Re: [PATCH 1/3] epoll: increase default max_user_instances to 1024

[Davide Libenzi]

On Tue, 27 Jan 2009, Ray Lee wrote:

> On Tue, Jan 27, 2009 at 8:00 PM, Davide Libenzi <davidel@xxxxxxxxxxxxxxx> wrote:
> > On Wed, 28 Jan 2009, Bron Gondwana wrote:
> >
> >> Both Postfix and Apache use an epoll instance per child, which
> >> leads to significant scalability issues with max_user_instances
> >> set so low.  Bump the default to 1024 so medium sized sites are
> >> not impacted.
> >
> > NACK. Epoll allocates globally about 100 to 160 bytes (32/64 bit) for each
> > file added to the interface:
> >
> >        for i 1..1024
> >                for j 1..1024
> >                        if i!=j
> >                                add j -> i
> >
> > That's (N^2 * {100, 160}) = 100MB to 160MB of pinned kernel memory,
> > explotable by simple users with untouched NFILES.
> > This is the reason such limit was introduced in the first place. Again,
> > for the 10th time, if you have a loaded server with multiple processes
> > using epoll:
> >
> > $ echo NN > /proc/sys/fs/epoll/max_user_instances
> >
> > Note that NN does not consume any resource "per se", so if you feel
> > threatened by such limit, you can go wild with it.
> 
> It's really simple. A kernel upgrade in a -stable series point release
> broke a rational user-space setup. If you don't want to adjust the
> defaults, then the sane thing to do is to revert the commit that
> caused the grief. Postfix is everywhere. Apache is everywhere.
> 
> Userspace is not broken here, and the whole idea of a -stable series
> is that administrators can upgrade to them without having to worry
> about things getting broken or making specific configuration changes
> by point release.

The reason Greg took it, was that in a multiuser systems, that's a DoS 
EZ-PZ Lemon Squeezie.



- Davide


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/