Sorry for the late reply. The call profiles look OK on the server side. I suspect it is still something to do with the client or network. Have you mounted the FUSE client with any special options? like --direct-io-mode? That can have a significant impact on read performance as read-ahead in the page-cache (which is way more efficient than gluster's read-ahead translator due to lack of context switch to serve the future page) is effectively turned off.<div>
<br></div><div>I'm not sure if any of your networking (tcp/ip) configuration is either good or bad.</div><div><br></div><div>Avati<br><br><div class="gmail_quote">On Mon, Mar 11, 2013 at 9:02 AM, Thomas Wakefield <span dir="ltr"><<a href="mailto:twake@cola.iges.org" target="_blank">twake@cola.iges.org</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word">Is there a way to make a ramdisk support extended attributes?<div><br></div><div>These are my current sysctl settings (and I have tried many different options):</div>
<div><div><div>net.ipv4.ip_forward = 0</div><div>net.ipv4.conf.default.rp_filter = 1</div><div>net.ipv4.conf.default.accept_source_route = 0</div><div>kernel.sysrq = 0</div><div>kernel.core_uses_pid = 1</div><div>net.ipv4.tcp_syncookies = 1</div>
<div>kernel.msgmnb = 65536</div><div>kernel.msgmax = 65536</div><div>kernel.shmmax = 68719476736</div><div>kernel.shmall = 4294967296</div><div>kernel.panic = 5</div><div>net.core.rmem_max = 67108864</div><div>net.core.wmem_max = 67108864</div>
<div>net.ipv4.tcp_rmem = 4096 87380 67108864</div><div>net.ipv4.tcp_wmem = 4096 65536 67108864</div><div>net.core.netdev_max_backlog = 250000</div><div>net.ipv4.tcp_congestion_control = htcp</div><div>net.ipv4.tcp_mtu_probing = 1</div>
</div><div><br></div><div><br></div><div>Here is the output from a dd write and dd read.</div><div><br></div><div><div><div>[root@cpu_crew1 ~]# dd if=/dev/zero of=/shared/working/benchmark/test.cpucrew1 bs=512k count=10000 ; dd if=/shared/working/benchmark/test.cpucrew1 of=/dev/null bs=512k</div>
<div>10000+0 records in</div><div>10000+0 records out</div><div>5242880000 bytes (5.2 GB) copied, 7.21958 seconds, 726 MB/s</div><div>10000+0 records in</div><div>10000+0 records out</div><div>5242880000 bytes (5.2 GB) copied, 86.4165 seconds, 60.7 MB/s</div>
</div><div><br></div></div></div></div></blockquote></div></div>