John,<br><br>I suspect speed is more important than timing.  In practice I don&#39;t mind a pause for a gc when nothing is happening in the market.  It&#39;s when the market is moving fast that we particularly want to keep our response time low. Busy times may continue for long periods though and I&#39;m not sure if being able to defer gc (if that&#39;s what you&#39;re suggesting) would be possible for that long.  We are still studying how the gc times are interacting with our response times and so hopefully I will have a better answer to this later on.  <br>
<br>Simon<br><br><div class="gmail_quote">On Tue, Mar 2, 2010 at 2:06 PM, John Van Enk <span dir="ltr">&lt;<a href="mailto:vanenkj@gmail.com">vanenkj@gmail.com</a>&gt;</span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Simon,<div><br></div><div>Would a more predictable GC or a faster GC be better in your case? (Of course, both would be nice.)</div><div><br></div><div><font color="#888888">/jve<br><br></font><div class="gmail_quote"><div>
<div></div><div class="h5">On Mon, Mar 1, 2010 at 9:33 PM, Simon Cranshaw <span dir="ltr">&lt;<a href="mailto:simon.cranshaw@gmail.com" target="_blank">simon.cranshaw@gmail.com</a>&gt;</span> wrote:<br>
</div></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div><div></div><div class="h5"><div class="gmail_quote"><div>On Sun, Feb 28, 2010 at 6:06 PM, Pavel Perikov <span dir="ltr">&lt;<a href="mailto:perikov@gmail.com" target="_blank">perikov@gmail.com</a>&gt;</span> wrote:<br>

</div><div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Did you really seen 100ms pauses?! I never did extensive research on this but my numbers are rather in microseconds range (below 1ms). What causes such a long garbage collection? Lots of allocated and long-living objects?<br>



<br></blockquote></div><div><br>I am using an automated options trading system written in Haskell.  I&#39;m more on the business side than the technical side of the issues so I&#39;m not clear on all the details.  I can confirm that without tweaking the RTS settings we were seeing over 100ms GC pauses.  I&#39;ve mainly been trying to minimise our overall response time and we were able to improve this by increasing the allocation area with -A.  I think this brought GC well under 100ms.  We are still working on analysis of this.  <br>


<br>I can also confirm, as others seem to have found, that under 6.12 the parallel GC seemed to make things much worse. I am always turning it off with -qg.  If there is a project to improve performance of the GC I could be interested to contribute.<br>


<br>Simon Cranshaw<br></div></div>
<br></div></div><div class="im">_______________________________________________<br>
Haskell-Cafe mailing list<br>
<a href="mailto:Haskell-Cafe@haskell.org" target="_blank">Haskell-Cafe@haskell.org</a><br>
<a href="http://www.haskell.org/mailman/listinfo/haskell-cafe" target="_blank">http://www.haskell.org/mailman/listinfo/haskell-cafe</a><br>
<br></div></blockquote></div><br></div>
</blockquote></div><br>