The patch titled
sched: fix jiffies comparisons in the balancing code
has been added to the -mm tree. Its filename is
sched-fix-jiffies-comparisons-in-the-balancing-code.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: fix jiffies comparisons in the balancing code
From: Christoph Lameter <clameter@xxxxxxx>
Fix up jiffy comparison function in the scheduler.
The jiffy comparison in reblance_tick() has always used a simple integer
comparison and I have followed that convention for the patchset that
rebalances sched domains via a tasklet.
However, jiffies may wrap around zero. If we do not use the time_after()
function then comparisons may not give the intended results.
Fix this up by using jiffy comparison functions.
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 | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff -puN kernel/sched.c~sched-fix-jiffies-comparisons-in-the-balancing-code kernel/sched.c
--- a/kernel/sched.c~sched-fix-jiffies-comparisons-in-the-balancing-code
+++ a/kernel/sched.c
@@ -2765,8 +2765,10 @@ static void idle_balance(int this_cpu, s
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance_newidle(this_cpu,
this_rq, sd);
- next_balance = min(next_balance,
- sd->last_balance + sd->balance_interval);
+ if (time_after(next_balance,
+ sd->last_balance + sd->balance_interval))
+ next_balance = sd->last_balance
+ + sd->balance_interval;
if (pulled_task)
break;
}
@@ -2890,7 +2892,7 @@ static void rebalance_domains(unsigned l
if (unlikely(!interval))
interval = 1;
- if (jiffies - sd->last_balance >= interval) {
+ if (time_after_eq(jiffies, sd->last_balance + interval)) {
if (load_balance(this_cpu, this_rq, sd, idle)) {
/*
* We've pulled tasks over so either we're no
@@ -2909,8 +2911,8 @@ static void rebalance_domains(unsigned l
* then idle_balance will reset next_balance so that we
* rebalance earlier.
*/
- next_balance = min(next_balance,
- sd->last_balance + interval);
+ if (time_after(next_balance, sd->last_balance + interval))
+ next_balance = sd->last_balance + interval;
}
this_rq->next_balance = next_balance;
}
@@ -3167,7 +3169,7 @@ void scheduler_tick(void)
task_running_tick(rq, p);
#ifdef CONFIG_SMP
update_load(rq);
- if (jiffies >= rq->next_balance)
+ if (time_after_eq(jiffies, rq->next_balance))
tasklet_schedule(&rebalance);
#endif
}
_
Patches currently in -mm which might be from clameter@xxxxxxx are
origin.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
sched-fix-jiffies-comparisons-in-the-balancing-code.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
