Re: Implementation PrevaylerEight

Marcel Oerlemans <[email protected]> Fri, 24 Oct 2014 14:03:30 +0200
Newsgroups gmane.comp.java.prevayler
Message-ID <CAKE0621WmDL85CKgsG55voRjcnxrU1a8LtJCx+jh4cQEjQHwyA@mail.gmail.com>
--===============1808750344698603576==
Content-Type: multipart/alternative; boundary=001a113970a02c804b050629f827

--001a113970a02c804b050629f827
Content-Type: text/plain; charset=UTF-8

Hiya,

I just ran the scalability test with P8 through JProfiler, and there seems
to be a locking problem at the basis of the steep decline in performance.
Hope that helps...

Best,
Marcel



On Fri, Oct 24, 2014 at 11:53 AM, Marcel Oerlemans <
[email protected]> wrote:

> Hiya,
>
> >And the exceptions still arose?
> Nope, in that case, no more exceptions, but then I had the incredible
> steep decline in performance.
>
> Best,
> Marcel
>
>
>
>
> On Fri, Oct 24, 2014 at 11:48 AM, Christian Stein <[email protected]>
> wrote:
>
>>
>>
>> On Fri, Oct 24, 2014 at 11:42 AM, Marcel Oerlemans <
>> [email protected]> wrote:
>>
>>> Hiya,
>>>
>>> Yes, I did. I forgot to include those results, here they are:
>>>
>>
>> And the exceptions still arose?
>>
>>
>>> 32077,44 transactions/second @ 1 thread
>>> 6836,89 transactions/second @ 2 threads
>>> 547,94 transactions/second @ 3 threads
>>> 30,33 transactions/second @ 4 threads
>>>
>>> On the other hand, when I run your BenchConcurrent test, I got a peak
>>> of 1712415 transactions per second for P8. Which is incredible!
>>>
>>>
>> This puzzles me, too. Both. The steep decline of performance in the
>> Scalability test shipping with Prevayler and the heap of transactions that
>> P8 handles in a simple "do a fast as you can" scenario.
>>
>> May be Klaus et al can elaborate this behaviour.
>>
>> Cheers,
>> Christian
>>
>> Btw. here http://www.chartgo.com/share.do?id=67c65287aa I'm charting my
>> current results. It's a nice online charting tool with a simple "GET"
>> interface.
>>
>>
>> ------------------------------------------------------------------------------
>>
>> _______________________________________________
>> To unsubscribe go to the end of this page:
>> http://lists.sourceforge.net/lists/listinfo/prevayler-discussion
>> _______________________________________________
>> "Databases in Memoriam" -- http://www.prevayler.org
>>
>>
>

--001a113970a02c804b050629f827
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Hiya,<div><br></div><div>I just ran the scalability test w=
ith P8 through JProfiler, and there seems to be a locking problem at the ba=
sis of the steep decline in performance. Hope that helps...</div><div><br><=
/div><div>Best,</div><div>Marcel</div><div><br></div><div><br></div></div><=
div class=3D"gmail_extra"><br><div class=3D"gmail_quote">On Fri, Oct 24, 20=
14 at 11:53 AM, Marcel Oerlemans <span dir=3D"ltr">&lt;<a href=3D"mailto:ma=
[email protected]" target=3D"_blank">[email protected]</a>&gt=
;</span> wrote:<br><blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 =
.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir=3D"ltr">Hiya,<sp=
an class=3D""><div><br></div><div>&gt;<span style=3D"font-family:arial,sans=
-serif;font-size:13px">And the exceptions still arose?</span></div></span><=
div>Nope, in that case, no more exceptions, but then I had the incredible s=
teep decline in performance.=C2=A0</div><div><br></div><div>Best,</div><div=
>Marcel</div><div><br></div><div><br></div><div><br></div></div><div class=
=3D"gmail_extra"><br><div class=3D"gmail_quote"><div><div class=3D"h5">On F=
ri, Oct 24, 2014 at 11:48 AM, Christian Stein <span dir=3D"ltr">&lt;<a href=
=3D"mailto:[email protected]" target=3D"_blank">[email protected]</a>&gt;=
</span> wrote:<br></div></div><blockquote class=3D"gmail_quote" style=3D"ma=
rgin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div clas=
s=3D"h5"><div dir=3D"ltr"><br><div class=3D"gmail_extra"><br><div class=3D"=
gmail_quote"><span>On Fri, Oct 24, 2014 at 11:42 AM, Marcel Oerlemans <span=
 dir=3D"ltr">&lt;<a href=3D"mailto:[email protected]" target=3D"_bl=
ank">[email protected]</a>&gt;</span> wrote:<br><blockquote class=
=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-left-width:1px;bo=
rder-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">=
<div dir=3D"ltr">Hiya,<div><br></div><div>Yes, I did. I forgot to include t=
hose results, here they are:</div></div></blockquote><div><br></div></span>=
<div>And the exceptions still arose?</div><span><div>=C2=A0</div><blockquot=
e class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-left-width=
:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-lef=
t:1ex"><div dir=3D"ltr"><div>32077,44 transactions/second @ 1 thread<br></d=
iv><div><div>6836,89 transactions/second @ 2 threads</div><div>547,94 trans=
actions/second @ 3 threads</div><div>30,33 transactions/second @ 4 threads<=
/div></div><div><br></div><div>On the other hand, when I run your BenchConc=
urrent test, I got a peak of=C2=A01712415 transactions per second for P8. W=
hich is incredible!</div><div><br></div></div></blockquote><div><br></div><=
/span><div>This puzzles me, too. Both. The steep decline of performance in =
the Scalability test shipping with Prevayler and the heap of transactions t=
hat P8 handles in a simple &quot;do a fast as you can&quot; scenario.</div>=
<div><br></div><div>May be Klaus et al can elaborate this behaviour.</div><=
div><br></div><div>Cheers,</div><div>Christian</div><div><br></div><div>Btw=
. here <a href=3D"http://www.chartgo.com/share.do?id=3D67c65287aa" target=
=3D"_blank">http://www.chartgo.com/share.do?id=3D67c65287aa</a> I&#39;m cha=
rting my current results. It&#39;s a nice online charting tool with a simpl=
e &quot;GET&quot; interface.</div></div></div></div>
<br></div></div><span class=3D"">------------------------------------------=
------------------------------------<br>
<br>_______________________________________________<br>
To unsubscribe go to the end of this page: <a href=3D"http://lists.sourcefo=
rge.net/lists/listinfo/prevayler-discussion" target=3D"_blank">http://lists=
.sourceforge.net/lists/listinfo/prevayler-discussion</a><br>
_______________________________________________<br>
&quot;Databases in Memoriam&quot; -- <a href=3D"http://www.prevayler.org" t=
arget=3D"_blank">http://www.prevayler.org</a><br>
<br></span></blockquote></div><br></div>
</blockquote></div><br></div>

--001a113970a02c804b050629f827--


--===============1808750344698603576==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

------------------------------------------------------------------------------

--===============1808750344698603576==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
To unsubscribe go to the end of this page: http://lists.sourceforge.net/lists/listinfo/prevayler-discussion
_______________________________________________
"Databases in Memoriam" -- http://www.prevayler.org

--===============1808750344698603576==--