Re: [PATCH v3 1/2] net: add support for threaded NAPI polling

2020-08-30 Thread Sebastian Gottschall
Am 22.08.2020 um 03:49 schrieb Jakub Kicinski: On Fri, 21 Aug 2020 21:01:50 +0200 Felix Fietkau wrote: For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI poll function does not perform well. Since NAPI poll is bound to the CPU it was scheduled from, we can easily end

Re: [PATCH v3 1/2] net: add support for threaded NAPI polling

2020-08-25 Thread Wei Wang
On Fri, Aug 21, 2020 at 12:03 PM Felix Fietkau wrote: > > For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI > poll function does not perform well. Since NAPI poll is bound to the CPU it > was scheduled from, we can easily end up with a few very busy CPUs spending > most

Re: [PATCH v3 1/2] net: add support for threaded NAPI polling

2020-08-22 Thread Eric Dumazet
On 8/21/20 6:49 PM, Jakub Kicinski wrote: > On Fri, 21 Aug 2020 21:01:50 +0200 Felix Fietkau wrote: >> For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI >> poll function does not perform well. Since NAPI poll is bound to the CPU it >> was scheduled from, we can easily

Re: [PATCH v3 1/2] net: add support for threaded NAPI polling

2020-08-21 Thread Jakub Kicinski
On Fri, 21 Aug 2020 21:01:50 +0200 Felix Fietkau wrote: > For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI > poll function does not perform well. Since NAPI poll is bound to the CPU it > was scheduled from, we can easily end up with a few very busy CPUs spending > most