From: Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>
To: "Wangnan (F)" <wangnan0@huawei.com>
Cc: He Kuang <hekuang@huawei.com>, Li Zefan <lizefan@huawei.com>,
ast@plumgrid.com, pi3orama@163.com, xiakaixu@huawei.com,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
Jiri Olsa <jolsa@redhat.com>, David Ahern <dsahern@gmail.com>,
Namhyung Kim <namhyung@kernel.org>
Subject: perf eBPF patch ordering. was: Re: perf test LLVM was: Re: [GIT PULL 00/39] perf tools: filtering events using eBPF programs
Date: Fri, 31 Jul 2015 12:35:22 -0300 [thread overview]
Message-ID: <20150731153522.GA16700@kernel.org> (raw)
In-Reply-To: <55AF1EA5.5020500@huawei.com>
Em Wed, Jul 22, 2015 at 12:40:05PM +0800, Wangnan (F) escreveu:
> I noticed that you have rebase your perf/ebpf branch to 4.2-rc3. I have also
> done it in my tree. Please see:
>
> https://github.com/WangNan0/linux.git ebpf
>
> Also, please recollect patch "perf tests: Add LLVM test for eBPF on-the-fly
> compiling", which adds verbose control. I'll also post it again.
I did it and some other rebases, expect more, but now I've got to:
commit f0f99c45295e67787ad532492d9bebd6d9b56d3a
Author: Wang Nan <wangnan0@huawei.com>
Date: Wed Jul 8 11:50:57 2015 +0000
perf record: Enable passing bpf object file to --event
Which I split in 3 patches, no changes to the code, just avoiding doing
multiple things per patch, but point here is, when I see "enable passing
bpf object file to --event" I apply the patch and expect to be able to
go straight away and do:
perf record -e foo.o sleep 1
And get some informative message as to hey, yes, I managed to do what
you asked or something is wrong, but I get:
[root@felicio ~]# perf record --event foo.o sleep
event syntax error: 'foo.o'
\___ parser error
Run 'perf list' for a list of valid events
usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-e, --event <event> event selector. use 'perf list' to list available events
[root@felicio ~]#
So, is it enabled or is it not? Doesn't look like. I.e. I think the best
thing is to only expose this when it can be used. Till that time, we can
go on adding infrastructure to enable that and test that infrastructure
via 'perf test', like you did with 'perf test LLVM', thanks for doing
that:
[root@felicio ~]# perf test LLVM
38: Test LLVM searching and compiling : Ok
And in verbose mode we can see that it is finding everything it needs on this
RHEL7.1 test machine, after I got all the pieces from the llvm project git
repos and built it:
[root@felicio ~]# perf test -v LLVM
38: Test LLVM searching and compiling :
--- start ---
test child forked, pid 24457
Kernel build dir is set to /lib/modules/4.2.0-rc3+/build
set env: KBUILD_DIR=/lib/modules/4.2.0-rc3+/build
unset env: KBUILD_OPTS
include option is set to -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.8.3/include -I/home/acme/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/acme/git/linux/include -Iinclude -I/home/acme/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/acme/git/linux/include/uapi -Iinclude/generated/uapi -include /home/acme/git/linux/include/linux/kconfig.h
set env: CLANG_EXEC=/usr/local/bin/clang
set env: CLANG_OPTIONS=-xc
set env: KERNEL_INC_OPTIONS= -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.8.3/include -I/home/acme/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/acme/git/linux/include -Iinclude -I/home/acme/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/acme/git/linux/include/uapi -Iinclude/generated/uapi -include /home/acme/git/linux/include/linux/kconfig.h
set env: WORKING_DIR=/lib/modules/4.2.0-rc3+/build
set env: CLANG_SOURCE=-
llvm compiling command template: echo '__attribute__((section("do_fork"), used)) int fork(void *ctx) {return 0;} char _license[] __attribute__((section("license"), used)) = "GPL";int _version __attribute__((section("version"), used)) = 0x40100;' | $CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS -Wno-unused-value -Wno-pointer-sign -working-directory $WORKING_DIR -c "$CLANG_SOURCE" -target bpf -O2 -o -
test child finished with 0
---- end ----
Test LLVM searching and compiling: Ok
[root@felicio ~]#
Then, the next patch is even more exciting:
perf record: Compile scriptlets if pass '.c' to --event
But its changelog doesn't come with a "hello_bpf.c" for me to use nor
the output of using it... bummer, I expected to use this new feature
right now :-)
Also, originally it had this name:
[acme@felicio linux]$ git show --oneline f0f99c45295e67787ad532492d9bebd6d9b56d3a | head -1
f0f99c45295e perf record: Enable passing bpf object file to --event
But it doesn't even touch 'perf record':
[acme@felicio linux]$ git show f0f99c45295e67787ad532492d9bebd6d9b56d3a | grep builtin-record
[acme@felicio linux]$
So perhaps this was an artifact of refactoring previous patchkits?
I.e. I haven't looked at the other patches, but conceptually I can't think
_why_ would we expose a new feature that would only later be wired up and
then _really_ work.
Please reorder the patches to only expose --event foo.[oc] to when we can use
it.
Please continue from what I have in my perf/ebpf branch, it is all rebased to
latest tip/perf/core and passes most of the tests I put it thru (make -C
tools/perf build-test, 'perf test', fedora 21, RHEL 7.1).
Thanks!
- Arnaldo
next prev parent reply other threads:[~2015-07-31 15:36 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-09 12:35 [GIT PULL 00/39] perf tools: filtering events using eBPF programs Wang Nan
2015-07-09 12:35 ` [PATCH 01/39] bpf tools: Collect symbol table from SHT_SYMTAB section Wang Nan
2015-07-09 12:35 ` [PATCH 02/39] bpf tools: Collect eBPF programs from their own sections Wang Nan
2015-07-09 15:58 ` Arnaldo Carvalho de Melo
2015-07-10 3:07 ` Wangnan (F)
2015-07-13 19:51 ` Arnaldo Carvalho de Melo
2015-07-14 3:58 ` Wangnan (F)
2015-07-09 12:35 ` [PATCH 03/39] bpf tools: Collect relocation sections from SHT_REL sections Wang Nan
2015-07-09 12:35 ` [PATCH 04/39] bpf tools: Record map accessing instructions for each program Wang Nan
2015-07-09 12:35 ` [PATCH 05/39] bpf tools: Add bpf.c/h for common bpf operations Wang Nan
2015-07-09 12:35 ` [PATCH 06/39] bpf tools: Create eBPF maps defined in an object file Wang Nan
2015-07-13 19:54 ` Arnaldo Carvalho de Melo
2015-07-14 3:59 ` Wangnan (F)
2015-07-09 12:35 ` [PATCH 07/39] bpf tools: Relocate eBPF programs Wang Nan
2015-07-09 12:35 ` [PATCH 08/39] bpf tools: Introduce bpf_load_program() to bpf.c Wang Nan
2015-07-09 12:35 ` [PATCH 09/39] bpf tools: Load eBPF programs in object files into kernel Wang Nan
2015-07-09 12:35 ` [PATCH 10/39] bpf tools: Introduce accessors for struct bpf_program Wang Nan
2015-07-09 12:35 ` [PATCH 11/39] bpf tools: Link all bpf objects onto a list Wang Nan
2015-07-09 12:35 ` [PATCH 12/39] perf tools: Introduce llvm config options Wang Nan
2015-07-21 11:13 ` [PATCH 12/39 update] " Wang Nan
2015-08-08 8:16 ` [tip:perf/core] " tip-bot for Wang Nan
2015-07-09 12:35 ` [PATCH 13/39] perf tools: Call clang to compile C source to object code Wang Nan
2015-07-09 12:35 ` [PATCH 14/39] perf tools: Auto detecting kernel build directory Wang Nan
2015-07-13 21:46 ` Arnaldo Carvalho de Melo
2015-07-14 6:56 ` Wangnan (F)
2015-07-14 7:16 ` Wangnan (F)
2015-07-09 12:35 ` [PATCH 15/39] perf tools: Auto detecting kernel include options Wang Nan
2015-08-08 8:17 ` [tip:perf/core] " tip-bot for Wang Nan
2015-07-09 12:35 ` [PATCH 16/39] perf tests: Add LLVM test for eBPF on-the-fly compiling Wang Nan
2015-07-15 10:54 ` [PATCH updated " Wang Nan
2015-07-22 4:46 ` [PATCH 16/39 RESEND] " Wang Nan
2015-07-09 12:35 ` [PATCH 17/39] perf tools: Make perf depend on libbpf Wang Nan
2015-07-09 12:35 ` [PATCH 18/39] perf record: Enable passing bpf object file to --event Wang Nan
2015-07-09 12:35 ` [PATCH 19/39] perf record: Compile scriptlets if pass '.c' " Wang Nan
2015-07-09 12:35 ` [PATCH 20/39] perf tools: Parse probe points of eBPF programs during preparation Wang Nan
2015-07-09 12:35 ` [PATCH 21/39] perf probe: Attach trace_probe_event with perf_probe_event Wang Nan
2015-07-09 12:35 ` [PATCH 22/39] perf record: Probe at kprobe points Wang Nan
2015-07-09 12:35 ` [PATCH 23/39] perf record: Load all eBPF object into kernel Wang Nan
2015-07-09 12:35 ` [PATCH 24/39] perf tools: Add bpf_fd field to evsel and config it Wang Nan
2015-07-09 12:35 ` [PATCH 25/39] perf tools: Attach eBPF program to perf event Wang Nan
2015-07-09 12:35 ` [PATCH 26/39] perf tools: Suppress probing messages when probing by BPF loading Wang Nan
2015-07-09 12:35 ` [PATCH 27/39] perf record: Add clang options for compiling BPF scripts Wang Nan
2015-07-09 12:35 ` [PATCH 28/39] bpf tools: Load a program with different instances using preprocessor Wang Nan
2015-07-13 5:44 ` Wangnan (F)
2015-07-09 12:35 ` [PATCH 29/39] perf tools: Fix probe-event.h include Wang Nan
2015-07-09 12:35 ` [PATCH 30/39] perf probe: Reset args and nargs for probe_trace_event when failure Wang Nan
2015-07-09 12:35 ` [PATCH 31/39] perf tools: Move linux/filter.h to tools/include Wang Nan
2015-07-09 12:35 ` [PATCH 32/39] perf tools: Add BPF_PROLOGUE config options for further patches Wang Nan
2015-07-09 12:35 ` [PATCH 33/39] perf tools: Introduce arch_get_reg_info() for x86 Wang Nan
2015-07-09 12:35 ` [PATCH 34/39] perf tools: Add prologue for BPF programs for fetching arguments Wang Nan
2015-07-09 12:35 ` [PATCH 35/39] perf tools: Generate prologue for BPF programs Wang Nan
2015-07-09 12:35 ` [PATCH 36/39] perf tools: Use same BPF program if arguments are identical Wang Nan
2015-07-09 12:35 ` [PATCH 37/39] perf record: Support custom vmlinux path Wang Nan
2015-07-09 12:35 ` [PATCH 38/39] perf probe: Init symbol as kprobe if any event is kprobe Wang Nan
2015-07-09 12:35 ` [PATCH 39/39] perf tools: Support attach BPF program on uprobe events Wang Nan
2015-07-14 15:36 ` perf test LLVM was: Re: [GIT PULL 00/39] perf tools: filtering events using eBPF programs Arnaldo Carvalho de Melo
2015-07-15 10:49 ` Wangnan (F)
2015-07-15 11:20 ` Arnaldo Carvalho de Melo
2015-07-17 2:34 ` Wangnan (F)
[not found] ` <CA+JHD93=ZMFP0gB1NqTXGBjTfSyYC-53Uj7r11gQJnKtQRKcDg@mail.gmail.com>
2015-07-21 11:09 ` Wangnan (F)
2015-07-21 11:41 ` Arnaldo Carvalho de Melo
2015-07-22 4:40 ` Wangnan (F)
2015-07-31 15:35 ` Arnaldo Carvalho de Melo [this message]
2015-07-31 20:31 ` perf eBPF patch ordering. was: " Arnaldo Carvalho de Melo
2015-08-03 2:37 ` Wangnan (F)
2015-08-03 15:07 ` Arnaldo Carvalho de Melo
2015-08-03 15:19 ` Arnaldo Carvalho de Melo
2015-08-03 15:53 ` pi3orama
2015-08-03 16:11 ` Arnaldo Carvalho de Melo
2015-08-03 19:49 ` Arnaldo Carvalho de Melo
2015-08-04 5:28 ` Wangnan (F)
2015-08-04 10:39 ` Wangnan (F)
2015-08-04 15:55 ` Arnaldo Carvalho de Melo
2015-08-04 16:11 ` Arnaldo Carvalho de Melo
2015-08-04 16:13 ` pi3orama
2015-08-06 1:44 ` Wangnan (F)
2015-08-06 14:46 ` Arnaldo Carvalho de Melo
2015-08-06 15:58 ` Arnaldo Carvalho de Melo
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=20150731153522.GA16700@kernel.org \
--to=arnaldo.melo@gmail.com \
--cc=ast@plumgrid.com \
--cc=dsahern@gmail.com \
--cc=hekuang@huawei.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.com \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=pi3orama@163.com \
--cc=wangnan0@huawei.com \
--cc=xiakaixu@huawei.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.