<div dir="ltr"><br><div>Hi Bernd --</div><div><br></div><div>It doesn't seem coupled to GC; here's an example snapshot:</div><div><br></div><div>sun.ci.codeCacheCapacity=13041664 </div><div>sun.ci.codeCacheMaxCapacity=50331648</div><div>sun.ci.codeCacheMethodsReclaimedNum=4281</div><div>sun.ci.codeCacheSweepsTotalNum=409</div><div>sun.ci.codeCacheSweepsTotalTimeMillis=1541</div><div>sun.ci.codeCacheUsed=10864704</div><div><br></div><div>sun.gc.collector.0.invocations=6319</div><div>sun.gc.collector.1.invocations=6</div><div><br></div><div>BTW, to a question of Vitaly's on this thread earlier, this code executes irrespective of whether you are running tiered or not (the above is from tiered explictly off -- earlier ones were with tiered on --, yet note the excessive time in the stack walk as part of this code in JDK 8):</div><div>
<p class="p1">[mark nmethods, 0.0171828 secs]</p><p class="p1">On a similar note (and to Vladimir's earlier note of turning off code cache flushing) and with the understanding that there were lots of changes related to tiered compilation and code cache flushing between 7 ad 8, turning on Tiered in 7 leads to the occasional (rare) long safepoint for the stack walks, but else not.</p><p class="p1">And finally the same issue must exist in 9 as well, albeit based on code inspection, not running with JDK 9 yet.</p>Have a good weekend!<br>-- ramki</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Jul 31, 2015 at 2:44 PM, Bernd Eckenfels <span dir="ltr"><<a href="mailto:ecki@zusammenkunft.net" target="_blank">ecki@zusammenkunft.net</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Am Fri, 31 Jul 2015 12:07:18 -0700<br>
schrieb Srinivas Ramakrishna <<a href="mailto:ysr1729@gmail.com">ysr1729@gmail.com</a>>:<br>
<br>
> sun.ci.codeCacheSweepsTotalNum=58<br>
...<br>
<span class="">> Notice that the code cache usage is less that 35 MB, for the 240 MB<br>
> capacity, yet it seems we have had 58 sweeps already<br>
<br>
</span>I would also be interested in what causes this. Is this caused by<br>
System.gc maybe? (we do see sweeps and decreasing code cache usage on<br>
systems where no pressure should exist).<br>
<br>
Gruss<br>
<span class="HOEnZb"><font color="#888888">Bernd<br>
</font></span></blockquote></div><br></div>