Messages in this thread | | | Date | Sat, 6 Aug 2016 08:05:41 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH 3/3] locking/rwsem: Scan the wait_list for readers only once |
| |
* Davidlohr Bueso <dave@stgolabs.net> wrote:
> When wanting to wakeup readers, __rwsem_mark_wakeup() currently > iterates the wait_list twice while looking to wakeup the first N > queued reader-tasks. While this can be quite inefficient, it was > there such that a awoken reader would be first and foremost > acknowledged by the lock counter. > > Keeping the same logic, we can further benefit from the use of > wake_qs and avoid entirely the first wait_list iteration that sets > the counter as wake_up_process() isn't going to occur right away, > and therefore we maintain the counter->list order of going about > things. > > Other than saving cycles with O(n) "scanning", this change also > nicely cleans up a good chunk of __rwsem_mark_wakeup(); both > visually and less tedious to read. > > For example, the following improvements where seen on some will > it scale microbenchmarks, on a 48-core Haswell: > > v4.7 v4.7-rwsem-v1 > Hmean signal1-processes-8 5792691.42 ( 0.00%) 5771971.04 ( -0.36%) > Hmean signal1-processes-12 6081199.96 ( 0.00%) 6072174.38 ( -0.15%) > Hmean signal1-processes-21 3071137.71 ( 0.00%) 3041336.72 ( -0.97%) > Hmean signal1-processes-48 3712039.98 ( 0.00%) 3708113.59 ( -0.11%) > Hmean signal1-processes-79 4464573.45 ( 0.00%) 4682798.66 ( 4.89%) > Hmean signal1-processes-110 4486842.01 ( 0.00%) 4633781.71 ( 3.27%) > Hmean signal1-processes-141 4611816.83 ( 0.00%) 4692725.38 ( 1.75%) > Hmean signal1-processes-172 4638157.05 ( 0.00%) 4714387.86 ( 1.64%) > Hmean signal1-processes-203 4465077.80 ( 0.00%) 4690348.07 ( 5.05%) > Hmean signal1-processes-224 4410433.74 ( 0.00%) 4687534.43 ( 6.28%)
Please always make it clear in changelogs what the numbers mean, that higher numbers are better, etc. - so that people don't have to re-read it 2-3 times to figure out what it means.
Also, what are 'will it scale microbenchmarks'?
Thanks,
Ingo
| |