Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-23 Thread Eric Dumazet
On Wed, Oct 23, 2019 at 11:30 AM Cong Wang wrote: > > On Wed, Oct 23, 2019 at 11:14 AM Eric Dumazet wrote: > > > In case you misunderstand, the CPU profiling I used is captured > > > during 256 parallel TCP_STREAM. > > > > When I asked you the workload, you gave me TCP_RR output, not TCP_STREAM :

Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-23 Thread Cong Wang
On Wed, Oct 23, 2019 at 11:14 AM Eric Dumazet wrote: > > In case you misunderstand, the CPU profiling I used is captured > > during 256 parallel TCP_STREAM. > > When I asked you the workload, you gave me TCP_RR output, not TCP_STREAM :/ > > "A single netperf TCP_RR could _also_ confirm the improve

Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-23 Thread Eric Dumazet
On Wed, Oct 23, 2019 at 10:40 AM Cong Wang wrote: > > On Tue, Oct 22, 2019 at 7:15 PM Eric Dumazet wrote: > > > > On Tue, Oct 22, 2019 at 6:10 PM Cong Wang wrote: > > > > > > On Tue, Oct 22, 2019 at 4:24 PM Eric Dumazet wrote: > > > > > > > > On Tue, Oct 22, 2019 at 4:11 PM Cong Wang > > > >

Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-23 Thread Cong Wang
On Tue, Oct 22, 2019 at 7:15 PM Eric Dumazet wrote: > > On Tue, Oct 22, 2019 at 6:10 PM Cong Wang wrote: > > > > On Tue, Oct 22, 2019 at 4:24 PM Eric Dumazet wrote: > > > > > > On Tue, Oct 22, 2019 at 4:11 PM Cong Wang > > > wrote: > > > > > > > > Currently RTO, TLP and PROBE0 all share a same

Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-22 Thread Eric Dumazet
On Tue, Oct 22, 2019 at 6:10 PM Cong Wang wrote: > > On Tue, Oct 22, 2019 at 4:24 PM Eric Dumazet wrote: > > > > On Tue, Oct 22, 2019 at 4:11 PM Cong Wang wrote: > > > > > > Currently RTO, TLP and PROBE0 all share a same timer instance > > > in kernel and use icsk->icsk_pending to dispatch the w

Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-22 Thread Cong Wang
On Tue, Oct 22, 2019 at 4:24 PM Eric Dumazet wrote: > > On Tue, Oct 22, 2019 at 4:11 PM Cong Wang wrote: > > > > Currently RTO, TLP and PROBE0 all share a same timer instance > > in kernel and use icsk->icsk_pending to dispatch the work. > > This causes spinlock contention when resetting the time

Re: [Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-22 Thread Eric Dumazet
On Tue, Oct 22, 2019 at 4:11 PM Cong Wang wrote: > > Currently RTO, TLP and PROBE0 all share a same timer instance > in kernel and use icsk->icsk_pending to dispatch the work. > This causes spinlock contention when resetting the timer is > too frequent, as clearly shown in the perf report: > >

[Patch net-next 3/3] tcp: decouple TLP timer from RTO timer

2019-10-22 Thread Cong Wang
Currently RTO, TLP and PROBE0 all share a same timer instance in kernel and use icsk->icsk_pending to dispatch the work. This causes spinlock contention when resetting the timer is too frequent, as clearly shown in the perf report: 61.72%61.71% swapper [kernel.kallsyms]