Reporting top cpu and memory consumers via rappor on chromeos

chrome/browser/chromeos/resource_reporter/resource_reporter.h

+// Copyright 2015 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#ifndef CHROME_BROWSER_CHROMEOS_RESOURCE_REPORTER_RESOURCE_REPORTER_H_
+#define CHROME_BROWSER_CHROMEOS_RESOURCE_REPORTER_RESOURCE_REPORTER_H_
+
+#include <map>
+#include <vector>

[ncarter (slow), 2015/11/13 22:44:32]

#include <string> here (& can remove from the .cc)

[afakhry, 2015/11/16 18:44:20]

Done.

+
+#include "base/gtest_prod_util.h"
+#include "base/macros.h"
+#include "base/memory/memory_pressure_listener.h"
+#include "chrome/browser/task_management/task_manager_observer.h"
+#include "components/metrics/metrics_service.h"
+#include "components/rappor/sample.h"
+
+namespace base {
+template <typename T>
+struct DefaultSingletonTraits;
+}
+
+using MemoryPressureLevel = base::MemoryPressureListener::MemoryPressureLevel;
+
+namespace chromeos {
+
+// A system that tracks the top |kTopConsumersCount| CPU and memory consumer
+// Chrome tasks and reports them via Rappor whenever memory pressure is moderate
+// or higher.
+class ResourceReporter
+    : public task_management::TaskManagerObserver,
+      public metrics::MetricsServiceObserver {
+ public:
+  // A collection of the data of a task manager's task that the ResourceReporter
+  // is interested in.
+  struct TaskRecord {
+    // The ID of the task.
+    task_management::TaskId id;
+
+    // The name of the Rappor sample to be used for recording a sample
+    // representing this task.
+    std::string rappor_sample;

[Steven Holte, 2015/11/13 21:42:18]

Similar to my other comment, this should probably be called simplified_task_id
or something similar, since this not a Sample, it's a value you intend to record
in a sample.

[afakhry, 2015/11/16 18:44:20]

Done.

+
+    // The CPU usage of the task from the most recent task manager refresh in
+    // percentage.
+    double cpu;
+
+    // The physical memory usage of the task from the most recent task manager
+    // refresh in bytes. It doesn't include shared memory. A value of -1 is
+    // invalid. See TaskManagerInterface::GetPhysicalMemoryUsage().
+    int64_t memory;
+
+    // True if the task is running on a process at background priority.
+    bool is_background;
+
+    explicit TaskRecord(task_management::TaskId the_id);
+
+    TaskRecord(task_management::TaskId the_id,

[ncarter (slow), 2015/11/13 22:44:32]

ctors before data members
https://google.github.io/styleguide/cppguide.html#Declaration_Order

[afakhry, 2015/11/16 18:44:19]

I thought in structs we put the member variable first. Done.

+               const std::string& the_sample,
+               double the_cpu,
+               int64_t the_memory,
+               bool background);
+  };
+
+  ~ResourceReporter() override;
+
+  // The system runs only if the user has opted-in to send anonymous usage
+  // stats. We observe state changes in the MetricsService which will determine
+  // if the ResourceReporter needs to observe the task manager and collect
+  // resource usage stats.
+  static void StartObservingMetricsService();
+  static void StopObservingMetricsService();
+
+  // The singleton instance.
+  static ResourceReporter* GetInstance();
+
+  // task_management::TaskManagerObserver:
+  void OnTaskAdded(task_management::TaskId id) override;
+  void OnTaskToBeRemoved(task_management::TaskId id) override;
+  void OnTasksRefreshed(const task_management::TaskIdList& task_ids) override;
+
+  // metrics::MetricsServiceObserver:
+  void OnMetricsServiceStart() override;
+  void OnMetricsServiceStop() override;
+
+ private:
+  friend struct base::DefaultSingletonTraits<ResourceReporter>;
+  friend class ResourceReporterTest;
+  FRIEND_TEST_ALL_PREFIXES(ResourceReporterTest, TestGetCpuRapporMetricName);
+  FRIEND_TEST_ALL_PREFIXES(ResourceReporterTest, TestGetMemoryRapporMetricName);
+  FRIEND_TEST_ALL_PREFIXES(ResourceReporterTest, TestAll);
+
+  enum TaskProcessPriority {
+    FOREGROUND = 0,
+    BACKGROUND,
+    PRIORITIES_NUM,
+  };
+
+  enum CpuUsageRange {
+    RANGE_0_TO_10_PERCENT = 0,
+    RANGE_10_TO_30_PERCENT,
+    RANGE_30_TO_60_PERCENT,
+    RANGE_ABOVE_60_PERCENT,
+    CPU_RANGES_NUM,
+  };
+
+  enum MemoryUsageRange {
+    RANGE_0_TO_200_MB = 0,
+    RANGE_200_TO_400_MB,
+    RANGE_400_TO_600_MB,
+    RANGE_600_TO_800_MB,
+    RANGE_800_TO_1_GB,
+    RANGE_ABOVE_1_GB,
+    MEMORY_RANGES_NUM,
+  };
+
+  enum CpuCoresNumberRange {
+    RANGE_CORES_NA = 0,
+    RANGE_CORES_1_CORE,
+    RANGE_CORES_2_CORES,
+    RANGE_CORES_3_TO_4_CORES,
+    RANGE_CORES_5_TO_8_CORES,
+    RANGE_CORES_9_TO_16_CORES,
+    RANGE_CORES_ABOVE_16_CORES,
+    CORES_RANGES_NUM,
+  };
+
+  // The maximum number of top consumer tasks of each resource that we're
+  // interested in reporting.
+  static const size_t kTopConsumersCount;
+
+  ResourceReporter();
+
+  // Creates a Rappor sample for the given |task_record|.
+  static scoped_ptr<rappor::Sample> CreateRapporSample(
+      rappor::RapporService* rappor_service,
+      const TaskRecord& task_record);
+
+  // Gets the CPU/memory usage ranges given the |cpu| / |memory_in_bytes|
+  // values.
+  static CpuUsageRange GetCpuUsageRange(double cpu);
+  static MemoryUsageRange GetMemoryUsageRange(int64_t memory_in_bytes);
+
+  // Gets the bucket in which the current system's number of CPU cores fall
+  // into.
+  static CpuCoresNumberRange GetCurrentSystemCpuCoresRange();
+
+  // Start / stop observing the task manager and the memory pressure events.
+  void StartMonitoring();
+  void StopMonitoring();
+
+  // The callback function that will be invoked on memory pressure events.
+  void OnMemoryPressure(MemoryPressureLevel memory_pressure_level);
+
+  // We'll use this to watch for memory pressure events so that we can trigger
+  // Rappor sampling at moderate memory pressure or higher.
+  scoped_ptr<base::MemoryPressureListener> memory_pressure_listener_;
+
+  // Contains the collected data about the currently running tasks from the most
+  // recent task manager refresh.
+  std::map<task_management::TaskId, scoped_ptr<TaskRecord>> task_records_;
+
+  // Contains the top |kTopConsumerCount| CPU consumer tasks sorted in a
+  // descending order by their CPU usage.
+  std::vector<TaskRecord*> task_records_by_cpu_;
+
+  // Contains the top |kTopConsumerCount| memory consumer tasks sorted in a
+  // descending order by their memory usage.
+  std::vector<TaskRecord*> task_records_by_memory_;
+
+  const CpuCoresNumberRange system_cpu_cores_range_;
+
+  // the most recent reading for the browser and GPU processes to be reported as
+  // UMA histograms when the system is under moderate memory pressure or higher.
+  double last_browser_process_cpu_ = 0.0;
+  double last_gpu_process_cpu_ = 0.0;
+  int64_t last_browser_process_memory_ = 0;
+  int64_t last_gpu_process_memory_ = 0;
+
+  MemoryPressureLevel previous_memory_pressure_level_ =
+      MemoryPressureLevel::MEMORY_PRESSURE_LEVEL_NONE;
+
+  // MetricsService::Start()/Stop() can be called multiple times which can cause
+  // all sort of trouble. We need to track whether we have already started
+  // monitoring or not using the below flag.
+  bool is_monitoring_;
+
+  DISALLOW_COPY_AND_ASSIGN(ResourceReporter);
+};
+
+}  // namespace chromeos
+
+#endif  // CHROME_BROWSER_CHROMEOS_RESOURCE_REPORTER_RESOURCE_REPORTER_H_