Re: [PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Eric Dumazet
On Fri, 2012-10-19 at 13:38 +0400, Stanislav Kinsbursky wrote: > 19.10.2012 11:56, Eric Dumazet пишет: > > I wonder if some applications relied on our idr, assuming they would get > > low values for their timer id. > > (We could imagine some applications use a table indexed by the timer id) > >

Re: [PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Stanislav Kinsbursky
19.10.2012 11:56, Eric Dumazet пишет: I wonder if some applications relied on our idr, assuming they would get low values for their timer id. (We could imagine some applications use a table indexed by the timer id) Hmm. Probably, this particular case can be optimised by tuning min_id to id of

Re: [PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Eric Dumazet
On Fri, 2012-10-19 at 11:50 +0400, Stanislav Kinsbursky wrote: > v4: > 1) a couple of coding style fixes (lines over 80 characters) > > v3: > 1) hash calculation simlified to improve perfomance. > > v2: > 1) Hash table become RCU-friendly. Hash table search now done under RCU lock > protection.

[PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Stanislav Kinsbursky
v4: 1) a couple of coding style fixes (lines over 80 characters) v3: 1) hash calculation simlified to improve perfomance. v2: 1) Hash table become RCU-friendly. Hash table search now done under RCU lock protection. I've tested scalability on KVM with 4 CPU. The testing environment was build of

[PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Stanislav Kinsbursky
v4: 1) a couple of coding style fixes (lines over 80 characters) v3: 1) hash calculation simlified to improve perfomance. v2: 1) Hash table become RCU-friendly. Hash table search now done under RCU lock protection. I've tested scalability on KVM with 4 CPU. The testing environment was build of

Re: [PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Eric Dumazet
On Fri, 2012-10-19 at 11:50 +0400, Stanislav Kinsbursky wrote: v4: 1) a couple of coding style fixes (lines over 80 characters) v3: 1) hash calculation simlified to improve perfomance. v2: 1) Hash table become RCU-friendly. Hash table search now done under RCU lock protection. This

Re: [PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Stanislav Kinsbursky
19.10.2012 11:56, Eric Dumazet пишет: I wonder if some applications relied on our idr, assuming they would get low values for their timer id. (We could imagine some applications use a table indexed by the timer id) Hmm. Probably, this particular case can be optimised by tuning min_id to id of

Re: [PATCH v4] posix timers: allocate timer id per process

2012-10-19 Thread Eric Dumazet
On Fri, 2012-10-19 at 13:38 +0400, Stanislav Kinsbursky wrote: 19.10.2012 11:56, Eric Dumazet пишет: I wonder if some applications relied on our idr, assuming they would get low values for their timer id. (We could imagine some applications use a table indexed by the timer id) Hmm.