<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
<title></title>
</head>
<body bgcolor="#ffffff" text="#000000">
Yes it is, it is VERY different! <br>
<br>
With GRAM/PBS, although the failed job only takes 10ms to fail, there
is about a 1 sec overhead to submit the job and get the error code. In
Falkon, the overhead is about 20ms. Also, in the time that the 1 node
was faulty (~30 sec), Falkon can submit and return about 1000 failed
tasks, while GRAM/PBS could only do about 15~30 failed jobs. The fact
that Falkon's submit/execute throughput is 2 orders of magnitude higher
than GRAM/PBS is what makes is different, and hence needs to be handled
different.<br>
<br>
Ioan<br>
<br>
Ben Clifford wrote:
<blockquote
cite="mid:Pine.LNX.4.64.0708271736280.3084@dildano.hawaga.org.uk"
type="cite">
<pre wrap="">
On Mon, 27 Aug 2007, Ioan Raicu wrote:
</pre>
<blockquote type="cite">
<pre wrap="">On a similar note, IMO, the heuristic in Karajan should be modified to take
into account the task execution time of the failed or successful task, and not
just the number of tasks. This would ensure that Swift is not throttling task
submission to Falkon when there are 1000s of successful tasks that take on the
order of 100s of second to complete, yet there are also 1000s of failed tasks
that are only 10 ms long. This is exactly the case with MolDyn, when we get a
bad node in a bunch of 100s of nodes, which ends up throttling the number of
active and running tasks to about 100, regardless of the number of processors
Falkon has.
</pre>
</blockquote>
<pre wrap=""><!---->
Is that different from when submitting to PBS or GRAM where there are
1000s of successful tasks taking 100s of seconds to complete but with
1000s of failed tasks that are only 10ms long?
</pre>
</blockquote>
<br>
<pre class="moz-signature" cols="72">--
============================================
Ioan Raicu
Ph.D. Student
============================================
Distributed Systems Laboratory
Computer Science Department
University of Chicago
1100 E. 58th Street, Ryerson Hall
Chicago, IL 60637
============================================
Email: <a class="moz-txt-link-abbreviated" href="mailto:iraicu@cs.uchicago.edu">iraicu@cs.uchicago.edu</a>
Web: <a class="moz-txt-link-freetext" href="http://www.cs.uchicago.edu/~iraicu">http://www.cs.uchicago.edu/~iraicu</a>
<a class="moz-txt-link-freetext" href="http://dsl.cs.uchicago.edu/">http://dsl.cs.uchicago.edu/</a>
============================================
============================================</pre>
</body>
</html>