<div dir="ltr">Tested again with HT disabled in the bios.<div><br></div><div>Paul, you're right, it is not related to HT itself, I get more or less the same difference.</div><div>It is more related to IO bottleneck impacting more the kernel scheduling.</div>
<div><br></div><div>It may not be the same at other zoom levels where the CPU is the bottleneck and not the IOs.</div><div><br></div><div>I'll switch to another topic... optimising render_list to better take advantage of data present in the cache.</div>
<div><br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">2014-07-17 17:03 GMT+02:00 Paul Norman <span dir="ltr"><<a href="mailto:penorman@mac.com" target="_blank">penorman@mac.com</a>></span>:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000"><div class="">
<br>
<div>On 2014-07-17 6:39 AM, Christian Quest
wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr">I'm currently doing some rendering benchmark to
tune a new tile server we're about to put online.<br clear="all">
<div><br>
</div>
<div>A strange thing I've found last night: render_list with 16
thread takes more time than with 8 .</div>
<div><br>
</div>
<div>The server has 2 quad-core Xeon (X5570), this means 8
physical cores. It looks like hyperthreading adds additionnal
context switches or something similar.</div>
<div>With "<span style="color:rgb(0,0,0);font-family:arial,sans,sans-serif;font-size:100%">-z
9 -Z 9 -n 16 -l 32" it takes 3016s, and with "</span><span style="color:rgb(0,0,0);font-family:arial,sans,sans-serif;font-size:13px;white-space:pre-wrap">-z
9 -Z 9 -n 8 -l 12" 2647s, 10% less.</span></div>
<div><span style="color:rgb(0,0,0);font-family:arial,sans,sans-serif;font-size:13px;white-space:pre-wrap"><br>
</span></div>
<div><font color="#000000" face="arial, sans, sans-serif"><span style="white-space:pre-wrap">I'll disable HT on my next
run in the server bios and see if it is consistent.</span></font></div>
</div>
</blockquote>
<br></div>
Is there a chance you're running into IO bottlenecks?<div class=""><br>
<br>
<blockquote type="cite">
<div dir="ltr">
<div><font color="#000000" face="arial, sans, sans-serif"><span style="white-space:pre-wrap">Another thing I found... do
not put your SSD behind a RAID card.</span></font></div>
<div><font color="#000000" face="arial, sans, sans-serif"><span style="white-space:pre-wrap">The RAID card (Dell Perc 6i)
add too much latency.</span></font></div>
<div><font color="#000000" face="arial, sans, sans-serif"><span style="white-space:pre-wrap">On the same render_list, the
iowait threads are increasing a lot and iops decreases a
lot.</span></font></div>
</div>
</blockquote></div>
The Perc 6 is an older lower-end RAID card using a LSI 10xx chip. It
doesn't surprise me it doesn't work ideally with SSDs. I'm also not
sure if it supports all the SATA commands a SSD uses, which can be a
serious issue for consistency, the bane of SSDs.<br>
<br>
A more modern card would probably perform better, but if you're not
RAIDing SSDs, you should really be using any card you have in HBA
mode, unless you have a battery-backed cache and can therefor tune
write barriers and related settings better.<br>
</div>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><div dir="ltr">Christian Quest - OpenStreetMap France</div>
</div>