<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix"><br>
Hi Ramki,<br>
<br>
On 12/20/12 9:21 PM, Srinivas Ramakrishna wrote:<br>
</div>
<blockquote
cite="mid:CABzyjy=G3+CDMSAFp1e3AGadGZih984zuKzxR30_qhazCtus8w@mail.gmail.com"
type="cite"><br>
<br>
<div class="gmail_quote"><br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000">
<div class="im">
<blockquote type="cite"> What happens when you run CMS on
a single-processor. I hope you don't see a deprecation
warning.<br>
</blockquote>
<br>
</div>
Ooops. Good point. It took me a long while to find a machine
with just one cpu that could actually run JDK8. But you are
correct. We will print a warning in that case.<br>
</div>
</blockquote>
<div><br>
Remember that virtualized platforms or LDOMS or Zones may
partition a large box into small 1-cpu slices (although may be
not 1-core).<br>
</div>
</div>
</blockquote>
<br>
Right. That is actually what I ended up doing. Running Ubuntu in a
VirtualBox set up to use one CPU.<br>
<br>
<blockquote
cite="mid:CABzyjy=G3+CDMSAFp1e3AGadGZih984zuKzxR30_qhazCtus8w@mail.gmail.com"
type="cite">
<div class="gmail_quote">
<div><br>
On Solaris, you can easily test your code by means of psradm
to turn off all but one virtual cpu.<br>
<br>
</div>
<blockquote class="gmail_quote" style="margin:0pt 0pt 0pt
0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000"> <br>
I think the fix is to not pick DefNew by default for single
processor machines. I'll see if I can get any performance
data for that.<br>
<br>
</div>
</blockquote>
<div><br>
I'd test that on a regular MP with ParNew=1 vs DefNew, as well
as separately with psrset and pbind (although my guess is that<br>
the latter two would be indistinguishable from each other). As
I recall, scaling was near linear at those small numbers for
ParNew,<br>
and the breakeven point was at 2, so my guess based on very
old data from the fogs of time is that we'd see a fairly
sizable pause<br>
time and overhead hit on a single cpu.<br>
</div>
</div>
</blockquote>
<br>
I did one set of test runs with SpecJBB2005 on the single CPU
VirtualBox instance that I have. I got these scores:<br>
<br>
17691 DefNew <br>
17778 ParNew ParallelGCThreads=0<br>
17770 ParNew ParallelGCThreads=1<br>
<br>
I will do more runs and I'll also try it on a MT system as you
suggested. But primarily the results look good.<br>
<br>
<blockquote
cite="mid:CABzyjy=G3+CDMSAFp1e3AGadGZih984zuKzxR30_qhazCtus8w@mail.gmail.com"
type="cite">
<div class="gmail_quote">
<div><br>
Stepping back for a moment, is supporting embedded
environments perhaps from the same parent code base an issue,
so DefNew &<br>
Serial is going to be part of the code base for a while,
anyway?<br>
<br>
I understand though that saving on testing resources by
pruning down supported combinations is one important
motivation, in which case<br>
DefNew+CMS gets deprecated (and switches to Parnew/1+CMS on
1-cpu configs), but DefNew continues to be part of the code
base,<br>
and so DefNew code gets used (and tested) at least in part to
the extent that ParNew uses at least some functionality
defined in DefNew.<br>
</div>
</div>
</blockquote>
<br>
Absolutely correct. We will keep the DefNew + SerialOld combo. We
just want to cut down on the permutations that we need to test and
support. So we aim to deprecate DefNew + CMS. But we will keep
DefNew and still support and test it in combination with SerialOld.<br>
<br>
Bengt<br>
<br>
<blockquote
cite="mid:CABzyjy=G3+CDMSAFp1e3AGadGZih984zuKzxR30_qhazCtus8w@mail.gmail.com"
type="cite">
<div class="gmail_quote">
<div><br>
-- ramki<br>
</div>
<br>
</div>
<br>
</blockquote>
<br>
</body>
</html>