hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8YB4M CVE: N/A

---------------------------------

When NOHZ_FULL is enabled, such as in HPC situation, CPUs are divided into housekeeping CPUs and non-housekeeping CPUs. Non-housekeeping CPUs are NOHZ_FULL CPUs and are often monopolized by the userspace process, such HPC application process. Any sort of interruption is not expected.

blk_mq_hctx_next_cpu() selects each cpu in 'hctx->cpumask' alternately to schedule the work thread blk_mq_run_work_fn(). When 'hctx->cpumask' contains housekeeping CPU and non-housekeeping CPU at the same time, a housekeeping CPU, which want to request a IO, may schedule a worker on a non-housekeeping CPU. This may affect the performance of the userspace application running on non-housekeeping CPUs.

So let's just schedule the worker thread on the current CPU when the current CPU is housekeeping CPU.

Signed-off-by: Xiongfeng Wang wangxiongfeng2@huawei.com

Conflicts: block/blk-mq.c include/linux/sched/isolation.h Signed-off-by: Xiongfeng Wang wangxiongfeng2@huawei.com --- block/blk-mq.c | 11 ++++++++++- include/linux/sched/isolation.h | 3 +++ kernel/sched/isolation.c | 8 ++++++++ 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c index 6ab7f360ff2a..52cfbeb75355 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -24,6 +24,7 @@ #include <linux/sched/sysctl.h> #include <linux/sched/topology.h> #include <linux/sched/signal.h> +#include <linux/sched/isolation.h> #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> @@ -2214,9 +2215,17 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) */ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { + int work_cpu; + if (unlikely(blk_mq_hctx_stopped(hctx))) return; - kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, + + if (enhanced_isolcpus && tick_nohz_full_enabled() && + housekeeping_cpu(raw_smp_processor_id(), HK_TYPE_WQ)) + work_cpu = raw_smp_processor_id(); + else + work_cpu = blk_mq_hctx_next_cpu(hctx); + kblockd_mod_delayed_work_on(work_cpu, &hctx->run_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index fe1a46f30d24..3894e74e8dc5 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -19,6 +19,7 @@ enum hk_type { };

#ifdef CONFIG_CPU_ISOLATION +extern bool enhanced_isolcpus; DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_type type); extern const struct cpumask *housekeeping_cpumask(enum hk_type type); @@ -29,6 +30,8 @@ extern void __init housekeeping_init(void);

#else

+#define enhanced_isolcpus 0 + static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 373d42c707bc..3884c245faf5 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -239,3 +239,11 @@ static int __init housekeeping_isolcpus_setup(char *str) return housekeeping_setup(str, flags); } __setup("isolcpus=", housekeeping_isolcpus_setup); + +bool enhanced_isolcpus; +static int __init enhanced_isolcpus_setup(char *str) +{ + enhanced_isolcpus = true; + return 0; +} +__setup("enhanced_isolcpus", enhanced_isolcpus_setup);