> - I would like to cap the size of the buffer cache at 200MB,
> giving us another 70MB or so of KVM which is equivalent to
> another 30,000 or so nmbclusters.
I know of many scientific applications that were written with low-memory
machines in mind, which use use lots of disk as temporary memory. It
would be nice in this case to allow them to buffer up large amounts of
the accessed disks in cache, instead of having them.
For certain kinds of programs/loads, using up a large amount of buffer
cache is a good thing, so I'd rather not see hardcoded limits on buffer
cache.
Yes, I know the programs will run fine w/out the additional cache, but
in many of the cases, they stick a huge amount of memory into the box in
an attempt to maximize performance of the box, especially w/FreeBSD
vaunted 'unified VM/cache'. :)
Nate
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
