Re: [Qemu-devel] [PATCH v2 0/7] coroutine: optimizations

2015-01-06 Thread Stefan Hajnoczi
On Tue, Dec 02, 2014 at 12:05:43PM +0100, Paolo Bonzini wrote: > As discussed in the other thread, this brings speedups from > dropping the coroutine mutex (which serializes multiple iothreads, > too) and using ELF thread-local storage. > > The speedup in perf/cost is about 50% (190->125). Window

Re: [Qemu-devel] [PATCH v2 0/7] coroutine: optimizations

2014-12-18 Thread Fam Zheng
On Tue, 12/02 12:05, Paolo Bonzini wrote: > As discussed in the other thread, this brings speedups from > dropping the coroutine mutex (which serializes multiple iothreads, > too) and using ELF thread-local storage. > > The speedup in perf/cost is about 50% (190->125). Windows port tested > with

Re: [Qemu-devel] [PATCH v2 0/7] coroutine: optimizations

2014-12-15 Thread Paolo Bonzini
On 11/12/2014 14:55, Peter Lieven wrote: > On 02.12.2014 12:05, Paolo Bonzini wrote: >> As discussed in the other thread, this brings speedups from >> dropping the coroutine mutex (which serializes multiple iothreads, >> too) and using ELF thread-local storage. >> >> The speedup in perf/cost is a

Re: [Qemu-devel] [PATCH v2 0/7] coroutine: optimizations

2014-12-11 Thread Peter Lieven
On 02.12.2014 12:05, Paolo Bonzini wrote: As discussed in the other thread, this brings speedups from dropping the coroutine mutex (which serializes multiple iothreads, too) and using ELF thread-local storage. The speedup in perf/cost is about 50% (190->125). Windows port tested with tests/test

[Qemu-devel] [PATCH v2 0/7] coroutine: optimizations

2014-12-02 Thread Paolo Bonzini
As discussed in the other thread, this brings speedups from dropping the coroutine mutex (which serializes multiple iothreads, too) and using ELF thread-local storage. The speedup in perf/cost is about 50% (190->125). Windows port tested with tests/test-coroutine.exe under Wine. Paolo v1->v2: i