sched/topology: Optimize topology_span_sane()
Subsystems (2)
v2 cover sched/topology: Optimize topology_span_sane()
A soft lockup is being detected in build_sched_domains() on 32 socket Sapphire Rapids systems with 3840 processors.
topology_span_sane(), called by build_sched_domains(), checks that each processor's non-NUMA scheduling domains are completely equal or completely disjoint. If a non-NUMA scheduling domain partially overlaps another, scheduling groups can break.
This series adds for_each_cpu_from() as a generic cpumask macro to optimize topology_span_sane() by removing duplicate comparisons. The total number of comparisons is reduced from N * (N - 1) to
N * (N - 1) / 2 on each non-NUMA scheduling domain level, decreasing the boot time by approximately 20 seconds and preventing the soft lockup on the mentioned systems.
Changes in v2:
* 1/2: Change for_each_cpu()'s description.
* 2/2: Add more information to the commit message.
* https://lore.kernel.org/linux-kernel/[email protected]/T/
Kyle Meyer (2):
cpumask: Add for_each_cpu_from()
sched/topology: Optimize topology_span_sane()
include/linux/cpumask.h | 10 ++++++++++ kernel/sched/topology.c | 6 ++---- 2 files changed, 12 insertions(+), 4 deletions(-)
Signature · 1 line
2.44.0
PATCH v2 1/2 cpumask: Add for_each_cpu_from()
Add for_each_cpu_from() as a generic cpumask macro.
for_each_cpu_from() is the same as for_each_cpu(), except it starts at @cpu instead of zero.
--- include/linux/cpumask.h | 10 ++++++++++ 1 file changed, 10 insertions(+)
include/linux/cpumask.h +10 -0
@@ -368,6 +368,16 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta#define for_each_cpu_or (cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) +/** +* for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. +* @cpu: the (optionally unsigned) integer iterator +* @mask: the cpumask pointer +* +* After the loop, cpu is >= nr_cpu_ids. +*/ +#define for_each_cpu_from (cpu, mask) \ + for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) +/** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search
Signature · 1 line
2.44.0
Re: [PATCH v2 1/2] cpumask: Add for_each_cpu_from()
Quoted 7 lines · Kyle Meyer
Add
for_each_cpu_from()as a generic cpumask macro.
for_each_cpu_from()is the same asfor_each_cpu(), except it starts at @cpu instead of zero.Signed-off-by Kyle Meyer <[email protected]>Acked-by Yury Norov <[email protected]>
PATCH v2 2/2 sched/topology: Optimize topology_span_sane()
In reply to Kyle MeyerOptimize topology_span_sane() by removing duplicate comparisons.
Since topology_span_sane() is called inside of for_each_cpu(), each pervious CPU has already been compared against every other CPU. The current CPU only needs to be compared against higher-numbered CPUs.
The total number of comparisons is reduced from N * (N - 1) to N * (N - 1) / 2 on each non-NUMA scheduling domain level.
--- kernel/sched/topology.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
kernel/sched/topology.c +2 -4
@@ -2347,7 +2347,7 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_levestatic bool topology_span_sane (struct sched_domain_topology_level *tl,const struct cpumask *cpu_map,int cpu) { -int i; +int i = cpu +1 ;/* NUMA levels are allowed to overlap */ if (tl->flags &SDTL_OVERLAP )
@@ -2359,9 +2359,7 @@ static bool topology_span_sane(struct sched_domain_topology_level *tl,* breaking the sched_group lists - i.e. a later get_group() pass * breaks the linking done for an earlier span. */ -for_each_cpu (i, cpu_map) { -if (i == cpu) -continue ; +for_each_cpu_from (i, cpu_map) {/* * We should 'and' all those masks with 'cpu_map' to exactly * match the topology we're about to build, but that can only
Signature · 1 line
2.44.0
Quoted 4 lines · Kyle Meyer
Optimize
topology_span_sane()by removing duplicate comparisons.Since
topology_span_sane()is called inside offor_each_cpu(), each pervious CPU has already been compared against every other CPU. The
previous
Quoted 4 lines
current CPU only needs to be compared against higher-numbered CPUs.
The total number of comparisons is reduced from N * (N - 1) to N * (N - 1) / 2 on each non-NUMA scheduling domain level.
Thank you, now it makes sense.
Signature · 2 lines
With Best Regards, Andy Shevchenko
Quoted 7 lines · Andy Shevchenko
Quoted 4 lines · Kyle Meyer
Optimize
topology_span_sane()by removing duplicate comparisons.Since
topology_span_sane()is called inside offor_each_cpu(), each pervious CPU has already been compared against every other CPU. Theprevious
Thank you for pointing that out. Should I send an updated version or can a maintainer correct my mistake?
Quoted 6 lines
Quoted 4 lines
current CPU only needs to be compared against higher-numbered CPUs.
The total number of comparisons is reduced from N * (N - 1) to N * (N - 1) / 2 on each non-NUMA scheduling domain level.
Thank you, now it makes sense.
Thanks,
Kyle Meyer
Quoted 2 lines · Kyle Meyer
Quoted 1 line · Andy Shevchenko
On Wed, Apr 10, 2024 at 04:33:11PM -0500, Kyle Meyer wrote:
...
Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
Since
topology_span_sane()is called inside offor_each_cpu(), each pervious CPU has already been compared against every other CPU. Theprevious
Thank you for pointing that out. Should I send an updated version or can a maintainer correct my mistake?
Depends on the maintainer. I'm not the one here, don't expect answer from me.
Quoted 1 line
Quoted 1 line
Quoted 1 line
current CPU only needs to be compared against higher-numbered CPUs.
Signature · 2 lines
With Best Regards, Andy Shevchenko
Yury Norov
maintainerQuoted 9 lines · Andy Shevchenko
Quoted 2 lines · Kyle Meyer
Quoted 1 line · Andy Shevchenko
On Wed, Apr 10, 2024 at 04:33:11PM -0500, Kyle Meyer wrote:
...
Quoted 3 lines
Quoted 3 lines
Quoted 2 lines
Since
topology_span_sane()is called inside offor_each_cpu(), each pervious CPU has already been compared against every other CPU. The
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
previous
Thank you for pointing that out. Should I send an updated version or can a maintainer correct my mistake?
Depends on the maintainer. I'm not the one here, don't expect answer from me.
I like this rework, and I'll take it in bitmap-for-next for testing.
I see Vincent already acked it, so I can also move it upstream, if no objections from Peter, Juri and Ingo.
Thanks,
Yury
Quoted 6 lines · Kyle Meyer
Optimize
topology_span_sane()by removing duplicate comparisons.Since
topology_span_sane()is called inside offor_each_cpu(), each pervious CPU has already been compared against every other CPU. The current CPU only needs to be compared against higher-numbered CPUs.
Quoted 6 lines
The total number of comparisons is reduced from N * (N - 1) to N * (N - 1) / 2 on each non-NUMA scheduling domain level.
Signed-off-by Kyle Meyer <[email protected]>Reviewed-by Yury Norov <[email protected]>Acked-by Vincent Guittot <[email protected]>