tech-kern archive
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]
per-mount maxvnodes
Hello
For now the kernel has a global maxvndes limit, and starts reclaiming
vnodes once the limit is reached. That means unused vnodes will remain
for a while in the kernel. This may be a problem for userland filesystems,
since they hold memory for that vnodes. For instance, perfused grows
and crash after a while because it exhausts the swap.
One solution is to lower kern.maxvnodes, but the consequence is
that all filesystems are impacted. Therefore comes the idea to
have a per-mount maxvnodes.
I tried implementing it, the biggest problem is how to set the value.
mount(2) only allows and int to be passed to the filesystem for
mount options, there seems to be no way to pass a numeric option.
Any idea on that front?
--
Emmanuel Dreyfus
manu%netbsd.org@localhost
Home |
Main Index |
Thread Index |
Old Index