From: Andrii Nakryiko <andrii.nakryiko@gmail.com>
To: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Eric Sage <eric@sage.org>, Networking <netdev@vger.kernel.org>,
bpf <bpf@vger.kernel.org>, Daniel Borkmann <daniel@iogearbox.net>,
xdp-newbies@vger.kernel.org, brouer@redhat.org,
Alexei Starovoitov <ast@kernel.org>, Jiri Olsa <jolsa@redhat.com>
Subject: Re: [PATCH] samples/bpf: make xdp_monitor use raw_tracepoints
Date: Tue, 15 Oct 2019 21:05:18 -0700 [thread overview]
Message-ID: <CAEf4BzacEF0Ga921DCuYCVTxR4rFdOzmRt5o0T7HH-H38gEccg@mail.gmail.com> (raw)
In-Reply-To: <20191007110020.6bf8dbc2@carbon>
On Mon, Oct 7, 2019 at 2:00 AM Jesper Dangaard Brouer <brouer@redhat.com> wrote:
>
>
> On Mon, 7 Oct 2019 04:57:26 +0000 Eric Sage <eric@sage.org> wrote:
>
> > raw_tracepoints are an eBPF alternative to standard tracepoints which
> > attach to a tracepoint without the perf layer being executed, making
> > them faster.
> >
> > Since xdp_monitor is supposed to have as little impact on the system as
> > possible it is switched to using them by append raw_ to the SEC names.
> >
> > There was also a small issues with 'samples/bpf/bpf_load' - it was
> > loading the raw_tracepoints with the tracing subsystem name still
> > attached, which the bpf syscall rejects with a No such file or directory
> > error. This is now fixed.
> >
> > Signed-off-by: Eric Sage <eric@sage.org>
> > ---
> > samples/bpf/bpf_load.c | 5 +++--
> > samples/bpf/xdp_monitor_kern.c | 26 +++++++++++++-------------
> > 2 files changed, 16 insertions(+), 15 deletions(-)
>
> If there is an issue in the loader 'samples/bpf/bpf_load.c' then we
> should of-cause fix it, but you should be aware that we are in general
> trying to deprecate this loader, and we want to convert users over to
> libbpf.
>
> This patch seems like a good first step forward. Longer term, I would
> like to see this converted into using libbpf. The library are missing
> attach helpers for regular tracepoints, but for raw_tracepoints it does
> contain bpf_raw_tracepoint_open().
libbpf has both bpf_program__attach_tracepoint() and
bpf_program__attach_raw_tracepoint(), please use them, not lower-level
bpf_raw_tracepoint_open(). See selftests/bpf/prog_tests/attach_probe.c
for examples.
>
> You can see an example of how xdp_monitor have been converted into
> using libbpf and raw_tracepoints here (by Jiri Olsa):
>
> https://github.com/xdp-project/xdp-tutorial/blob/master/tracing02-xdp-monitor/trace_prog_kern.c
>
>
[...]
next prev parent reply other threads:[~2019-10-16 4:05 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-07 4:57 [PATCH] samples/bpf: make xdp_monitor use raw_tracepoints Eric Sage
2019-10-07 9:00 ` Jesper Dangaard Brouer
2019-10-16 4:05 ` Andrii Nakryiko [this message]
2019-10-16 4:21 ` Eric Sage
2019-10-16 13:34 ` Jesper Dangaard Brouer
2019-10-16 15:57 ` Eric Sage
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=CAEf4BzacEF0Ga921DCuYCVTxR4rFdOzmRt5o0T7HH-H38gEccg@mail.gmail.com \
--to=andrii.nakryiko@gmail.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brouer@redhat.com \
--cc=brouer@redhat.org \
--cc=daniel@iogearbox.net \
--cc=eric@sage.org \
--cc=jolsa@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=xdp-newbies@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).