diff options
| author | Peter Zijlstra | 2025-11-07 17:01:31 +0100 |
|---|---|---|
| committer | Peter Zijlstra | 2025-11-17 17:13:16 +0100 |
| commit | 33cf66d88306663d16e4759e9d24766b0aaa2e17 (patch) | |
| tree | fd2bb005a2826c142798f5da1f14b91a36250e47 /kernel/sched/fair.c | |
| parent | 08d473dd8718e4a4d698b1113a14a40ad64a909b (diff) | |
sched/fair: Proportional newidle balance
Add a randomized algorithm that runs newidle balancing proportional to
its success rate.
This improves schbench significantly:
6.18-rc4: 2.22 Mrps/s
6.18-rc4+revert: 2.04 Mrps/s
6.18-rc4+revert+random: 2.18 Mrps/S
Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%:
6.17: -6%
6.17+revert: 0%
6.17+revert+random: -1%
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Chris Mason <clm@meta.com>
Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com
Link: https://patch.msgid.link/20251107161739.770122091@infradead.org
Diffstat (limited to 'kernel/sched/fair.c')
| -rw-r--r-- | kernel/sched/fair.c | 44 |
1 files changed, 40 insertions, 4 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index abcbb67dd785..1855975b8248 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -12224,11 +12224,27 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) +{ + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) { unsigned long next_decay = sd->last_decay_max_lb_cost + HZ; unsigned long now = jiffies; + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the @@ -12276,7 +12292,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -12912,6 +12928,22 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = sched_balance_rq(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -12919,10 +12951,14 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - update_newidle_cost(sd, domain_cost); - curr_cost += domain_cost; t0 = t1; + + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* |