[PATCH v3] cgroup2: New memory.max.effective like cgroup1 hierarchical_memory_limit

[PATCH v3] cgroup2: New memory.max.effective like cgroup1 hierarchical_memory_limit

[Jan Kratochvil (Azul)]

Hello,

cgroup1 (by function memcg1_stat_format) contains two lines
	hierarchical_memory_limit %llu
	hierarchical_memsw_limit %llu

which are useful for userland to easily and performance-wise find out the
effective cgroup limits being applied. Otherwise userland has to
open+read+close the file "memory.max" and/or "memory.swap.max" in multiple
parent directories of a nested cgroup.

For cgroup1 it was implemented by:
	memcg: show real limit under hierarchy mode
	https://github.com/torvalds/linux/commit/fee7b548e6f2bd4bfd03a1a45d3afd593de7d5e9
	Date:   Wed Jan 7 18:08:26 2009 -0800

But for cgroup2 it has been missing so far. Based on Michal Koutny's idea this
patch now implements "memory.max.effective" and "memory.swap.max.effective"
files similar to existing "cpuset.cpus.effective".


Jan Kratochvil


v3:
memory.stat fields -> *.max.effective separate files suggested by Michal Koutny
v2:
hierarchical_memsw_limit -> hierarchical_swap_limit fix found by Waiman Long
v1:
hierarchical_memory_limit && hierarchical_memsw_limit in memory.stat


Signed-off-by: Jan Kratochvil (Azul) <jkratochvil@azul.com>

 mm/memcontrol.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1ed40f9d3..8c4cb5f60 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6845,6 +6845,19 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int memory_max_effective_show(struct seq_file *m, void *v)
+{
+	unsigned long memory;
+	struct mem_cgroup *mi;
+
+	/* Hierarchical information */
+	memory = PAGE_COUNTER_MAX;
+	for (mi = mem_cgroup_from_seq(m); mi; mi = parent_mem_cgroup(mi))
+		memory = min(memory, READ_ONCE(mi->memory.max));
+
+	return seq_puts_memcg_tunable(m, memory);
+}
+
 /*
  * Note: don't forget to update the 'samples/cgroup/memcg_event_listener'
  * if any new events become available.
@@ -7038,6 +7051,11 @@ static struct cftype memory_files[] = {
 		.seq_show = memory_max_show,
 		.write = memory_max_write,
 	},
+	{
+		.name = "max.effective",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = memory_max_effective_show,
+	},
 	{
 		.name = "events",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -8040,6 +8058,19 @@ static ssize_t swap_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int swap_max_effective_show(struct seq_file *m, void *v)
+{
+	unsigned long swap;
+	struct mem_cgroup *mi;
+
+	/* Hierarchical information */
+	swap = PAGE_COUNTER_MAX;
+	for (mi = mem_cgroup_from_seq(m); mi; mi = parent_mem_cgroup(mi))
+		swap = min(swap, READ_ONCE(mi->swap.max));
+
+	return seq_puts_memcg_tunable(m, swap);
+}
+
 static int swap_events_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
@@ -8072,6 +8103,11 @@ static struct cftype swap_files[] = {
 		.seq_show = swap_max_show,
 		.write = swap_max_write,
 	},
+	{
+		.name = "swap.max.effective",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = swap_max_effective_show,
+	},
 	{
 		.name = "swap.peak",
 		.flags = CFTYPE_NOT_ON_ROOT,

Re: [PATCH v3] cgroup2: New memory.max.effective like cgroup1 hierarchical_memory_limit

[Waiman Long]

On 2/13/24 07:36, Jan Kratochvil (Azul) wrote:
> Hello,
>
> cgroup1 (by function memcg1_stat_format) contains two lines
> 	hierarchical_memory_limit %llu
> 	hierarchical_memsw_limit %llu
>
> which are useful for userland to easily and performance-wise find out the
> effective cgroup limits being applied. Otherwise userland has to
> open+read+close the file "memory.max" and/or "memory.swap.max" in multiple
> parent directories of a nested cgroup.
>
> For cgroup1 it was implemented by:
> 	memcg: show real limit under hierarchy mode
> 	https://github.com/torvalds/linux/commit/fee7b548e6f2bd4bfd03a1a45d3afd593de7d5e9
> 	Date:   Wed Jan 7 18:08:26 2009 -0800
>
> But for cgroup2 it has been missing so far. Based on Michal Koutny's idea this
> patch now implements "memory.max.effective" and "memory.swap.max.effective"
> files similar to existing "cpuset.cpus.effective".
>
>
> Jan Kratochvil
>
>
> v3:
> memory.stat fields -> *.max.effective separate files suggested by Michal Koutny
> v2:
> hierarchical_memsw_limit -> hierarchical_swap_limit fix found by Waiman Long
> v1:
> hierarchical_memory_limit && hierarchical_memsw_limit in memory.stat
>
>
> Signed-off-by: Jan Kratochvil (Azul) <jkratochvil@azul.com>

The code changes look good to me. However, your commit log isn't of the 
right format. We don't start the commit log with "Hello". See

https://www.kernel.org/doc/Documentation/process/submitting-patches.rst

You can also do a "git log" of a linux git tree and see how other people 
write their commit logs.

Cheers,
Longman

>
>   mm/memcontrol.c | 36 ++++++++++++++++++++++++++++++++++++
>   1 file changed, 36 insertions(+)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 1ed40f9d3..8c4cb5f60 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -6845,6 +6845,19 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
>   	return nbytes;
>   }
>   
> +static int memory_max_effective_show(struct seq_file *m, void *v)
> +{
> +	unsigned long memory;
> +	struct mem_cgroup *mi;
> +
> +	/* Hierarchical information */
> +	memory = PAGE_COUNTER_MAX;
> +	for (mi = mem_cgroup_from_seq(m); mi; mi = parent_mem_cgroup(mi))
> +		memory = min(memory, READ_ONCE(mi->memory.max));
> +
> +	return seq_puts_memcg_tunable(m, memory);
> +}
> +
>   /*
>    * Note: don't forget to update the 'samples/cgroup/memcg_event_listener'
>    * if any new events become available.
> @@ -7038,6 +7051,11 @@ static struct cftype memory_files[] = {
>   		.seq_show = memory_max_show,
>   		.write = memory_max_write,
>   	},
> +	{
> +		.name = "max.effective",
> +		.flags = CFTYPE_NOT_ON_ROOT,
> +		.seq_show = memory_max_effective_show,
> +	},
>   	{
>   		.name = "events",
>   		.flags = CFTYPE_NOT_ON_ROOT,
> @@ -8040,6 +8058,19 @@ static ssize_t swap_max_write(struct kernfs_open_file *of,
>   	return nbytes;
>   }
>   
> +static int swap_max_effective_show(struct seq_file *m, void *v)
> +{
> +	unsigned long swap;
> +	struct mem_cgroup *mi;
> +
> +	/* Hierarchical information */
> +	swap = PAGE_COUNTER_MAX;
> +	for (mi = mem_cgroup_from_seq(m); mi; mi = parent_mem_cgroup(mi))
> +		swap = min(swap, READ_ONCE(mi->swap.max));
> +
> +	return seq_puts_memcg_tunable(m, swap);
> +}
> +
>   static int swap_events_show(struct seq_file *m, void *v)
>   {
>   	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
> @@ -8072,6 +8103,11 @@ static struct cftype swap_files[] = {
>   		.seq_show = swap_max_show,
>   		.write = swap_max_write,
>   	},
> +	{
> +		.name = "swap.max.effective",
> +		.flags = CFTYPE_NOT_ON_ROOT,
> +		.seq_show = swap_max_effective_show,
> +	},
>   	{
>   		.name = "swap.peak",
>   		.flags = CFTYPE_NOT_ON_ROOT,
>