This is Suresh's patch with some modifications.
--
SUSE Labs, Novell Inc.
Remove degenerate scheduler domains during the sched-domain init.
For example on x86_64, we always have NUMA configured in. On Intel EM64T
systems, top most sched domain will be of NUMA and with only one sched_group in
it.
With fork/exec balances(recent Nick's fixes in -mm tree), we always endup
taking wrong decisions because of this topmost domain (as it contains only
one group and find_idlest_group always returns NULL). We will endup loading
HT package completely first, letting active load balance kickin and correct it.
In general, this patch also makes sense with out recent Nick's fixes
in -mm.
Signed-off-by: Suresh Siddha <[email protected]>
Modified to account for more than just sched_groups when scanning for
degenerate domains by Nick Piggin. Allow a runqueue's sd to go NULL, which
required small changes to the smtnice code.
Signed-off-by: Nick Piggin <[email protected]>
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c 2005-04-05 16:38:21.000000000 +1000
+++ linux-2.6/kernel/sched.c 2005-04-05 18:39:09.000000000 +1000
@@ -2583,11 +2583,15 @@ out:
#ifdef CONFIG_SCHED_SMT
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
- struct sched_domain *sd = this_rq->sd;
+ struct sched_domain *tmp, *sd = NULL;
cpumask_t sibling_map;
int i;
+
+ for_each_domain(this_cpu, tmp)
+ if (tmp->flags & SD_SHARE_CPUPOWER)
+ sd = tmp;
- if (!(sd->flags & SD_SHARE_CPUPOWER))
+ if (!sd)
return;
/*
@@ -2628,13 +2632,17 @@ static inline void wake_sleeping_depende
static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
- struct sched_domain *sd = this_rq->sd;
+ struct sched_domain *tmp, *sd = NULL;
cpumask_t sibling_map;
prio_array_t *array;
int ret = 0, i;
task_t *p;
- if (!(sd->flags & SD_SHARE_CPUPOWER))
+ for_each_domain(this_cpu, tmp)
+ if (tmp->flags & SD_SHARE_CPUPOWER)
+ sd = tmp;
+
+ if (!sd)
return 0;
/*
@@ -4604,6 +4612,11 @@ static void sched_domain_debug(struct sc
{
int level = 0;
+ if (!sd) {
+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+ return;
+ }
+
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
do {
@@ -4809,6 +4822,50 @@ static void init_sched_domain_sysctl(voi
}
#endif
+static int __devinit sd_degenerate(struct sched_domain *sd)
+{
+ if (cpus_weight(sd->span) == 1)
+ return 1;
+
+ /* Following flags need at least 2 groups */
+ if (sd->flags & (SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC)) {
+ if (sd->groups != sd->groups->next)
+ return 0;
+ }
+
+ /* Following flags don't use groups */
+ if (sd->flags & (SD_WAKE_IDLE |
+ SD_WAKE_AFFINE |
+ SD_WAKE_BALANCE))
+ return 0;
+
+ return 1;
+}
+
+static int __devinit sd_parent_degenerate(struct sched_domain *sd,
+ struct sched_domain *parent)
+{
+ unsigned long cflags = sd->flags, pflags = parent->flags;
+
+ if (sd_degenerate(parent))
+ return 1;
+
+ if (!cpus_equal(sd->span, parent->span))
+ return 0;
+
+ /* Does parent contain flags not in child? */
+ /* WAKE_BALANCE is a subset of WAKE_AFFINE */
+ if (cflags & SD_WAKE_AFFINE)
+ pflags &= ~SD_WAKE_BALANCE;
+ if ((~sd->flags) & parent->flags)
+ return 0;
+
+ return 1;
+}
+
/*
* Attach the domain 'sd' to 'cpu' as its base domain. Callers must
* hold the hotplug lock.
@@ -4819,6 +4876,19 @@ void __devinit cpu_attach_domain(struct
unsigned long flags;
runqueue_t *rq = cpu_rq(cpu);
int local = 1;
+ struct sched_domain *tmp;
+
+ /* Remove the sched domains which do not contribute to scheduling. */
+ for (tmp = sd; tmp; tmp = tmp->parent) {
+ struct sched_domain *parent = tmp->parent;
+ if (!parent)
+ break;
+ if (sd_parent_degenerate(tmp, parent))
+ tmp->parent = parent->parent;
+ }
+
+ if (sd_degenerate(sd))
+ sd = sd->parent;
sched_domain_debug(sd, cpu);
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]