On 21/07/21(Wed) 09:19, Martin Pieuchot wrote:
> On 23/06/21(Wed) 15:53, Alexander Bluhm wrote:
> > On Wed, Jun 23, 2021 at 11:40:18AM +0200, Martin Pieuchot wrote:
> > > Our previous attempt [0] to replace the current select(2) implementation
> > > has been reverted due to non-acceptable latency i
On 23/06/21(Wed) 15:53, Alexander Bluhm wrote:
> On Wed, Jun 23, 2021 at 11:40:18AM +0200, Martin Pieuchot wrote:
> > Our previous attempt [0] to replace the current select(2) implementation
> > has been reverted due to non-acceptable latency increase on sockets [1].
>
> I have measured the perfor
Alexander Bluhm wrote:
> On Wed, Jun 23, 2021 at 11:40:18AM +0200, Martin Pieuchot wrote:
> > Our previous attempt [0] to replace the current select(2) implementation
> > has been reverted due to non-acceptable latency increase on sockets [1].
>
> I have measured the performance difference.
>
>
On Wed, Jun 23, 2021 at 11:40:18AM +0200, Martin Pieuchot wrote:
> Our previous attempt [0] to replace the current select(2) implementation
> has been reverted due to non-acceptable latency increase on sockets [1].
I have measured the performance difference.
http://bluhm.genua.de/perform/results/
Our previous attempt [0] to replace the current select(2) implementation
has been reverted due to non-acceptable latency increase on sockets [1].
This performance regression has been analysed and partially addressed
thanks to bluhm@ and visa@. The cost of allocating/freeing 'knote'
descriptors ha
