<html>
<head>
<meta content="text/html; charset=windows-1252"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">On 3/18/16 3:58 PM, Kim Barrett wrote:<br>
</div>
<blockquote
cite="mid:8A35C6D0-1CB1-447F-BBCF-AA160A3F2E4B@oracle.com"
type="cite">
<pre wrap="">Please review this fix for a performance scaling problem in
SuspendibleThreadSet, leading to unnecessary additional safepoint
latency as the number of suspendible threads increases. See the CR for
details of the problem and some performance data.
CR:
<a class="moz-txt-link-freetext" href="https://bugs.openjdk.java.net/browse/JDK-8152196">https://bugs.openjdk.java.net/browse/JDK-8152196</a>
Webrev:
<a class="moz-txt-link-freetext" href="http://cr.openjdk.java.net/~kbarrett/8152196/webrev.00/">http://cr.openjdk.java.net/~kbarrett/8152196/webrev.00/</a>
Testing:
JPRT, RBT GC Nightly, local specjbb2015.</pre>
</blockquote>
Hi Kim, this looks good.<br>
<br>
I looked at the suspendibleThreadSet.cpp, line 88 for a bit. There
used to be notify_all() after "_nthreads_stopped--;". But the
thinking is that nobody cares about the "
<meta http-equiv="content-type" content="text/html;
charset=windows-1252">
is_synchronized() -> !
<meta http-equiv="content-type" content="text/html;
charset=windows-1252">
is_synchronized()" transition, so this was never really needed, and
certainly isn't needed now. Is this correct?<br>
<br>
- Derek
<meta http-equiv="content-type" content="text/html;
charset=windows-1252">
<blockquote
cite="mid:8A35C6D0-1CB1-447F-BBCF-AA160A3F2E4B@oracle.com"
type="cite">
</blockquote>
<br>
</body>
</html>