<p dir="ltr">I've wrote below email. However it seems I missed mail key word rule on subject. <br>
So I'm sending it again. <br>
Please check the below mail and any response will be helpful. <br>
Thanks,</p>
<div class="gmail_quote">2013. 10. 25. 오후 6:01에 "Jung Young Seok" <<a href="mailto:jung.youngseok@gmail.com">jung.youngseok@gmail.com</a>>님이 작성:<br type="attribution"><blockquote class="quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div dir="ltr"><br><div>Dear GlusterFS Engineer,</div><div><br></div><div>I have questions that my glusterfs server and fuse client</div><div>perform properly on below specification.</div><div><br></div><div>It can write only <b>65MB</b>/s through FUSE client to 1 glusterfs server (1 brick and no replica for 1 volume )</div>
<div> - NW bandwidth are enough for now. I've check it with iftop</div><div> - However it can write <b>120MB</b>/s when I mount nfs on the same volume.</div><div><br></div><div>Could anyone check if the glusterfs and fuse client perform properly?</div>
<div><br></div><div><br></div><div>Detail explanations are below.</div><div>=======================================================================</div><div>I've set 4 glusterfs servers and 1 fuse client.</div><div>
Each spec is as followings.</div>
<div><br></div><div><b>Server x 4</b></div><div> - CPU : Intel(R) Xeon(R) CPU E5-2609 0 @ 2.40GHz (2 cpu * 4 core)</div><div> - Memory : 32GB</div><div> - HDD (3TB 7.2K RPM SATA x 14 )</div><div> * RAID6(33T)</div><div>
* XFS</div><div> - OS : RHS 2.1</div><div> - 4 Gluster Server will be used 2 replica x 2 distributed as 1 volume</div><div> - NW 1G for replica</div><div> - NW 1G for Storage and management</div><div> - Current active profile: rhs-high-throughput</div>
<div><br></div><div><b>FUSE Client (gluster 3.4)</b></div><div> - CPU : Intel(R) Xeon(R) CPU E5-2640 0 @ 2.50GHz</div><div> - Memory : 32GB</div><div> - OS : CentOS6.4</div><div> - NW 2G for Storage (NIC bonding)</div><div>
<br></div><div>All server will be in 10G network. (for now 1G network)</div><div><br></div><div><br></div><div>I've tested to check primitive disk performance.<br></div><div> - on first glusterfs server <br></div><div>
* it can write 870MB/s (dd if=/dev/zero of=./dummy bs=4096 count=10000)</div><div> * it can read 1GB/s (cat test_file.23 > /dev/null )</div><div> - on fuse client (mount volume : 1 brick(1dist, no-replica)</div>
<div>
* it can write 64.8MB/s</div><div> - on nfs client (mount volume : 1 brick(1dist, no-replica)</div><div> * it can write 120MB/s (it reached NW bandwith</div><div><br></div><div><br></div><div>I wonder why fuse client much slower than nfs client. (it's no-replica peer)</div>
<div>Is it normal performance?</div><div><br></div><div>=========================================================================</div><div><br></div><div><br></div><div>Thanks in advance</div><div>Youngseok Jung </div><div>
</div><div><br></div><div><br></div></div>
</blockquote></div>