The patch titled
sched: stagger load balancing in build_sched_domains
has been added to the -mm tree. Its filename is
sched-stagger-load-balancing-in-build_sched_domains.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: sched: stagger load balancing in build_sched_domains
From: Christoph Lameter <clameter@xxxxxxx>
Instead of dealing with the staggering of load balancing during actual load
balancing we just do it once when the sched domains set up.
Signed-off-by: Christoph Lameter <clameter@xxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: "Siddha, Suresh B" <suresh.b.siddha@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
kernel/sched.c | 26 +++++++++++++++++---------
1 files changed, 17 insertions(+), 9 deletions(-)
diff -puN kernel/sched.c~sched-stagger-load-balancing-in-build_sched_domains kernel/sched.c
--- a/kernel/sched.c~sched-stagger-load-balancing-in-build_sched_domains
+++ a/kernel/sched.c
@@ -2848,17 +2848,10 @@ static void update_load(struct rq *this_
*
* Balancing parameters are set up in arch_init_sched_domains.
*/
-
-/* Don't have all balancing operations going off at once: */
-static inline unsigned long cpu_offset(int cpu)
-{
- return jiffies + cpu * HZ / NR_CPUS;
-}
-
static void
rebalance_tick(int this_cpu, struct rq *this_rq, enum idle_type idle)
{
- unsigned long interval, j = cpu_offset(this_cpu);
+ unsigned long interval;
struct sched_domain *sd;
for_each_domain(this_cpu, sd) {
@@ -2874,7 +2867,7 @@ rebalance_tick(int this_cpu, struct rq *
if (unlikely(!interval))
interval = 1;
- if (j - sd->last_balance >= interval) {
+ if (jiffies - sd->last_balance >= interval) {
if (load_balance(this_cpu, this_rq, sd, idle)) {
/*
* We've pulled tasks over so either we're no
@@ -6332,6 +6325,16 @@ static void init_sched_groups_power(int
}
/*
+ * Calculate jiffies start to use for each cpu. On sched domain
+ * initialization this jiffy value is used to stagger the load balancing
+ * of the cpus so that they do not load balance all at at the same time.
+ */
+static inline unsigned long cpu_offset(int cpu)
+{
+ return jiffies + cpu * HZ / NR_CPUS;
+}
+
+/*
* Build sched domains for a given set of cpus and attach the sched domains
* to the individual cpus
*/
@@ -6387,6 +6390,7 @@ static int build_sched_domains(const cpu
sd->span = *cpu_map;
group = cpu_to_allnodes_group(i, cpu_map);
sd->groups = &sched_group_allnodes[group];
+ sd->last_balance = cpu_offset(i);
p = sd;
} else
p = NULL;
@@ -6395,6 +6399,7 @@ static int build_sched_domains(const cpu
*sd = SD_NODE_INIT;
sd->span = sched_domain_node_span(cpu_to_node(i));
sd->parent = p;
+ sd->last_balance = cpu_offset(i);
if (p)
p->child = sd;
cpus_and(sd->span, sd->span, *cpu_map);
@@ -6406,6 +6411,7 @@ static int build_sched_domains(const cpu
*sd = SD_CPU_INIT;
sd->span = nodemask;
sd->parent = p;
+ sd->last_balance = cpu_offset(i);
if (p)
p->child = sd;
sd->groups = &sched_group_phys[group];
@@ -6418,6 +6424,7 @@ static int build_sched_domains(const cpu
sd->span = cpu_coregroup_map(i);
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
+ sd->last_balance = cpu_offset(i);
p->child = sd;
sd->groups = &sched_group_core[group];
#endif
@@ -6430,6 +6437,7 @@ static int build_sched_domains(const cpu
sd->span = cpu_sibling_map[i];
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
+ sd->last_balance = cpu_offset(i);
p->child = sd;
sd->groups = &sched_group_cpus[group];
#endif
_
Patches currently in -mm which might be from clameter@xxxxxxx are
create-compat_sys_migrate_pages.patch
wire-up-sys_migrate_pages.patch
memory-page-alloc-minor-cleanups.patch
memory-page-alloc-minor-cleanups-fix.patch
get-rid-of-zone_table.patch
deal-with-cases-of-zone_dma-meaning-the-first-zone.patch
get-rid-of-zone_table-fix-3.patch
introduce-config_zone_dma.patch
optional-zone_dma-in-the-vm.patch
optional-zone_dma-in-the-vm-no-gfp_dma-check-in-the-slab-if-no-config_zone_dma-is-set.patch
optional-zone_dma-in-the-vm-no-gfp_dma-check-in-the-slab-if-no-config_zone_dma-is-set-reduce-config_zone_dma-ifdefs.patch
optional-zone_dma-for-ia64.patch
remove-zone_dma-remains-from-parisc.patch
remove-zone_dma-remains-from-sh-sh64.patch
set-config_zone_dma-for-arches-with-generic_isa_dma.patch
zoneid-fix-up-calculations-for-zoneid_pgshift.patch
radix-tree-rcu-lockless-readside.patch
sched-avoid-taking-rq-lock-in-wake_priority_sleeper.patch
sched-disable-interrupts-for-locking-in-load_balance.patch
sched-extract-load-calculation-from-rebalance_tick.patch
sched-stagger-load-balancing-in-build_sched_domains.patch
sched-move-idle-stat-calculation-into-rebalance_tick.patch
sched-use-tasklet-to-call-balancing.patch
sched-call-tasklet-less-frequently.patch
zvc-support-nr_slab_reclaimable--nr_slab_unreclaimable-swap_prefetch.patch
reduce-max_nr_zones-swap_prefetch-remove-incorrect-use-of-zone_highmem.patch
numa-add-zone_to_nid-function-swap_prefetch.patch
readahead-state-based-method-aging-accounting.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
