From: Song Liu <songliubraving@fb.com>
To: Andrii Nakryiko <andriin@fb.com>
Cc: bpf <bpf@vger.kernel.org>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
Alexei Starovoitov <ast@fb.com>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
"andrii.nakryiko@gmail.com" <andrii.nakryiko@gmail.com>,
Kernel Team <Kernel-team@fb.com>
Subject: Re: [PATCH bpf-next 4/5] samples/bpf: switch trace_output sample to perf_buffer API
Date: Tue, 23 Jul 2019 09:29:55 +0000 [thread overview]
Message-ID: <3ED4F7C4-CE2D-41D6-B26D-FFD1EDB23157@fb.com> (raw)
In-Reply-To: <20190723043112.3145810-5-andriin@fb.com>
> On Jul 22, 2019, at 9:31 PM, Andrii Nakryiko <andriin@fb.com> wrote:
>
> Convert trace_output sample to libbpf's perf_buffer API.
>
> Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
> ---
> samples/bpf/trace_output_user.c | 43 +++++++++++----------------------
> 1 file changed, 14 insertions(+), 29 deletions(-)
>
> diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
> index 2dd1d39b152a..8ee47699a870 100644
> --- a/samples/bpf/trace_output_user.c
> +++ b/samples/bpf/trace_output_user.c
> @@ -18,9 +18,6 @@
> #include <libbpf.h>
> #include "bpf_load.h"
> #include "perf-sys.h"
> -#include "trace_helpers.h"
> -
> -static int pmu_fd;
>
> static __u64 time_get_ns(void)
> {
> @@ -31,12 +28,12 @@ static __u64 time_get_ns(void)
> }
>
> static __u64 start_time;
> +static __u64 cnt;
>
> #define MAX_CNT 100000ll
>
> -static int print_bpf_output(void *data, int size)
> +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
> {
> - static __u64 cnt;
> struct {
> __u64 pid;
> __u64 cookie;
> @@ -45,7 +42,7 @@ static int print_bpf_output(void *data, int size)
> if (e->cookie != 0x12345678) {
> printf("BUG pid %llx cookie %llx sized %d\n",
> e->pid, e->cookie, size);
> - return LIBBPF_PERF_EVENT_ERROR;
> + return;
> }
>
> cnt++;
> @@ -53,30 +50,14 @@ static int print_bpf_output(void *data, int size)
> if (cnt == MAX_CNT) {
> printf("recv %lld events per sec\n",
> MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
> - return LIBBPF_PERF_EVENT_DONE;
> + return;
> }
> -
> - return LIBBPF_PERF_EVENT_CONT;
> -}
> -
> -static void test_bpf_perf_event(void)
> -{
> - struct perf_event_attr attr = {
> - .sample_type = PERF_SAMPLE_RAW,
> - .type = PERF_TYPE_SOFTWARE,
> - .config = PERF_COUNT_SW_BPF_OUTPUT,
> - };
> - int key = 0;
> -
> - pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
> -
> - assert(pmu_fd >= 0);
> - assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
> - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
> }
>
> int main(int argc, char **argv)
> {
> + struct perf_buffer_opts pb_opts = {};
> + struct perf_buffer *pb;
> char filename[256];
> FILE *f;
> int ret;
> @@ -88,16 +69,20 @@ int main(int argc, char **argv)
> return 1;
> }
>
> - test_bpf_perf_event();
> -
> - if (perf_event_mmap(pmu_fd) < 0)
> + pb_opts.sample_cb = print_bpf_output;
> + pb = perf_buffer__new(map_fd[0], 8, &pb_opts);
> + ret = libbpf_get_error(pb);
> + if (ret) {
> + printf("failed to setup perf_buffer: %d\n", ret);
> return 1;
> + }
>
> f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r");
> (void) f;
>
> start_time = time_get_ns();
> - ret = perf_event_poller(pmu_fd, print_bpf_output);
> + while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) {
> + }
> kill(0, SIGINT);
> return ret;
> }
> --
> 2.17.1
>
next prev parent reply other threads:[~2019-07-23 9:30 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-23 4:31 [PATCH bpf-next 0/5] switch samples and tests to libbpf perf buffer API Andrii Nakryiko
2019-07-23 4:31 ` [PATCH bpf-next 1/5] selftests/bpf: convert test_get_stack_raw_tp to perf_buffer API Andrii Nakryiko
2019-07-23 9:25 ` Song Liu
2019-07-23 17:38 ` Andrii Nakryiko
2019-07-23 4:31 ` [PATCH bpf-next 2/5] selftests/bpf: switch test_tcpnotify " Andrii Nakryiko
2019-07-23 9:35 ` Song Liu
2019-07-23 4:31 ` [PATCH bpf-next 3/5] samples/bpf: convert xdp_sample_pkts_user " Andrii Nakryiko
2019-07-23 9:39 ` Song Liu
2019-07-23 12:34 ` Toke Høiland-Jørgensen
2019-07-23 4:31 ` [PATCH bpf-next 4/5] samples/bpf: switch trace_output sample " Andrii Nakryiko
2019-07-23 9:29 ` Song Liu [this message]
2019-07-23 4:31 ` [PATCH bpf-next 5/5] selftests/bpf: remove perf buffer helpers Andrii Nakryiko
2019-07-23 9:39 ` Song Liu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3ED4F7C4-CE2D-41D6-B26D-FFD1EDB23157@fb.com \
--to=songliubraving@fb.com \
--cc=Kernel-team@fb.com \
--cc=andrii.nakryiko@gmail.com \
--cc=andriin@fb.com \
--cc=ast@fb.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).