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@xxxxxxxxxx>
---
block/blk-mq.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1adfe4824ef5..ff9a4bf16858 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>
@@ -2036,6 +2037,8 @@ 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;
@@ -2050,7 +2053,17 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
put_cpu();
}
- kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
+ /*
+ * Avoid housekeeping CPUs scheduling a worker on a non-housekeeping
+ * CPU
+ */
+ if (tick_nohz_full_enabled() && housekeeping_cpu(smp_processor_id(),
+ HK_FLAG_WQ))
+ work_cpu = 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));
}
--
2.20.1
