mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Jiri Olsa <jolsa@kernel.org>, LKML <linux-kernel@vger.kernel.org>,
	David Ahern <dsahern@gmail.com>, Andi Kleen <andi@firstfloor.org>,
	Stephane Eranian <eranian@google.com>,
	Wang Nan <wangnan0@huawei.com>
Subject: [PATCH v6 14/25] perf hists: Resort after filtering hierarchy
Date: Tue, 16 Feb 2016 23:08:32 +0900	[thread overview]
Message-ID: <1455631723-17345-15-git-send-email-namhyung@kernel.org> (raw)
In-Reply-To: <1455631723-17345-1-git-send-email-namhyung@kernel.org>

In hierarchy mode, a filter can affect periods of entries in upper
hierarchy.  So it needs to resort the hists after filter.

For example, let's look at following example:

 Overhead      Command / Shared Object / Symbol
 ------------  --------------------------------
 30.00%        perf
    20.00%        perf
       10.00%        main
        5.00%        pr_debug
	5.00%        memcpy
    10.00%        [kernel.vmlinux]
        8.00%        memset
	2.00%        cpu_idle

If we apply simbol filter for 'mem' it should look like this

 13.00%        perf
     8.00%        [kernel.vmlinux]
        8.00%        memset
     5.00%        perf
	5.00%        memcpy

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/hist.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 585743853ca7..f7b86a372b87 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1645,9 +1645,47 @@ static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t fil
 	}
 }
 
+static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct rb_root new_root = RB_ROOT;
+	struct rb_node *nd;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	if (he->leaf || he->filtered)
+		return;
+
+	nd = rb_first(&he->hroot_out);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &he->hroot_out);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	he->hroot_out = new_root;
+}
+
 static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
 	struct rb_node *nd;
+	struct rb_root new_root = RB_ROOT;
 
 	hists->stats.nr_non_filtered_samples = 0;
 
@@ -1691,6 +1729,22 @@ static void hists__filter_hierarchy(struct hists *hists, int type, const void *a
 			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
 		}
 	}
+
+	/*
+	 * resort output after applying a new filter since filter in a lower
+	 * hierarchy can change periods in a upper hierarchy.
+	 */
+	nd = rb_first(&hists->entries);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &hists->entries);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	hists->entries = new_root;
 }
 
 void hists__filter_by_thread(struct hists *hists)
-- 
2.7.1

  parent reply	other threads:[~2016-02-16 14:10 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-16 14:08 [PATCHSET 00/25] perf tools: Add support for hierachy view (v6) Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 01/25] perf hists browser: Fix percentage update on key press Namhyung Kim
2016-02-16 20:06   ` Arnaldo Carvalho de Melo
2016-02-16 20:53     ` Arnaldo Carvalho de Melo
2016-02-16 23:39       ` Namhyung Kim
2016-02-17 13:41         ` Arnaldo Carvalho de Melo
2016-02-20 11:39   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 02/25] perf callchain: Check return value of add_child() Namhyung Kim
2016-02-20 11:39   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 03/25] perf callchain: Check return value of fill_node() Namhyung Kim
2016-02-20 11:39   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 04/25] perf callchain: Add enum match_result for match_chain() Namhyung Kim
2016-02-20 11:40   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 05/25] perf callchain: Check return value of split_add_child() Namhyung Kim
2016-02-20 11:40   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 06/25] perf callchain: Check return value of append_chain_children() Namhyung Kim
2016-02-20 11:40   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 07/25] perf hists: Return error from hists__collapse_resort() Namhyung Kim
2016-02-20 11:41   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 08/25] perf report: Check error during report__collapse_hists() Namhyung Kim
2016-02-20 11:41   ` [tip:perf/core] " tip-bot for Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 09/25] perf hists: Basic support of hierarchical report view Namhyung Kim
2016-02-20 23:18   ` Jiri Olsa
2016-02-21  8:32     ` Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 10/25] perf hists: Resort hist entries with hierarchy Namhyung Kim
2016-02-20 23:19   ` Jiri Olsa
2016-02-21  8:36     ` Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 11/25] perf hists: Add helper functions for hierarchy mode Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 12/25] perf hists: Introduce hist_entry__filter() Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 13/25] perf hists: Support filtering in hierarchy mode Namhyung Kim
2016-02-16 14:08 ` Namhyung Kim [this message]
2016-02-16 14:08 ` [PATCH v6 15/25] perf hists: Count number of sort keys Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 16/25] perf ui/stdio: Implement hierarchy output mode Namhyung Kim
2016-02-20 23:18   ` Jiri Olsa
2016-02-21  8:43     ` Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 17/25] perf ui/stdio: Align column header for hierarchy output Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 18/25] perf hists browser: Count number of hierarchy entries Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 19/25] perf hists browser: Support collapsing/expanding whole entries in hierarchy Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 20/25] perf hists browser: Implement hierarchy output Namhyung Kim
2016-02-20 23:19   ` Jiri Olsa
2016-02-16 14:08 ` [PATCH v6 21/25] perf hists browser: Align column header in hierarchy mode Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 22/25] perf ui/gtk: Implement hierarchy output mode Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 23/25] perf report: Add --hierarchy option Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 24/25] perf hists: Support decaying in hierarchy mode Namhyung Kim
2016-02-16 14:08 ` [PATCH v6 25/25] perf top: Add --hierarchy option Namhyung Kim
2016-02-20 23:19   ` Jiri Olsa
2016-02-21  9:19     ` Namhyung Kim

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=1455631723-17345-15-git-send-email-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=acme@kernel.org \
    --cc=andi@firstfloor.org \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=wangnan0@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®