<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
On 07/11/2017 08:14 AM, Jo Goossens wrote:<br>
<blockquote type="cite"
cite="mid:zarafa.5964eb6b.5272.7a26670758480e61@web.hosted-power.com">
<meta name="Generator" content="Zarafa WebAccess v7.1.14-51822">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>RE: [Gluster-users] Gluster native mount is really slow
compared to nfs</title>
<style type="text/css">
body
{
font-family: Arial, Verdana, Sans-Serif ! important;
font-size: 12px;
padding: 5px 5px 5px 5px;
margin: 0px;
border-style: none;
background-color: #ffffff;
}
p, ul, li
{
margin-top: 0px;
margin-bottom: 0px;
}
</style>
<p>Hello Joe,</p>
<p> </p>
<p> </p>
<p>I really appreciate your feedback, but I already tried the
opcache stuff (to not valildate at all). It improves of course
then, but not completely somehow. Still quite slow.</p>
<p> </p>
<div>I did not try the mount options yet, but I will now!</div>
<p> </p>
<p> </p>
<p>With nfs (doesnt matter much built-in version 3 or ganesha
version 4) I can even host the site perfectly fast without these
extreme opcache settings.</p>
<p> </p>
<p>I still can't understand why the nfs mount is easily 80 times
faster, actually no matter what options I set it seems. It's
almost there is something really wrong somehow...</p>
</blockquote>
<br>
Because the linux nfs client doesn't touch the network for many
operations and are, in stead, held in the kernel's FSCache.<br>
<br>
<blockquote type="cite"
cite="mid:zarafa.5964eb6b.5272.7a26670758480e61@web.hosted-power.com">
<p> </p>
<p>I tried the ceph mount now and out of the box it's comparable
with gluster with nfs mount.</p>
<p> </p>
<p> </p>
<p>Regards</p>
<p>Jo</p>
<p> </p>
<p>BE: +32 53 599 000</p>
<p>NL: +31 85 888 4 555</p>
<p> </p>
<p><a href="https://www.hosted-power.com/" moz-do-not-send="true">https://www.hosted-power.com/</a></p>
<p> </p>
<p><br>
</p>
<blockquote style="border-left: 2px solid #325FBA; padding-left:
5px;margin-left:5px;">-----Original message-----<br>
<strong>From:</strong> Joe Julian <a class="moz-txt-link-rfc2396E" href="mailto:joe@julianfamily.org"><joe@julianfamily.org></a><br>
<strong>Sent:</strong> Tue 11-07-2017 17:04<br>
<strong>Subject:</strong> Re: [Gluster-users] Gluster native
mount is really slow compared to nfs<br>
<strong>To:</strong> <a class="moz-txt-link-abbreviated" href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a>; <br>
<style type="text/css">body { font-family: monospace; }</style>
<div style="color: #000000; background-color: #FFFFFF; ">
<p>My standard response to someone needing filesystem
performance for www traffic is generally, "you're doing it
wrong". <a
href="https://joejulian.name/blog/optimizing-web-performance-with-glusterfs/"
target="_blank" title="This external link will open in a
new window" moz-do-not-send="true">https://joejulian.name/blog/optimizing-web-performance-with-glusterfs/</a><br>
<br>
That said, you might also look at these mount options:
attribute-timeout, entry-timeout, negative-timeout (set to
some large amount of time), and fopen-keep-cache.</p>
<br>
<div>On 07/11/2017 07:48 AM, Jo Goossens wrote:</div>
<blockquote type="cite"
cite="mid:zarafa.5964e533.4b1c.70763d1a6208ff82@web.hosted-power.com">
<style type="text/css"> .bodyclass { font-family: Arial, Verdana, Sans-Serif ! important; font-size: 12px; padding: 5px 5px 5px 5px; margin: 0px; border-style: none; background-color: #ffffff; } p, ul, li { margin-top: 0px; margin-bottom: 0px; } </style>
<p>Hello,</p>
<p> </p>
<p> </p>
<p>Here is the volume info as requested by soumya:</p>
<p> </p>
<div>#gluster volume info www</div>
<div> </div>
<div>Volume Name: www</div>
<div>Type: Replicate</div>
<div>Volume ID: 5d64ee36-828a-41fa-adbf-75718b954aff</div>
<div>Status: Started</div>
<div>Snapshot Count: 0</div>
<div>Number of Bricks: 1 x 3 = 3</div>
<div>Transport-type: tcp</div>
<div>Bricks:</div>
<div>Brick1: 192.168.140.41:/gluster/www</div>
<div>Brick2: 192.168.140.42:/gluster/www</div>
<div>Brick3: 192.168.140.43:/gluster/www</div>
<div>Options Reconfigured:</div>
<div>cluster.read-hash-mode: 0</div>
<div>performance.quick-read: on</div>
<div>performance.write-behind-window-size: 4MB</div>
<div>server.allow-insecure: on</div>
<div>performance.read-ahead: disable</div>
<div>performance.readdir-ahead: on</div>
<div>performance.io-thread-count: 64</div>
<div>performance.io-cache: on</div>
<div>performance.client-io-threads: on</div>
<div>server.outstanding-rpc-limit: 128</div>
<div>server.event-threads: 3</div>
<div>client.event-threads: 3</div>
<div>performance.cache-size: 32MB</div>
<div>transport.address-family: inet</div>
<div>nfs.disable: on</div>
<div>nfs.addr-namelookup: off</div>
<div>nfs.export-volumes: on</div>
<div>nfs.rpc-auth-allow: 192.168.140.*</div>
<div>features.cache-invalidation: on</div>
<div>features.cache-invalidation-timeout: 600</div>
<div>performance.stat-prefetch: on</div>
<div>performance.cache-samba-metadata: on</div>
<div>performance.cache-invalidation: on</div>
<div>performance.md-cache-timeout: 600</div>
<div>network.inode-lru-limit: 100000</div>
<div>performance.parallel-readdir: on</div>
<div>performance.cache-refresh-timeout: 60</div>
<div>performance.rda-cache-limit: 50MB</div>
<div>cluster.nufa: on</div>
<div>network.ping-timeout: 5</div>
<div>cluster.lookup-optimize: on</div>
<div>cluster.quorum-type: auto</div>
<div> </div>
<div>I started with none of them set and I added/changed
while testing. But it was always slow, by tuning some
kernel parameters it improved slightly (just a few
percent, nothing reasonable)</div>
<div> </div>
<div>I also tried ceph just to compare, I got this with
default settings and no tweaks:</div>
<div> </div>
<div>
<div> ./smallfile_cli.py --top /var/www/test --host-set
192.168.140.41 --threads 8 --files 5000 --file-size 64
--record-size 64</div>
<div>smallfile version 3.0</div>
<div> hosts in test :
['192.168.140.41']</div>
<div> top test directory(s) :
['/var/www/test']</div>
<div> operation : cleanup</div>
<div> files/thread : 5000</div>
<div> threads : 8</div>
<div> record size (KB, 0 = maximum) : 64</div>
<div> file size (KB) : 64</div>
<div> file size distribution : fixed</div>
<div> files per dir : 100</div>
<div> dirs per dir : 10</div>
<div> threads share directories? : N</div>
<div> filename prefix :</div>
<div> filename suffix :</div>
<div> hash file number into dir.? : N</div>
<div> fsync after modify? : N</div>
<div> pause between files (microsec) : 0</div>
<div> finish all requests? : Y</div>
<div> stonewall? : Y</div>
<div> measure response times? : N</div>
<div> verify read? : Y</div>
<div> verbose? : False</div>
<div> log to stderr? : False</div>
<div> ext.attr.size : 0</div>
<div> ext.attr.count : 0</div>
<div> permute host directories? : N</div>
<div> remote program directory :
/root/smallfile-master</div>
<div> network thread sync. dir. :
/var/www/test/network_shared</div>
<div>starting all threads by creating starting gate file
/var/www/test/network_shared/starting_gate.tmp</div>
<div>host = 192.168.140.41,thr = 00,elapsed =
1.339621,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 01,elapsed =
1.436776,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 02,elapsed =
1.498681,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 03,elapsed =
1.483886,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 04,elapsed =
1.454833,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 05,elapsed =
1.469340,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 06,elapsed =
1.439060,files = 5000,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 07,elapsed =
1.375074,files = 5000,records = 0,status = ok</div>
<div>total threads = 8</div>
<div>total files = 40000</div>
<div>100.00% of requested files processed, minimum is
70.00</div>
<div>1.498681 sec elapsed time</div>
<div>26690.134975 files/sec</div>
<div> </div>
<div> </div>
</div>
<p><br>
Regards</p>
<p>Jo</p>
<p> </p>
<blockquote style="border-left: 2px solid #325FBA;
padding-left: 5px;margin-left:5px;">-----Original
message-----<br>
<strong>From:</strong> Jo Goossens <a
href="mailto:jo.goossens@hosted-power.com"
onclick="parent.webclient.openWindow(this, 'createmail',
'index.php?load=dialog&task=createmail_standard&to=jo.goossens@hosted-power.com');
return false;" target="_blank" title="This external link
will open in a new window" moz-do-not-send="true"><jo.goossens@hosted-power.com></a><br>
<strong>Sent:</strong> Tue 11-07-2017 12:15<br>
<strong>Subject:</strong> Re: [Gluster-users] Gluster
native mount is really slow compared to nfs<br>
<strong>To:</strong> Soumya Koduri <a
href="mailto:skoduri@redhat.com"
onclick="parent.webclient.openWindow(this, 'createmail',
'index.php?load=dialog&task=createmail_standard&to=skoduri@redhat.com');
return false;" target="_blank" title="This external link
will open in a new window" moz-do-not-send="true"><skoduri@redhat.com></a>;
<a href="mailto:gluster-users@gluster.org"
onclick="parent.webclient.openWindow(this, 'createmail',
'index.php?load=dialog&task=createmail_standard&to=gluster-users@gluster.org');
return false;" target="_blank" title="This external link
will open in a new window" moz-do-not-send="true">gluster-users@gluster.org</a>;
<br>
<strong>CC:</strong> Ambarish Soman <a
href="mailto:asoman@redhat.com"
onclick="parent.webclient.openWindow(this, 'createmail',
'index.php?load=dialog&task=createmail_standard&to=asoman@redhat.com');
return false;" target="_blank" title="This external link
will open in a new window" moz-do-not-send="true"><asoman@redhat.com></a>;
<br>
<style type="text/css">.bodyclass { font-family: monospace; }</style>
<style type="text/css"> .bodyclass { font-family: Arial, Verdana, Sans-Serif ! important; font-size: 12px; padding: 5px 5px 5px 5px; margin: 0px; border-style: none; background-color: #ffffff; } p, ul, li { margin-top: 0px; margin-bottom: 0px; } </style>
<div>
<p>Hello,</p>
<p> </p>
<p> </p>
<p>Here is some speedtest with a new setup we just made
with gluster 3.10, there are no other differences,
except glusterfs versus nfs. The nfs is about 80 times
faster:</p>
<p> </p>
<p> </p>
<div>root@app1:~/smallfile-master# mount -t glusterfs -o
use-readdirp=no,log-level=WARNING,log-file=/var/log/glusterxxx.log
192.168.140.41:/www /var/www</div>
<div>root@app1:~/smallfile-master# ./smallfile_cli.py
--top /var/www/test --host-set 192.168.140.41
--threads 8 --files 500 --file-size 64 --record-size
64</div>
<div>smallfile version 3.0</div>
<div> hosts in test :
['192.168.140.41']</div>
<div> top test directory(s) :
['/var/www/test']</div>
<div> operation : cleanup</div>
<div> files/thread : 500</div>
<div> threads : 8</div>
<div> record size (KB, 0 = maximum) : 64</div>
<div> file size (KB) : 64</div>
<div> file size distribution : fixed</div>
<div> files per dir : 100</div>
<div> dirs per dir : 10</div>
<div> threads share directories? : N</div>
<div> filename prefix :</div>
<div> filename suffix :</div>
<div> hash file number into dir.? : N</div>
<div> fsync after modify? : N</div>
<div> pause between files (microsec) : 0</div>
<div> finish all requests? : Y</div>
<div> stonewall? : Y</div>
<div> measure response times? : N</div>
<div> verify read? : Y</div>
<div> verbose? : False</div>
<div> log to stderr? : False</div>
<div> ext.attr.size : 0</div>
<div> ext.attr.count : 0</div>
<div> permute host directories? : N</div>
<div> remote program directory :
/root/smallfile-master</div>
<div> network thread sync. dir. :
/var/www/test/network_shared</div>
<div>starting all threads by creating starting gate file
/var/www/test/network_shared/starting_gate.tmp</div>
<div>host = 192.168.140.41,thr = 00,elapsed =
68.845450,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 01,elapsed =
67.601088,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 02,elapsed =
58.677994,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 03,elapsed =
65.901922,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 04,elapsed =
66.971720,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 05,elapsed =
71.245102,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 06,elapsed =
67.574845,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 07,elapsed =
54.263242,files = 500,records = 0,status = ok</div>
<div>total threads = 8</div>
<div>total files = 4000</div>
<div>100.00% of requested files processed, minimum is
70.00</div>
<div>71.245102 sec elapsed time</div>
<div>56.144211 files/sec</div>
<div> </div>
<div>umount /var/www</div>
<div> </div>
<div>root@app1:~/smallfile-master# mount -t nfs -o tcp
192.168.140.41:/www /var/www</div>
<div>root@app1:~/smallfile-master# ./smallfile_cli.py
--top /var/www/test --host-set 192.168.140.41
--threads 8 --files 500 --file-size 64 --record-size
64</div>
<div>smallfile version 3.0</div>
<div> hosts in test :
['192.168.140.41']</div>
<div> top test directory(s) :
['/var/www/test']</div>
<div> operation : cleanup</div>
<div> files/thread : 500</div>
<div> threads : 8</div>
<div> record size (KB, 0 = maximum) : 64</div>
<div> file size (KB) : 64</div>
<div> file size distribution : fixed</div>
<div> files per dir : 100</div>
<div> dirs per dir : 10</div>
<div> threads share directories? : N</div>
<div> filename prefix :</div>
<div> filename suffix :</div>
<div> hash file number into dir.? : N</div>
<div> fsync after modify? : N</div>
<div> pause between files (microsec) : 0</div>
<div> finish all requests? : Y</div>
<div> stonewall? : Y</div>
<div> measure response times? : N</div>
<div> verify read? : Y</div>
<div> verbose? : False</div>
<div> log to stderr? : False</div>
<div> ext.attr.size : 0</div>
<div> ext.attr.count : 0</div>
<div> permute host directories? : N</div>
<div> remote program directory :
/root/smallfile-master</div>
<div> network thread sync. dir. :
/var/www/test/network_shared</div>
<div>starting all threads by creating starting gate file
/var/www/test/network_shared/starting_gate.tmp</div>
<div>host = 192.168.140.41,thr = 00,elapsed =
0.962424,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 01,elapsed =
0.942673,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 02,elapsed =
0.940622,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 03,elapsed =
0.915218,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 04,elapsed =
0.934349,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 05,elapsed =
0.922466,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 06,elapsed =
0.954381,files = 500,records = 0,status = ok</div>
<div>host = 192.168.140.41,thr = 07,elapsed =
0.946127,files = 500,records = 0,status = ok</div>
<div>total threads = 8</div>
<div>total files = 4000</div>
<div>100.00% of requested files processed, minimum is
70.00</div>
<div>0.962424 sec elapsed time</div>
<div>4156.173189 files/sec</div>
<div> </div>
<p> </p>
<p> </p>
<blockquote style="border-left: 2px solid #325FBA;
padding-left: 5px;margin-left:5px;">-----Original
message-----<br>
<strong>From:</strong> Jo Goossens <a
href="mailto:jo.goossens@hosted-power.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=jo.goossens@hosted-power.com');
return false;" target="_blank" title="This external
link will open in a new window"
moz-do-not-send="true"><jo.goossens@hosted-power.com></a><br>
<strong>Sent:</strong> Tue 11-07-2017 11:26<br>
<strong>Subject:</strong> Re: [Gluster-users] Gluster
native mount is really slow compared to nfs<br>
<strong>To:</strong> <a
href="mailto:gluster-users@gluster.org"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=gluster-users@gluster.org');
return false;" target="_blank" title="This external
link will open in a new window"
moz-do-not-send="true">gluster-users@gluster.org</a>;
Soumya Koduri <a href="mailto:skoduri@redhat.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=skoduri@redhat.com');
return false;" target="_blank" title="This external
link will open in a new window"
moz-do-not-send="true"><skoduri@redhat.com></a>;
<br>
<strong>CC:</strong> Ambarish Soman <a
href="mailto:asoman@redhat.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=asoman@redhat.com');
return false;" target="_blank" title="This external
link will open in a new window"
moz-do-not-send="true"><asoman@redhat.com></a>;
<br>
<style type="text/css">.bodyclass { font-family: monospace; }</style>
<style type="text/css"> .bodyclass { font-family: Arial, Verdana, Sans-Serif ! important; font-size: 12px; padding: 5px 5px 5px 5px; margin: 0px; border-style: none; background-color: #ffffff; } p, ul, li { margin-top: 0px; margin-bottom: 0px; } </style>
<div>
<p>Hi all,</p>
<p> </p>
<p> </p>
<p>One more thing, we have 3 apps servers with the
gluster on it, replicated on 3 different gluster
nodes. (So the gluster nodes are app servers at
the same time). We could actually almost work
locally if we wouldn't need to have the same files
on the 3 nodes and redundancy :)</p>
<p> </p>
<p>Initial cluster was created like this:</p>
<p> </p>
<div>gluster volume create www replica 3 transport
tcp 192.168.140.41:/gluster/www
192.168.140.42:/gluster/www
192.168.140.43:/gluster/www force</div>
<div>gluster volume set www network.ping-timeout 5</div>
<div>gluster volume set www performance.cache-size
1024MB</div>
<div>gluster volume set www nfs.disable on # No need
for NFS currently</div>
<div>gluster volume start www</div>
<div> </div>
<div>To my understanding it still wouldn't explain
why nfs has such great performance compared to
native ...</div>
<div> </div>
<p> </p>
<p>Regards</p>
<p>Jo</p>
<p> </p>
<p><br>
</p>
<blockquote style="border-left: 2px solid #325FBA;
padding-left: 5px;margin-left:5px;">-----Original
message-----<br>
<strong>From:</strong> Soumya Koduri <a
href="mailto:skoduri@redhat.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=skoduri@redhat.com');
return false;" target="_blank" title="This
external link will open in a new window"
moz-do-not-send="true"><skoduri@redhat.com></a><br>
<strong>Sent:</strong> Tue 11-07-2017 11:16<br>
<strong>Subject:</strong> Re: [Gluster-users]
Gluster native mount is really slow compared to
nfs<br>
<strong>To:</strong> Jo Goossens <a
href="mailto:jo.goossens@hosted-power.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=jo.goossens@hosted-power.com');
return false;" target="_blank" title="This
external link will open in a new window"
moz-do-not-send="true"><jo.goossens@hosted-power.com></a>;
<a href="mailto:gluster-users@gluster.org"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=gluster-users@gluster.org');
return false;" target="_blank" title="This
external link will open in a new window"
moz-do-not-send="true">gluster-users@gluster.org</a>;
<br>
<strong>CC:</strong> Ambarish Soman <a
href="mailto:asoman@redhat.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=asoman@redhat.com');
return false;" target="_blank" title="This
external link will open in a new window"
moz-do-not-send="true"><asoman@redhat.com></a>;
Karan Sandha <a href="mailto:ksandha@redhat.com"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=ksandha@redhat.com');
return false;" target="_blank" title="This
external link will open in a new window"
moz-do-not-send="true"><ksandha@redhat.com></a>;
<br>
+ Ambarish<br>
<br>
On 07/11/2017 02:31 PM, Jo Goossens wrote:<br>
> Hello,<br>
><br>
><br>
><br>
><br>
><br>
> We tried tons of settings to get a php app
running on a native gluster<br>
> mount:<br>
><br>
><br>
><br>
> e.g.: 192.168.140.41:/www /var/www glusterfs<br>
>
defaults,_netdev,backup-volfile-servers=192.168.140.42:192.168.140.43,direct-io-mode=disable<br>
> 0 0<br>
><br>
><br>
><br>
> I tried some mount variants in order to speed
up things without luck.<br>
><br>
><br>
><br>
><br>
><br>
> After that I tried nfs (native gluster nfs 3
and ganesha nfs 4), it was<br>
> a crazy performance difference.<br>
><br>
><br>
><br>
> e.g.: 192.168.140.41:/www /var/www nfs4
defaults,_netdev 0 0<br>
><br>
><br>
><br>
> I tried a test like this to confirm the
slowness:<br>
><br>
><br>
><br>
> ./smallfile_cli.py --top /var/www/test
--host-set 192.168.140.41<br>
> --threads 8 --files 5000 --file-size 64
--record-size 64<br>
><br>
> This test finished in around 1.5 seconds with
NFS and in more than 250<br>
> seconds without nfs (can't remember exact
numbers, but I reproduced it<br>
> several times for both).<br>
><br>
> With the native gluster mount the php app had
loading times of over 10<br>
> seconds, with the nfs mount the php app
loaded around 1 second maximum<br>
> and even less. (reproduced several times)<br>
><br>
><br>
><br>
> I tried all kind of performance settings and
variants of this but not<br>
> helped , the difference stayed huge, here are
some of the settings<br>
> played with in random order:<br>
><br>
<br>
Request Ambarish & Karan (cc'ed who have been
working on evaluating <br>
performance of various access protocols gluster
supports) to look at the <br>
below settings and provide inputs.<br>
<br>
Thanks,<br>
Soumya<br>
<br>
><br>
><br>
> gluster volume set www
features.cache-invalidation on<br>
> gluster volume set www
features.cache-invalidation-timeout 600<br>
> gluster volume set www
performance.stat-prefetch on<br>
> gluster volume set www
performance.cache-samba-metadata on<br>
> gluster volume set www
performance.cache-invalidation on<br>
> gluster volume set www
performance.md-cache-timeout 600<br>
> gluster volume set www
network.inode-lru-limit 250000<br>
><br>
> gluster volume set www
performance.cache-refresh-timeout 60<br>
> gluster volume set www performance.read-ahead
disable<br>
> gluster volume set www
performance.readdir-ahead on<br>
> gluster volume set www
performance.parallel-readdir on<br>
> gluster volume set www
performance.write-behind-window-size 4MB<br>
> gluster volume set www
performance.io-thread-count 64<br>
><br>
> gluster volume set www
performance.client-io-threads on<br>
><br>
> gluster volume set www performance.cache-size
1GB<br>
> gluster volume set www performance.quick-read
on<br>
> gluster volume set www
performance.flush-behind on<br>
> gluster volume set www
performance.write-behind on<br>
> gluster volume set www nfs.disable on<br>
><br>
> gluster volume set www client.event-threads 3<br>
> gluster volume set www server.event-threads 3<br>
><br>
><br>
><br>
><br>
><br>
><br>
> The NFS ha adds a lot of complexity which we
wouldn't need at all in our<br>
> setup, could you please explain what is going
on here? Is NFS the only<br>
> solution to get acceptable performance? Did I
miss one crucial settting<br>
> perhaps?<br>
><br>
><br>
><br>
> We're really desperate, thanks a lot for your
help!<br>
><br>
><br>
><br>
><br>
><br>
> PS: We tried with gluster 3.11 and 3.8 on
Debian, both had terrible<br>
> performance when not used with nfs.<br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
> Kind regards<br>
><br>
> Jo Goossens<br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
>
_______________________________________________<br>
> Gluster-users mailing list<br>
> <a href="mailto:Gluster-users@gluster.org"
onclick="parent.webclient.openWindow(this,
'createmail',
'index.php?load=dialog&task=createmail_standard&to=Gluster-users@gluster.org');
return false;" target="_blank" title="This
external link will open in a new window"
moz-do-not-send="true">Gluster-users@gluster.org</a><br>
> <a
href="http://lists.gluster.org/mailman/listinfo/gluster-users"
target="_blank" title="This external link will
open in a new window" moz-do-not-send="true">http://lists.gluster.org/mailman/listinfo/gluster-users</a><br>
><br>
</blockquote>
</div>
<pre> _______________________________________________ Gluster-users mailing list <a href="mailto:Gluster-users@gluster.org" onclick="parent.webclient.openWindow(this, 'createmail', 'index.php?load=dialog&task=createmail_standard&to=Gluster-users@gluster.org'); return false;" target="_blank" title="This external link will open in a new window" moz-do-not-send="true">Gluster-users@gluster.org</a> <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" target="_blank" title="This external link will open in a new window" moz-do-not-send="true">http://lists.gluster.org/mailman/listinfo/gluster-users</a></pre>
</blockquote>
</div>
<pre>_______________________________________________ Gluster-users mailing list <a href="mailto:Gluster-users@gluster.org" onclick="parent.webclient.openWindow(this, 'createmail', 'index.php?load=dialog&task=createmail_standard&to=Gluster-users@gluster.org'); return false;" target="_blank" title="This external link will open in a new window" moz-do-not-send="true">Gluster-users@gluster.org</a> <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" target="_blank" title="This external link will open in a new window" moz-do-not-send="true">http://lists.gluster.org/mailman/listinfo/gluster-users</a></pre>
</blockquote>
<br>
<br>
<pre wrap="">_______________________________________________ Gluster-users mailing list <a href="mailto:Gluster-users@gluster.org" onclick="parent.webclient.openWindow(this, 'createmail', 'index.php?load=dialog&task=createmail_standard&to=Gluster-users@gluster.org'); return false;" target="_blank" title="This external link will open in a new window" moz-do-not-send="true">Gluster-users@gluster.org</a> <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" target="_blank" title="This external link will open in a new window" moz-do-not-send="true">http://lists.gluster.org/mailman/listinfo/gluster-users</a></pre>
</blockquote>
</div>
<pre>_______________________________________________
Gluster-users mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a>
<a class="moz-txt-link-freetext" href="http://lists.gluster.org/mailman/listinfo/gluster-users">http://lists.gluster.org/mailman/listinfo/gluster-users</a></pre>
</blockquote>
</blockquote>
<br>
</body>
</html>