[PATCH 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[PATCH 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[riel]

Ensure that cpus specified with the isolcpus= boot commandline
option stay outside of the load balancing in the kernel scheduler.

Operations like load balancing can introduce unwanted latencies,
which is exactly what the isolcpus= commandline is there to prevent.

Previously, simply creating a new cpuset, without even touching the
cpuset.cpus field inside the new cpuset, would undo the effects of
isolcpus=, by creating a scheduler domain spanning the whole system,
and setting up load balancing inside that domain. The cpuset root
cpuset.cpus file is read-only, so there was not even a way to undo
that effect.

This does not impact the majority of cpusets users, since isolcpus=
is a fairly specialized feature used for realtime purposes.

[PATCH 1/2] cpusets,isolcpus: exclude isolcpus from load balancing in cpusets

[riel]

From: Rik van Riel <riel@redhat.com>

Ensure that cpus specified with the isolcpus= boot commandline
option stay outside of the load balancing in the kernel scheduler.

Operations like load balancing can introduce unwanted latencies,
which is exactly what the isolcpus= commandline is there to prevent.

Previously, simply creating a new cpuset, without even touching the
cpuset.cpus field inside the new cpuset, would undo the effects of
isolcpus=, by creating a scheduler domain spanning the whole system,
and setting up load balancing inside that domain. The cpuset root
cpuset.cpus file is read-only, so there was not even a way to undo
that effect.

This does not impact the majority of cpusets users, since isolcpus=
is a fairly specialized feature used for realtime purposes.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: cgroups@vger.kernel.org
Signed-off-by: Rik van Riel <riel@redhat.com>
---
 include/linux/sched.h |  2 ++
 kernel/cpuset.c       | 13 +++++++++++--
 kernel/sched/core.c   |  2 +-
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index cb5cdc777c8a..af1b32a5ddcc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1038,6 +1038,8 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
+extern cpumask_var_t cpu_isolated_map;
+
 /* Allocate an array of sched domains, for partition_sched_domains(). */
 cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 64b257f6bca2..1ad63fa37cb4 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -625,6 +625,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
 	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
+	cpumask_var_t non_isolated_cpus;  /* load balanced CPUs */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -634,6 +635,10 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	dattr = NULL;
 	csa = NULL;
 
+	if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
+		goto done;
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
 		ndoms = 1;
@@ -646,7 +651,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms[0], top_cpuset.effective_cpus);
+		cpumask_and(doms[0], top_cpuset.effective_cpus,
+				     non_isolated_cpus);
 
 		goto done;
 	}
@@ -669,7 +675,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 * the corresponding sched domain.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
-		    !is_sched_load_balance(cp))
+		    !(is_sched_load_balance(cp) &&
+		      cpumask_intersects(cp->cpus_allowed, non_isolated_cpus)))
 			continue;
 
 		if (is_sched_load_balance(cp))
@@ -751,6 +758,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 
 			if (apn == b->pn) {
 				cpumask_or(dp, dp, b->effective_cpus);
+				cpumask_and(dp, dp, non_isolated_cpus);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -763,6 +771,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	BUG_ON(nslot != ndoms);
 
 done:
+	free_cpumask_var(non_isolated_cpus);
 	kfree(csa);
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 97fe79cf613e..6069f3703240 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5831,7 +5831,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 }
 
 /* cpus with isolated domains */
-static cpumask_var_t cpu_isolated_map;
+cpumask_var_t cpu_isolated_map;
 
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
-- 
1.9.3

Re: [PATCH 1/2] cpusets,isolcpus: exclude isolcpus from load balancing in cpusets

[David Rientjes]

On Mon, 23 Feb 2015, riel@redhat.com wrote:

> From: Rik van Riel <riel@redhat.com>
> 
> Ensure that cpus specified with the isolcpus= boot commandline
> option stay outside of the load balancing in the kernel scheduler.
> 
> Operations like load balancing can introduce unwanted latencies,
> which is exactly what the isolcpus= commandline is there to prevent.
> 
> Previously, simply creating a new cpuset, without even touching the
> cpuset.cpus field inside the new cpuset, would undo the effects of
> isolcpus=, by creating a scheduler domain spanning the whole system,
> and setting up load balancing inside that domain. The cpuset root
> cpuset.cpus file is read-only, so there was not even a way to undo
> that effect.
> 
> This does not impact the majority of cpusets users, since isolcpus=
> is a fairly specialized feature used for realtime purposes.
> 
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Clark Williams <williams@redhat.com>
> Cc: Li Zefan <lizefan@huawei.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Luiz Capitulino <lcapitulino@redhat.com>
> Cc: cgroups@vger.kernel.org
> Signed-off-by: Rik van Riel <riel@redhat.com>

Tested-by: David Rientjes <rientjes@google.com>

[PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[riel]

From: Rik van Riel <riel@redhat.com>

The previous patch makes it so the code skips over isolcpus when
building scheduler load balancing domains. This makes it hard to
see for a user which of the CPUs in a cpuset are participating in
load balancing, and which ones are isolated cpus.

Add a cpuset.isolcpus file with info on which cpus in a cpuset are
isolated CPUs.

This file is read-only for now. In the future we could extend things
so isolcpus can be changed at run time, for the root (system wide)
cpuset only.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: cgroups@vger.kernel.org
Signed-off-by: Rik van Riel <riel@redhat.com>
---
 kernel/cpuset.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1ad63fa37cb4..19ad5d3377f8 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1563,6 +1563,7 @@ typedef enum {
 	FILE_MEMORY_PRESSURE,
 	FILE_SPREAD_PAGE,
 	FILE_SPREAD_SLAB,
+	FILE_ISOLCPUS,
 } cpuset_filetype_t;
 
 static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
@@ -1704,6 +1705,23 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	return retval ?: nbytes;
 }
 
+static size_t cpuset_sprintf_isolcpus(char *s, ssize_t pos, struct cpuset *cs)
+{
+	cpumask_var_t my_isolated_cpus;
+	ssize_t count;
+	
+	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
+		return 0;
+
+	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
+
+	count = cpulist_scnprintf(s, pos, my_isolated_cpus);
+
+	free_cpumask_var(my_isolated_cpus);
+
+	return count;
+}
+
 /*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
@@ -1738,6 +1756,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_EFFECTIVE_MEMLIST:
 		s += nodelist_scnprintf(s, count, cs->effective_mems);
 		break;
+	case FILE_ISOLCPUS:
+		s += cpuset_sprintf_isolcpus(s, count, cs);
+		break;
 	default:
 		ret = -EINVAL;
 		goto out_unlock;
@@ -1906,6 +1927,12 @@ static struct cftype files[] = {
 		.private = FILE_MEMORY_PRESSURE_ENABLED,
 	},
 
+	{
+		.name = "isolcpus",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_ISOLCPUS,
+	},
+
 	{ }	/* terminate */
 };
 
-- 
1.9.3

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[David Rientjes]

On Mon, 23 Feb 2015, riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org wrote:

> From: Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> 
> The previous patch makes it so the code skips over isolcpus when
> building scheduler load balancing domains. This makes it hard to
> see for a user which of the CPUs in a cpuset are participating in
> load balancing, and which ones are isolated cpus.
> 
> Add a cpuset.isolcpus file with info on which cpus in a cpuset are
> isolated CPUs.
> 
> This file is read-only for now. In the future we could extend things
> so isolcpus can be changed at run time, for the root (system wide)
> cpuset only.
> 
> Cc: Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
> Cc: Clark Williams <williams-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Cc: Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
> Cc: Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Cc: Luiz Capitulino <lcapitulino-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> Signed-off-by: Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> ---
>  kernel/cpuset.c | 27 +++++++++++++++++++++++++++
>  1 file changed, 27 insertions(+)
> 
> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
> index 1ad63fa37cb4..19ad5d3377f8 100644
> --- a/kernel/cpuset.c
> +++ b/kernel/cpuset.c
> @@ -1563,6 +1563,7 @@ typedef enum {
>  	FILE_MEMORY_PRESSURE,
>  	FILE_SPREAD_PAGE,
>  	FILE_SPREAD_SLAB,
> +	FILE_ISOLCPUS,
>  } cpuset_filetype_t;
>  
>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
> @@ -1704,6 +1705,23 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>  	return retval ?: nbytes;
>  }
>  
> +static size_t cpuset_sprintf_isolcpus(char *s, ssize_t pos, struct cpuset *cs)
> +{
> +	cpumask_var_t my_isolated_cpus;
> +	ssize_t count;
> +	

Whitespace.

> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
> +		return 0;
> +
> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
> +
> +	count = cpulist_scnprintf(s, pos, my_isolated_cpus);
> +
> +	free_cpumask_var(my_isolated_cpus);
> +
> +	return count;
> +}
> +
>  /*
>   * These ascii lists should be read in a single call, by using a user
>   * buffer large enough to hold the entire map.  If read in smaller
> @@ -1738,6 +1756,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>  	case FILE_EFFECTIVE_MEMLIST:
>  		s += nodelist_scnprintf(s, count, cs->effective_mems);
>  		break;
> +	case FILE_ISOLCPUS:
> +		s += cpuset_sprintf_isolcpus(s, count, cs);
> +		break;

This patch looks fine, and I think cpuset.effective_cpus and 
cpuset.isolcpus can be used well together, but will need updating now that 
commit e8e6d97c9b ("cpuset: use %*pb[l] to print bitmaps including 
cpumasks and nodemasks") has been merged which reworks this function.

It's a little unfortunate, though, that the user sees Cpus_allowed, 
cpuset.cpus, and cpuset.effective_cpus that include isolcpus and then have 
to check another cpulist for the isolcpus to see their sched domain, 
though.

>  	default:
>  		ret = -EINVAL;
>  		goto out_unlock;
> @@ -1906,6 +1927,12 @@ static struct cftype files[] = {
>  		.private = FILE_MEMORY_PRESSURE_ENABLED,
>  	},
>  
> +	{
> +		.name = "isolcpus",
> +		.seq_show = cpuset_common_seq_show,
> +		.private = FILE_ISOLCPUS,
> +	},
> +
>  	{ }	/* terminate */
>  };
>  

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[David Rientjes]

On Mon, 23 Feb 2015, riel@redhat.com wrote:

> From: Rik van Riel <riel@redhat.com>
> 
> The previous patch makes it so the code skips over isolcpus when
> building scheduler load balancing domains. This makes it hard to
> see for a user which of the CPUs in a cpuset are participating in
> load balancing, and which ones are isolated cpus.
> 
> Add a cpuset.isolcpus file with info on which cpus in a cpuset are
> isolated CPUs.
> 
> This file is read-only for now. In the future we could extend things
> so isolcpus can be changed at run time, for the root (system wide)
> cpuset only.
> 
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Clark Williams <williams@redhat.com>
> Cc: Li Zefan <lizefan@huawei.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Luiz Capitulino <lcapitulino@redhat.com>
> Cc: cgroups@vger.kernel.org
> Signed-off-by: Rik van Riel <riel@redhat.com>
> ---
>  kernel/cpuset.c | 27 +++++++++++++++++++++++++++
>  1 file changed, 27 insertions(+)
> 
> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
> index 1ad63fa37cb4..19ad5d3377f8 100644
> --- a/kernel/cpuset.c
> +++ b/kernel/cpuset.c
> @@ -1563,6 +1563,7 @@ typedef enum {
>  	FILE_MEMORY_PRESSURE,
>  	FILE_SPREAD_PAGE,
>  	FILE_SPREAD_SLAB,
> +	FILE_ISOLCPUS,
>  } cpuset_filetype_t;
>  
>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
> @@ -1704,6 +1705,23 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>  	return retval ?: nbytes;
>  }
>  
> +static size_t cpuset_sprintf_isolcpus(char *s, ssize_t pos, struct cpuset *cs)
> +{
> +	cpumask_var_t my_isolated_cpus;
> +	ssize_t count;
> +	

Whitespace.

> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
> +		return 0;
> +
> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
> +
> +	count = cpulist_scnprintf(s, pos, my_isolated_cpus);
> +
> +	free_cpumask_var(my_isolated_cpus);
> +
> +	return count;
> +}
> +
>  /*
>   * These ascii lists should be read in a single call, by using a user
>   * buffer large enough to hold the entire map.  If read in smaller
> @@ -1738,6 +1756,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>  	case FILE_EFFECTIVE_MEMLIST:
>  		s += nodelist_scnprintf(s, count, cs->effective_mems);
>  		break;
> +	case FILE_ISOLCPUS:
> +		s += cpuset_sprintf_isolcpus(s, count, cs);
> +		break;

This patch looks fine, and I think cpuset.effective_cpus and 
cpuset.isolcpus can be used well together, but will need updating now that 
commit e8e6d97c9b ("cpuset: use %*pb[l] to print bitmaps including 
cpumasks and nodemasks") has been merged which reworks this function.

It's a little unfortunate, though, that the user sees Cpus_allowed, 
cpuset.cpus, and cpuset.effective_cpus that include isolcpus and then have 
to check another cpulist for the isolcpus to see their sched domain, 
though.

>  	default:
>  		ret = -EINVAL;
>  		goto out_unlock;
> @@ -1906,6 +1927,12 @@ static struct cftype files[] = {
>  		.private = FILE_MEMORY_PRESSURE_ENABLED,
>  	},
>  
> +	{
> +		.name = "isolcpus",
> +		.seq_show = cpuset_common_seq_show,
> +		.private = FILE_ISOLCPUS,
> +	},
> +
>  	{ }	/* terminate */
>  };
>  

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[Rik van Riel]

On 02/24/2015 09:15 PM, David Rientjes wrote:
> On Mon, 23 Feb 2015, riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org wrote:
> 
>> From: Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>>
>> The previous patch makes it so the code skips over isolcpus when
>> building scheduler load balancing domains. This makes it hard to
>> see for a user which of the CPUs in a cpuset are participating in
>> load balancing, and which ones are isolated cpus.
>>
>> Add a cpuset.isolcpus file with info on which cpus in a cpuset are
>> isolated CPUs.
>>
>> This file is read-only for now. In the future we could extend things
>> so isolcpus can be changed at run time, for the root (system wide)
>> cpuset only.
>>
>> Cc: Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
>> Cc: Clark Williams <williams-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>> Cc: Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
>> Cc: Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>> Cc: Luiz Capitulino <lcapitulino-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>> Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
>> Signed-off-by: Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>> ---
>>  kernel/cpuset.c | 27 +++++++++++++++++++++++++++
>>  1 file changed, 27 insertions(+)
>>
>> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
>> index 1ad63fa37cb4..19ad5d3377f8 100644
>> --- a/kernel/cpuset.c
>> +++ b/kernel/cpuset.c
>> @@ -1563,6 +1563,7 @@ typedef enum {
>>  	FILE_MEMORY_PRESSURE,
>>  	FILE_SPREAD_PAGE,
>>  	FILE_SPREAD_SLAB,
>> +	FILE_ISOLCPUS,
>>  } cpuset_filetype_t;
>>  
>>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
>> @@ -1704,6 +1705,23 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>>  	return retval ?: nbytes;
>>  }
>>  
>> +static size_t cpuset_sprintf_isolcpus(char *s, ssize_t pos, struct cpuset *cs)
>> +{
>> +	cpumask_var_t my_isolated_cpus;
>> +	ssize_t count;
>> +	
> 
> Whitespace.
> 
>> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
>> +		return 0;
>> +
>> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
>> +
>> +	count = cpulist_scnprintf(s, pos, my_isolated_cpus);
>> +
>> +	free_cpumask_var(my_isolated_cpus);
>> +
>> +	return count;
>> +}
>> +
>>  /*
>>   * These ascii lists should be read in a single call, by using a user
>>   * buffer large enough to hold the entire map.  If read in smaller
>> @@ -1738,6 +1756,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>>  	case FILE_EFFECTIVE_MEMLIST:
>>  		s += nodelist_scnprintf(s, count, cs->effective_mems);
>>  		break;
>> +	case FILE_ISOLCPUS:
>> +		s += cpuset_sprintf_isolcpus(s, count, cs);
>> +		break;
> 
> This patch looks fine, and I think cpuset.effective_cpus and 
> cpuset.isolcpus can be used well together, but will need updating now that 
> commit e8e6d97c9b ("cpuset: use %*pb[l] to print bitmaps including 
> cpumasks and nodemasks") has been merged which reworks this function.

I will take a look at that changeset. It was not in the
tip tree I worked against.

Expect a v2 :)

> It's a little unfortunate, though, that the user sees Cpus_allowed, 
> cpuset.cpus, and cpuset.effective_cpus that include isolcpus and then have 
> to check another cpulist for the isolcpus to see their sched domain, 
> though.

Agreed, but all the alternatives I could think of would break the
userspace API, leaving this as the best way to go.

-- 
All rights reversed

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[Rik van Riel]

On 02/24/2015 09:15 PM, David Rientjes wrote:
> On Mon, 23 Feb 2015, riel@redhat.com wrote:
> 
>> From: Rik van Riel <riel@redhat.com>
>>
>> The previous patch makes it so the code skips over isolcpus when
>> building scheduler load balancing domains. This makes it hard to
>> see for a user which of the CPUs in a cpuset are participating in
>> load balancing, and which ones are isolated cpus.
>>
>> Add a cpuset.isolcpus file with info on which cpus in a cpuset are
>> isolated CPUs.
>>
>> This file is read-only for now. In the future we could extend things
>> so isolcpus can be changed at run time, for the root (system wide)
>> cpuset only.
>>
>> Cc: Peter Zijlstra <peterz@infradead.org>
>> Cc: Clark Williams <williams@redhat.com>
>> Cc: Li Zefan <lizefan@huawei.com>
>> Cc: Ingo Molnar <mingo@redhat.com>
>> Cc: Luiz Capitulino <lcapitulino@redhat.com>
>> Cc: cgroups@vger.kernel.org
>> Signed-off-by: Rik van Riel <riel@redhat.com>
>> ---
>>  kernel/cpuset.c | 27 +++++++++++++++++++++++++++
>>  1 file changed, 27 insertions(+)
>>
>> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
>> index 1ad63fa37cb4..19ad5d3377f8 100644
>> --- a/kernel/cpuset.c
>> +++ b/kernel/cpuset.c
>> @@ -1563,6 +1563,7 @@ typedef enum {
>>  	FILE_MEMORY_PRESSURE,
>>  	FILE_SPREAD_PAGE,
>>  	FILE_SPREAD_SLAB,
>> +	FILE_ISOLCPUS,
>>  } cpuset_filetype_t;
>>  
>>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
>> @@ -1704,6 +1705,23 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>>  	return retval ?: nbytes;
>>  }
>>  
>> +static size_t cpuset_sprintf_isolcpus(char *s, ssize_t pos, struct cpuset *cs)
>> +{
>> +	cpumask_var_t my_isolated_cpus;
>> +	ssize_t count;
>> +	
> 
> Whitespace.
> 
>> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
>> +		return 0;
>> +
>> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
>> +
>> +	count = cpulist_scnprintf(s, pos, my_isolated_cpus);
>> +
>> +	free_cpumask_var(my_isolated_cpus);
>> +
>> +	return count;
>> +}
>> +
>>  /*
>>   * These ascii lists should be read in a single call, by using a user
>>   * buffer large enough to hold the entire map.  If read in smaller
>> @@ -1738,6 +1756,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>>  	case FILE_EFFECTIVE_MEMLIST:
>>  		s += nodelist_scnprintf(s, count, cs->effective_mems);
>>  		break;
>> +	case FILE_ISOLCPUS:
>> +		s += cpuset_sprintf_isolcpus(s, count, cs);
>> +		break;
> 
> This patch looks fine, and I think cpuset.effective_cpus and 
> cpuset.isolcpus can be used well together, but will need updating now that 
> commit e8e6d97c9b ("cpuset: use %*pb[l] to print bitmaps including 
> cpumasks and nodemasks") has been merged which reworks this function.

I will take a look at that changeset. It was not in the
tip tree I worked against.

Expect a v2 :)

> It's a little unfortunate, though, that the user sees Cpus_allowed, 
> cpuset.cpus, and cpuset.effective_cpus that include isolcpus and then have 
> to check another cpulist for the isolcpus to see their sched domain, 
> though.

Agreed, but all the alternatives I could think of would break the
userspace API, leaving this as the best way to go.

-- 
All rights reversed

Re: [PATCH 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[Mike Galbraith]

On Mon, 2015-02-23 at 16:45 -0500, riel@redhat.com wrote:
> Ensure that cpus specified with the isolcpus= boot commandline
> option stay outside of the load balancing in the kernel scheduler.
> 
> Operations like load balancing can introduce unwanted latencies,
> which is exactly what the isolcpus= commandline is there to prevent.
> 
> Previously, simply creating a new cpuset, without even touching the
> cpuset.cpus field inside the new cpuset, would undo the effects of
> isolcpus=, by creating a scheduler domain spanning the whole system,
> and setting up load balancing inside that domain. The cpuset root
> cpuset.cpus file is read-only, so there was not even a way to undo
> that effect.
> 
> This does not impact the majority of cpusets users, since isolcpus=
> is a fairly specialized feature used for realtime purposes.

3/3: nohz_full cpus become part of that unified isolated map?

	-Mike

Re: [PATCH 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[Rik van Riel]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 02/23/2015 09:18 PM, Mike Galbraith wrote:
> On Mon, 2015-02-23 at 16:45 -0500, riel@redhat.com wrote:
>> Ensure that cpus specified with the isolcpus= boot commandline 
>> option stay outside of the load balancing in the kernel
>> scheduler.
>> 
>> Operations like load balancing can introduce unwanted latencies, 
>> which is exactly what the isolcpus= commandline is there to
>> prevent.
>> 
>> Previously, simply creating a new cpuset, without even touching
>> the cpuset.cpus field inside the new cpuset, would undo the
>> effects of isolcpus=, by creating a scheduler domain spanning the
>> whole system, and setting up load balancing inside that domain.
>> The cpuset root cpuset.cpus file is read-only, so there was not
>> even a way to undo that effect.
>> 
>> This does not impact the majority of cpusets users, since
>> isolcpus= is a fairly specialized feature used for realtime
>> purposes.
> 
> 3/3: nohz_full cpus become part of that unified isolated map?

There may be use cases where users want nohz_full, but still
want the scheduler to automatically load balance the CPU.

I am not sure whether we want nohz_full and isolcpus to always
overlap 100%.

On the other hand, any CPU that is isolated with isolcpus=
probably wants nohz_full...

- -- 
All rights reversed
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1

iQEcBAEBAgAGBQJU7IbwAAoJEM553pKExN6DxpAIAIt3Wp1fYhyTiceCZPZj/75y
aNdpa1tsdyZmC3UoqHlWPajhU9kz3LV88gkDuRVLkBSIbAdc+Krpj0QwU80SBpn8
MIRkzlDE5pHwqgpNEmY0dTI8OP/BWH6SzgkbAqACTeffR8glz49ELFL2IK9hSl4P
2j5gOc1sgBD24cpqComw0qpIJwhRfDTr270zHPzEcqwESYLD57Z6AZxLuz8UjDnD
vgvmz5+zCeVKfPWfFSCUHGDZ56PuQAvQk0olAVp5pd6wwGoPyAMNJm12RgE2ru0M
8y/xyHAhbtzdV7XsdfBWWe6F4jmodvjhKKtqRdwGzQSGkJzxGjdlFBeSkOkeBsk=
=4dML
-----END PGP SIGNATURE-----

Re: [PATCH 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[Mike Galbraith]

On Tue, 2015-02-24 at 09:13 -0500, Rik van Riel wrote:
> On 02/23/2015 09:18 PM, Mike Galbraith wrote:
> > On Mon, 2015-02-23 at 16:45 -0500, riel@redhat.com wrote:
> >> Ensure that cpus specified with the isolcpus= boot commandline 
> >> option stay outside of the load balancing in the kernel
> >> scheduler.
> >> 
> >> Operations like load balancing can introduce unwanted latencies, 
> >> which is exactly what the isolcpus= commandline is there to
> >> prevent.
> >> 
> >> Previously, simply creating a new cpuset, without even touching
> >> the cpuset.cpus field inside the new cpuset, would undo the
> >> effects of isolcpus=, by creating a scheduler domain spanning the
> >> whole system, and setting up load balancing inside that domain.
> >> The cpuset root cpuset.cpus file is read-only, so there was not
> >> even a way to undo that effect.
> >> 
> >> This does not impact the majority of cpusets users, since
> >> isolcpus= is a fairly specialized feature used for realtime
> >> purposes.
> > 
> > 3/3: nohz_full cpus become part of that unified isolated map?
> 
> There may be use cases where users want nohz_full, but still
> want the scheduler to automatically load balance the CPU.
> 
> I am not sure whether we want nohz_full and isolcpus to always
> overlap 100%.
> 
> On the other hand, any CPU that is isolated with isolcpus=
> probably wants nohz_full...

I can't imagine caring deeply about the tiny interference of the tick,
yet not caring about the massive interference of load balancing.

	-Mike

Re: [PATCH 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[Mike Galbraith]

On Tue, 2015-02-24 at 09:13 -0500, Rik van Riel wrote:

> On the other hand, any CPU that is isolated with isolcpus=
> probably wants nohz_full...

Not here.  I isolate (via cpusets) for a 60 core rt load, but it's not
single task/core, and doesn't like the nohz_full overhead.

	-Mike 

[PATCH -v2 0/2] cpusets,isolcpus: resolve conflict between cpusets and isolcpus

[riel]

-v2 addresses the conflict David Rientjes spotted between my previous
patches and commit e8e6d97c9b ("cpuset: use %*pb[l] to print bitmaps
including cpumasks and nodemasks")

Ensure that cpus specified with the isolcpus= boot commandline
option stay outside of the load balancing in the kernel scheduler.

Operations like load balancing can introduce unwanted latencies,
which is exactly what the isolcpus= commandline is there to prevent.

Previously, simply creating a new cpuset, without even touching the
cpuset.cpus field inside the new cpuset, would undo the effects of
isolcpus=, by creating a scheduler domain spanning the whole system,
and setting up load balancing inside that domain. The cpuset root
cpuset.cpus file is read-only, so there was not even a way to undo
that effect.

This does not impact the majority of cpusets users, since isolcpus=
is a fairly specialized feature used for realtime purposes.

[PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[riel]

From: Rik van Riel <riel@redhat.com>

The previous patch makes it so the code skips over isolcpus when
building scheduler load balancing domains. This makes it hard to
see for a user which of the CPUs in a cpuset are participating in
load balancing, and which ones are isolated cpus.

Add a cpuset.isolcpus file with info on which cpus in a cpuset are
isolated CPUs.

This file is read-only for now. In the future we could extend things
so isolcpus can be changed at run time, for the root (system wide)
cpuset only.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: cgroups@vger.kernel.org
Signed-off-by: Rik van Riel <riel@redhat.com>
---
 kernel/cpuset.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b544e5229d99..94bf59588e23 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1563,6 +1563,7 @@ typedef enum {
 	FILE_MEMORY_PRESSURE,
 	FILE_SPREAD_PAGE,
 	FILE_SPREAD_SLAB,
+	FILE_ISOLCPUS,
 } cpuset_filetype_t;
 
 static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
@@ -1704,6 +1705,20 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	return retval ?: nbytes;
 }
 
+static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
+{
+	cpumask_var_t my_isolated_cpus;
+
+	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
+		return;
+
+	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
+
+	seq_printf(sf, "%*pbl\n", nodemask_pr_args(my_isolated_cpus));
+
+	free_cpumask_var(my_isolated_cpus);
+}
+
 /*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
@@ -1733,6 +1748,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_EFFECTIVE_MEMLIST:
 		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
 		break;
+	case FILE_ISOLCPUS:
+		cpuset_seq_print_isolcpus(sf, cs);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -1893,6 +1911,12 @@ static struct cftype files[] = {
 		.private = FILE_MEMORY_PRESSURE_ENABLED,
 	},
 
+	{
+		.name = "isolcpus",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_ISOLCPUS,
+	},
+
 	{ }	/* terminate */
 };
 
-- 
2.1.0

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[David Rientjes]

On Wed, 25 Feb 2015, riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org wrote:

> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
> index b544e5229d99..94bf59588e23 100644
> --- a/kernel/cpuset.c
> +++ b/kernel/cpuset.c
> @@ -1563,6 +1563,7 @@ typedef enum {
>  	FILE_MEMORY_PRESSURE,
>  	FILE_SPREAD_PAGE,
>  	FILE_SPREAD_SLAB,
> +	FILE_ISOLCPUS,
>  } cpuset_filetype_t;
>  
>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
> @@ -1704,6 +1705,20 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>  	return retval ?: nbytes;
>  }
>  
> +static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
> +{
> +	cpumask_var_t my_isolated_cpus;
> +
> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
> +		return;
> +
> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
> +
> +	seq_printf(sf, "%*pbl\n", nodemask_pr_args(my_isolated_cpus));

That unfortunately won't output anything, it needs to be 
cpumask_pr_args().  After that's fixed, feel free to add my

	Acked-by: David Rientjes <rientjes-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>

> +
> +	free_cpumask_var(my_isolated_cpus);
> +}
> +
>  /*
>   * These ascii lists should be read in a single call, by using a user
>   * buffer large enough to hold the entire map.  If read in smaller
> @@ -1733,6 +1748,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>  	case FILE_EFFECTIVE_MEMLIST:
>  		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
>  		break;
> +	case FILE_ISOLCPUS:
> +		cpuset_seq_print_isolcpus(sf, cs);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  	}
> @@ -1893,6 +1911,12 @@ static struct cftype files[] = {
>  		.private = FILE_MEMORY_PRESSURE_ENABLED,
>  	},
>  
> +	{
> +		.name = "isolcpus",
> +		.seq_show = cpuset_common_seq_show,
> +		.private = FILE_ISOLCPUS,
> +	},
> +
>  	{ }	/* terminate */
>  };
>  

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[David Rientjes]

On Wed, 25 Feb 2015, riel@redhat.com wrote:

> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
> index b544e5229d99..94bf59588e23 100644
> --- a/kernel/cpuset.c
> +++ b/kernel/cpuset.c
> @@ -1563,6 +1563,7 @@ typedef enum {
>  	FILE_MEMORY_PRESSURE,
>  	FILE_SPREAD_PAGE,
>  	FILE_SPREAD_SLAB,
> +	FILE_ISOLCPUS,
>  } cpuset_filetype_t;
>  
>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
> @@ -1704,6 +1705,20 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>  	return retval ?: nbytes;
>  }
>  
> +static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
> +{
> +	cpumask_var_t my_isolated_cpus;
> +
> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
> +		return;
> +
> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
> +
> +	seq_printf(sf, "%*pbl\n", nodemask_pr_args(my_isolated_cpus));

That unfortunately won't output anything, it needs to be 
cpumask_pr_args().  After that's fixed, feel free to add my

	Acked-by: David Rientjes <rientjes@google.com>

> +
> +	free_cpumask_var(my_isolated_cpus);
> +}
> +
>  /*
>   * These ascii lists should be read in a single call, by using a user
>   * buffer large enough to hold the entire map.  If read in smaller
> @@ -1733,6 +1748,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>  	case FILE_EFFECTIVE_MEMLIST:
>  		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
>  		break;
> +	case FILE_ISOLCPUS:
> +		cpuset_seq_print_isolcpus(sf, cs);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  	}
> @@ -1893,6 +1911,12 @@ static struct cftype files[] = {
>  		.private = FILE_MEMORY_PRESSURE_ENABLED,
>  	},
>  
> +	{
> +		.name = "isolcpus",
> +		.seq_show = cpuset_common_seq_show,
> +		.private = FILE_ISOLCPUS,
> +	},
> +
>  	{ }	/* terminate */
>  };
>  

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[Rik van Riel]

On 02/25/2015 04:09 PM, David Rientjes wrote:
> On Wed, 25 Feb 2015, riel@redhat.com wrote:
> 
>> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
>> index b544e5229d99..94bf59588e23 100644
>> --- a/kernel/cpuset.c
>> +++ b/kernel/cpuset.c
>> @@ -1563,6 +1563,7 @@ typedef enum {
>>  	FILE_MEMORY_PRESSURE,
>>  	FILE_SPREAD_PAGE,
>>  	FILE_SPREAD_SLAB,
>> +	FILE_ISOLCPUS,
>>  } cpuset_filetype_t;
>>  
>>  static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
>> @@ -1704,6 +1705,20 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>>  	return retval ?: nbytes;
>>  }
>>  
>> +static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
>> +{
>> +	cpumask_var_t my_isolated_cpus;
>> +
>> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
>> +		return;
>> +
>> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
>> +
>> +	seq_printf(sf, "%*pbl\n", nodemask_pr_args(my_isolated_cpus));
> 
> That unfortunately won't output anything, it needs to be 
> cpumask_pr_args().  After that's fixed, feel free to add my
> 
> 	Acked-by: David Rientjes <rientjes@google.com>

Gah. Too many things going on at once.

Let me resend a v3 of just patch 2/2 with your ack.

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[Zefan Li]

> +static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
> +{
> +	cpumask_var_t my_isolated_cpus;
> +
> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
> +		return;
> +

Make it return -ENOMEM ? Or make it a global variable and allocate memory for it
in cpuset_init().

> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
> +
> +	seq_printf(sf, "%*pbl\n", nodemask_pr_args(my_isolated_cpus));
> +
> +	free_cpumask_var(my_isolated_cpus);
> +}
> +
>  /*
>   * These ascii lists should be read in a single call, by using a user
>   * buffer large enough to hold the entire map.  If read in smaller
> @@ -1733,6 +1748,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>  	case FILE_EFFECTIVE_MEMLIST:
>  		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
>  		break;
> +	case FILE_ISOLCPUS:
> +		cpuset_seq_print_isolcpus(sf, cs);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  	}
> @@ -1893,6 +1911,12 @@ static struct cftype files[] = {
>  		.private = FILE_MEMORY_PRESSURE_ENABLED,
>  	},
>  
> +	{
> +		.name = "isolcpus",
> +		.seq_show = cpuset_common_seq_show,
> +		.private = FILE_ISOLCPUS,
> +	},
> +
>  	{ }	/* terminate */
>  };
>  
> 

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[Zefan Li]

> +static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
> +{
> +	cpumask_var_t my_isolated_cpus;
> +
> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
> +		return;
> +

Make it return -ENOMEM ? Or make it a global variable and allocate memory for it
in cpuset_init().

> +	cpumask_and(my_isolated_cpus, cs->cpus_allowed, cpu_isolated_map);
> +
> +	seq_printf(sf, "%*pbl\n", nodemask_pr_args(my_isolated_cpus));
> +
> +	free_cpumask_var(my_isolated_cpus);
> +}
> +
>  /*
>   * These ascii lists should be read in a single call, by using a user
>   * buffer large enough to hold the entire map.  If read in smaller
> @@ -1733,6 +1748,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>  	case FILE_EFFECTIVE_MEMLIST:
>  		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
>  		break;
> +	case FILE_ISOLCPUS:
> +		cpuset_seq_print_isolcpus(sf, cs);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  	}
> @@ -1893,6 +1911,12 @@ static struct cftype files[] = {
>  		.private = FILE_MEMORY_PRESSURE_ENABLED,
>  	},
>  
> +	{
> +		.name = "isolcpus",
> +		.seq_show = cpuset_common_seq_show,
> +		.private = FILE_ISOLCPUS,
> +	},
> +
>  	{ }	/* terminate */
>  };
>  
> 

Re: [PATCH 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset

[Rik van Riel]

On 02/26/2015 06:05 AM, Zefan Li wrote:
>> +static void cpuset_seq_print_isolcpus(struct seq_file *sf, struct cpuset *cs)
>> +{
>> +	cpumask_var_t my_isolated_cpus;
>> +
>> +	if (!alloc_cpumask_var(&my_isolated_cpus, GFP_KERNEL))
>> +		return;
>> +
> 
> Make it return -ENOMEM ? Or make it a global variable and allocate memory for it
> in cpuset_init().

OK, can do.

I see that cpuset_common_seq_show already takes a lock, so having
one global variable for this should not introduce any additional
contention.

I will send a v4.

>> @@ -1733,6 +1748,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
>>  	case FILE_EFFECTIVE_MEMLIST:
>>  		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
>>  		break;
>> +	case FILE_ISOLCPUS:
>> +		cpuset_seq_print_isolcpus(sf, cs);
>> +		break;
>>  	default:
>>  		ret = -EINVAL;
>>  	}


-- 
All rights reversed