Re: [PATCH 13/14] selftests/sched_ext: Add test for sched_ext dl_server

[Andrea Righi <arighi@nvidia.com>]

Hi Emil,

On Sun, Oct 19, 2025 at 03:04:22PM -0400, Emil Tsalapatis wrote:
> On Fri, Oct 17, 2025 at 5:38 AM Andrea Righi <arighi@nvidia.com> wrote:
> >
> > Add a selftest to validate the correct behavior of the deadline server
> > for the ext_sched_class.
> >
> > [ Joel: Replaced occurences of CFS in the test with EXT. ]
> >
> > Co-developed-by: Joel Fernandes <joelagnelf@nvidia.com>
> > Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
> > Signed-off-by: Andrea Righi <arighi@nvidia.com>
> > ---
> 
> Nits listed below, but otherwise:
> Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
> 
> Code review aside, on my VM the test alternates between 4.81% and 5.20% for me
> so it's working as expected.

Yeah, that sounds right, a bit of fluctuation like that is expected.

> 
> >  tools/testing/selftests/sched_ext/Makefile    |   1 +
> >  .../selftests/sched_ext/rt_stall.bpf.c        |  23 ++
> >  tools/testing/selftests/sched_ext/rt_stall.c  | 214 ++++++++++++++++++
> >  3 files changed, 238 insertions(+)
> >  create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c
> >  create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c
> >
> > diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
> > index 5fe45f9c5f8fd..c9255d1499b6e 100644
> > --- a/tools/testing/selftests/sched_ext/Makefile
> > +++ b/tools/testing/selftests/sched_ext/Makefile
> > @@ -183,6 +183,7 @@ auto-test-targets :=                        \
> >         select_cpu_dispatch_bad_dsq     \
> >         select_cpu_dispatch_dbl_dsp     \
> >         select_cpu_vtime                \
> > +       rt_stall                        \
> >         test_example                    \
> >
> >  testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
> > diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
> > new file mode 100644
> > index 0000000000000..80086779dd1eb
> > --- /dev/null
> > +++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
> > @@ -0,0 +1,23 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * A scheduler that verified if RT tasks can stall SCHED_EXT tasks.
> > + *
> > + * Copyright (c) 2025 NVIDIA Corporation.
> > + */
> > +
> > +#include <scx/common.bpf.h>
> > +
> > +char _license[] SEC("license") = "GPL";
> > +
> > +UEI_DEFINE(uei);
> > +
> > +void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei)
> > +{
> > +       UEI_RECORD(uei, ei);
> > +}
> > +
> > +SEC(".struct_ops.link")
> > +struct sched_ext_ops rt_stall_ops = {
> > +       .exit                   = (void *)rt_stall_exit,
> > +       .name                   = "rt_stall",
> > +};
> > diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
> > new file mode 100644
> > index 0000000000000..e9a0def9ee323
> > --- /dev/null
> > +++ b/tools/testing/selftests/sched_ext/rt_stall.c
> > @@ -0,0 +1,214 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Copyright (c) 2025 NVIDIA Corporation.
> > + */
> > +#define _GNU_SOURCE
> > +#include <stdio.h>
> > +#include <stdlib.h>
> > +#include <unistd.h>
> > +#include <sched.h>
> > +#include <sys/prctl.h>
> > +#include <sys/types.h>
> > +#include <sys/wait.h>
> > +#include <time.h>
> > +#include <linux/sched.h>
> > +#include <signal.h>
> > +#include <bpf/bpf.h>
> > +#include <scx/common.h>
> > +#include <sys/wait.h>
> > +#include <unistd.h>
> > +#include "rt_stall.bpf.skel.h"
> > +#include "scx_test.h"
> > +#include "../kselftest.h"
> > +
> > +#define CORE_ID                0       /* CPU to pin tasks to */
> > +#define RUN_TIME        5      /* How long to run the test in seconds */
> > +
> > +/* Simple busy-wait function for test tasks */
> > +static void process_func(void)
> > +{
> > +       while (1) {
> > +               /* Busy wait */
> > +               for (volatile unsigned long i = 0; i < 10000000UL; i++)
> > +                       ;
> > +       }
> > +}
> > +
> > +/* Set CPU affinity to a specific core */
> > +static void set_affinity(int cpu)
> > +{
> > +       cpu_set_t mask;
> > +
> > +       CPU_ZERO(&mask);
> > +       CPU_SET(cpu, &mask);
> > +       if (sched_setaffinity(0, sizeof(mask), &mask) != 0) {
> > +               perror("sched_setaffinity");
> > +               exit(EXIT_FAILURE);
> > +       }
> > +}
> > +
> > +/* Set task scheduling policy and priority */
> > +static void set_sched(int policy, int priority)
> > +{
> > +       struct sched_param param;
> > +
> > +       param.sched_priority = priority;
> > +       if (sched_setscheduler(0, policy, &param) != 0) {
> > +               perror("sched_setscheduler");
> > +               exit(EXIT_FAILURE);
> > +       }
> > +}
> > +
> > +/* Get process runtime from /proc/<pid>/stat */
> > +static float get_process_runtime(int pid)
> > +{
> > +       char path[256];
> > +       FILE *file;
> > +       long utime, stime;
> > +       int fields;
> > +
> > +       snprintf(path, sizeof(path), "/proc/%d/stat", pid);
> > +       file = fopen(path, "r");
> > +       if (file == NULL) {
> > +               perror("Failed to open stat file");
> > +               return -1;
> > +       }
> > +
> > +       /* Skip the first 13 fields and read the 14th and 15th */
> > +       fields = fscanf(file,
> > +                       "%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu",
> > +                       &utime, &stime);
> > +       fclose(file);
> > +
> > +       if (fields != 2) {
> > +               fprintf(stderr, "Failed to read stat file\n");
> > +               return -1;
> > +       }
> > +
> > +       /* Calculate the total time spent in the process */
> > +       long total_time = utime + stime;
> > +       long ticks_per_second = sysconf(_SC_CLK_TCK);
> > +       float runtime_seconds = total_time * 1.0 / ticks_per_second;
> > +
> > +       return runtime_seconds;
> > +}
> > +
> > +static enum scx_test_status setup(void **ctx)
> > +{
> > +       struct rt_stall *skel;
> > +
> > +       skel = rt_stall__open();
> > +       SCX_FAIL_IF(!skel, "Failed to open");
> > +       SCX_ENUM_INIT(skel);
> > +       SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel");
> > +
> > +       *ctx = skel;
> > +
> > +       return SCX_TEST_PASS;
> > +}
> > +
> > +static bool sched_stress_test(void)
> > +{
> > +       float cfs_runtime, rt_runtime, actual_ratio;
> > +       int cfs_pid, rt_pid;
> 
> I think it should be cfs_pid -> ext_pid, cfs_runtime -> ext_runtime
> 
> > +       float expected_min_ratio = 0.04; /* 4% */
> 
> Maybe add a comment that explains the 4% value? As in, we're expecting
> it to be around 5% so 0.04 accounts for values close enough but
> below < 5%.

Makes sense, I’ll add this comment (or something along those lines).

> 
> > +
> > +       ksft_print_header();
> > +       ksft_set_plan(1);
> > +
> > +       /* Create and set up a EXT task */
> > +       cfs_pid = fork();
> > +       if (cfs_pid == 0) {
> > +               set_affinity(CORE_ID);
> > +               process_func();
> > +               exit(0);
> > +       } else if (cfs_pid < 0) {
> > +               perror("fork for EXT task");
> > +               ksft_exit_fail();
> > +       }
> > +
> > +       /* Create an RT task */
> > +       rt_pid = fork();
> > +       if (rt_pid == 0) {
> > +               set_affinity(CORE_ID);
> > +               set_sched(SCHED_FIFO, 50);
> > +               process_func();
> > +               exit(0);
> > +       } else if (rt_pid < 0) {
> > +               perror("fork for RT task");
> > +               ksft_exit_fail();
> > +       }
> > +
> > +       /* Let the processes run for the specified time */
> > +       sleep(RUN_TIME);
> > +
> > +       /* Get runtime for the EXT task */
> > +       cfs_runtime = get_process_runtime(cfs_pid);
> > +       if (cfs_runtime != -1)
> > +               ksft_print_msg("Runtime of EXT task (PID %d) is %f seconds\n",
> > +                              cfs_pid, cfs_runtime);
> > +       else
> > +               ksft_exit_fail_msg("Error getting runtime for EXT task (PID %d)\n", cfs_pid);
> > +
> > +       /* Get runtime for the RT task */
> > +       rt_runtime = get_process_runtime(rt_pid);
> > +       if (rt_runtime != -1)
> > +               ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime);
> > +       else
> > +               ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid);
> > +
> 
> Minor, but why not
> 
> if (rt_runtime == -1)
>         ksft_exit_fail_msg("Error getting runtime for RT task (PID
> %d)\n", rt_pid);
> ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid,
> rt_runtime);
> 
> since ksft_exit_fail_msg never returns?

Ack.

> 
> > +       /* Kill the processes */
> > +       kill(cfs_pid, SIGKILL);
> > +       kill(rt_pid, SIGKILL);
> > +       waitpid(cfs_pid, NULL, 0);
> > +       waitpid(rt_pid, NULL, 0);
> > +
> > +       /* Verify that the scx task got enough runtime */
> > +       actual_ratio = cfs_runtime / (cfs_runtime + rt_runtime);
> > +       ksft_print_msg("EXT task got %.2f%% of total runtime\n", actual_ratio * 100);
> > +
> > +       if (actual_ratio >= expected_min_ratio) {
> > +               ksft_test_result_pass("PASS: EXT task got more than %.2f%% of runtime\n",
> > +                                     expected_min_ratio * 100);
> > +               return true;
> > +       }
> > +       ksft_test_result_fail("FAIL: EXT task got less than %.2f%% of runtime\n",
> > +                             expected_min_ratio * 100);
> > +       return false;
> > +}
> > +
> > +static enum scx_test_status run(void *ctx)
> > +{
> > +       struct rt_stall *skel = ctx;
> > +       struct bpf_link *link;
> > +       bool res;
> > +
> > +       link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops);
> > +       SCX_FAIL_IF(!link, "Failed to attach scheduler");
> > +
> > +       res = sched_stress_test();
> > +
> > +       SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
> > +       bpf_link__destroy(link);
> > +
> > +       if (!res)
> > +               ksft_exit_fail();
> > +
> > +       return SCX_TEST_PASS;
> > +}
> > +
> > +static void cleanup(void *ctx)
> > +{
> > +       struct rt_stall *skel = ctx;
> > +
> > +       rt_stall__destroy(skel);
> > +}
> > +
> > +struct scx_test rt_stall = {
> > +       .name = "rt_stall",
> > +       .description = "Verify that RT tasks cannot stall SCHED_EXT tasks",
> > +       .setup = setup,
> > +       .run = run,
> > +       .cleanup = cleanup,
> > +};
> > +REGISTER_SCX_TEST(&rt_stall)
> > --
> > 2.51.0
> >
> >

Thanks,
-Andrea