On Thu, Jul 27, 2023 at 03:11:00PM -0700, Yonghong Song wrote: > > > On 7/27/23 1:34 AM, Adam Sindelar wrote: > > We already provide ring_buffer__epoll_fd to enable use of external > > polling systems. However, the only API available to consume the ring > > buffer is ring_buffer__consume, which always checks all rings. When > > polling for many events, this can be wasteful. > > > > Signed-off-by: Adam Sindelar <adam@xxxxxxxxxxxx> > > --- > > v1->v2: Added entry to libbpf.map > > v2->v3: Correctly set errno and handle overflow > > v3->v4: Fixed an embarrasing typo from zealous autocomplete > > > > tools/lib/bpf/libbpf.h | 1 + > > tools/lib/bpf/libbpf.map | 1 + > > tools/lib/bpf/ringbuf.c | 22 ++++++++++++++++++++++ > > 3 files changed, 24 insertions(+) > > Could you add a selftest to exercise ring_buffer__consume_ring()? > This way, people can better understand how this API could be used. > Yes, will do - I'll try to send out v5 with a test case this afternoon. As a note, I looked at the perf ring buffer API and it turns out Andrii Nakryiko saw the same problem and solved in a similar way in 2020. (See perf_buffer__consume_buffer). > > > > diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h > > index 55b97b2087540..20ccc65eb3f9d 100644 > > --- a/tools/lib/bpf/libbpf.h > > +++ b/tools/lib/bpf/libbpf.h > > @@ -1195,6 +1195,7 @@ LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd, > > ring_buffer_sample_fn sample_cb, void *ctx); > > LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); > > LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); > > +LIBBPF_API int ring_buffer__consume_ring(struct ring_buffer *rb, uint32_t ring_id); > > LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb); > [...]
