<!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">
<font face="Bitstream Vera Sans Mono">Hi Tobias,<br>
<br>
Thank you for your reply.<br>
<br>
</font><br>
Tobias Oetiker wrote:
<blockquote
cite="mid:alpine.DEB.1.10.0806130052310.8113@qygrfg01.brgvxre.pu"
type="cite">
<pre wrap=""><!---->
I have not yet done setups of this scale, but having multiple
fpings running in paralell is certainly a goood thing ... I would
not think that you are disk bound with only 6400 targets ...
especially not if you have plenty of memory ... Also moving off xen
to real HW should help ...
If you use rrdtool 1.3 you may be able to reduce your cache
consumtion and improve performance ...
</pre>
</blockquote>
Thank you for that suggestion. I will try rrdtool 1.3 when I get a
chance. We are currently using rrdtool-1.2.99907080300.<br>
<br>
<blockquote
cite="mid:alpine.DEB.1.10.0806130052310.8113@qygrfg01.brgvxre.pu"
type="cite">
<pre wrap="">
that does sound odd ... your smokeping process uses
3.5 GB or RAM ???
</pre>
</blockquote>
The individual processes do not use that much. I got that value by
adding the memory usage of all of the probe processes. Each of the 30
probes uses somewhere in the neighborhood of 115-120 MB. Is that due to
the fact that results are all stored in RAM and then written to disk
all at the same time? I've noticed that there are a fair amount of
writes that take place across the interval, but there seem to be large
writes and high disk utilization all at once.<br>
<br>
<blockquote
cite="mid:alpine.DEB.1.10.0806130052310.8113@qygrfg01.brgvxre.pu"
type="cite">
<pre wrap="">
Glad to hear smokeping makes you happy. If you want to make sure it
continues to evolve you could always become a sponsor and ensure
its continued development ...</pre>
</blockquote>
I will have to talk to my boss about that. Thanks again.<br>
<br>
</body>
</html>