@@ -11,9 +11,9 @@ const volatile __u64 min_us = 0;
const volatile pid_t targ_pid = 0;
struct {
- __uint(type, BPF_MAP_TYPE_HASH);
- __uint(max_entries, 10240);
- __type(key, u32);
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
__type(value, u64);
} start SEC(".maps");
@@ -25,15 +25,20 @@ struct {
/* record enqueue timestamp */
__always_inline
-static int trace_enqueue(u32 tgid, u32 pid)
+static int trace_enqueue(struct task_struct *t)
{
- u64 ts;
+ u32 pid = t->pid;
+ u64 *ptr;
if (!pid || (targ_pid && targ_pid != pid))
return 0;
- ts = bpf_ktime_get_ns();
- bpf_map_update_elem(&start, &pid, &ts, 0);
+ ptr = bpf_task_storage_get(&start, t, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!ptr)
+ return 0;
+
+ *ptr = bpf_ktime_get_ns();
return 0;
}
@@ -43,7 +48,7 @@ int handle__sched_wakeup(u64 *ctx)
/* TP_PROTO(struct task_struct *p) */
struct task_struct *p = (void *)ctx[0];
- return trace_enqueue(p->tgid, p->pid);
+ return trace_enqueue(p);
}
SEC("tp_btf/sched_wakeup_new")
@@ -52,7 +57,7 @@ int handle__sched_wakeup_new(u64 *ctx)
/* TP_PROTO(struct task_struct *p) */
struct task_struct *p = (void *)ctx[0];
- return trace_enqueue(p->tgid, p->pid);
+ return trace_enqueue(p);
}
SEC("tp_btf/sched_switch")
@@ -70,12 +75,16 @@ int handle__sched_switch(u64 *ctx)
/* ivcsw: treat like an enqueue event and store timestamp */
if (prev->state == TASK_RUNNING)
- trace_enqueue(prev->tgid, prev->pid);
+ trace_enqueue(prev);
pid = next->pid;
+ /* For pid mismatch, save a bpf_task_storage_get */
+ if (!pid || (targ_pid && targ_pid != pid))
+ return 0;
+
/* fetch timestamp and calculate delta */
- tsp = bpf_map_lookup_elem(&start, &pid);
+ tsp = bpf_task_storage_get(&start, next, 0, 0);
if (!tsp)
return 0; /* missed enqueue */
@@ -91,7 +100,7 @@ int handle__sched_switch(u64 *ctx)
bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
&event, sizeof(event));
- bpf_map_delete_elem(&start, &pid);
+ bpf_task_storage_delete(&start, next);
return 0;
}
Replace hashtab with task local storage in runqslower. This improves the performance of these BPF programs. The following table summarizes average runtime of these programs, in nanoseconds: task-local hash-prealloc hash-no-prealloc handle__sched_wakeup 125 340 3124 handle__sched_wakeup_new 2812 1510 2998 handle__sched_switch 151 208 991 Note that, task local storage gives better performance than hashtab for handle__sched_wakeup and handle__sched_switch. On the other hand, for handle__sched_wakeup_new, task local storage is slower than hashtab with prealloc. This is because handle__sched_wakeup_new accesses the data for the first time, so it has to allocate the data for task local storage. Once the initial allocation is done, subsequent accesses, as those in handle__sched_wakeup, are much faster with task local storage. If we disable hashtab prealloc, task local storage is much faster for all 3 functions. Acked-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Song Liu <songliubraving@fb.com> --- tools/bpf/runqslower/runqslower.bpf.c | 33 +++++++++++++++++---------- 1 file changed, 21 insertions(+), 12 deletions(-)