[PATCH v2] selftests/cgroup: Adjust cpu.max quota based on HZ

[PATCH v2] selftests/cgroup: Adjust cpu.max quota based on HZ

[Joe Simmons-Talbott]

For lower HZ values a quota of 1000us is much lower than the amount
of microseconds per tick which makes the tests test_cpucg_max and
test_cpugc_max_nested fail. Use the amount of microseconds per tick
as the quota value.

Signed-off-by: Joe Simmons-Talbott <joest@redhat.com>
---
changes since v1:
- Try checking /proc/config.gz to get the actual kernel HZ value and
  fallback to 1000 if the value cannot be determined.

 tools/testing/selftests/cgroup/test_cpu.c | 33 +++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index 7a40d76b9548..65e09555309f 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -639,6 +639,29 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
 	return run_cpucg_nested_weight_test(root, false);
 }
 
+/*
+ * Best effort attempt to get the kernel's HZ value from the config.
+ * Return the HZ value if found otherwise return -1 to indicate failure.
+ */
+static long
+_get_config_hz(void)
+{
+	long hz = -1;
+	FILE *f;
+	char cmd[256] = "zcat /proc/config.gz 2>/dev/null | grep '^CONFIG_HZ='";
+
+	f = popen(cmd, "r");
+
+	if (!f)
+		goto out;
+
+	fscanf(f, "CONFIG_HZ=%ld", &hz);
+
+out:
+	pclose(f);
+	return hz;
+}
+
 /*
  * This test creates a cgroup with some maximum value within a period, and
  * verifies that a process in the cgroup is not overscheduled.
@@ -646,7 +669,8 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
 static int test_cpucg_max(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long quota_usec = 1000;
+	long hz = _get_config_hz();
+	long quota_usec;
 	long default_period_usec = 100000; /* cpu.max's default period */
 	long duration_seconds = 1;
 
@@ -655,6 +679,8 @@ static int test_cpucg_max(const char *root)
 	char *cpucg;
 	char quota_buf[32];
 
+	quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
+
 	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
 
 	cpucg = cg_name(root, "cpucg_test");
@@ -710,7 +736,8 @@ static int test_cpucg_max(const char *root)
 static int test_cpucg_max_nested(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long quota_usec = 1000;
+	long quota_usec;
+	long hz = _get_config_hz();
 	long default_period_usec = 100000; /* cpu.max's default period */
 	long duration_seconds = 1;
 
@@ -719,6 +746,8 @@ static int test_cpucg_max_nested(const char *root)
 	char *parent, *child;
 	char quota_buf[32];
 
+	quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
+
 	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
 
 	parent = cg_name(root, "cpucg_parent");
-- 
2.54.0

Re: [PATCH v2] selftests/cgroup: Adjust cpu.max quota based on HZ

[Tao Cui]

Hi Joe,

One comment on the fallback:

  quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;

When HZ can't be determined (no CONFIG_IKCONFIG_PROC, or zcat missing),
the fallback to 1000 is the exact value that fails at low HZ — so this
doesn't actually fix such kernels. A larger fallback (e.g. 10000, the
HZ=100 equivalent) would make the tests robust regardless of whether the
config is exposed.

在 2026/6/23 03:43, Joe Simmons-Talbott 写道:
> For lower HZ values a quota of 1000us is much lower than the amount
> of microseconds per tick which makes the tests test_cpucg_max and
> test_cpugc_max_nested fail. Use the amount of microseconds per tick
> as the quota value.
> 
> Signed-off-by: Joe Simmons-Talbott <joest@redhat.com>
> ---
> changes since v1:
> - Try checking /proc/config.gz to get the actual kernel HZ value and
>   fallback to 1000 if the value cannot be determined.
> 
>  tools/testing/selftests/cgroup/test_cpu.c | 33 +++++++++++++++++++++--
>  1 file changed, 31 insertions(+), 2 deletions(-)
> 
> diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
> index 7a40d76b9548..65e09555309f 100644
> --- a/tools/testing/selftests/cgroup/test_cpu.c
> +++ b/tools/testing/selftests/cgroup/test_cpu.c
> @@ -639,6 +639,29 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
>  	return run_cpucg_nested_weight_test(root, false);
>  }
>  
> +/*
> + * Best effort attempt to get the kernel's HZ value from the config.
> + * Return the HZ value if found otherwise return -1 to indicate failure.
> + */
> +static long
> +_get_config_hz(void)
> +{
> +	long hz = -1;
> +	FILE *f;
> +	char cmd[256] = "zcat /proc/config.gz 2>/dev/null | grep '^CONFIG_HZ='";
> +
> +	f = popen(cmd, "r");
> +
> +	if (!f)
> +		goto out;
> +
> +	fscanf(f, "CONFIG_HZ=%ld", &hz);
> +
> +out:
> +	pclose(f);
> +	return hz;
> +}
> +
>  /*
>   * This test creates a cgroup with some maximum value within a period, and
>   * verifies that a process in the cgroup is not overscheduled.
> @@ -646,7 +669,8 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
>  static int test_cpucg_max(const char *root)
>  {
>  	int ret = KSFT_FAIL;
> -	long quota_usec = 1000;
> +	long hz = _get_config_hz();
> +	long quota_usec;
>  	long default_period_usec = 100000; /* cpu.max's default period */
>  	long duration_seconds = 1;
>  
> @@ -655,6 +679,8 @@ static int test_cpucg_max(const char *root)
>  	char *cpucg;
>  	char quota_buf[32];
>  
> +	quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
> +
>  	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
>  
>  	cpucg = cg_name(root, "cpucg_test");
> @@ -710,7 +736,8 @@ static int test_cpucg_max(const char *root)
>  static int test_cpucg_max_nested(const char *root)
>  {
>  	int ret = KSFT_FAIL;
> -	long quota_usec = 1000;
> +	long quota_usec;
> +	long hz = _get_config_hz();
>  	long default_period_usec = 100000; /* cpu.max's default period */
>  	long duration_seconds = 1;
>  
> @@ -719,6 +746,8 @@ static int test_cpucg_max_nested(const char *root)
>  	char *parent, *child;
>  	char quota_buf[32];
>  
> +	quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
> +
>  	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
>  
>  	parent = cg_name(root, "cpucg_parent");

Re: [PATCH v2] selftests/cgroup: Adjust cpu.max quota based on HZ

[Joe Simmons-Talbott]

On Tue, Jun 23, 2026 at 01:32:08PM +0800, Tao Cui wrote:
> 
> Hi Joe,
> 
> One comment on the fallback:
> 
>   quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
> 
> When HZ can't be determined (no CONFIG_IKCONFIG_PROC, or zcat missing),
> the fallback to 1000 is the exact value that fails at low HZ — so this
> doesn't actually fix such kernels. A larger fallback (e.g. 10000, the
> HZ=100 equivalent) would make the tests robust regardless of whether the
> config is exposed.

Hi Tao Cui,

Thank you for your review.

I am happy to use 10000 as the fallback value.  I will address this as
well as the sashiko comments in v3.

Thanks,
Joe
> 
> 在 2026/6/23 03:43, Joe Simmons-Talbott 写道:
> > For lower HZ values a quota of 1000us is much lower than the amount
> > of microseconds per tick which makes the tests test_cpucg_max and
> > test_cpugc_max_nested fail. Use the amount of microseconds per tick
> > as the quota value.
> > 
> > Signed-off-by: Joe Simmons-Talbott <joest@redhat.com>
> > ---
> > changes since v1:
> > - Try checking /proc/config.gz to get the actual kernel HZ value and
> >   fallback to 1000 if the value cannot be determined.
> > 
> >  tools/testing/selftests/cgroup/test_cpu.c | 33 +++++++++++++++++++++--
> >  1 file changed, 31 insertions(+), 2 deletions(-)
> > 
> > diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
> > index 7a40d76b9548..65e09555309f 100644
> > --- a/tools/testing/selftests/cgroup/test_cpu.c
> > +++ b/tools/testing/selftests/cgroup/test_cpu.c
> > @@ -639,6 +639,29 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
> >  	return run_cpucg_nested_weight_test(root, false);
> >  }
> >  
> > +/*
> > + * Best effort attempt to get the kernel's HZ value from the config.
> > + * Return the HZ value if found otherwise return -1 to indicate failure.
> > + */
> > +static long
> > +_get_config_hz(void)
> > +{
> > +	long hz = -1;
> > +	FILE *f;
> > +	char cmd[256] = "zcat /proc/config.gz 2>/dev/null | grep '^CONFIG_HZ='";
> > +
> > +	f = popen(cmd, "r");
> > +
> > +	if (!f)
> > +		goto out;
> > +
> > +	fscanf(f, "CONFIG_HZ=%ld", &hz);
> > +
> > +out:
> > +	pclose(f);
> > +	return hz;
> > +}
> > +
> >  /*
> >   * This test creates a cgroup with some maximum value within a period, and
> >   * verifies that a process in the cgroup is not overscheduled.
> > @@ -646,7 +669,8 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
> >  static int test_cpucg_max(const char *root)
> >  {
> >  	int ret = KSFT_FAIL;
> > -	long quota_usec = 1000;
> > +	long hz = _get_config_hz();
> > +	long quota_usec;
> >  	long default_period_usec = 100000; /* cpu.max's default period */
> >  	long duration_seconds = 1;
> >  
> > @@ -655,6 +679,8 @@ static int test_cpucg_max(const char *root)
> >  	char *cpucg;
> >  	char quota_buf[32];
> >  
> > +	quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
> > +
> >  	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
> >  
> >  	cpucg = cg_name(root, "cpucg_test");
> > @@ -710,7 +736,8 @@ static int test_cpucg_max(const char *root)
> >  static int test_cpucg_max_nested(const char *root)
> >  {
> >  	int ret = KSFT_FAIL;
> > -	long quota_usec = 1000;
> > +	long quota_usec;
> > +	long hz = _get_config_hz();
> >  	long default_period_usec = 100000; /* cpu.max's default period */
> >  	long duration_seconds = 1;
> >  
> > @@ -719,6 +746,8 @@ static int test_cpucg_max_nested(const char *root)
> >  	char *parent, *child;
> >  	char quota_buf[32];
> >  
> > +	quota_usec = hz != -1 ? USEC_PER_SEC / hz : 1000;
> > +
> >  	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
> >  
> >  	parent = cg_name(root, "cpucg_parent");
> 
> 

Re: [PATCH v2] selftests/cgroup: Adjust cpu.max quota based on HZ

[Michal Koutný]

[-- Attachment #1: Type: text/plain, Size: 3924 bytes --]

On Mon, Jun 22, 2026 at 03:43:04PM -0400, Joe Simmons-Talbott <joest@redhat.com> wrote:
> +static long
> +_get_config_hz(void)
> +{
> +	long hz = -1;
> +	FILE *f;
> +	char cmd[256] = "zcat /proc/config.gz 2>/dev/null | grep '^CONFIG_HZ='";
> +
> +	f = popen(cmd, "r");
> +
> +	if (!f)
> +		goto out;
> +
> +	fscanf(f, "CONFIG_HZ=%ld", &hz);
> +
> +out:
> +	pclose(f);
> +	return hz;
> +}

I like that you voiced this dependency on CONFIG_HZ and also that
_SC_CLK_TCK is useless in this regards.
(I see that BPF selftests have similar infra for this.)


> +
>  /*
>   * This test creates a cgroup with some maximum value within a period, and
>   * verifies that a process in the cgroup is not overscheduled.
> @@ -646,7 +669,8 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
>  static int test_cpucg_max(const char *root)
>  {
>  	int ret = KSFT_FAIL;
> -	long quota_usec = 1000;
> +	long hz = _get_config_hz();
> +	long quota_usec;
>  	long default_period_usec = 100000; /* cpu.max's default period */
>  	long duration_seconds = 1;

I would not bend the tested value but it's expectation (so that
approximately same quantity is tested acroos configs).

I reckon the problem might be tasks that overrun the quota due to long
tick, fortunately, we can assume this is compensated over multiple
periods, so _on average_ quota should be honored (more) precisely.
But the test duration may be not well aligned with all the compensation
periods, to that must be accounted for in the expectation.

When I write it all down, I get this:

--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -651,7 +651,9 @@ static int test_cpucg_max(const char *root)
        long duration_seconds = 1;

        long duration_usec = duration_seconds * USEC_PER_SEC;
-       long usage_usec, n_periods, remainder_usec, expected_usage_usec;
+       long usage_usec, expected_usage_usec;
+       long n_periods, spread_periods, unaligned;
+       long tick_usec, low_usage, high_usage;
        char *cpucg;
        char quota_buf[32];

@@ -687,9 +689,16 @@ static int test_cpucg_max(const char *root)
         * the cpu hog is set to run as per wall-clock time
         */
        n_periods = duration_usec / default_period_usec;
-       remainder_usec = duration_usec - n_periods * default_period_usec;
-       expected_usage_usec
-               = n_periods * quota_usec + MIN(remainder_usec, quota_usec);
+       tick_usec = USEC_PER_SEC / hz;
+       /* Up to tick_usec (over)run is compensated over multiple periods */
+       spread_periods = MAX(1, tick_usec / quota_usec);
+       low_usage = n_periods / spread_periods;
+       high_usage = (n_periods + spread_periods - 1) / spread_periods;
+       unaligned = n_periods % spread_periods;
+
+       expected_usage_usec = quota_usec * (
+               unaligned * high_usage +
+               (spread_periods - unaligned) * low_usage);

        if (!values_close_report(usage_usec, expected_usage_usec, 10))
                goto cleanup;


(I neglected (and dropped) remainder_usec because it is zero with
default values)

However, not all preemptions are tick-based, so there'd be noise 
and one has to tune the values_clone_report(,,err) anyway.

Then to reduce noise, the simpler solution is to let the test run
longer

duration_usec = duration_seconds * USEC_PER_SEC * 1000 / hz;

(where 1000 is the CONFIG_HZ=1000 where the test runs sufficiently [1] well.)

Joe, how do to the two variants above (unalignment account and prolonged
duration) affect test_cpu behavior on your setup?

(I'm personally wondering what is bigger quantity: systemic error due to
HZ quantization or random (SMP) error.)

Thanks,
Michal

[1] Even there one runs into noise depending on nr_cpus, thus even that
    fixed err=10 is not ideal.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 265 bytes --]