Re: [Xen-devel] xen-netfront possibly rides the rocket too often

[Wei Liu <wei.liu2@xxxxxxxxxx>]

On Fri, May 16, 2014 at 10:48:42AM +0100, Wei Liu wrote:
> On Thu, May 15, 2014 at 02:14:00PM +0200, Stefan Bader wrote:
> [...]
> > > Wei.
> > > 
> > Reading more of the code I would agree. The definition of MAX_SKB_FRAGS (at
> > least now with compound pages) cannot be used in any way to derive the 
> > number of
> > 4k slots a transfer will require.
> > 
> > Zoltan already commented on worst cases. Not sure it would get as bad as 
> > that or
> > "just" 16*4k frags all in the middle of compound pages. That would then end 
> > in
> > around 33 or 34 slots, depending on the header.
> > 
> > Zoltan wrote:
> > > I think the worst case scenario is when every frag and the linear buffer 
> > > contains 2 bytes,
> > > which are overlapping a page boundary (that's (17+1)*2=36 so far), plus 
> > > 15 of
> > them have a 4k
> > > page in the middle of them, so, a 1+4096+1 byte buffer can span over 3 
> > > page.
> > > That's 51 individual pages.
> > 
> > I cannot claim to really know what to expect worst case. Somewhat I was 
> > thinking
> > of a
> > worst case of (16+1)*2, which would be inconvenient enough.
> > 
> > So without knowing exactly how to do it, but as Ian said it sounds best to 
> > come
> > up with some sort of exception coalescing in cases the slot count goes over 
> > 18
> > and we know the data size is below 64K.
> > 
> 
> I took a stab at it this morning and came up with this patch. Ran
> redis-benchmark, it seemed to fix that for me -- only saw one "failed to
> linearize skb" during
> 
>   redis-benchmark -h XXX -d 1000 -t lrange
> 
> And before this change, a lot of "rides rocket" were triggered.
> 
> Thought?
> 

And don't take this as a formal patch because I haven't tested it
thoroughly. It's just an idea to coalesce SKBs. We can certainly code
up a loop to do so by ourself.

Wei.

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel