memory usage on Scyld slave nodes (fwd)

[Jag]

On Fri, 16 Feb 2001, Rick Niles wrote:

> 
> > It works fine, but when I use BeoStatus to look at the slaves it
> > shows that the slaves all have about 400MB of their memory taken up.
> > Anyone know what is eating up the RAM on those slaves?  Each node
> > has a total of 512MB of RAM.  Why is beowulf eating up so much of
> > it?  Thanks.
> 
> I'm adding up all the memory that's in use on the entire machine, include
> buffer cache for the filesystem.  Linux tries to use any spare memory up
> to about 90% of available as a cache of the filesystem.
> 
> I realize that this make that value in beostatus pretty much
> worthless.  It's also been pointed out that it's also the more
> expensive for the kernel to compute.  I believe "top" actually walks
> though the proc table and adds up all the memory to get it's value,
> but that also seems a bit expensive to me.
> 
> So short answer, it's not a problem, it's just not a real useful number
> and I'll still deciding how to make it better.

When you run the 'free' command, the first few numbers it shows seems to
be similar to what beostatus shows.  What would probablly be a lot more
useful would be the numbers from the seconds line, with the buffer/cache
usage subtracted from to total used.  I haven't yet looked to see how
expensive that computation is, but I think this number would be a lot
more useful to show as I know the kernel will generally make total usage
near 90%


Jag
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 232 bytes
Desc: not available
Url : http://www.scyld.com/pipermail/beowulf/attachments/20010216/9314513e/attachment.bin