Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-06-26 Thread Jan Kiszka
On 2011-06-26 00:44, Andreas Färber wrote: > Am 25.06.2011 um 10:38 schrieb Jan Kiszka: > >> On 2011-04-13 22:16, Aurelien Jarno wrote: >>> On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: These patches were posted before. They bring down the overhead of the io-thread mode for

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-06-25 Thread Andreas Färber
Am 25.06.2011 um 10:38 schrieb Jan Kiszka: On 2011-04-13 22:16, Aurelien Jarno wrote: On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: These patches were posted before. They bring down the overhead of the io-thread mode for TCG here, specifically when emulating SMP. The major cha

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-06-25 Thread Jan Kiszka
On 2011-04-13 22:16, Aurelien Jarno wrote: > On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: >> These patches were posted before. They bring down the overhead of the >> io-thread mode for TCG here, specifically when emulating SMP. >> >> The major change in this version, besides rebasing

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-26 Thread Jan Kiszka
On 2011-04-25 20:35, Aurelien Jarno wrote: > On Thu, Apr 14, 2011 at 09:14:35AM +0200, Jan Kiszka wrote: >> On 2011-04-13 22:16, Aurelien Jarno wrote: >>> On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: These patches were posted before. They bring down the overhead of the io-t

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-25 Thread Aurelien Jarno
On Thu, Apr 14, 2011 at 09:14:35AM +0200, Jan Kiszka wrote: > On 2011-04-13 22:16, Aurelien Jarno wrote: > > On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: > >> These patches were posted before. They bring down the overhead of the > >> io-thread mode for TCG here, specifically when emu

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-14 Thread Avi Kivity
On 04/14/2011 04:59 PM, Anthony Liguori wrote: On 04/14/2011 08:45 AM, Avi Kivity wrote: On 04/14/2011 10:14 AM, Jan Kiszka wrote: On 2011-04-13 22:16, Aurelien Jarno wrote: > On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: >> These patches were posted before. They bring down the

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-14 Thread Anthony Liguori
On 04/14/2011 08:45 AM, Avi Kivity wrote: On 04/14/2011 10:14 AM, Jan Kiszka wrote: On 2011-04-13 22:16, Aurelien Jarno wrote: > On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: >> These patches were posted before. They bring down the overhead of the >> io-thread mode for TCG her

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-14 Thread Avi Kivity
On 04/14/2011 10:14 AM, Jan Kiszka wrote: On 2011-04-13 22:16, Aurelien Jarno wrote: > On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: >> These patches were posted before. They bring down the overhead of the >> io-thread mode for TCG here, specifically when emulating SMP. >> >> Th

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-14 Thread Jan Kiszka
On 2011-04-13 22:16, Aurelien Jarno wrote: > On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: >> These patches were posted before. They bring down the overhead of the >> io-thread mode for TCG here, specifically when emulating SMP. >> >> The major change in this version, besides rebasing

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-13 Thread Aurelien Jarno
On Mon, Apr 11, 2011 at 10:27:41PM +0200, Jan Kiszka wrote: > These patches were posted before. They bring down the overhead of the > io-thread mode for TCG here, specifically when emulating SMP. > > The major change in this version, besides rebasing, is the exclusion of > KVM from the main loop p

Re: [Qemu-devel] [PATCH v2 0/3] io-thread optimizations

2011-04-12 Thread Paolo Bonzini
On 04/11/2011 10:27 PM, Jan Kiszka wrote: These patches were posted before. They bring down the overhead of the io-thread mode for TCG here, specifically when emulating SMP. The major change in this version, besides rebasing, is the exclusion of KVM from the main loop polling optimization. Ja