This patch speeds up coroutine creation by reusing freed coroutines.
When a coroutine terminates it is placed in the pool instead of having
its resources freed. The next time a coroutine is created it can be
taken straight from the pool and requires no initialization.
Performance results on an
terAm 12.05.2011 11:54, schrieb Stefan Hajnoczi:
This patch speeds up coroutine creation by reusing freed coroutines.
When a coroutine terminates it is placed in the pool instead of having
its resources freed. The next time a coroutine is created it can be
taken straight from the pool and
On Thu, May 12, 2011 at 11:13 AM, Kevin Wolf kw...@redhat.com wrote:
terAm 12.05.2011 11:54, schrieb Stefan Hajnoczi:
This patch speeds up coroutine creation by reusing freed coroutines.
When a coroutine terminates it is placed in the pool instead of having
its resources freed. The next time
Am 12.05.2011 12:22, schrieb Stefan Hajnoczi:
On Thu, May 12, 2011 at 11:13 AM, Kevin Wolf kw...@redhat.com wrote:
terAm 12.05.2011 11:54, schrieb Stefan Hajnoczi:
This patch speeds up coroutine creation by reusing freed coroutines.
When a coroutine terminates it is placed in the pool instead
On 05/12/2011 12:38 PM, Kevin Wolf wrote:
I don't want to add qemu-img/qemu-io things yet because we don't have
a block layer user for coroutines yet. The qcow2 patches should
contain these changes.
I hope we won't forget it. A missing atexit isn't a very obvious bug.
I was going to reply
On Thu, May 12, 2011 at 12:12 PM, Paolo Bonzini pbonz...@redhat.com wrote:
On 05/12/2011 12:38 PM, Kevin Wolf wrote:
I don't want to add qemu-img/qemu-io things yet because we don't have
a block layer user for coroutines yet. The qcow2 patches should
contain these changes.
I hope we won't
On 05/12/2011 01:15 PM, Stefan Hajnoczi wrote:
It's just for completeness to make tools like valgrind happy. Sure,
the kernel will reclaim memory and we're just burning CPU by freeing
this stuff;).
But valgrind will not complain about reachable memory still allocated at
exit, at least not
On Thu, May 12, 2011 at 12:18 PM, Paolo Bonzini pbonz...@redhat.com wrote:
On 05/12/2011 01:15 PM, Stefan Hajnoczi wrote:
It's just for completeness to make tools like valgrind happy. Sure,
the kernel will reclaim memory and we're just burning CPU by freeing
this stuff;).
But valgrind will