Re: [PATCH] mempool: cache align mempool cache objects

2022-10-27 Thread Olivier Matz
On Thu, Oct 27, 2022 at 02:11:29PM +0200, Morten Brørup wrote: > > From: Olivier Matz [mailto:olivier.m...@6wind.com] > > Sent: Thursday, 27 October 2022 13.43 > > > > On Thu, Oct 27, 2022 at 11:22:07AM +0200, Morten Brørup wrote: > > > > From: Olivier Matz [mailto:olivier.m...@6wind.com] > > > >

RE: [PATCH] mempool: cache align mempool cache objects

2022-10-27 Thread Morten Brørup
> From: Olivier Matz [mailto:olivier.m...@6wind.com] > Sent: Thursday, 27 October 2022 13.43 > > On Thu, Oct 27, 2022 at 11:22:07AM +0200, Morten Brørup wrote: > > > From: Olivier Matz [mailto:olivier.m...@6wind.com] > > > Sent: Thursday, 27 October 2022 10.35 > > > > > > Hi Morten, > > > > > > On

Re: [PATCH] mempool: cache align mempool cache objects

2022-10-27 Thread Olivier Matz
On Thu, Oct 27, 2022 at 11:22:07AM +0200, Morten Brørup wrote: > > From: Olivier Matz [mailto:olivier.m...@6wind.com] > > Sent: Thursday, 27 October 2022 10.35 > > > > Hi Morten, > > > > On Wed, Oct 26, 2022 at 04:44:36PM +0200, Morten Brørup wrote: > > > Add __rte_cache_aligned to the objs array

RE: [PATCH] mempool: cache align mempool cache objects

2022-10-27 Thread Morten Brørup
> From: Olivier Matz [mailto:olivier.m...@6wind.com] > Sent: Thursday, 27 October 2022 10.35 > > Hi Morten, > > On Wed, Oct 26, 2022 at 04:44:36PM +0200, Morten Brørup wrote: > > Add __rte_cache_aligned to the objs array. > > > > It makes no difference in the general case, but if get/put operatio

Re: [PATCH] mempool: cache align mempool cache objects

2022-10-27 Thread Olivier Matz
Hi Morten, On Wed, Oct 26, 2022 at 04:44:36PM +0200, Morten Brørup wrote: > Add __rte_cache_aligned to the objs array. > > It makes no difference in the general case, but if get/put operations are > always 32 objects, it will reduce the number of memory (or last level > cache) accesses from five

Re: [PATCH] mempool: cache align mempool cache objects

2022-10-26 Thread Andrew Rybchenko
On 10/26/22 17:44, Morten Brørup wrote: Add __rte_cache_aligned to the objs array. It makes no difference in the general case, but if get/put operations are always 32 objects, it will reduce the number of memory (or last level cache) accesses from five to four 64 B cache lines for every get/put