Messages in this thread | | | Date | Thu, 9 Feb 2012 19:32:59 +0100 | From | Frederic Weisbecker <> | Subject | Re: [v7 0/8] Reduce cross CPU IPI interference |
| |
On Thu, Feb 09, 2012 at 10:26:02AM -0600, Christoph Lameter wrote: > On Thu, 9 Feb 2012, Frederic Weisbecker wrote: > > > > The vmstat timer only makes sense when the OS is doing something on the > > > processor. Otherwise if no counters are incremented and the page and slab > > > allocator caches are empty then there is no need to run the vmstat timer. > > > > So this is a typical example of a timer we want to shutdown when the CPU is idle > > but we want to keep it running when we run in adaptive tickless mode (ie: shutdown > > the tick while the CPU is busy). > > You can also shut it down when the cpu is busy and not doing any system > calls. If the percpu differentials are all zero (because you just ran the > timer f.e.) and there are no system activities that would change the > counters then there is no point in running the vmstat timer.
Yep. I believe we can probably find that timer pattern elsewhere as well. A class of userspace/idle defferable timers.
| |