[OpenAFS] Network becomes terribly slow when cache manager flushes updates over xDSL

Carson Gaspar carson@taltos.org
Wed, 08 Jul 2009 13:55:31 -0700

Derrick Brashear wrote:
> On Wed, Jul 8, 2009 at 1:06 PM, Carson Gaspar<carson@taltos.org> wrote:
>> Sean O'Malley wrote:
>>> -icmp shouldn't be used. Some BOFH block/drop icmp.
>> ...
>>> -is there a standard way to do UDP mtu link detection on any platform
>>> already?
>> The standard is ICMP WOULD FRAGMENT. People who block that don't deserve
>> functional apps. Don't cater to them.
> Don't cater to people who are using the network they have and don't
> control? I guess you advocate OpenAFS minimizing its usability?

Minimize, no. Not add marginally useful and arguably harmful code at the expense 
of _far_ more critical deliverables, yes. Developer resources are not infinite. 
And in the case of OpenAFS, are really entirely inadequate (through no fault of 
the folks who dedicate far too much of their time already). And yes, my employer 
already pays Sine Nomine for support and development efforts.

Please feel free to argue that nonstandard fragmentation detection (or _any_ 
fragmentation detection, for that matter) should be high in the priority queue 
for resources. I just can't see a sane rationale for it.