zonelimit issues...

[Robert Watson]

On Fri, 18 Apr 2008, gnn at freebsd.org wrote:

> I am wondering why this patch was never committed?
>
> http://people.freebsd.org/~delphij/misc/patch-zonelimit-workaround
>
> It does seem to address an issue I'm seeing where processes get into the 
> zonelimit state through the use of mbufs (a high speed UDP packet receiver) 
> but even after network pressure is reduced/removed the process never gets 
> out of that state again.  Applying the patch fixed the issue, but I'd like 
> to have some discussion as to the general merits of the approach.
>
> Unfortunately the test that currently causes this is tied very tightly to 
> code at work that I can't share, but I will hopefully be improving mctest to 
> try to exhibit this behavior.

When you take all load off the system, do mbufs and clusters get properly 
freed back to UMA (as visible in netstat -m)?  If not, continuing to bump up 
against the zonelimit would suggest an mbuf/cluster leak, in which case we 
need to track that bug.

You might consider adding a debugging-only zonelimit waiter count to the UMA 
zone, and checks/assertions that a wakeup is being generated properly.  That 
is, to confirm that the wakeup is generated when memory is freed up if there 
are threads waiting.  There is at least one as-yet MFC'd fix to the 
sleep/wakeup code, I believe, that might be relevant here.  Is the problem 
you're reporting on 7.x, or on 8.x?  If 8.x, that's probably not it, but if 
7.x, it could be.  (This same sleep/wakeup bug occasionally leads to wedging 
of dump(8), I believe).

Robert N M Watson
Computer Laboratory
University of Cambridge