chrome/browser/page_load_metrics/page_load_tracker.h

// Copyright 2016 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_PAGE_LOAD_METRICS_PAGE_LOAD_TRACKER_H_
#define CHROME_BROWSER_PAGE_LOAD_METRICS_PAGE_LOAD_TRACKER_H_

#include <memory>
#include <vector>

#include "base/macros.h"
#include "base/time/time.h"
#include "chrome/browser/page_load_metrics/page_load_metrics_observer.h"
#include "chrome/common/page_load_metrics/page_load_timing.h"
#include "ui/base/page_transition_types.h"

class GURL;

namespace blink {
class WebInputEvent;
}  // namespace blink

namespace content {
class NavigationHandle;
}  // namespace content

namespace page_load_metrics {

class PageLoadMetricsEmbedderInterface;
class PageLoadMetricsObserver;

namespace internal {

extern const char kErrorEvents[];
extern const char kAbortChainSizeReload[];
extern const char kAbortChainSizeForwardBack[];
extern const char kAbortChainSizeNewNavigation[];
extern const char kAbortChainSizeNoCommit[];
extern const char kAbortChainSizeSameURL[];
extern const char kPageLoadCompletedAfterAppBackground[];

}  // namespace internal

// These errors are internal to the page_load_metrics subsystem and do not
// reflect actual errors that occur during a page load.
//
// If you add elements to this enum, make sure you update the enum
// value in histograms.xml. Only add elements to the end to prevent
// inconsistencies between versions.
enum InternalErrorLoadEvent {
  // A timing IPC was sent from the renderer that did not line up with previous
  // data we've received (i.e. navigation start is different or the timing
  // struct is somehow invalid). This error can only occur once the IPC is
  // vetted in other ways (see other errors).
  ERR_BAD_TIMING_IPC,

  // The following IPCs are not mutually exclusive.
  //
  // We received an IPC when we weren't tracking a committed load. This will
  // often happen if we get an IPC from a bad URL scheme (that is, the renderer
  // sent us an IPC from a navigation we don't care about).
  ERR_IPC_WITH_NO_RELEVANT_LOAD,

  // Received a notification from a frame that has been navigated away from.
  ERR_IPC_FROM_WRONG_FRAME,

  // We received an IPC even through the last committed url from the browser
  // was not http/s. This can happen with the renderer sending IPCs for the
  // new tab page. This will often come paired with
  // ERR_IPC_WITH_NO_RELEVANT_LOAD.
  ERR_IPC_FROM_BAD_URL_SCHEME,

  // If we track a navigation, but the renderer sends us no IPCs. This could
  // occur if the browser filters loads less aggressively than the renderer.
  ERR_NO_IPCS_RECEIVED,

  // Tracks frequency with which we record an abort time that occurred before
  // navigation start. This is expected to happen in some cases (see comments in
  // cc file for details). We use this error counter to understand how often it
  // happens.
  ERR_ABORT_BEFORE_NAVIGATION_START,

  // A new navigation triggers abort updates in multiple trackers in
  // |aborted_provisional_loads_|, when usually there should only be one (the
  // navigation that just aborted because of this one). If this happens, the
  // latest aborted load is used to track the chain size.
  ERR_NAVIGATION_SIGNALS_MULIPLE_ABORTED_LOADS,

  // Received user input without a relevant load. This error type is deprecated,
  // as it is valid to receive user input without a relevant load. We leave the
  // enum value here since it's also used in histogram recording, so it's
  // important that we not re-use this enum entry for a different value.
  DEPRECATED_ERR_USER_INPUT_WITH_NO_RELEVANT_LOAD,

  // A TimeTicks value in the browser process has value less than
  // navigation_start_. This could happen if navigation_start_ was computed in
  // renderer process and the system clock has inter process time tick skew.
  ERR_INTER_PROCESS_TIME_TICK_SKEW,

  // At the time a PageLoadTracker was destroyed, we had received neither a
  // commit nor a failed provisional load.
  ERR_NO_COMMIT_OR_FAILED_PROVISIONAL_LOAD,

  // Add values before this final count.
  ERR_LAST_ENTRY,
};

// NOTE: these functions are shared by page_load_tracker.cc and
// metrics_web_contents_observer.cc. They are declared here to allow both files
// to access them.
void RecordInternalError(InternalErrorLoadEvent event);
UserAbortType AbortTypeForPageTransition(ui::PageTransition transition);
void LogAbortChainSameURLHistogram(int aborted_chain_size_same_url);
bool IsNavigationUserInitiated(content::NavigationHandle* handle);

// This class tracks a given page load, starting from navigation start /
// provisional load, until a new navigation commits or the navigation fails.
// MetricsWebContentsObserver manages a set of provisional PageLoadTrackers, as
// well as a committed PageLoadTracker.
class PageLoadTracker {
 public:
  // Caller must guarantee that the embedder_interface pointer outlives this
  // class. The PageLoadTracker must not hold on to
  // currently_committed_load_or_null or navigation_handle beyond the scope of
  // the constructor.
  PageLoadTracker(bool in_foreground,
                  PageLoadMetricsEmbedderInterface* embedder_interface,
                  const GURL& currently_committed_url,
                  content::NavigationHandle* navigation_handle,
                  int aborted_chain_size,
                  int aborted_chain_size_same_url);
  ~PageLoadTracker();
  void Redirect(content::NavigationHandle* navigation_handle);
  void Commit(content::NavigationHandle* navigation_handle);
  void FailedProvisionalLoad(content::NavigationHandle* navigation_handle);
  void WebContentsHidden();
  void WebContentsShown();

  void OnInputEvent(const blink::WebInputEvent& event);

  // Flush any buffered metrics, as part of the metrics subsystem persisting
  // metrics as the application goes into the background. The application may be
  // killed at any time after this method is invoked without further
  // notification.
  void FlushMetricsOnAppEnterBackground();

  void NotifyClientRedirectTo(const PageLoadTracker& destination);

  // Returns true if the timing was successfully updated.
  bool UpdateTiming(const PageLoadTiming& timing,
                    const PageLoadMetadata& metadata);

  void OnLoadedSubresource(bool was_cached);

  // Signals that we should stop tracking metrics for the associated page load.
  // We may stop tracking a page load if it doesn't meet the criteria for
  // tracking metrics in DidFinishNavigation.
  void StopTracking();

  int aborted_chain_size() const { return aborted_chain_size_; }
  int aborted_chain_size_same_url() const {
    return aborted_chain_size_same_url_;
  }

  UserAbortType abort_type() const { return abort_type_; }
  base::TimeTicks abort_time() const { return abort_time_; }

  void AddObserver(std::unique_ptr<PageLoadMetricsObserver> observer);

  // If the user performs some abort-like action while we are tracking this page
  // load, notify the tracker. Note that we may not classify this as an abort if
  // we've already performed a first paint.
  // is_certainly_browser_timestamp signifies if the timestamp passed is taken
  // in the
  // browser process or not. We need this to possibly clamp browser timestamp on
  // a machine with inter process time tick skew.
  void NotifyAbort(UserAbortType abort_type,
                   bool user_initiated,
                   base::TimeTicks timestamp,
                   bool is_certainly_browser_timestamp);
  void UpdateAbort(UserAbortType abort_type,
                   bool user_initiated,
                   base::TimeTicks timestamp,
                   bool is_certainly_browser_timestamp);

  // This method returns true if this page load has been aborted with type of
  // ABORT_OTHER, and the |abort_cause_time| is within a sufficiently close
  // delta to when it was aborted. Note that only provisional loads can be
  // aborted with ABORT_OTHER. While this heuristic is coarse, it works better
  // and is simpler than other feasible methods. See https://goo.gl/WKRG98.
  bool IsLikelyProvisionalAbort(base::TimeTicks abort_cause_time) const;

  bool MatchesOriginalNavigation(content::NavigationHandle* navigation_handle);

  // Only valid to call post-commit.
  const GURL& committed_url() const {
    DCHECK(!committed_url_.is_empty());
    return committed_url_;
  }

  base::TimeTicks navigation_start() const { return navigation_start_; }

  PageLoadExtraInfo ComputePageLoadExtraInfo();

  ui::PageTransition page_transition() const { return page_transition_; }

 private:
  // This function converts a TimeTicks value taken in the browser process
  // to navigation_start_ if:
  // - base::TimeTicks is not comparable across processes because the clock
  // is not system wide monotonic.
  // - *event_time < navigation_start_
  void ClampBrowserTimestampIfInterProcessTimeTickSkew(
      base::TimeTicks* event_time);

  void UpdateAbortInternal(UserAbortType abort_type,
                           bool user_initiated,
                           base::TimeTicks timestamp,
                           bool is_certainly_browser_timestamp);

  // If |final_navigation| is null, then this is an "unparented" abort chain,
  // and represents a sequence of provisional aborts that never ends with a
  // committed load.
  void LogAbortChainHistograms(content::NavigationHandle* final_navigation);

  // Whether we stopped tracking this navigation after it was initiated. We may
  // stop tracking a navigation if it doesn't meet the criteria for tracking
  // metrics in DidFinishNavigation.
  bool did_stop_tracking_;

  // Whether the application went into the background when this PageLoadTracker
  // was active. This is a temporary boolean for UMA tracking.
  bool app_entered_background_;

  // The navigation start in TimeTicks, not the wall time reported by Blink.
  const base::TimeTicks navigation_start_;

  // The committed URL of this page load.
  GURL committed_url_;

  // The start URL for this page load (before redirects).
  GURL start_url_;

  std::unique_ptr<FailedProvisionalLoadInfo> failed_provisional_load_info_;

  // Will be ABORT_NONE if we have not aborted this load yet. Otherwise will
  // be the first abort action the user performed.
  UserAbortType abort_type_;

  // Whether the abort for this page load was user initiated. For example, if
  // this page load was aborted by a new navigation, this field tracks whether
  // that new navigation was user-initiated. This field is only useful if this
  // page load's abort type is a value other than ABORT_NONE. Note that this
  // value is currently experimental, and is subject to change. In particular,
  // this field is never set to true for some abort types, such as stop and
  // close, since we don't yet have sufficient instrumentation to know if a stop
  // or close was caused by a user action.
  bool abort_user_initiated_;

  base::TimeTicks abort_time_;

  // We record separate metrics for events that occur after a background,
  // because metrics like layout/paint are delayed artificially
  // when they occur in the background.
  base::TimeTicks background_time_;
  base::TimeTicks foreground_time_;
  bool started_in_foreground_;

  PageLoadTiming timing_;
  PageLoadMetadata metadata_;

  ui::PageTransition page_transition_;

  // Note: these are only approximations, based on WebContents attribution from
  // ResourceRequestInfo objects while this is the currently committed load in
  // the WebContents.
  int num_cache_requests_;
  int num_network_requests_;

  // This is derived from the user gesture bit in the renderer. For browser
  // initiated navigations this will always be true.
  bool user_initiated_;

  // This is a subtle member. If a provisional load A gets aborted by
  // provisional load B, which gets aborted by C that eventually commits, then
  // there exists an abort chain of length 2, starting at A's navigation_start.
  // This is useful because it allows histograming abort chain lengths based on
  // what the last load's transition type is. i.e. holding down F-5 to spam
  // reload will produce a long chain with the RELOAD transition.
  const int aborted_chain_size_;

  // This member counts consecutive provisional aborts that share a url. It will
  // always be less than or equal to |aborted_chain_size_|.
  const int aborted_chain_size_same_url_;

  // Interface to chrome features. Must outlive the class.
  PageLoadMetricsEmbedderInterface* const embedder_interface_;

  std::vector<std::unique_ptr<PageLoadMetricsObserver>> observers_;

  DISALLOW_COPY_AND_ASSIGN(PageLoadTracker);
};

}  // namespace page_load_metrics

#endif  // CHROME_BROWSER_PAGE_LOAD_METRICS_PAGE_LOAD_TRACKER_H_