public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Jiri Olsa <jolsa@redhat.com>, LKML <linux-kernel@vger.kernel.org>,
	David Ahern <dsahern@gmail.com>,
	Stephane Eranian <eranian@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Andi Kleen <andi@firstfloor.org>,
	Frederic Weisbecker <fweisbec@gmail.com>
Subject: Re: [PATCH 37/37] perf data: Implement 'split' subcommand
Date: Wed, 24 Dec 2014 10:51:05 -0300	[thread overview]
Message-ID: <20141224135105.GR7644@kernel.org> (raw)
In-Reply-To: <1419405333-27952-38-git-send-email-namhyung@kernel.org>

Em Wed, Dec 24, 2014 at 04:15:33PM +0900, Namhyung Kim escreveu:
> The perf data split command is for splitting a (large) single data
> file into multiple files under a directory (perf.data.dir by default)
> so that it can be processed and reported using multiple threads.

How is it split? By CPU?
Will the metadata stay in a different file?
Please be as verbose on the description as possible :-)

- ARnaldo
 
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/Documentation/perf-data.txt |  28 +++++
>  tools/perf/builtin-data.c              | 223 +++++++++++++++++++++++++++++++++
>  2 files changed, 251 insertions(+)
> 
> diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
> index b8c83947715c..42708702f10c 100644
> --- a/tools/perf/Documentation/perf-data.txt
> +++ b/tools/perf/Documentation/perf-data.txt
> @@ -13,3 +13,31 @@ SYNOPSIS
>  DESCRIPTION
>  -----------
>  Data file related processing.
> +
> +COMMANDS
> +--------
> +split::
> +	Split single data file (perf.data) into multiple files under a directory
> +	in order to be reported by multiple threads.
> +
> +OPTIONS for 'split'
> +---------------------
> +-i::
> +--input::
> +	Specify input perf data file path.
> +
> +-o::
> +--output::
> +	Specify output perf data directory path.
> +
> +-v::
> +--verbose::
> +        Be more verbose (show counter open errors, etc).
> +
> +-f::
> +--force::
> +        Don't complain, do it.
> +
> +SEE ALSO
> +--------
> +linkperf:perf[1], linkperf:perf-report[1]
> diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
> index 1eee97d020fa..5f3173826850 100644
> --- a/tools/perf/builtin-data.c
> +++ b/tools/perf/builtin-data.c
> @@ -2,10 +2,14 @@
>  #include "builtin.h"
>  #include "perf.h"
>  #include "debug.h"
> +#include "session.h"
> +#include "evlist.h"
>  #include "parse-options.h"
>  
>  typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
>  
> +static const char *output_name;
> +
>  struct data_cmd {
>  	const char	*name;
>  	const char	*summary;
> @@ -41,10 +45,229 @@ static void print_usage(void)
>  	printf("\n");
>  }
>  
> +static int data_cmd_split(int argc, const char **argv, const char *prefix);
> +
>  static struct data_cmd data_cmds[] = {
> +	{ "split", "split single data file into multi-file", data_cmd_split },
>  	{ NULL },
>  };
>  
> +#define FD_HASH_BITS  7
> +#define FD_HASH_SIZE  (1 << FD_HASH_BITS)
> +#define FD_HASH_MASK  (FD_HASH_SIZE - 1)
> +
> +struct data_split {
> +	struct perf_tool	tool;
> +	struct perf_session	*session;
> +	enum {
> +		PER_CPU,
> +		PER_THREAD,
> +	} mode;
> +	int 			header_fd;
> +	u64			header_written;
> +	struct hlist_head	fd_hash[FD_HASH_SIZE];
> +	int			fd_hash_nr;
> +};
> +
> +struct fdhash_node {
> +	int			id;
> +	int			fd;
> +	struct hlist_node	list;
> +};
> +
> +static struct hlist_head *get_hash(struct data_split *split, int id)
> +{
> +	return &split->fd_hash[id % FD_HASH_MASK];
> +}
> +
> +static int perf_event__rewrite_header(struct perf_tool *tool,
> +				      union perf_event *event)
> +{
> +	struct data_split *split = container_of(tool, struct data_split, tool);
> +	ssize_t size;
> +
> +	size = writen(split->header_fd, event, event->header.size);
> +	if (size < 0)
> +		return -errno;
> +
> +	split->header_written += size;
> +	return 0;
> +}
> +
> +static int split_other_events(struct perf_tool *tool,
> +				union perf_event *event,
> +				struct perf_sample *sample __maybe_unused,
> +				struct machine *machine __maybe_unused)
> +{
> +	return perf_event__rewrite_header(tool, event);
> +}
> +
> +static int split_sample_event(struct perf_tool *tool,
> +				union perf_event *event,
> +				struct perf_sample *sample,
> +				struct perf_evsel *evsel __maybe_unused,
> +				struct machine *machine __maybe_unused)
> +{
> +	struct data_split *split = container_of(tool, struct data_split, tool);
> +	int id = split->mode == PER_CPU ? sample->cpu : sample->tid;
> +	int fd = -1;
> +	char buf[PATH_MAX];
> +	struct hlist_head *head;
> +	struct fdhash_node *node;
> +
> +	head = get_hash(split, id);
> +	hlist_for_each_entry(node, head, list) {
> +		if (node->id == id) {
> +			fd = node->fd;
> +			break;
> +		}
> +	}
> +
> +	if (fd == -1) {
> +		scnprintf(buf, sizeof(buf), "%s/perf.data.%d",
> +			  output_name, split->fd_hash_nr++);
> +
> +		fd = open(buf, O_RDWR|O_CREAT|O_TRUNC, 0600);
> +		if (fd < 0) {
> +			pr_err("cannot open data file: %s: %m\n", buf);
> +			return -1;
> +		}
> +
> +		node = malloc(sizeof(*node));
> +		if (node == NULL) {
> +			pr_err("memory allocation failed\n");
> +			return -1;
> +		}
> +
> +		node->id = id;
> +		node->fd = fd;
> +
> +		hlist_add_head(&node->list, head);
> +	}
> +
> +	return writen(fd, event, event->header.size) > 0 ? 0 : -errno;
> +}
> +
> +static int __data_cmd_split(struct data_split *split)
> +{
> +	struct perf_session *session = split->session;
> +	char *output = NULL;
> +	char buf[PATH_MAX];
> +	u64 sample_type;
> +	int header_fd;
> +	int ret = -1;
> +	int i;
> +
> +	if (!output_name) {
> +		if (asprintf(&output, "%s.dir", input_name) < 0) {
> +			pr_err("memory allocation failed\n");
> +			return -1;
> +		}
> +		output_name = output;
> +	}
> +
> +	mkdir(output_name, 0700);
> +
> +	/*
> +	 * This is necessary to write (copy) build-id table.  After
> +	 * processing header, dsos list will contain dso which was on
> +	 * the original build-id table.
> +	 */
> +	dsos__hit_all(session);
> +
> +	scnprintf(buf, sizeof(buf), "%s/perf.header", output_name);
> +	header_fd = open(buf, O_RDWR|O_CREAT|O_TRUNC, 0600);
> +	if (header_fd < 0) {
> +		pr_err("cannot open header file: %s: %m\n", buf);
> +		goto out;
> +	}
> +
> +	lseek(header_fd, session->header.data_offset, SEEK_SET);
> +
> +	sample_type = perf_evlist__combined_sample_type(session->evlist);
> +	if (sample_type & PERF_SAMPLE_CPU)
> +		split->mode = PER_CPU;
> +	else
> +		split->mode = PER_THREAD;
> +
> +	pr_debug("splitting data file for %s\n",
> +		 split->mode == PER_CPU ? "CPUs" : "threads");
> +
> +	split->header_fd = header_fd;
> +	perf_session__process_events(session, &split->tool);
> +
> +	for (i = 0; i < FD_HASH_SIZE; i++) {
> +		struct fdhash_node *pos;
> +		struct hlist_node *tmp;
> +
> +		hlist_for_each_entry_safe(pos, tmp, &split->fd_hash[i], list) {
> +			hlist_del(&pos->list);
> +			close(pos->fd);
> +			free(pos);
> +		}
> +	}
> +
> +	session->header.data_size = split->header_written;
> +	perf_session__write_header(session, session->evlist, header_fd, true);
> +
> +	close(header_fd);
> +	ret = 0;
> +out:
> +	free(output);
> +	return ret;
> +}
> +
> +int data_cmd_split(int argc, const char **argv, const char *prefix __maybe_unused)
> +{
> +	bool force = false;
> +	struct perf_session *session;
> +	struct perf_data_file file = {
> +		.mode  = PERF_DATA_MODE_READ,
> +	};
> +	struct data_split split = {
> +		.tool = {
> +			.sample		= split_sample_event,
> +			.fork		= split_other_events,
> +			.comm		= split_other_events,
> +			.exit		= split_other_events,
> +			.mmap		= split_other_events,
> +			.mmap2		= split_other_events,
> +			.lost		= split_other_events,
> +			.throttle	= split_other_events,
> +			.unthrottle	= split_other_events,
> +		},
> +	};
> +	const char * const split_usage[] = {
> +		"perf data split [<options>]",
> +		NULL
> +	};
> +	const struct option split_options[] = {
> +	OPT_STRING('i', "input", &input_name, "file", "input file name"),
> +	OPT_STRING('o', "output", &output_name, "file", "output directory name"),
> +	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
> +	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
> +	OPT_END()
> +	};
> +
> +	argc = parse_options(argc, argv, split_options, split_usage, 0);
> +	if (argc)
> +		usage_with_options(split_usage, split_options);
> +
> +	file.path = input_name;
> +	file.force = force;
> +	session = perf_session__new(&file, false, &split.tool);
> +	if (session == NULL)
> +		return -1;
> +
> +	split.session = session;
> +	symbol__init(&session->header.env);
> +
> +	__data_cmd_split(&split);
> +
> +	perf_session__delete(session);
> +	return 0;
> +}
> +
>  int cmd_data(int argc, const char **argv, const char *prefix)
>  {
>  	struct data_cmd *cmd;
> -- 
> 2.1.3

  reply	other threads:[~2014-12-24 13:51 UTC|newest]

Thread overview: 91+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-12-24  7:14 [RFC/PATCHSET 00/37] perf tools: Speed-up perf report by using multi thread (v1) Namhyung Kim
2014-12-24  7:14 ` [PATCH 01/37] perf tools: Set attr.task bit for a tracking event Namhyung Kim
2014-12-31 11:25   ` Jiri Olsa
2014-12-24  7:14 ` [PATCH 02/37] perf record: Use a software dummy event to track task/mmap events Namhyung Kim
2014-12-26 16:27   ` David Ahern
2014-12-27  5:28     ` Namhyung Kim
2014-12-29 12:58       ` Adrian Hunter
2014-12-30  5:51         ` Namhyung Kim
2014-12-30  9:04           ` Adrian Hunter
2014-12-24  7:14 ` [PATCH 03/37] perf tools: Use perf_data_file__fd() consistently Namhyung Kim
2014-12-26 16:30   ` David Ahern
2014-12-27  5:30     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 04/37] perf tools: Add multi file interface to perf_data_file Namhyung Kim
2014-12-25 22:08   ` Jiri Olsa
2014-12-26  1:19     ` Namhyung Kim
2014-12-31 11:26   ` Jiri Olsa
2014-12-31 14:55     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 05/37] perf tools: Create separate mmap for dummy tracking event Namhyung Kim
2014-12-25 22:08   ` Jiri Olsa
2014-12-26  1:45     ` Namhyung Kim
2014-12-25 22:09   ` Jiri Olsa
2014-12-26  1:55     ` Namhyung Kim
2014-12-26 16:51   ` David Ahern
2014-12-27  5:32     ` Namhyung Kim
2014-12-29 13:44   ` Adrian Hunter
2014-12-30  5:57     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 06/37] perf tools: Introduce perf_evlist__mmap_multi() Namhyung Kim
2014-12-24  7:15 ` [PATCH 07/37] perf tools: Do not use __perf_session__process_events() directly Namhyung Kim
2014-12-31 11:33   ` Jiri Olsa
2014-12-24  7:15 ` [PATCH 08/37] perf tools: Handle multi-file session properly Namhyung Kim
2014-12-31 12:01   ` Jiri Olsa
2014-12-31 14:53     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 09/37] perf record: Add -M/--multi option for multi file recording Namhyung Kim
2014-12-24  7:15 ` [PATCH 10/37] perf report: Skip dummy tracking event Namhyung Kim
2014-12-24  7:15 ` [PATCH 11/37] perf tools: Introduce thread__comm_time() helpers Namhyung Kim
2014-12-26 17:00   ` David Ahern
2014-12-27  5:36     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 12/37] perf tools: Add a test case for thread comm handling Namhyung Kim
2014-12-24  7:15 ` [PATCH 13/37] perf tools: Use thread__comm_time() when adding hist entries Namhyung Kim
2014-12-25 22:53   ` Jiri Olsa
2014-12-26  2:10     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 14/37] perf tools: Convert dead thread list into rbtree Namhyung Kim
2014-12-25 23:05   ` Jiri Olsa
2014-12-26  2:26     ` Namhyung Kim
2014-12-26 17:14       ` David Ahern
2014-12-27  5:42         ` Namhyung Kim
2014-12-27 15:31   ` David Ahern
2014-12-28 13:24     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 15/37] perf tools: Introduce machine__find*_thread_time() Namhyung Kim
2014-12-27 16:33   ` David Ahern
2014-12-28 14:50     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 16/37] perf tools: Add a test case for timed thread handling Namhyung Kim
2014-12-31 14:17   ` Jiri Olsa
2014-12-31 15:32     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 17/37] perf tools: Maintain map groups list in a leader thread Namhyung Kim
2014-12-24  7:15 ` [PATCH 18/37] perf tools: Remove thread when map groups initialization failed Namhyung Kim
2014-12-28  0:45   ` David Ahern
2014-12-29  7:08     ` Namhyung Kim
2014-12-24  7:15 ` [PATCH 19/37] perf tools: Introduce thread__find_addr_location_time() and friends Namhyung Kim
2014-12-24  7:15 ` [PATCH 20/37] perf tools: Add a test case for timed map groups handling Namhyung Kim
2014-12-24  7:15 ` [PATCH 21/37] perf tools: Protect dso symbol loading using a mutex Namhyung Kim
2014-12-24  7:15 ` [PATCH 22/37] perf tools: Protect dso cache tree using dso->lock Namhyung Kim
2014-12-24  7:15 ` [PATCH 23/37] perf tools: Protect dso cache fd with a mutex Namhyung Kim
2014-12-24  7:15 ` [PATCH 24/37] perf session: Pass struct events stats to event processing functions Namhyung Kim
2014-12-24  7:15 ` [PATCH 25/37] perf hists: Pass hists struct to hist_entry_iter functions Namhyung Kim
2014-12-24  7:15 ` [PATCH 26/37] perf tools: Move BUILD_ID_SIZE definition to perf.h Namhyung Kim
2014-12-24  7:15 ` [PATCH 27/37] perf report: Parallelize perf report using multi-thread Namhyung Kim
2014-12-24  7:15 ` [PATCH 28/37] perf tools: Add missing_threads rb tree Namhyung Kim
2014-12-24  7:15 ` [PATCH 29/37] perf top: Always creates thread in the current task tree Namhyung Kim
2014-12-24  7:15 ` [PATCH 30/37] perf tools: Fix progress ui to support multi thread Namhyung Kim
2014-12-24  7:15 ` [PATCH 31/37] perf record: Show total size of multi file data Namhyung Kim
2014-12-24  7:15 ` [PATCH 32/37] perf report: Add --multi-thread option and config item Namhyung Kim
2014-12-24  7:15 ` [PATCH 33/37] perf tools: Add front cache for dso data access Namhyung Kim
2014-12-24  7:15 ` [PATCH 34/37] perf tools: Convert lseek + read to pread Namhyung Kim
2014-12-24  7:15 ` [PATCH 35/37] perf callchain: Save eh/debug frame offset for dwarf unwind Namhyung Kim
2014-12-24  7:15 ` [PATCH 36/37] perf tools: Add new perf data command Namhyung Kim
2014-12-24  7:15 ` [PATCH 37/37] perf data: Implement 'split' subcommand Namhyung Kim
2014-12-24 13:51   ` Arnaldo Carvalho de Melo [this message]
2014-12-24 14:14     ` Namhyung Kim
2014-12-24 14:45       ` Arnaldo Carvalho de Melo
2014-12-26 13:59   ` Jiri Olsa
2014-12-27  5:21     ` Namhyung Kim
2014-12-26 14:02 ` [RFC/PATCHSET 00/37] perf tools: Speed-up perf report by using multi thread (v1) Jiri Olsa
2014-12-27  5:23   ` Namhyung Kim
2015-01-05 18:48 ` Andi Kleen
2015-01-06 15:50   ` Stephane Eranian
2015-01-07  7:13     ` Namhyung Kim
2015-01-07 15:14       ` Stephane Eranian
2015-01-08  5:19         ` Namhyung Kim
2015-01-07  6:58   ` Namhyung Kim
2015-01-08 14:52     ` Andi Kleen

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=20141224135105.GR7644@kernel.org \
    --to=acme@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=adrian.hunter@intel.com \
    --cc=andi@firstfloor.org \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@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