Re: [patch] epoll reduced (to 1) number of passes over the ready set ...

[Davide Libenzi <davidel@xmailserver.org>]

On Tue, 27 Feb 2007, Eric Dumazet wrote:

> On Tuesday 27 February 2007 03:32, Davide Libenzi wrote:
> > Epoll is doing multiple passes over the ready set at the moment, because
> > of the constraints over the f_op->poll() call. Looking at the code again,
> > I noticed that we already hold the epoll semaphore in read, and this
> > (together with other locking conditions that hold while doing an
> > epoll_wait()) can lead to a smarter way to "ship" events to userspace (in
> > a single pass). I added more (even) more comments to the code to explain
> > the conditions why certain operations are safe.
> > This is a stress application that can be used to test the new code. It
> > spwans multiple thread and call epoll_wait() and epoll_ctl() from many
> > threads. Stress tested on my dual Opteron 254 w/out any problems.
> 
> Davide,
> 
> This is really cool, because the size of epitem would fit now in 128 bytes 
> instead of 192 (on x86_64 platforms). So we also reduce memory usage.

Yeah, I forgot to mention that I removed the txlink member.



> I have one comment :
> 
> >  	 */
> > -	list_for_each(lnk, txlist) {
> > -		epi = list_entry(lnk, struct epitem, txlink);
> > +	for (eventcnt = 0; !list_empty(txlist) && eventcnt < maxevents;) {
> > +		epi = list_entry(txlist->next, struct epitem, rdllink);
> 
> Now that we scan the rdllist list once, it may be usefull to use a prefetch() 
> hint. 
> 
> list_for_each() has one prefetch(pos->next) automatically included, but not 
> your open coded loop.
> 
> I suggest adding after epi = list_entry(txlist->next, struct epitem, rdllink);
> prefetch(epi->rdllink.next);

Will do in the next version, thx!



- Davide