<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta content="text/html; charset=utf-8">
</head>
<body>
<div id="compose-container" itemscope="" itemtype="https://schema.org/EmailMessage" style="direction:ltr">
<span itemprop="creator" itemscope="" itemtype="https://schema.org/Organization"><span itemprop="name"></span></span>
<div>
<div style="direction:ltr">Maybe it would be better to concentrate the processor optimizations on accessors and barrriers without introducing a completely new GC architecture. I can imagine that especially in the area of NUMA, TLAB, huge pages, cache consistency
and possibly MMX extensions there is some potential. </div>
<div><br>
</div>
<div style="direction:ltr">Abandoning the global STW - while it seems like a pretty powerful change - is I guess not a good starter exercise. Especially since it is not only a question of mutator threads.</div>
<div><br>
</div>
<div class="acompli_signature">Gruss<br>
Bernd<br>
-- <br>
<a dir="ltr" href="http://bernd.eckenfels.net">http://bernd.eckenfels.net</a></div>
</div>
</div>
<hr tabindex="-1" style="display:inline-block; width:98%">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> hotspot-gc-dev <hotspot-gc-dev-bounces@openjdk.java.net> on behalf of Ram Krishnan <ramkri123@gmail.com><br>
<b>Sent:</b> Friday, April 14, 2017 6:36:27 AM<br>
<b>To:</b> Asif Qamar; Andrew Haley; hotspot-gc-dev@openjdk.java.net<br>
<b>Subject:</b> Re: linux os processor optimizations for OpenJDK GC performance enhancement</font>
<div> </div>
</div>
<div>
<div dir="ltr">
<div class="gmail_default" style="font-family:courier new,monospace">Thanks Andrew.<br>
<br>
>>Surely there is: a thread could have its TLAB allocated from a region<br>
>>local to that socket (or core), and the GC thread for that region<br>
>>could run on the same socket. It only works for young gen, but that's<br>
>>a lot of the problem.<br>
<br>
</div>
<div class="gmail_default" style="font-family:courier new,monospace">A clarification -- does the TLAB allocation apply to tenured space also? If not, the above would work only for young gen cases where there is no promotion to tenured right?<br>
</div>
<div class="gmail_default" style="font-family:courier new,monospace"><br>
Thanks,<br>
</div>
<div class="gmail_default" style="font-family:courier new,monospace">Ramki<br>
</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">On Thu, Apr 13, 2017 at 12:55 PM, Ram Krishnan <span dir="ltr">
<<a href="mailto:ramkri123@gmail.com" target="_blank">ramkri123@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex; border-left:1px solid rgb(204,204,204); padding-left:1ex">
<div dir="ltr">
<div style="font-family:courier new,monospace"><br>
</div>
<div class="gmail_quote">---------- Forwarded message ----------<br>
From: <b class="gmail_sendername">
<div class="gmail_default" style="font-family:courier new,monospace; display:inline">
</div>
Andrew Haley</b> <span dir="ltr"><<a href="mailto:aph@redhat.com" target="_blank">aph@redhat.com</a>></span><br>
Date: Thu, Apr 13, 2017 at 9:52 AM<br>
Subject: Re: linux os processor optimizations for OpenJDK GC performance enhancement<br>
To: <a href="mailto:hotspot-gc-dev@openjdk.java.net" target="_blank">
<div class="gmail_default" style="font-family:courier new,monospace; display:inline">
</div>
hotspot-gc-dev@openjdk.java.<wbr>net</a><br>
<br>
<br>
On 13/04/17 16:33, Kim Barrett wrote:<br>
> An application thread may touch memory in any region; there is no<br>
> notion of a thread being "scoped" to a specific set of regions. While<br>
> it might happen that a thread would only touch regions not being<br>
> worked on by the collector, there is no a priori way to know that.<br>
<br>
<div class="gmail_default" style="font-family:courier new,monospace; display:inline">
</div>
Surely there is: a thread could have its TLAB allocated from a region<br>
local to that socket (or core), and the GC thread for that region<br>
could run on the same socket. It only works for young gen, but that's<br>
a lot of the problem.<br>
<span class="gmail-m_-294745917701019861HOEnZb"><font color="#888888"><br>
Andrew.<span class="gmail-HOEnZb"><font color="#888888"><br>
<br>
</font></span></font></span></div>
<span class="gmail-HOEnZb"><font color="#888888"><br>
<br clear="all">
<br>
-- <br>
<div class="gmail-m_-294745917701019861gmail_signature">
<div dir="ltr">Thanks,
<div>Ramki<br>
</div>
</div>
</div>
</font></span></div>
</blockquote>
</div>
<br>
<br clear="all">
<br>
-- <br>
<div class="gmail_signature">
<div dir="ltr">Thanks,
<div>Ramki<br>
</div>
</div>
</div>
</div>
</div>
</div>
</body>
</html>