[PATCH 13/19] perf tools: Add 'cgroup_id' sort order keyword

[Arnaldo Carvalho de Melo <acme@kernel.org>]

From: Hari Bathini <hbathini@linux.vnet.ibm.com>

This patch introduces a cgroup identifier entry field in perf report to
identify or distinguish data of different cgroups. It uses the device
number and inode number of cgroup namespace, included in perf data with
the new PERF_RECORD_NAMESPACES event, as cgroup identifier.

With the assumption that each container is created with it's own cgroup
namespace,  this allows assessment/analysis of multiple containers at
once.

A simple test for this would be to clone a few processes passing
SIGCHILD & CLONE_NEWCROUP flags to each of them, execute shell and run
different workloads  on each of those contexts,  while running perf
record command with --namespaces option.

Shown below is the output of perf report, sorted with cgroup identifier,
on perf.data generated with the above test scenario, clearly indicating
one context's considerable use of kernel memory in comparison with
others:

	$ perf report -s cgroup_id,sample --stdio
	#
	# Total Lost Samples: 0
	#
	# Samples: 5K of event 'kmem:kmalloc'
	# Event count (approx.): 5965
	#
	# Overhead  cgroup id (dev/inode)       Samples
	# ........  .....................  ............
	#
	    81.27%  3/0xeffffffb                   4848
	    16.24%  3/0xf00000d0                    969
	     1.16%  3/0xf00000ce                     69
	     0.82%  3/0xf00000cf                     49
	     0.50%  0/0x0                            30

While this is a start, there is further scope of improving this. For
example, instead of cgroup namespace's device and inode numbers, dev
and inode numbers of some or all namespaces may be used to distinguish
which processes are running in a given container context.

Also, scripts to map device and inode info to containers sounds
plausible for better tracing of containers.

Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891933338.25309.756882900782042645.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-report.txt |  4 +++-
 tools/perf/util/hist.c                   |  7 ++++++
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/sort.c                   | 41 ++++++++++++++++++++++++++++++++
 tools/perf/util/sort.h                   |  7 ++++++
 5 files changed, 59 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 672b149aa80a..e9a61f5485eb 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -72,7 +72,8 @@ OPTIONS
 --sort=::
 	Sort histogram entries by given key(s) - multiple keys can be specified
 	in CSV format.  Following sort keys are available:
-	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
+	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight,
+	local_weight, cgroup_id.
 
 	Each key has following meaning:
 
@@ -92,6 +93,7 @@ OPTIONS
 	- weight: Event specific weight, e.g. memory latency or transaction
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
+	- cgroup_id: ID derived from cgroup namespace device and inode numbers.
 	- transaction: Transaction abort flags.
 	- overhead: Overhead percentage of sample
 	- overhead_sys: Overhead percentage of sample running in system mode
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index eaf72a938fb4..e3b38f629504 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,6 +3,7 @@
 #include "hist.h"
 #include "map.h"
 #include "session.h"
+#include "namespaces.h"
 #include "sort.h"
 #include "evlist.h"
 #include "evsel.h"
@@ -169,6 +170,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
 	}
 
+	hists__new_col_len(hists, HISTC_CGROUP_ID, 20);
 	hists__new_col_len(hists, HISTC_CPU, 3);
 	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
@@ -574,9 +576,14 @@ __hists__add_entry(struct hists *hists,
 		   bool sample_self,
 		   struct hist_entry_ops *ops)
 {
+	struct namespaces *ns = thread__namespaces(al->thread);
 	struct hist_entry entry = {
 		.thread	= al->thread,
 		.comm = thread__comm(al->thread),
+		.cgroup_id = {
+			.dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0,
+			.ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0,
+		},
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 2e839bf40bdd..ee3670a388df 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -30,6 +30,7 @@ enum hist_column {
 	HISTC_DSO,
 	HISTC_THREAD,
 	HISTC_COMM,
+	HISTC_CGROUP_ID,
 	HISTC_PARENT,
 	HISTC_CPU,
 	HISTC_SOCKET,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 93f755ac60ca..8b0d4e39f640 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -536,6 +536,46 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* --sort cgroup_id */
+
+static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev)
+{
+	return (int64_t)(right_dev - left_dev);
+}
+
+static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino)
+{
+	return (int64_t)(right_ino - left_ino);
+}
+
+static int64_t
+sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev);
+	if (ret != 0)
+		return ret;
+
+	return _sort__cgroup_inode_cmp(right->cgroup_id.ino,
+				       left->cgroup_id.ino);
+}
+
+static int hist_entry__cgroup_id_snprintf(struct hist_entry *he,
+					  char *bf, size_t size,
+					  unsigned int width __maybe_unused)
+{
+	return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev,
+			       he->cgroup_id.ino);
+}
+
+struct sort_entry sort_cgroup_id = {
+	.se_header      = "cgroup id (dev/inode)",
+	.se_cmp	        = sort__cgroup_id_cmp,
+	.se_snprintf    = hist_entry__cgroup_id_snprintf,
+	.se_width_idx	= HISTC_CGROUP_ID,
+};
+
 /* --sort socket */
 
 static int64_t
@@ -1464,6 +1504,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
 	DIM(SORT_TRACE, "trace", sort_trace),
 	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
+	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index f583325a3743..baf20a399f34 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -54,6 +54,11 @@ struct he_stat {
 	u32			nr_events;
 };
 
+struct namespace_id {
+	u64			dev;
+	u64			ino;
+};
+
 struct hist_entry_diff {
 	bool	computed;
 	union {
@@ -91,6 +96,7 @@ struct hist_entry {
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
+	struct namespace_id	cgroup_id;
 	u64			ip;
 	u64			transaction;
 	s32			socket;
@@ -212,6 +218,7 @@ enum sort_type {
 	SORT_TRANSACTION,
 	SORT_TRACE,
 	SORT_SYM_SIZE,
+	SORT_CGROUP_ID,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
-- 
2.9.3