sched_ext/scx_qmap: Add an example usage of DSQ iterator

Implement periodic dumping of the shared DSQ to demonstrate the use of the
newly added DSQ iterator.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: bpf@vger.kernel.org

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index b1d0b09c966e010962a32a112d48cb2fda30407e..27e35066a6029c864bc9e77bd30dd75ce6d3ec9c 100644 (file)
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -36,6 +36,7 @@ const volatile u32 stall_user_nth;
 const volatile u32 stall_kernel_nth;
 const volatile u32 dsp_inf_loop_after;
 const volatile u32 dsp_batch;
+const volatile bool print_shared_dsq;
 const volatile s32 disallow_tgid;
 const volatile bool suppress_dump;
 
@@ -604,10 +605,34 @@ out:
        scx_bpf_put_cpumask(online);
 }
 
+/*
+ * Dump the currently queued tasks in the shared DSQ to demonstrate the usage of
+ * scx_bpf_dsq_nr_queued() and DSQ iterator. Raise the dispatch batch count to
+ * see meaningful dumps in the trace pipe.
+ */
+static void dump_shared_dsq(void)
+{
+       struct task_struct *p;
+       s32 nr;
+
+       if (!(nr = scx_bpf_dsq_nr_queued(SHARED_DSQ)))
+               return;
+
+       bpf_printk("Dumping %d tasks in SHARED_DSQ in reverse order", nr);
+
+       bpf_rcu_read_lock();
+       bpf_for_each(scx_dsq, p, SHARED_DSQ, SCX_DSQ_ITER_REV)
+               bpf_printk("%s[%d]", p->comm, p->pid);
+       bpf_rcu_read_unlock();
+}
+
 static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer)
 {
        monitor_cpuperf();
 
+       if (print_shared_dsq)
+               dump_shared_dsq();
+
        bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
        return 0;
 }

diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index e4e3ecffc4cf3ae59a5ef932a3ec0bb497fbd176..304f0488a386b8d2c64c8404183b9f324d9e991c 100644 (file)
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -20,7 +20,7 @@ const char help_fmt[] =
 "See the top-level comment in .bpf.c for more details.\n"
 "\n"
 "Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
-"       [-d PID] [-D LEN] [-p] [-v]\n"
+"       [-P] [-d PID] [-D LEN] [-p] [-v]\n"
 "\n"
 "  -s SLICE_US   Override slice duration\n"
 "  -e COUNT      Trigger scx_bpf_error() after COUNT enqueues\n"
@@ -28,6 +28,7 @@ const char help_fmt[] =
 "  -T COUNT      Stall every COUNT'th kernel thread\n"
 "  -l COUNT      Trigger dispatch infinite looping after COUNT dispatches\n"
 "  -b COUNT      Dispatch upto COUNT tasks together\n"
+"  -P            Print out DSQ content to trace_pipe every second, use with -b\n"
 "  -d PID        Disallow a process from switching into SCHED_EXT (-1 for self)\n"
 "  -D LEN        Set scx_exit_info.dump buffer length\n"
 "  -S            Suppress qmap-specific debug dump\n"
@@ -62,7 +63,7 @@ int main(int argc, char **argv)
 
        skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
 
-       while ((opt = getopt(argc, argv, "s:e:t:T:l:b:d:D:Spvh")) != -1) {
+       while ((opt = getopt(argc, argv, "s:e:t:T:l:b:Pd:D:Spvh")) != -1) {
                switch (opt) {
                case 's':
                        skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -82,6 +83,9 @@ int main(int argc, char **argv)
                case 'b':
                        skel->rodata->dsp_batch = strtoul(optarg, NULL, 0);
                        break;
+               case 'P':
+                       skel->rodata->print_shared_dsq = true;
+                       break;
                case 'd':
                        skel->rodata->disallow_tgid = strtol(optarg, NULL, 0);
                        if (skel->rodata->disallow_tgid < 0)