lkml.org 
[lkml]   [2009]   [Jan]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 1/3] epoll: increase default max_user_instances to 1024
On Wed, Jan 28, 2009 at 08:52:51AM -0800, Davide Libenzi wrote:
> On Wed, 28 Jan 2009, Vegard Nossum wrote:
>
> > On Wed, Jan 28, 2009 at 6:32 AM, Bron Gondwana <brong@fastmail.fm> wrote:
> > > That's clearly not happening here - so it seems that maybe our "happy
> > > medium" is actually in closer inspection of what's going on rather than
> > > a blanket low N to keep N^2 down.
> >
> > Mh, could another solution to this all be to limit the number times
> > you can add a single epoll descriptor to another descriptor's set?
>
> In the example that was posted, a single fd was added a single time inside
> the other 1000+ fds. Epoll already has detection for too long chains and
> closed loops, but you can't put those in the fast path. And epoll_ctl() is
> one of those.

Not even if you're adding an epoll watcher inside another epoll watcher?

The problem I have here is that "a single fd was added a single time
inside the other 1000+ fds" is different behaviour to the daemons out
there. They're pretty much all using flat layouts:

process 1:
epoll_watcher:
leaf fd
leaf fd 2
leaf fd 3
leaf fd 4
...

process 2:
epoll_watcher:
...

While the attack happens inside a single process.

Indeed, if you had a _per_process_ watcher limit, you would stop the
attack working while not breaking at least postfix and apache. I'm not
sure what Java's doing under the hood, I have a feeling it's more
thready.

But most of all a way of detecting between a leaf fd and an epoll
watcher fd in epoll_ctl and doing deeper tests if it's an epoll watcher
that's being added would stop the attack.

Bron.



\
 
 \ /
  Last update: 2009-01-28 22:03    [W:0.732 / U:0.216 seconds]
©2003-2011 Jasper Spaans