganathan ha escrit:<br>
</div>
<blockquote type="cite">On
10/31/2017 08:36 PM, Ben Turner wrote:
<br>
<blockquote type="cite">
<blockquote type="cite">* Erasure coded volumes with sharding -
seen as a good fit for VM disk
<br>
storage
<br>
</blockquote>
I am working on this with a customer, we have been able to do
400-500 MB / sec writes! Normally things max out at ~150-250.
The trick is to use multiple files, create the lvm stack and use
native LVM striping. We have found that 4-6 files seems to give
the best perf on our setup. I don't think we are using sharding
on the EC vols, just multiple files and LVM striping. Sharding
may be able to avoid the LVM striping, but I bet dollars to
doughnuts you won't see this level of perf:) I am working on a
blog post for RHHI and RHEV + RHS performance where I am able to
in some cases get 2x+ the performance out of VMs / VM storage.
I'd be happy to share my data / findings.
<br>
<br>
</blockquote>
<br>
Ben, we would like to hear more, so please do share your thoughts
further. There are a fair number of users in the community who
have this use-case and may have some interesting questions around
the proposed method.
<br>
<br>
Shyam
<br>
______________________________<wbr>_________________
<br>
Gluster-devel mailing list
<br>
<a class="m_5627811959350600145moz-txt-link-abbreviated" href="mailto:Gluster-devel@gluster.org" target="_blank">Gluster-devel@gluster.org</a>
<br>
<a class="m_5627811959350600145moz-txt-link-freetext" href="http://lists.gluster.org/mailman/listinfo/gluster-devel" target="_blank">http://lists.gluster.org/<wbr>mailman/listinfo/gluster-devel</a>
<br>
</blockquote>
<br>
</div>
<br>______________________________<wbr>_________________<br>
Gluster-devel mailing list<br>
<a href="mailto:Gluster-devel@gluster.org">Gluster-devel@gluster.org</a><br>
<a href="http://lists.gluster.org/mailman/listinfo/gluster-devel" rel="noreferrer" target="_blank">http://lists.gluster.org/<wbr>mailman/listinfo/gluster-devel</a><br></blockquote></div></div>