Commit f8700df7 authored by Suresh Siddha's avatar Suresh Siddha Committed by Ingo Molnar

sched: fix broken SMT/MC optimizations

On a four package system with HT - HT load balancing optimizations were
broken.  For example, if two tasks end up running on two logical threads
of one of the packages, scheduler is not able to pull one of the tasks
to a completely idle package.

In this scenario, for nice-0 tasks, imbalance calculated by scheduler
will be 512 and find_busiest_queue() will return 0 (as each cpu's load
is 1024 > imbalance and has only one task running).

Similarly MC scheduler optimizations also get fixed with this patch.

[ mingo@elte.hu: restored fair balancing by increasing the fuzz and
                 adding it back to the power decision, without the /2
                 factor. ]
Signed-off-by: default avatarSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent efe567fc
...@@ -681,7 +681,7 @@ enum cpu_idle_type { ...@@ -681,7 +681,7 @@ enum cpu_idle_type {
#define SCHED_LOAD_SHIFT 10 #define SCHED_LOAD_SHIFT 10
#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) #define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
#define SCHED_LOAD_SCALE_FUZZ (SCHED_LOAD_SCALE >> 1) #define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */ #define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */
......
...@@ -2517,7 +2517,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, ...@@ -2517,7 +2517,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
* a think about bumping its value to force at least one task to be * a think about bumping its value to force at least one task to be
* moved * moved
*/ */
if (*imbalance + SCHED_LOAD_SCALE_FUZZ < busiest_load_per_task/2) { if (*imbalance + SCHED_LOAD_SCALE_FUZZ < busiest_load_per_task) {
unsigned long tmp, pwr_now, pwr_move; unsigned long tmp, pwr_now, pwr_move;
unsigned int imbn; unsigned int imbn;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment