Commit 425fdbca authored by Xiongfeng Wang's avatar Xiongfeng Wang
Browse files

blk-mq: avoid housekeeping CPUs scheduling a worker on a non-housekeeping CPU 

hulk inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZBTV


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: default avatarXiongfeng Wang <wangxiongfeng2@huawei.com>
parent bcf0a9c4

block/blk-mq.c

+11 −1
Original line number Diff line number Diff line
@@ -23,6 +23,9 @@ 
#include <linux/sched/sysctl.h>

#include <linux/sched/topology.h>

#include <linux/sched/signal.h>

#ifndef __GENKSYMS__

#include <linux/sched/isolation.h>

#endif

#include <linux/delay.h>

#include <linux/crash_dump.h>

#include <linux/prefetch.h>
@@ -1676,6 +1679,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) 
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,

					unsigned long msecs)

{

	int work_cpu;



	if (unlikely(blk_mq_hctx_stopped(hctx)))

		return;
@@ -1697,7 +1702,12 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, 
	if (!percpu_ref_tryget(&hctx->queue->q_usage_counter))

		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_FLAG_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));

	percpu_ref_put(&hctx->queue->q_usage_counter);

}

include/linux/sched/isolation.h

+2 −0
Original line number Diff line number Diff line
@@ -18,6 +18,7 @@ enum hk_flags { 
};



#ifdef CONFIG_CPU_ISOLATION

extern bool enhanced_isolcpus;

DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);

extern int housekeeping_any_cpu(enum hk_flags flags);

extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
@@ -28,6 +29,7 @@ extern void __init housekeeping_init(void); 


#else



#define enhanced_isolcpus 0

static inline int housekeeping_any_cpu(enum hk_flags flags)

{

	return smp_processor_id();

kernel/sched/isolation.c

+8 −0
Original line number Diff line number Diff line
@@ -198,3 +198,11 @@ 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);