Redirect handling in resource prefetch predictor

chrome/browser/predictors/resource_prefetch_predictor.h

 // Copyright 2014 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_PREDICTORS_RESOURCE_PREFETCH_PREDICTOR_H_
 #define CHROME_BROWSER_PREDICTORS_RESOURCE_PREFETCH_PREDICTOR_H_
 
 #include <stddef.h>
 
 #include <map>
@@ skipping 81 matching lines @@
 
     bool has_validators;
     bool always_revalidate;
 
     // Initializes a |URLRequestSummary| from a |URLRequest| response.
     // Returns true for success.
     static bool SummarizeResponse(const net::URLRequest& request,
                                   URLRequestSummary* summary);
   };
 
+  // Stores information about inflight navigations.
+  struct Navigation {

[Benoit L, 2016/09/19 13:53:48]

Navigation and requests are vague, overloaded words. I guess that Navigation is
fine here, but "requests" doesn't tell me what this relates to.

I suspect it's the vector of main resource requests due to redirects. What about
main_resource_requests?

Also, it feels a bit weird for Navigation and NavigationID to be two entirely
unrelated objects.

[alexilin, 2016/09/19 16:49:25]

This is actually an opposite thing :) This is a vector of subresource requests
only within single navigation. So I think that I should call it
subresource_requests.
This is exactly the same vector that was stored in inflight_navigations_ map
earlier.
Navigation is stored in NavigationMap by NavigationID key. I could add
NavigationID field in Navigation structure but NavigationID is used only as a
key for the map. What kind of relation do you expect?

+    explicit Navigation(const GURL& initial_url);
+    ~Navigation();
+
+    GURL initial_url;
+    std::vector<URLRequestSummary> requests;

[Benoit L, 2016/09/19 13:53:48]

Is there some invariant here, such as:
- requests is not empty
- requests[0].url == initial_url?

If so, is it DCHECK()-d somewhere?

[alexilin, 2016/09/19 16:49:25]

Related with misunderstanding in the comment above.
Vector could be empty, it means that we didn't see any subresources within this
navigation.

+  };
+
   ResourcePrefetchPredictor(const ResourcePrefetchPredictorConfig& config,
                             Profile* profile);
   ~ResourcePrefetchPredictor() override;
 
   // Thread safe.
   static bool ShouldRecordRequest(net::URLRequest* request,
                                   content::ResourceType resource_type);
   static bool ShouldRecordResponse(net::URLRequest* response);
   static bool ShouldRecordRedirect(net::URLRequest* response);
 
@@ skipping 34 matching lines @@
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest,
                            LazilyInitializeEmpty);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest,
                            LazilyInitializeWithData);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest,
                            NavigationNotRecorded);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, NavigationUrlInDB);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, NavigationUrlNotInDB);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest,
                            NavigationUrlNotInDBAndDBFull);
+  FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, RedirectUrlNotInDB);
+  FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, RedirectUrlInDB);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, OnMainFrameRequest);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, OnMainFrameRedirect);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest,
                            OnSubresourceResponse);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, GetCorrectPLT);
   FRIEND_TEST_ALL_PREFIXES(ResourcePrefetchPredictorTest, HandledResourceTypes);
 
   enum InitializationState {
     NOT_INITIALIZED = 0,
     INITIALIZING = 1,
     INITIALIZED = 2
   };
 
   // Stores prefetching results.
   struct Result {
     // Takes ownership of requests.
     Result(PrefetchKeyType key_type,
            ResourcePrefetcher::RequestVector* requests);
     ~Result();
 
     PrefetchKeyType key_type;
     std::unique_ptr<ResourcePrefetcher::RequestVector> requests;
 
    private:
     DISALLOW_COPY_AND_ASSIGN(Result);
   };
 
   typedef ResourcePrefetchPredictorTables::ResourceRow ResourceRow;
-  typedef ResourcePrefetchPredictorTables::ResourceRows ResourceRows;
   typedef ResourcePrefetchPredictorTables::PrefetchData PrefetchData;
   typedef ResourcePrefetchPredictorTables::PrefetchDataMap PrefetchDataMap;
-  typedef std::map<NavigationID, linked_ptr<std::vector<URLRequestSummary> > >
-      NavigationMap;
+
+  typedef ResourcePrefetchPredictorTables::RedirectRow RedirectRow;
+  typedef ResourcePrefetchPredictorTables::RedirectData RedirectData;
+  typedef ResourcePrefetchPredictorTables::RedirectDataMap RedirectDataMap;
+
+  typedef std::map<NavigationID, std::unique_ptr<Navigation>> NavigationMap;
   typedef std::map<NavigationID, std::unique_ptr<Result>> ResultsMap;
 
   // Returns true if the main page request is supported for prediction.
   static bool IsHandledMainPage(net::URLRequest* request);
 
   // Returns true if the subresource request is supported for prediction.
   static bool IsHandledSubresource(net::URLRequest* request,
                                    content::ResourceType resource_type);
 
   // Returns true if the subresource has a supported type.
@@ skipping 34 matching lines @@
   void StartPrefetching(const NavigationID& navigation_id);
 
   // Stops prefetching that may be in progress corresponding to |navigation_id|.
   void StopPrefetching(const NavigationID& navigation_id);
 
   // Starts initialization by posting a task to the DB thread to read the
   // predictor database.
   void StartInitialization();
 
   // Callback for task to read predictor database. Takes ownership of
-  // |url_data_map| and |host_data_map|.
+  // all arguments.
   void CreateCaches(std::unique_ptr<PrefetchDataMap> url_data_map,
-                    std::unique_ptr<PrefetchDataMap> host_data_map);
+                    std::unique_ptr<PrefetchDataMap> host_data_map,
+                    std::unique_ptr<RedirectDataMap> url_redirect_data_map,
+                    std::unique_ptr<RedirectDataMap> host_redirect_data_map);
 
   // Called during initialization when history is read and the predictor
   // database has been read.
   void OnHistoryAndCacheLoaded();
 
   // Removes data for navigations where the onload never fired. Will cleanup
   // inflight_navigations_ and results_map_.
   void CleanupAbandonedNavigations(const NavigationID& navigation_id);
 
   // Deletes all URLs from the predictor database, the caches and removes all
   // inflight navigations.
   void DeleteAllUrls();
 
   // Deletes data for the input |urls| and their corresponding hosts from the
   // predictor database and caches.
   void DeleteUrls(const history::URLRows& urls);
 
   // Callback for GetUrlVisitCountTask.
   void OnVisitCountLookup(size_t visit_count,
                           const NavigationID& navigation_id,
-                          const std::vector<URLRequestSummary>& requests);
+                          const Navigation& navigation);
 
   // Removes the oldest entry in the input |data_map|, also deleting it from the
   // predictor database.
   void RemoveOldestEntryInPrefetchDataMap(PrefetchKeyType key_type,
                                           PrefetchDataMap* data_map);
 
+  void RemoveOldestEntryInRedirectDataMap(PrefetchKeyType key_type,
+                                          RedirectDataMap* data_map);
+
   // Merges resources in |new_resources| into the |data_map| and correspondingly
   // updates the predictor database.
   void LearnNavigation(const std::string& key,
                        PrefetchKeyType key_type,
                        const std::vector<URLRequestSummary>& new_resources,
                        size_t max_data_map_size,
                        PrefetchDataMap* data_map);
 
+  // Updates information about final redirect destination for |key| in
+  // |redirect_map| and correspondingly updates the predictor database
+  void LearnRedirect(const std::string& key,
+                     PrefetchKeyType key_type,
+                     const std::string& final_redirect,
+                     size_t max_redirect_map_size,
+                     RedirectDataMap* redirect_map);
+
   // Reports overall page load time.
   void ReportPageLoadTimeStats(base::TimeDelta plt) const;
 
   // Reports page load time for prefetched and not prefetched pages
   void ReportPageLoadTimePrefetchStats(
       base::TimeDelta plt,
       bool prefetched,
       base::Callback<void(int)> report_network_type_callback,
       PrefetchKeyType key_type) const;
 
@@ skipping 34 matching lines @@
     tables_ = tables;
   }
 
   Profile* const profile_;
   ResourcePrefetchPredictorConfig const config_;
   InitializationState initialization_state_;
   scoped_refptr<ResourcePrefetchPredictorTables> tables_;
   scoped_refptr<ResourcePrefetcherManager> prefetch_manager_;
   base::CancelableTaskTracker history_lookup_consumer_;
 
-  // Map of all the navigations in flight to their resource requests.
-  NavigationMap inflight_navigations_;
-
   // Copy of the data in the predictor tables.
   std::unique_ptr<PrefetchDataMap> url_table_cache_;
   std::unique_ptr<PrefetchDataMap> host_table_cache_;
+  std::unique_ptr<RedirectDataMap> url_redirect_table_cache_;
+  std::unique_ptr<RedirectDataMap> host_redirect_table_cache_;
 
+  NavigationMap inflight_navigations_;
   ResultsMap results_map_;
 
   ScopedObserver<history::HistoryService, history::HistoryServiceObserver>
       history_service_observer_;
 
   DISALLOW_COPY_AND_ASSIGN(ResourcePrefetchPredictor);
 };
 
 }  // namespace predictors
 
 #endif  // CHROME_BROWSER_PREDICTORS_RESOURCE_PREFETCH_PREDICTOR_H_