perf flamegraph: flamegraph.py script improvements

* display perf.data header
* display PIDs of user stacks
* added option to change color scheme
* default to blue/green color scheme to improve accessibility
* correctly identify kernel stacks when kernel-debuginfo is installed

Signed-off-by: Andreas Gerstmayr <agerstmayr@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210830164729.116049-1-agerstmayr@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/scripts/python/flamegraph.py

@@ -13,6 +13,10 @@
 # Written by Andreas Gerstmayr <agerstmayr@redhat.com>
 # Flame Graphs invented by Brendan Gregg <bgregg@netflix.com>
 # Works in tandem with d3-flame-graph by Martin Spier <mspier@netflix.com>
+#
+# pylint: disable=missing-module-docstring
+# pylint: disable=missing-class-docstring
+# pylint: disable=missing-function-docstring
 
 from __future__ import print_function
 import sys
@@ -20,16 +24,19 @@ import os
 import io
 import argparse
 import json
+import subprocess
 
-
+# pylint: disable=too-few-public-methods
 class Node:
-    def __init__(self, name, libtype=""):
+    def __init__(self, name, libtype):
         self.name = name
+        # "root" | "kernel" | ""
+        # "" indicates user space
         self.libtype = libtype
         self.value = 0
         self.children = []
 
-    def toJSON(self):
+    def to_json(self):
         return {
             "n": self.name,
             "l": self.libtype,
@@ -41,7 +48,7 @@ class Node:
 class FlameGraphCLI:
     def __init__(self, args):
         self.args = args
-        self.stack = Node("root")
+        self.stack = Node("all", "root")
 
         if self.args.format == "html" and \
                 not os.path.isfile(self.args.template):
@@ -53,13 +60,21 @@ class FlameGraphCLI:
                   file=sys.stderr)
             sys.exit(1)
 
-    def find_or_create_node(self, node, name, dso):
+    @staticmethod
-        libtype = "kernel" if dso == "[kernel.kallsyms]" else ""
+    def get_libtype_from_dso(dso):
-        if name is None:
+        """
-            name = "[unknown]"
+        when kernel-debuginfo is installed,
+        dso points to /usr/lib/debug/lib/modules/*/vmlinux
+        """
+        if dso and (dso == "[kernel.kallsyms]" or dso.endswith("/vmlinux")):
+            return "kernel"
 
+        return ""
+
+    @staticmethod
+    def find_or_create_node(node, name, libtype):
         for child in node.children:
-            if child.name == name and child.libtype == libtype:
+            if child.name == name:
                 return child
 
         child = Node(name, libtype)
@@ -67,30 +82,65 @@ class FlameGraphCLI:
         return child
 
     def process_event(self, event):
-        node = self.find_or_create_node(self.stack, event["comm"], None)
+        pid = event.get("sample", {}).get("pid", 0)
-        if "callchain" in event:
+        # event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux
-            for entry in reversed(event['callchain']):
+        # for user-space processes; let's use pid for kernel or user-space distinction
-                node = self.find_or_create_node(
+        if pid == 0:
-                    node, entry.get("sym", {}).get("name"), event.get("dso"))
+            comm = event["comm"]
+            libtype = "kernel"
         else:
-            node = self.find_or_create_node(
+            comm = "{} ({})".format(event["comm"], pid)
-                node, entry.get("symbol"), event.get("dso"))
+            libtype = ""
+        node = self.find_or_create_node(self.stack, comm, libtype)
+
+        if "callchain" in event:
+            for entry in reversed(event["callchain"]):
+                name = entry.get("sym", {}).get("name", "[unknown]")
+                libtype = self.get_libtype_from_dso(entry.get("dso"))
+                node = self.find_or_create_node(node, name, libtype)
+        else:
+            name = event.get("symbol", "[unknown]")
+            libtype = self.get_libtype_from_dso(event.get("dso"))
+            node = self.find_or_create_node(node, name, libtype)
         node.value += 1
 
+    def get_report_header(self):
+        if self.args.input == "-":
+            # when this script is invoked with "perf script flamegraph",
+            # no perf.data is created and we cannot read the header of it
+            return ""
+
+        try:
+            output = subprocess.check_output(["perf", "report", "--header-only"])
+            return output.decode("utf-8")
+        except Exception as err:  # pylint: disable=broad-except
+            print("Error reading report header: {}".format(err), file=sys.stderr)
+            return ""
+
     def trace_end(self):
-        json_str = json.dumps(self.stack, default=lambda x: x.toJSON())
+        stacks_json = json.dumps(self.stack, default=lambda x: x.to_json())
 
         if self.args.format == "html":
+            report_header = self.get_report_header()
+            options = {
+                "colorscheme": self.args.colorscheme,
+                "context": report_header
+            }
+            options_json = json.dumps(options)
+
             try:
-                with io.open(self.args.template, encoding="utf-8") as f:
+                with io.open(self.args.template, encoding="utf-8") as template:
-                    output_str = f.read().replace("/** @flamegraph_json **/",
+                    output_str = (
-                                                  json_str)
+                        template.read()
-            except IOError as e:
+                        .replace("/** @options_json **/", options_json)
-                print("Error reading template file: {}".format(e), file=sys.stderr)
+                        .replace("/** @flamegraph_json **/", stacks_json)
+                    )
+            except IOError as err:
+                print("Error reading template file: {}".format(err), file=sys.stderr)
                 sys.exit(1)
             output_fn = self.args.output or "flamegraph.html"
         else:
-            output_str = json_str
+            output_str = stacks_json
             output_fn = self.args.output or "stacks.json"
 
         if output_fn == "-":
@@ -101,8 +151,8 @@ class FlameGraphCLI:
             try:
                 with io.open(output_fn, "w", encoding="utf-8") as out:
                     out.write(output_str)
-            except IOError as e:
+            except IOError as err:
-                print("Error writing output file: {}".format(e), file=sys.stderr)
+                print("Error writing output file: {}".format(err), file=sys.stderr)
                 sys.exit(1)
 
 
@@ -115,12 +165,16 @@ if __name__ == "__main__":
                         help="output file name")
     parser.add_argument("--template",
                         default="/usr/share/d3-flame-graph/d3-flamegraph-base.html",
-                        help="path to flamegraph HTML template")
+                        help="path to flame graph HTML template")
+    parser.add_argument("--colorscheme",
+                        default="blue-green",
+                        help="flame graph color scheme",
+                        choices=["blue-green", "orange"])
     parser.add_argument("-i", "--input",
                         help=argparse.SUPPRESS)
 
-    args = parser.parse_args()
+    cli_args = parser.parse_args()
-    cli = FlameGraphCLI(args)
+    cli = FlameGraphCLI(cli_args)
 
     process_event = cli.process_event
     trace_end = cli.trace_end