From: Song Liu <songliubraving@fb.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Netdev <netdev@vger.kernel.org>,
lkml <linux-kernel@vger.kernel.org>,
Kernel Team <Kernel-team@fb.com>,
"ast@kernel.org" <ast@kernel.org>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
"acme@kernel.org" <acme@kernel.org>
Subject: Re: [RFC perf,bpf 1/5] perf, bpf: Introduce PERF_RECORD_BPF_EVENT
Date: Thu, 8 Nov 2018 18:04:44 +0000 [thread overview]
Message-ID: <C858C862-E523-4CE8-AB39-CC9B27BE2538@fb.com> (raw)
In-Reply-To: <20181108150028.GU9761@hirez.programming.kicks-ass.net>
Hi Peter,
> On Nov 8, 2018, at 7:00 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>
> On Wed, Nov 07, 2018 at 06:25:04PM +0000, Song Liu wrote:
>>
>>
>>> On Nov 7, 2018, at 12:40 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>>>
>>> On Tue, Nov 06, 2018 at 12:52:42PM -0800, Song Liu wrote:
>>>> For better performance analysis of BPF programs, this patch introduces
>>>> PERF_RECORD_BPF_EVENT, a new perf_event_type that exposes BPF program
>>>> load/unload information to user space.
>>>>
>>>> /*
>>>> * Record different types of bpf events:
>>>> * enum perf_bpf_event_type {
>>>> * PERF_BPF_EVENT_UNKNOWN = 0,
>>>> * PERF_BPF_EVENT_PROG_LOAD = 1,
>>>> * PERF_BPF_EVENT_PROG_UNLOAD = 2,
>>>> * };
>>>> *
>>>> * struct {
>>>> * struct perf_event_header header;
>>>> * u16 type;
>>>> * u16 flags;
>>>> * u32 id; // prog_id or map_id
>>>> * };
>>>> */
>>>> PERF_RECORD_BPF_EVENT = 17,
>>>>
>>>> PERF_RECORD_BPF_EVENT contains minimal information about the BPF program.
>>>> Perf utility (or other user space tools) should listen to this event and
>>>> fetch more details about the event via BPF syscalls
>>>> (BPF_PROG_GET_FD_BY_ID, BPF_OBJ_GET_INFO_BY_FD, etc.).
>>>
>>> Why !? You're failing to explain why it cannot provide the full
>>> information there.
>>
>> Aha, I missed this part. I will add the following to next version. Please
>> let me know if anything is not clear.
>
>>
>> This design decision is picked for the following reasons. First, BPF
>> programs could be loaded-and-jited and/or unloaded before/during/after
>> perf-record run. Once a BPF programs is unloaded, it is impossible to
>> recover details of the program. It is impossible to provide the
>> information through a simple key (like the build ID). Second, BPF prog
>> annotation is under fast developments. Multiple informations will be
>> added to bpf_prog_info in the next few releases. Including all the
>> information of a BPF program in the perf ring buffer requires frequent
>> changes to the perf ABI, and thus makes it very difficult to manage
>> compatibility of perf utility.
>
> So I don't agree with that reasoning. If you want symbol information
> you'll just have to commit to some form of ABI. That bpf_prog_info is an
> ABI too.
At the beginning of the perf-record run, perf need to query bpf_prog_info
of already loaded BPF programs. Therefore, we need to commit to the
bpf_prog_info ABI. If we also include full information of the BPF program
in the perf ring buffer, we will commit to TWO ABIs.
Also, perf-record write the event to perf.data file, so the data need to be
serialized. This is implemented in patch 4/5. To include the data in the
ring buffer, we will need another piece of code in the kernel to do the
same serialization work.
On the other hand, processing BPF load/unload events synchronously should
not introduce too much overhead for meaningful use cases. If many BPF progs
are being loaded/unloaded within short period of time, it is not the steady
state that profiling works care about.
Would these resolve your concerns?
Thanks,
Song
next prev parent reply other threads:[~2018-11-08 18:05 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-06 20:52 [RFC perf,bpf 0/5] reveal invisible bpf programs Song Liu
2018-11-06 20:52 ` [RFC perf,bpf 1/5] perf, bpf: Introduce PERF_RECORD_BPF_EVENT Song Liu
2018-11-07 8:40 ` Peter Zijlstra
2018-11-07 18:25 ` Song Liu
2018-11-08 15:00 ` Peter Zijlstra
2018-11-08 18:04 ` Song Liu [this message]
2018-11-08 18:26 ` David Ahern
2018-11-08 18:49 ` Song Liu
2018-11-09 17:08 ` David Ahern
2018-11-09 18:49 ` Song Liu
2018-11-09 19:14 ` Alexei Starovoitov
2018-11-06 20:52 ` [RFC perf,bpf 2/5] perf: sync tools/include/uapi/linux/perf_event.h Song Liu
2018-11-06 20:52 ` [RFC perf,bpf 3/5] perf util: basic handling of PERF_RECORD_BPF_EVENT Song Liu
2018-11-06 20:52 ` [RFC perf,bpf 4/5] perf util: introduce bpf_prog_info_event Song Liu
2018-11-06 21:11 ` Alexei Starovoitov
2018-11-06 20:52 ` [RFC perf,bpf 5/5] perf util: generate bpf_prog_info_event for short living bpf programs Song Liu
2018-11-06 21:54 ` David Ahern
2018-11-06 23:17 ` Song Liu
2018-11-06 23:29 ` Alexei Starovoitov
2018-11-06 23:36 ` David Miller
2018-11-07 0:13 ` Alexei Starovoitov
2018-11-07 0:23 ` David Ahern
2018-11-07 0:26 ` Alexei Starovoitov
2018-11-07 0:44 ` David Ahern
2018-11-07 1:09 ` Alexei Starovoitov
2018-11-07 18:12 ` David Ahern
2018-11-07 18:28 ` 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=C858C862-E523-4CE8-AB39-CC9B27BE2538@fb.com \
--to=songliubraving@fb.com \
--cc=Kernel-team@fb.com \
--cc=acme@kernel.org \
--cc=ast@kernel.org \
--cc=daniel@iogearbox.net \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=peterz@infradead.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).