Messages in this thread | | | Date | Tue, 13 Dec 2011 12:33:48 +0200 | From | Avi Kivity <> | Subject | Re: [patch 0/3] kvm tool: Serial emulation overhaul |
| |
On 12/12/2011 08:31 PM, Pekka Enberg wrote: > On Mon, 2011-12-12 at 20:19 +0200, Avi Kivity wrote: > > On 12/12/2011 01:19 PM, Pekka Enberg wrote: > > > On Sun, Dec 11, 2011 at 5:53 PM, Ingo Molnar <mingo@elte.hu> wrote: > > > > Okay, but look at it from another angle: the top output i > > > > generate is about 300k characters. 5000 msecs to execute it > > > > means 16 usecs overhead per character - or about 50k cycles - on > > > > a top of the class x86 CPU. > > > > > > I'm seeing 1.5 usecs per character for this little benchmark: > > > > No interrupts, right? Things look differently with one interrupt per > > character and none. > > No interrupts. I was simply trying to measure PIO overhead to see how > bad the 15 usec per character Ingo measured really is.
Yeah.
Anyway, uart serial is never going to be fast. That's what virtio-serial is for.
-- error compiling committee.c: too many arguments to function
| |