Messages in this thread | | | Date | Thu, 28 Mar 2024 18:27:20 +0200 | Subject | Re: [PATCH 1/1] sched/fair: allow disabling newidle_balance with sched_relax_domain_level | From | Vitalii Bursov <> |
| |
On 28.03.24 16:43, Vincent Guittot wrote: > On Thu, 28 Mar 2024 at 01:31, Vitalii Bursov <vitaly@bursov.com> wrote: >> >> Change relax_domain_level checks so that it would be possible >> to exclude all domains from newidle balancing. >> >> This matches the behavior described in the documentation: >> -1 no request. use system default or follow request of others. >> 0 no search. >> 1 search siblings (hyperthreads in a core). >> >> "2" enables levels 0 and 1, level_max excludes the last (level_max) >> level, and level_max+1 includes all levels. > > I was about to say that max+1 is useless because it's the same as -1 > but it's not exactly the same because it can supersede the system wide > default_relax_domain_level. I wonder if one should be able to enable > more levels than what the system has set by default.
I don't know is such systems exist, but cpusets.rst suggests that increasing it beyoud the default value is possible: > If your situation is: > > - The migration costs between each cpu can be assumed considerably > small(for you) due to your special application's behavior or > special hardware support for CPU cache etc. > - The searching cost doesn't have impact(for you) or you can make > the searching cost enough small by managing cpuset to compact etc. > - The latency is required even it sacrifices cache hit rate etc. > then increasing 'sched_relax_domain_level' would benefit you.
>> >> Signed-off-by: Vitalii Bursov <vitaly@bursov.com> >> --- >> kernel/cgroup/cpuset.c | 2 +- >> kernel/sched/debug.c | 1 + >> kernel/sched/topology.c | 2 +- >> 3 files changed, 3 insertions(+), 2 deletions(-) >> >> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c >> index 4237c874871..da24187c4e0 100644 >> --- a/kernel/cgroup/cpuset.c >> +++ b/kernel/cgroup/cpuset.c >> @@ -2948,7 +2948,7 @@ bool current_cpuset_is_being_rebound(void) >> static int update_relax_domain_level(struct cpuset *cs, s64 val) >> { >> #ifdef CONFIG_SMP >> - if (val < -1 || val >= sched_domain_level_max) >> + if (val < -1 || val > sched_domain_level_max + 1) >> return -EINVAL; >> #endif >> >> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c >> index 8d5d98a5834..8454cd4e5e1 100644 >> --- a/kernel/sched/debug.c >> +++ b/kernel/sched/debug.c >> @@ -423,6 +423,7 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent) >> >> #undef SDM >> >> + debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level); > > IMO, this should be a separate patch as it's not part of the fix
Thanks, I'll split it.
>> debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops); >> debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops); >> } >> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c >> index 99ea5986038..3127c9b30af 100644 >> --- a/kernel/sched/topology.c >> +++ b/kernel/sched/topology.c >> @@ -1468,7 +1468,7 @@ static void set_domain_attribute(struct sched_domain *sd, >> } else >> request = attr->relax_domain_level; >> >> - if (sd->level > request) { >> + if (sd->level >= request) { > > good catch and worth : > Fixes: 9ae7ab20b483 ("sched/topology: Don't set SD_BALANCE_WAKE on > cpuset domain relax") > Will add this. Thanks.
> >> /* Turn off idle balance on this domain: */ >> sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); >> } >> -- >> 2.20.1 >>
| |