sched: revert load_balance_monitor() changes

The following commits cause a number of regressions:

  commit 58e2d4ca581167c2a079f4ee02be2f0bc52e8729
  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
  Date:   Fri Jan 25 21:08:00 2008 +0100
  sched: group scheduling, change how cpu load is calculated

  commit 6b2d7700266b9402e12824e11e0099ae6a4a6a79
  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
  Date:   Fri Jan 25 21:08:00 2008 +0100
  sched: group scheduler, fix fairness of cpu bandwidth allocation for task groups

Namely:
 - very frequent wakeups on SMP, reported by PowerTop users.
 - cacheline trashing on (large) SMP
 - some latencies larger than 500ms

While there is a mergeable patch to fix the latter, the former issues
are not fixable in a manner suitable for .25 (we're at -rc3 now).

Hence we revert them and try again in v2.6.26.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
CC: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Tested-by: Alexey Zaytsev <alexey.zaytsev@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 70 insertions, 350 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index f06950c8a6ce..dcd553cc4ee8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -174,41 +174,6 @@ struct task_group {
         struct sched_entity **se;
         /* runqueue "owned" by this group on each cpu */
         struct cfs_rq **cfs_rq;
-
-        /*
-         * shares assigned to a task group governs how much of cpu bandwidth
-         * is allocated to the group. The more shares a group has, the more is
-         * the cpu bandwidth allocated to it.
-         *
-         * For ex, lets say that there are three task groups, A, B and C which
-         * have been assigned shares 1000, 2000 and 3000 respectively. Then,
-         * cpu bandwidth allocated by the scheduler to task groups A, B and C
-         * should be:
-         *
-         *      Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66%
-         *      Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33%
-         *      Bw(C) = 3000/(1000+2000+3000) * 100 = 50%
-         *
-         * The weight assigned to a task group's schedulable entities on every
-         * cpu (task_group.se[a_cpu]->load.weight) is derived from the task
-         * group's shares. For ex: lets say that task group A has been
-         * assigned shares of 1000 and there are two CPUs in a system. Then,
-         *
-         *  tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000;
-         *
-         * Note: It's not necessary that each of a task's group schedulable
-         *       entity have the same weight on all CPUs. If the group
-         *       has 2 of its tasks on CPU0 and 1 task on CPU1, then a
-         *       better distribution of weight could be:
-         *
-         *      tg_A->se[0]->load.weight = 2/3 * 2000 = 1333
-         *      tg_A->se[1]->load.weight = 1/2 * 2000 =  667
-         *
-         * rebalance_shares() is responsible for distributing the shares of a
-         * task groups like this among the group's schedulable entities across
-         * cpus.
-         *
-         */
         unsigned long shares;
 #endif
 
@@ -250,22 +215,12 @@ static DEFINE_SPINLOCK(task_group_lock);
 static DEFINE_MUTEX(doms_cur_mutex);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
-/* kernel thread that runs rebalance_shares() periodically */
-static struct task_struct *lb_monitor_task;
-static int load_balance_monitor(void *unused);
-#endif
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares);
-
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD   (2*NICE_0_LOAD)
 #else
 # define INIT_TASK_GROUP_LOAD   NICE_0_LOAD
 #endif
 
-#define MIN_GROUP_SHARES        2
-
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
 
@@ -1245,16 +1200,6 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
 #endif
 
-static inline void inc_cpu_load(struct rq *rq, unsigned long load)
-{
-        update_load_add(&rq->load, load);
-}
-
-static inline void dec_cpu_load(struct rq *rq, unsigned long load)
-{
-        update_load_sub(&rq->load, load);
-}
-
 #ifdef CONFIG_SMP
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1272,14 +1217,26 @@ static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
 
 #define sched_class_highest (&rt_sched_class)
 
-static void inc_nr_running(struct rq *rq)
+static inline void inc_load(struct rq *rq, const struct task_struct *p)
+{
+        update_load_add(&rq->load, p->se.load.weight);
+}
+
+static inline void dec_load(struct rq *rq, const struct task_struct *p)
+{
+        update_load_sub(&rq->load, p->se.load.weight);
+}
+
+static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
         rq->nr_running++;
+        inc_load(rq, p);
 }
 
-static void dec_nr_running(struct rq *rq)
+static void dec_nr_running(struct task_struct *p, struct rq *rq)
 {
         rq->nr_running--;
+        dec_load(rq, p);
 }
 
 static void set_load_weight(struct task_struct *p)
@@ -1371,7 +1328,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
                 rq->nr_uninterruptible--;
 
         enqueue_task(rq, p, wakeup);
-        inc_nr_running(rq);
+        inc_nr_running(p, rq);
 }
 
 /*
@@ -1383,7 +1340,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
                 rq->nr_uninterruptible++;
 
         dequeue_task(rq, p, sleep);
-        dec_nr_running(rq);
+        dec_nr_running(p, rq);
 }
 
 /**
@@ -2023,7 +1980,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                  * management (if any):
                  */
                 p->sched_class->task_new(rq, p);
-                inc_nr_running(rq);
+                inc_nr_running(p, rq);
         }
         check_preempt_curr(rq, p);
 #ifdef CONFIG_SMP
@@ -4362,8 +4319,10 @@ void set_user_nice(struct task_struct *p, long nice)
                 goto out_unlock;
         }
         on_rq = p->se.on_rq;
-        if (on_rq)
+        if (on_rq) {
                 dequeue_task(rq, p, 0);
+                dec_load(rq, p);
+        }
 
         p->static_prio = NICE_TO_PRIO(nice);
         set_load_weight(p);
@@ -4373,6 +4332,7 @@ void set_user_nice(struct task_struct *p, long nice)
 
         if (on_rq) {
                 enqueue_task(rq, p, 0);
+                inc_load(rq, p);
                 /*
                  * If the task increased its priority or is running and
                  * lowered its priority, then reschedule its CPU:
@@ -7087,21 +7047,6 @@ void __init sched_init_smp(void)
         if (set_cpus_allowed(current, non_isolated_cpus) < 0)
                 BUG();
         sched_init_granularity();
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-        if (nr_cpu_ids == 1)
-                return;
-
-        lb_monitor_task = kthread_create(load_balance_monitor, NULL,