<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<br>
Hi Derek,<br>
<br>
<div class="moz-cite-prefix">On 2015-03-30 18:54, Derek White wrote:<br>
</div>
<blockquote cite="mid:55197FD1.8090006@oracle.com" type="cite">
<meta http-equiv="content-type" content="text/html; charset=utf-8">
<meta http-equiv="content-type" content="text/html; charset=utf-8">
This is a P1 bug in JDK 9 - a conflict when freeing
continues_humongous regions. <br>
<br>
The scenario is a region was continues_humongous is then freed by
one worker when the whole H-object is freed. The
continues_humongous region needs to be claimed by the first
worker, otherwise other workers may run into the free region. It
turns out the fix was to revert a change made a few months ago.<br>
</blockquote>
<br>
Nice catch!<br>
<br>
<blockquote cite="mid:55197FD1.8090006@oracle.com" type="cite"> <br>
It didn't help out that an assert actually did the right thing, so
it never failed in debug code :-)<br>
</blockquote>
<br>
Yes, that must have been very confusing!<br>
<br>
<blockquote cite="mid:55197FD1.8090006@oracle.com" type="cite"> <br>
<a moz-do-not-send="true" id="key-val" rel="4762349"
href="https://bugs.openjdk.java.net/browse/JDK-8069004">BUG:
JDK-8069004 Kitchensink hanged with 16Gb heap and GC pause
>30 min </a><br>
Webrev: <a moz-do-not-send="true" class="moz-txt-link-freetext"
href="http://cr.openjdk.java.net/%7Edrwhite/8069004/webrev.00/">http://cr.openjdk.java.net/~drwhite/8069004/webrev.00/</a>
<br>
<br>
</blockquote>
<br>
Change looks good.<br>
<br>
Thanks,<br>
Bengt<br>
<br>
<br>
<blockquote cite="mid:55197FD1.8090006@oracle.com" type="cite"> Ran
jprt.<br>
<br>
Thanks!<br>
<br>
- Derek<br>
</blockquote>
<br>
</body>
</html>