<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Hi Ramki,<br>
<br>
Thank you for reviewing this.<br>
<br>
<div class="moz-cite-prefix">On 04/06/2015 03:40 PM, Srinivas
Ramakrishna wrote:<br>
</div>
<blockquote
cite="mid:CABzyjykZc33fDUObYZMJ1UGOisAJ6-FxXrV5cO7Q53R-adVRkw@mail.gmail.com"
type="cite">
<div dir="ltr">Hi Sangheon --
<div><br>
</div>
<div>Does the number of GC workers ever change dynamically
within a stop-world GC phase?</div>
</div>
</blockquote>
Yes.<br>
<br>
<blockquote
cite="mid:CABzyjykZc33fDUObYZMJ1UGOisAJ6-FxXrV5cO7Q53R-adVRkw@mail.gmail.com"
type="cite">
<div dir="ltr">
<div>
<div>If not, you might save a little work by just doing the
division once when you decide the number of</div>
<div>workers at the start of the copying phase, and then use
that value for the remainder of the copying</div>
<div>phase of the collection when you know the number of
workers won't change. However, that is just a</div>
<div>nit, I am sure the work involved in calculating the value
at each PLAB refill shouldn't typically be a</div>
<div>big deal either way.</div>
</div>
</div>
</blockquote>
Right. I was also considered about using the calculated size for
same workers, but as it's not a big deal I ended up to calculate
every time.<br>
<br>
<blockquote
cite="mid:CABzyjykZc33fDUObYZMJ1UGOisAJ6-FxXrV5cO7Q53R-adVRkw@mail.gmail.com"
type="cite">
<div dir="ltr">
<div>
<div><br>
</div>
<div>I might rename the _desired_plab_sz field to clarify that
it's the net value, say by calling it</div>
<div>_desired_net_plab_sz. (Alternatively, you could change
the name of the method</div>
<div>desired_plab_sz(int) to
desired_plab_size_for_n_workers(int), but the former seems
better,</div>
<div>since the parameter already signals the intention for the
latter.)</div>
</div>
</div>
</blockquote>
I will change the field name to '_desired_net_plat_sz'.<br>
<br>
Thanks,<br>
Sangheon<br>
<br>
<br>
<blockquote
cite="mid:CABzyjykZc33fDUObYZMJ1UGOisAJ6-FxXrV5cO7Q53R-adVRkw@mail.gmail.com"
type="cite">
<div dir="ltr">
<div>
<div><br>
</div>
<div>looks good to me otherwise.</div>
<div>-- ramki (openjdk: ysr)</div>
<div><br>
</div>
</div>
</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">On Mon, Apr 6, 2015 at 2:40 PM,
Sangheon Kim <span dir="ltr"><<a moz-do-not-send="true"
href="mailto:sangheon.kim@oracle.com" target="_blank">sangheon.kim@oracle.com</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">Hi all,<br>
<br>
Please review this change to determine the desired PLAB size
for current gc worker threads.<br>
<br>
Currently we calculate an optimal PLAB size with current
number of gc workers.<br>
When the number of workers changes dynamically (-XX:+UseDynamicNumberOfGCThreads),
the desired PLAB size returned(by desired_plab_sz()) is
still tuned to the number of gc workers that has been used
previously.<br>
<br>
This change is first calculate the desired PLAB value for a
single gc worker and then return desired PLAB size according
to the current number of threads.<br>
<br>
CR:<br>
<a moz-do-not-send="true"
href="https://bugs.openjdk.java.net/browse/JDK-8073204"
target="_blank">https://bugs.openjdk.java.net/browse/JDK-8073204</a><br>
<br>
Webrev:<br>
<a moz-do-not-send="true"
href="http://cr.openjdk.java.net/%7Esangheki/8073204/webrev.01"
target="_blank">http://cr.openjdk.java.net/~sangheki/8073204/webrev.01</a><br>
<br>
Test:<br>
JPRT<br>
<br>
Thanks,<br>
Sangheon<br>
</blockquote>
</div>
<br>
</div>
</blockquote>
<br>
</body>
</html>