Found an interactivity problem on a quad core test-system - simple CPU loops would occasionally delay the system un an unacceptable way. After much debugging with Peter Zijlstra it turned out that the problem is caused by the string of sched_clock() changes - they caused the CPU clock to jump backwards a bit - which confuses the scheduler arithmetics. (which is unsigned for performance reasons) So revert: # c300ba2: sched_clock: and multiplier for TSC to gtod drift # c0c8773: sched_clock: only update deltas with local reads. # af52a90: sched_clock: stop maximum check on NO HZ # f7cce27: sched_clock: widen the max and min time This solves the interactivity problems.
Showing the changes to kernel/time (1 of 3 files). Show all
Unified · Split
| @@ -289,7 +289,6 @@ void tick_nohz_stop_sched_tick(int inidle) · 288 unmodified lines | |||
| 289 | ts->tick_stopped = 1; | 289 | ts->tick_stopped = 1; |
| 290 | ts->idle_jiffies = last_jiffies; | 290 | ts->idle_jiffies = last_jiffies; |
| 291 | rcu_enter_nohz(); | 291 | rcu_enter_nohz(); |
| 292 | sched_clock_tick_stop(cpu); | ||
| 293 | } | 292 | } |
| 294 | 293 | ||
| 295 | /* | 294 | /* |
| @@ -392,7 +391,6 @@ void tick_nohz_restart_sched_tick(void) · 96 unmodified lines | |||
| 392 | select_nohz_load_balancer(0); | 391 | select_nohz_load_balancer(0); |
| 393 | now = ktime_get(); | 392 | now = ktime_get(); |
| 394 | tick_do_update_jiffies64(now); | 393 | tick_do_update_jiffies64(now); |
| 395 | sched_clock_tick_start(cpu); | ||
| 396 | cpu_clear(cpu, nohz_cpu_mask); | 394 | cpu_clear(cpu, nohz_cpu_mask); |
| 397 | 395 | ||
| 398 | /* | 396 | /* |