Andrew Deason <[email protected]> writes:
> Russ Allbery <[email protected]> wrote:

>> If you abandon and retry operations on a locked vnode and hence tie up
>> more and more server threads waiting on the same vnode, you will
>> eventually cause a file server meltdown, which most definitely *does*
>> screw up other clients.

> That's what it is like _now_, yes. But speaking in a more general
> manner, the fileserver really should have mechanisms to deal with this.

Oh, I agree.  Certainly another way of addressing the same general set of
issues is to find some way to make the file server cope with pathological
client behavior.  But I also think that's much harder to do, and I say
that on the basis that various attempts at that have been made over the
last five years and none of them have really worked.

-- 
Russ Allbery ([email protected])             <http://www.eyrie.org/~eagle/>
_______________________________________________
OpenAFS-devel mailing list
[email protected]
https://lists.openafs.org/mailman/listinfo/openafs-devel

Reply via email to