On 2002.06.01 23:49 Leif Delgass wrote:
> ...
>
> I found and fixed this problem (I was using ring.tail to set the offset
> for buffer "aging" before it was incremented).
>
> ...
>
> I've cleaned this up a bit and done the work in COMMIT_RING.
>
> ...
>
> OK, I'm still not sure if I have this
On Sat, 1 Jun 2002, Leif Delgass wrote:
> the ring_wait is really not necessary, since 128 16kB buffers can use a
> max of 512 of the 1024 descriptors. We'd need 4MB of buffers to fill
> the ring.
On second thought, this is only true as long as we're not reusing buffers.
If we reuse buffers f
On Fri, 31 May 2002, José Fonseca wrote:
> On 2002.05.31 02:53 Leif Delgass wrote:
> > On Thu, 30 May 2002, José Fonseca wrote:
> >
> > I've fixed one bug already that was related to the ring tail being left
> > pre-incremented (the table_end I had before wasn't). Some of my problems
> > were r
