From: Rik van Riel <riel@xxxxxxxxxx>
Ensure that cpus specified with the isolcpus= boot commandline
option stay outside of the load balancing in the kernel scheduler.
Operations like load balancing can introduce unwanted latencies,
which is exactly what the isolcpus= commandline is there to prevent.
Previously, simply creating a new cpuset, without even touching the
cpuset.cpus field inside the new cpuset, would undo the effects of
isolcpus=, by creating a scheduler domain spanning the whole system,
and setting up load balancing inside that domain. The cpuset root
cpuset.cpus file is read-only, so there was not even a way to undo
that effect.
This does not impact the majority of cpusets users, since isolcpus=
is a fairly specialized feature used for realtime purposes.
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Clark Williams <williams@xxxxxxxxxx>
Cc: Li Zefan <lizefan@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Luiz Capitulino <lcapitulino@xxxxxxxxxx>
Cc: cgroups@xxxxxxxxxxxxxxx
Signed-off-by: Rik van Riel <riel@xxxxxxxxxx>
---
include/linux/sched.h | 2 ++
kernel/cpuset.c | 13 +++++++++++--
kernel/sched/core.c | 2 +-
3 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index cb5cdc777c8a..af1b32a5ddcc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1038,6 +1038,8 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new);
+extern cpumask_var_t cpu_isolated_map;
+
/* Allocate an array of sched domains, for partition_sched_domains(). */
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 64b257f6bca2..1ad63fa37cb4 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -625,6 +625,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
int csn; /* how many cpuset ptrs in csa so far */
int i, j, k; /* indices for partition finding loops */
cpumask_var_t *doms; /* resulting partition; i.e. sched domains */
+ cpumask_var_t non_isolated_cpus; /* load balanced CPUs */
struct sched_domain_attr *dattr; /* attributes for custom domains */
int ndoms = 0; /* number of sched domains in result */
int nslot; /* next empty doms[] struct cpumask slot */
@@ -634,6 +635,10 @@ static int generate_sched_domains(cpumask_var_t **domains,
dattr = NULL;
csa = NULL;
+ if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
+ goto done;
+ cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+
/* Special case for the 99% of systems with one, full, sched domain */
if (is_sched_load_balance(&top_cpuset)) {
ndoms = 1;
@@ -646,7 +651,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
*dattr = SD_ATTR_INIT;
update_domain_attr_tree(dattr, &top_cpuset);
}
- cpumask_copy(doms[0], top_cpuset.effective_cpus);
+ cpumask_and(doms[0], top_cpuset.effective_cpus,
+ non_isolated_cpus);
goto done;
}
@@ -669,7 +675,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
* the corresponding sched domain.
*/
if (!cpumask_empty(cp->cpus_allowed) &&
- !is_sched_load_balance(cp))
+ !(is_sched_load_balance(cp) &&
+ cpumask_intersects(cp->cpus_allowed, non_isolated_cpus)))
continue;
if (is_sched_load_balance(cp))
@@ -751,6 +758,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
if (apn == b->pn) {
cpumask_or(dp, dp, b->effective_cpus);
+ cpumask_and(dp, dp, non_isolated_cpus);
if (dattr)
update_domain_attr_tree(dattr + nslot, b);
@@ -763,6 +771,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
BUG_ON(nslot != ndoms);
done:
+ free_cpumask_var(non_isolated_cpus);
kfree(csa);
/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 97fe79cf613e..6069f3703240 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5831,7 +5831,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
}
/* cpus with isolated domains */
-static cpumask_var_t cpu_isolated_map;
+cpumask_var_t cpu_isolated_map;
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
