Skip to contentSkip to conversation

sched/core: Make idle_cpu return 0 if doing softirq work

RFC PATCH NAK Jonathan Davies 3 participants 5 messages Jul 18, 2014 – Jul 22, 2014 Scheduler

lore
Share & tools
lore
#0 lore raw

RFC PATCH 1/1 sched/core: Make idle_cpu return 0 if doing softirq work

The current implementation of idle_cpu only considers tasks that might be in the CPU's runqueue. If there's nothing in the specified CPU's runqueue, it will return 1. But if the CPU is doing work in the softirq context, it is wrong for idle_cpu to return 1. This patch makes it return 0.

I observed this to be a problem with a device driver kicking a kthread by executing wake_up from softirq context. The Completely Fair Scheduler's select_task_rq_fair was looking for an "idle sibling" of the CPU executing it by calling select_idle_sibling, passing the executing CPU as the 'target' parameter. The first thing that select_idle_sibling does is to check whether the 'target' CPU is idle, using idle_cpu, and to return that CPU if so. Despite the executing CPU being busy in softirq context, idle_cpu was returning 1, meaning that the scheduler would consistently try to run the kthread on the same CPU as the kick came from. Given that the softirq work was on-going, this led to a multi-millisecond delay before the scheduler eventually realised it should migrate the kthread to a different CPU.

A solution to this problem would be to make idle_cpu return 0 when the CPU is running in softirq context. I haven't got a patch for that because I couldn't find an easy way of querying whether an arbitrary CPU is doing this. (Perhaps I should look at the per-CPU softirq_work_list[]...?)

Instead, the following patch is a partial solution, only handling the case when the currently-executing CPU is in softirq context. This was sufficient to solve the problem I observed.

---
 kernel/sched/core.c | 4 ++++
 1 file changed, 4 insertions(+)
kernel/sched/core.c +4 -0
index 7bc599d..4ee58c4 100644
@@ -3169,6 +3169,10 @@ int idle_cpu(int cpu)
 		return 0;
 #endif
 
+	/* When the current CPU is in softirq context, count it as non-idle */
+	if (cpu == smp_processor_id() && in_softirq())
+		return 0;
+
 	return 1;
 }
 
Signature · 1 line
1.9.1
maintainer NAK
#1 lore raw
Quoted 5 lines · Jonathan Davies

The current implementation of idle_cpu only considers tasks that might be in the CPU's runqueue. If there's nothing in the specified CPU's runqueue, it will return 1. But if the CPU is doing work in the softirq context, it is wrong for idle_cpu to return 1. This patch makes it return 0.

Quoted 11 lines

I observed this to be a problem with a device driver kicking a kthread by executing wake_up from softirq context. The Completely Fair Scheduler's select_task_rq_fair was looking for an "idle sibling" of the CPU executing it by calling select_idle_sibling, passing the executing CPU as the 'target' parameter. The first thing that select_idle_sibling does is to check whether the 'target' CPU is idle, using idle_cpu, and to return that CPU if so. Despite the executing CPU being busy in softirq context, idle_cpu was returning 1, meaning that the scheduler would consistently try to run the kthread on the same CPU as the kick came from. Given that the softirq work was on-going, this led to a multi-millisecond delay before the scheduler eventually realised it should migrate the kthread to a different CPU.

If your softirq takes _that_ long its broken anyhow.

Quoted 4 lines

A solution to this problem would be to make idle_cpu return 0 when the CPU is running in softirq context. I haven't got a patch for that because I couldn't find an easy way of querying whether an arbitrary CPU is doing this. (Perhaps I should look at the per-CPU softirq_work_list[]...?)

in_serving_softirq()?

Quoted 3 lines

Instead, the following patch is a partial solution, only handling the case when the currently-executing CPU is in softirq context. This was sufficient to solve the problem I observed.

NAK, IRQ and SoftIRQ are outside of what the scheduler can control, so for its purpose the CPU is indeed idle.

#2 lore raw
Quoted 18 lines · Peter Zijlstra
Quoted 5 lines · Jonathan Davies

The current implementation of idle_cpu only considers tasks that might be in the CPU's runqueue. If there's nothing in the specified CPU's runqueue, it will return 1. But if the CPU is doing work in the softirq context, it is wrong for idle_cpu to return 1. This patch makes it return 0.

Quoted 11 lines

I observed this to be a problem with a device driver kicking a kthread by executing wake_up from softirq context. The Completely Fair Scheduler's select_task_rq_fair was looking for an "idle sibling" of the CPU executing it by calling select_idle_sibling, passing the executing CPU as the 'target' parameter. The first thing that select_idle_sibling does is to check whether the 'target' CPU is idle, using idle_cpu, and to return that CPU if so. Despite the executing CPU being busy in softirq context, idle_cpu was returning 1, meaning that the scheduler would consistently try to run the kthread on the same CPU as the kick came from. Given that the softirq work was on-going, this led to a multi-millisecond delay before the scheduler eventually realised it should migrate the kthread to a different CPU.

Quoted 1 line

If your softirq takes _that_ long its broken anyhow.

Modern NICs can sustain 40 Gb/s of traffic. For network device drivers that use NAPI, polling is done in softirq context. At this data-rate, the per-packet processing overhead means means that a lot of CPU time is spent in softirq.

(CCing Dave and Eric for their thoughts about long-running softirq due to NAPI. The example I gave above was of xen-netback sending data to another virtual interface at a high rate.)

Quoted 6 lines
Quoted 4 lines

A solution to this problem would be to make idle_cpu return 0 when the CPU is running in softirq context. I haven't got a patch for that because I couldn't find an easy way of querying whether an arbitrary CPU is doing this. (Perhaps I should look at the per-CPU softirq_work_list[]...?)

in_serving_softirq()?

That's probably more appropriate, but only tells us about the currently executing CPU, rather than what other CPUs are doing.

Quoted 6 lines
Quoted 3 lines

Instead, the following patch is a partial solution, only handling the case when the currently-executing CPU is in softirq context. This was sufficient to solve the problem I observed.

NAK, IRQ and SoftIRQ are outside of what the scheduler can control, so for its purpose the CPU is indeed idle.

The scheduler can't control those things, but surely it wants to make the best possible placement for the things it can control? So it seems odd to me that it would ignore relevant information about the resources it can use. As I observed, it leads to pathological behaviour, and is easily fixed.

Jonathan

maintainer
#3 lore raw
Quoted 10 lines · Jonathan Davies
Quoted 1 line

If your softirq takes _that_ long its broken anyhow.

Modern NICs can sustain 40 Gb/s of traffic. For network device drivers that use NAPI, polling is done in softirq context. At this data-rate, the per-packet processing overhead means means that a lot of CPU time is spent in softirq.

(CCing Dave and Eric for their thoughts about long-running softirq due to NAPI. The example I gave above was of xen-netback sending data to another virtual interface at a high rate.)

So thing more or less assume that softirq handling (as ran off the tail of hardirqs) does not take longer than a tick. Otherwise things start to pile up and you get all kinds of nasty. Not to mention you get into horrid latencies etc..

How hard would you scream if people ran multi tick hard interrupts? Why do you then think its OK so do the effective same thing?

Quoted 11 lines
Quoted 6 lines
Quoted 3 lines

Instead, the following patch is a partial solution, only handling the case when the currently-executing CPU is in softirq context. This was sufficient to solve the problem I observed.

NAK, IRQ and SoftIRQ are outside of what the scheduler can control, so for its purpose the CPU is indeed idle.

The scheduler can't control those things, but surely it wants to make the best possible placement for the things it can control? So it seems odd to me that it would ignore relevant information about the resources it can use. As I observed, it leads to pathological behaviour, and is easily fixed.

We already lower the compute capacity due to irq/softirq overhead, if we don't correctly handle that then we need to fix that. But as far as the scheduler is concerned that cpu is _IDLE_. We didn't put anything on, and therefore there's not anything on, end of story.

#4 lore raw
In reply to Jonathan Davies

Hi Jonathan

Quoted 34 lines · Jonathan Davies
Quoted 31 lines · Peter Zijlstra
Quoted 27 lines · Jonathan Davies

The current implementation of idle_cpu only considers tasks that might be in the
CPU's runqueue. If there's nothing in the specified CPU's runqueue, it will
return 1. But if the CPU is doing work in the softirq context, it is wrong for
idle_cpu to return 1. This patch makes it return 0.

I observed this to be a problem with a device driver kicking a kthread by executing wake_up from softirq context. The Completely Fair Scheduler's select_task_rq_fair was looking for an "idle sibling" of the CPU executing it by
calling select_idle_sibling, passing the executing CPU as the 'target' parameter. The first thing that select_idle_sibling does is to check whether the
'target' CPU is idle, using idle_cpu, and to return that CPU if so. Despite the
executing CPU being busy in softirq context, idle_cpu was returning 1, meaning
that the scheduler would consistently try to run the kthread on the same CPU as
the kick came from. Given that the softirq work was on-going, this led to a
multi-millisecond delay before the scheduler eventually realised it should
migrate the kthread to a different CPU.

Quoted 8 lines
Quoted 1 line

If your softirq takes _that_ long its broken anyhow.

Modern NICs can sustain 40 Gb/s of traffic. For network device drivers that use NAPI, polling is done in softirq context. At this data-rate, the per-packet processing overhead means means that a lot of CPU time is spent in softirq.

Perhaps fcoe_percpu_receive_thread (linux/drivers/scsi/fcoe/fcoe.c) can help you.

Hillf