On 31 March 2015 at 12:25, Viresh Kumar viresh.kumar@linaro.org wrote:
While queuing a timer, we try to migrate it to a non-idle core if the local core is idle, but we don't try that if the timer is re-armed from its handler.
There were few unsolved problems due to which it was avoided until now. But there are cases where solving these problems can be useful. When the timer is always re-armed from its handler, it never migrates to other cores. And many a times, it ends up waking an idle core to just service the timer, which could have been handled by a non-idle core.
Peter suggested [1] few changes which can make that work and the first patch does exactly that. The second one is a minor improvement, that replaces 'running_timer' pointer with 'busy'. That variable was required as part of a sanity check during CPU hot-unplug operation. I was not sure if we should drop this extra variable ('running_timer' or 'busy') and the sanity check.
Peter reminded me that I failed to tell if it really worked or not :)
So yes it worked. I tested this on a Dual-core ARM cortex-A15 board with 5 timers getting re-armed 100 times each from their handler.
Most of the time the remote CPU was idle (along with the local one) and so migration didn't happen.
But as and when the local CPU was idle and remote one wasn't, timers got successfully migrated.
My branches are also tested by Fengguang's build-bot, and in case of any of wreckage on other machines, we will be informed :)
-- viresh