On Sat, 2005-04-30 at 11:16, Miklos Szeredi wrote:
> The big problem is the page cache, because that is not limited. The
> user can mmap huge amounts of memory, dirty them, and then when the
> machine runs out of memory, and writeback kicks in, it may already be
> too late.
Yes - we have seen the inode caching get too aggressive in testcases
with paired machines each mounting two clients and also running two
servers - in particular running an NFS and CIFS mounts from the same
client to a server running nfsd and Samba, and then doing the reverse
and launching large file copy testcases going both directions at the
same time. To make it nastier they add exports for Samba and NFS of
more than one local filesystem type. Fortunately most of the issues
there have been fixed, but it is an incredibly hard thing to guarantee
that there is enough memory in those cases because so much is taken up
by the page manager doing inode data caching and multimachine deadlock
could occur if the server is blocked on a client doing writepage which
is blocked on the other server which is blocked on the other client ...
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
