* Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> wrote:

> Ingo,
> 	Here's an update of the group fairness patch I have been 
> working on. Its against CFS v16 (sched-cfs-v2.6.22-rc4-mm2-v16.patch).

thanks!

> The core idea is to reuse much of CFS logic to apply fairness at 
> higher hierarchical levels (user, container etc). In this regard CFS 
> engine has been modified to deal with generic 'schedulable entities'. 
> The patches introduce two essential structures in CFS core:
> 
> 	- struct sched_entity
> 		- represents a schedulable entity in a hierarchy. Task
> 		  is the lowest element in this hierarchy. Its ancestors
> 		  could be user, container etc. This structure stores
> 		  essential attributes/execution-history (wait_runtime etc) 
> 		  which is required by CFS engine to provide fairness between
> 		  'struct sched_entities' at the same hierarchy.
> 
> 	- struct lrq
> 		- represents (per-cpu) runqueue in which ready-to-run 
> 		  'struct sched_entities' are queued. The fair clock
> 		  calculation is split to be per 'struct lrq'.
> 
> Here's a brief description of the patches to follow:
> 
> Patches 1-3 introduce the essential changes in CFS core to support 
> this concept. They rework existing code w/o any (intended!) change in 
> functionality.

i currently have these 3 patches applied to the CFS queue and it's 
looking pretty good so far! If it continues to be problem-free i'll 
release them as part of -v17, just to check that they truly have no bad 
side-effects (they shouldnt). Then #4 can go into -v18.

i've attached my current -v17 tree - it should apply mostly cleanly 
ontop of the -mm queue (with a minor number of fixups). Could you 
refactor the remaining 3 patches ontop of this base? There's some 
rejects in the last 3 patches due to the update_load_fair() change.

> Patch 4 fixes some bad interaction between SCHED_RT and SCHED_NORMAL
> tasks in current CFS.

btw., the plan here is to turn off 'bit 0' in sched_features: i.e. to 
use the precise statistics to calculate lrq->cpu_load[], not the 
timer-irq-sampled imprecise statistics. Dmitry has fixed a couple of 
bugs in it that made it not work too well in previous CFS versions, but 
now we are ready to turn it on for -v17. (indeed in my tree it's already 
turned on - i.e. sched_features defaults to '14')

> Patch 5 introduces basic changes in CFS core to support group 
> fairness.
>
> Patch 6 hooks up scheduler with container patches in mm (as an 
> interface for task-grouping functionality).

ok. Kirill, how do you like Srivatsa's current approach? Would be nice 
to kill two birds with the same stone, if possible :-)

> Note: I have noticed that running lat_ctx in a loop for 10 times 
> doesnt give me good results. Basically I expected the loop to take 
> same time for both users (when run simultaneously), whereas it was 
> taking different times for different users. I think this can be solved 
> by increasing sysctl_sched_runtime_limit at group level (to remeber 
> execution history over a longer period).

you'll get the best hackbench results by using SCHED_BATCH:

   chrt -b 0 ./hackbench 10

or indeed increasing the runtime_limit would work too.

	Ingo

Index: linux/Makefile
===================================================================
--- linux.orig/Makefile
+++ linux/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 21
-EXTRAVERSION = .4-cfs-v16
+EXTRAVERSION = .4-cfs-v17
 NAME = Nocturnal Monster Puppy
 
 # *DOCUMENTATION*
Index: linux/fs/proc/array.c
===================================================================
--- linux.orig/fs/proc/array.c
+++ linux/fs/proc/array.c
@@ -319,7 +319,7 @@ static clock_t task_utime(struct task_st
 	 * Use CFS's precise accounting, if available:
 	 */
 	if (!(sysctl_sched_features & 128)) {
-		u64 temp = (u64)nsec_to_clock_t(p->sum_exec_runtime);
+		u64 temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
 
 		if (total) {
 			temp *= utime;
@@ -341,7 +341,7 @@ static clock_t task_stime(struct task_st
 	 * by userspace grows monotonically - apps rely on that):
 	 */
 	if (!(sysctl_sched_features & 128))
-		stime = nsec_to_clock_t(p->sum_exec_runtime) - task_utime(p);
+		stime = nsec_to_clock_t(p->se.sum_exec_runtime) - task_utime(p);
 
 	return stime;
 }
Index: linux/include/linux/sched.h
===================================================================
--- linux.orig/include/linux/sched.h
+++ linux/include/linux/sched.h
@@ -534,8 +534,7 @@ struct signal_struct {
 
 #define rt_prio(prio)		unlikely((prio) < MAX_RT_PRIO)
 #define rt_task(p)		rt_prio((p)->prio)
-#define batch_task(p)		(unlikely((p)->policy == SCHED_BATCH))
-#define is_rt_policy(p)		((p) != SCHED_NORMAL && (p) != SCHED_BATCH)
+#define is_rt_policy(p)		((p) == SCHED_FIFO || (p) == SCHED_RR)
 #define has_rt_policy(p)	unlikely(is_rt_policy((p)->policy))
 
 /*
@@ -819,6 +818,29 @@ struct sched_class {
 	void (*task_new) (struct rq *rq, struct task_struct *p);
 };
 
+/* CFS stats for a schedulable entity (task, task-group etc) */
+struct sched_entity {
+	int load_weight;	/* for niceness load balancing purposes */
+	int on_rq;
+	struct rb_node run_node;
+	u64 wait_start_fair;
+	u64 wait_start;
+	u64 exec_start;
+	u64 sleep_start, sleep_start_fair;
+	u64 block_start;
+	u64 sleep_max;
+	u64 block_max;
+	u64 exec_max;
+	u64 wait_max;
+	u64 last_ran;
+
+	s64 wait_runtime;
+	u64 sum_exec_runtime;
+	s64 fair_key;
+	s64 sum_wait_runtime, sum_sleep_runtime;
+	unsigned long wait_runtime_overruns, wait_runtime_underruns;
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	struct thread_info *thread_info;
@@ -833,33 +855,15 @@ struct task_struct {
 	int oncpu;
 #endif
 #endif
-	int load_weight;	/* for niceness load balancing purposes */
 
 	int prio, static_prio, normal_prio;
-	int on_rq;
 	struct list_head run_list;
-	struct rb_node run_node;
+	struct sched_entity se;
 
 	unsigned short ioprio;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	unsigned int btrace_seq;
 #endif
-	/* CFS scheduling class statistics fields: */
-	u64 wait_start_fair;
-	u64 wait_start;
-	u64 exec_start;
-	u64 sleep_start, sleep_start_fair;
-	u64 block_start;
-	u64 sleep_max;
-	u64 block_max;
-	u64 exec_max;
-	u64 wait_max;
-
-	s64 wait_runtime;
-	u64 sum_exec_runtime;
-	s64 fair_key;
-	s64 sum_wait_runtime, sum_sleep_runtime;
-	unsigned long wait_runtime_overruns, wait_runtime_underruns;
 
 	unsigned long policy;
 	cpumask_t cpus_allowed;
Index: linux/kernel/exit.c
===================================================================
--- linux.orig/kernel/exit.c
+++ linux/kernel/exit.c
@@ -112,7 +112,7 @@ static void __exit_signal(struct task_st
 		sig->maj_flt += tsk->maj_flt;
 		sig->nvcsw += tsk->nvcsw;
 		sig->nivcsw += tsk->nivcsw;
-		sig->sum_sched_runtime += tsk->sum_exec_runtime;
+		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
 
Index: linux/kernel/posix-cpu-timers.c
===================================================================
--- linux.orig/kernel/posix-cpu-timers.c
+++ linux/kernel/posix-cpu-timers.c
@@ -249,7 +249,7 @@ static int cpu_clock_sample_group_locked
 		cpu->sched = p->signal->sum_sched_runtime;
 		/* Add in each other live thread.  */
 		while ((t = next_thread(t)) != p) {
-			cpu->sched += t->sum_exec_runtime;
+			cpu->sched += t->se.sum_exec_runtime;
 		}
 		cpu->sched += sched_ns(p);
 		break;
@@ -467,7 +467,7 @@ static void cleanup_timers(struct list_h
 void posix_cpu_timers_exit(struct task_struct *tsk)
 {
 	cleanup_timers(tsk->cpu_timers,
-		       tsk->utime, tsk->stime, tsk->sum_exec_runtime);
+		       tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
 
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
@@ -475,7 +475,7 @@ void posix_cpu_timers_exit_group(struct 
 	cleanup_timers(tsk->signal->cpu_timers,
 		       cputime_add(tsk->utime, tsk->signal->utime),
 		       cputime_add(tsk->stime, tsk->signal->stime),
-		       tsk->sum_exec_runtime + tsk->signal->sum_sched_runtime);
+		     tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime);
 }
 
 
@@ -536,7 +536,7 @@ static void process_timer_rebalance(stru
 		nsleft = max_t(unsigned long long, nsleft, 1);
 		do {
 			if (likely(!(t->flags & PF_EXITING))) {
-				ns = t->sum_exec_runtime + nsleft;
+				ns = t->se.sum_exec_runtime + nsleft;
 				if (t->it_sched_expires == 0 ||
 				    t->it_sched_expires > ns) {
 					t->it_sched_expires = ns;
@@ -1004,7 +1004,7 @@ static void check_thread_timers(struct t
 		struct cpu_timer_list *t = list_entry(timers->next,
 						      struct cpu_timer_list,
 						      entry);
-		if (!--maxfire || tsk->sum_exec_runtime < t->expires.sched) {
+		if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
 			tsk->it_sched_expires = t->expires.sched;
 			break;
 		}
@@ -1049,7 +1049,7 @@ static void check_process_timers(struct 
 	do {
 		utime = cputime_add(utime, t->utime);
 		stime = cputime_add(stime, t->stime);
-		sum_sched_runtime += t->sum_exec_runtime;
+		sum_sched_runtime += t->se.sum_exec_runtime;
 		t = next_thread(t);
 	} while (t != tsk);
 	ptime = cputime_add(utime, stime);
@@ -1208,7 +1208,7 @@ static void check_process_timers(struct 
 				t->it_virt_expires = ticks;
 			}
 
-			sched = t->sum_exec_runtime + sched_left;
+			sched = t->se.sum_exec_runtime + sched_left;
 			if (sched_expires && (t->it_sched_expires == 0 ||
 					      t->it_sched_expires > sched)) {
 				t->it_sched_expires = sched;
@@ -1300,7 +1300,7 @@ void run_posix_cpu_timers(struct task_st
 
 	if (UNEXPIRED(prof) && UNEXPIRED(virt) &&
 	    (tsk->it_sc