Send the list of used and unused resources for precache

components/precache/core/precache_database.cc

 // Copyright 2013 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.
 
 #include "components/precache/core/precache_database.h"
 
 #include "base/bind.h"
 #include "base/files/file_path.h"
 #include "base/location.h"
 #include "base/metrics/histogram_macros.h"
@@ skipping 40 matching lines @@
   db_.reset(new sql::Connection());
   db_->set_histogram_tag("Precache");
 
   if (!db_->Open(db_path)) {
     // Don't initialize the URL table if unable to access
     // the database.
     return false;
   }
 
   if (!precache_url_table_.Init(db_.get()) ||
+      !precache_referrer_host_table_.Init(db_.get()) ||
       !precache_session_table_.Init(db_.get())) {
     // Raze and close the database connection to indicate that it's not usable,
     // and so that the database will be created anew next time, in case it's
     // corrupted.
     db_->RazeAndClose();
     return false;
   }
   return true;
 }
 
 void PrecacheDatabase::DeleteExpiredPrecacheHistory(
     const base::Time& current_time) {
   if (!IsDatabaseAccessible()) {
     // Do nothing if unable to access the database.
     return;
   }
 
   // Delete old precache history that has expired.
   base::Time delete_end = current_time - base::TimeDelta::FromDays(
                                              kPrecacheHistoryExpiryPeriodDays);
   buffered_writes_.push_back(
       base::Bind(&PrecacheURLTable::DeleteAllPrecachedBefore,
                  base::Unretained(&precache_url_table_), delete_end));
+  buffered_writes_.push_back(
+      base::Bind(&PrecacheReferrerHostTable::DeleteAllEntriesBefore,
+                 base::Unretained(&precache_referrer_host_table_), delete_end));
   Flush();
 }
 
 void PrecacheDatabase::ClearHistory() {
   if (!IsDatabaseAccessible()) {
     // Do nothing if unable to access the database.
     return;
   }
 
   buffered_writes_.push_back(base::Bind(
       &PrecacheURLTable::DeleteAll, base::Unretained(&precache_url_table_)));
+  buffered_writes_.push_back(
+      base::Bind(&PrecacheReferrerHostTable::DeleteAll,
+                 base::Unretained(&precache_referrer_host_table_)));
   Flush();
 }
 
 void PrecacheDatabase::SetLastPrecacheTimestamp(const base::Time& time) {
   last_precache_timestamp_ = time;
 
   if (!IsDatabaseAccessible()) {
     // Do nothing if unable to access the database.
     return;
   }
 
   buffered_writes_.push_back(
       base::Bind(&PrecacheSessionTable::SetLastPrecacheTimestamp,
                  base::Unretained(&precache_session_table_), time));
   MaybePostFlush();
 }
 
 base::Time PrecacheDatabase::GetLastPrecacheTimestamp() {
   if (last_precache_timestamp_.is_null() && IsDatabaseAccessible()) {
     last_precache_timestamp_ =
         precache_session_table_.GetLastPrecacheTimestamp();
   }
   return last_precache_timestamp_;
 }
 
-void PrecacheDatabase::RecordURLPrefetch(const GURL& url,
-                                         const base::TimeDelta& latency,
-                                         const base::Time& fetch_time,
-                                         const net::HttpResponseInfo& info,
-                                         int64_t size) {
+PrecacheReferrerHostEntry PrecacheDatabase::GetReferrerHost(
+    const std::string& referrer_host) {
+  DCHECK(thread_checker_.CalledOnValidThread());
+  return precache_referrer_host_table_.GetReferrerHost(referrer_host);
+}
+
+void PrecacheDatabase::GetURLListForReferrerHost(
+    int64_t referrer_host_id,
+    std::deque<GURL>& used_urls,
+    std::deque<GURL>& unused_urls) {
+  DCHECK_NE(PrecacheReferrerHostEntry::INVALID_ID, referrer_host_id);
+  precache_url_table_.GetURLListForReferrerHost(referrer_host_id, used_urls,
+                                                unused_urls);
+}
+
+void PrecacheDatabase::RecordURLPrefetchMetrics(
+    const net::HttpResponseInfo& info,
+    const base::TimeDelta& latency) {
+  DCHECK(thread_checker_.CalledOnValidThread());
+
   UMA_HISTOGRAM_TIMES("Precache.Latency.Prefetch", latency);
 
-  if (!IsDatabaseAccessible()) {
-    // Don't track anything if unable to access the database.
-    return;
-  }
-
-  if (buffered_urls_.find(url.spec()) != buffered_urls_.end()) {
-    // If the URL for this fetch is in the write buffer, then flush the write
-    // buffer.
-    Flush();
-  }
-
   DCHECK(info.headers) << "The headers are required to get the freshness.";
   if (info.headers) {
     UMA_HISTOGRAM_CUSTOM_COUNTS(
         "Precache.Freshness.Prefetch",
         info.headers->GetFreshnessLifetimes(info.response_time)
             .freshness.InSeconds(),
         base::TimeDelta::FromMinutes(5).InSeconds() /* min */,
         base::TimeDelta::FromDays(356).InSeconds() /* max */,
         100 /* bucket_count */);
   }
+}
 
-  if (info.was_cached && !precache_url_table_.HasURL(url)) {
-    // Since the precache came from the cache, and there's no entry in the URL
-    // table for the URL, this means that the resource was already in the cache
-    // because of user browsing. Therefore, this precache won't be considered as
-    // precache-motivated since it had no significant effect (besides a possible
-    // revalidation and a change in the cache LRU priority).
+void PrecacheDatabase::RecordURLPrefetch(const GURL& url,
+                                         const std::string& referrer_host,
+                                         const base::Time& fetch_time,
+                                         bool was_cached,
+                                         int64_t size) {
+  DCHECK(thread_checker_.CalledOnValidThread());
+
+  if (!IsDatabaseAccessible()) {
+    // Don't track anything if unable to access the database.
     return;
   }
 
-  if (!info.was_cached) {
+  if (buffered_urls_.find(url.spec()) != buffered_urls_.end()) {
+    // If the URL for this fetch is in the write buffer, then flush the write
+    // buffer.
+    Flush();
+  }
+
+  if (!was_cached) {
     // The precache only counts as overhead if it was downloaded over the
     // network.
     UMA_HISTOGRAM_COUNTS("Precache.DownloadedPrecacheMotivated",
                          static_cast<base::HistogramBase::Sample>(size));
   }
 
-  // Use the URL table to keep track of URLs that are in the cache thanks to
-  // precaching. If a row for the URL already exists, than update the timestamp
-  // to |fetch_time|.
-  buffered_writes_.push_back(
-      base::Bind(&PrecacheURLTable::AddURL,
-                 base::Unretained(&precache_url_table_), url, fetch_time));
+  // Use the URL table to keep track of URLs. URLs that are fetched via network
+  // or already in the cache due to prior precaching are recorded as
+  // precache-motivated. URLs that came from the cache and not recorded as
+  // precached previously, were already in the cache because of user browsing.
+  // Therefore, this precache will not be considered as precache-motivated,
+  // since it had no significant effect (besides a possible revalidation and a
+  // change in the cache LRU priority). If a row for the URL already exists,
+  // then the timestamp is updated.
+  buffered_writes_.push_back(base::Bind(
+      &PrecacheDatabase::RecordURLPrefetchInternal, GetWeakPtr(), url,
+      referrer_host, !was_cached || precache_url_table_.IsURLPrecached(url),
+      fetch_time));
   buffered_urls_.insert(url.spec());
   MaybePostFlush();
 }
 
+void PrecacheDatabase::RecordURLPrefetchInternal(
+    const GURL& url,
+    const std::string& referrer_host,
+    bool is_precached,
+    const base::Time& fetch_time) {
+  auto referrer_host_id =
+      precache_referrer_host_table_.GetReferrerHost(referrer_host).id;
+  if (referrer_host_id == PrecacheReferrerHostEntry::INVALID_ID) {
+    referrer_host_id = precache_referrer_host_table_.UpdateReferrerHost(
+        referrer_host, 0, fetch_time);
+    DCHECK_NE(referrer_host_id, PrecacheReferrerHostEntry::INVALID_ID);
+  }
+  precache_url_table_.AddURL(url, referrer_host_id, is_precached, fetch_time);
+}
+
 void PrecacheDatabase::RecordURLNonPrefetch(const GURL& url,
                                             const base::TimeDelta& latency,
                                             const base::Time& fetch_time,
                                             const net::HttpResponseInfo& info,
                                             int64_t size,
                                             int host_rank,
                                             bool is_connection_cellular) {
   UMA_HISTOGRAM_TIMES("Precache.Latency.NonPrefetch", latency);
   UMA_HISTOGRAM_ENUMERATION("Precache.CacheStatus.NonPrefetch",
                             info.cache_entry_status,
@@ skipping 15 matching lines @@
   }
 
   RecordTimeSinceLastPrecache(fetch_time);
 
   if (buffered_urls_.find(url.spec()) != buffered_urls_.end()) {
     // If the URL for this fetch is in the write buffer, then flush the write
     // buffer.
     Flush();
   }
 
-  if (info.was_cached && !precache_url_table_.HasURL(url)) {
+  bool is_precached = precache_url_table_.IsURLPrecachedAndUnused(url);
+  if (info.was_cached && !is_precached) {
     // Ignore cache hits that precache can't take credit for.
     return;
   }
 
   base::HistogramBase::Sample size_sample =
       static_cast<base::HistogramBase::Sample>(size);
   if (!info.was_cached) {
     // The fetch was served over the network during user browsing, so count it
     // as downloaded non-precache bytes.
     UMA_HISTOGRAM_COUNTS("Precache.DownloadedNonPrecache", size_sample);
@@ skipping 17 matching lines @@
       UMA_HISTOGRAM_CUSTOM_COUNTS(
           "Precache.Saved.Freshness",
           info.headers->GetFreshnessLifetimes(info.response_time)
               .freshness.InSeconds(),
           base::TimeDelta::FromMinutes(5).InSeconds() /* min */,
           base::TimeDelta::FromDays(356).InSeconds() /* max */,
           100 /* bucket_count */);
     }
   }
 
-  // Since the resource has been fetched during user browsing, remove any record
-  // of that URL having been precached from the URL table, if any exists.
-  // The current fetch would have put this resource in the cache regardless of
-  // whether or not it was previously precached, so delete any record of that
-  // URL having been precached from the URL table.
+  if (is_precached) {
+    // Since the resource has been fetched during user browsing, mark the URL as
+    // used in the precache URL table, if any exists. The current fetch would
+    // have put this resource in the cache regardless of whether or not it was
+    // previously precached, so mark the URL as used.
+    buffered_writes_.push_back(
+        base::Bind(&PrecacheURLTable::SetPrecachedURLAsUsed,
+                   base::Unretained(&precache_url_table_), url));
+    buffered_urls_.insert(url.spec());
+    MaybePostFlush();
+  }
+}
+
+void PrecacheDatabase::UpdatePrecacheReferrerHost(
+    const std::string& hostname,
+    int64_t manifest_id,
+    const base::Time& fetch_time) {
+  DCHECK(thread_checker_.CalledOnValidThread());
+
+  if (!IsDatabaseAccessible()) {
+    // Don't track anything if unable to access the database.
+    return;
+  }
+
   buffered_writes_.push_back(
-      base::Bind(&PrecacheURLTable::DeleteURL,
-                 base::Unretained(&precache_url_table_), url));
-  buffered_urls_.insert(url.spec());
+      base::Bind(&PrecacheDatabase::UpdatePrecacheReferrerHostInternal,
+                 GetWeakPtr(), hostname, manifest_id, fetch_time));
   MaybePostFlush();
 }
 
+void PrecacheDatabase::UpdatePrecacheReferrerHostInternal(
+    const std::string& hostname,
+    int64_t manifest_id,
+    const base::Time& fetch_time) {
+  precache_referrer_host_table_.UpdateReferrerHost(hostname, manifest_id,
+                                                   fetch_time);
+}
+
 void PrecacheDatabase::RecordTimeSinceLastPrecache(
     const base::Time& fetch_time) {
   const base::Time& last_precache_timestamp = GetLastPrecacheTimestamp();
   // It could still be null if the DB was not accessible.
   if (!last_precache_timestamp.is_null()) {
     // This is the timespan (in seconds) between the last call to
     // PrecacheManager::StartPrecaching and the fetch time of a non-precache
     // URL. Please note that the session started by that call to
     // PrecacheManager::StartPrecaching may not have precached this particular
     // URL or even any URL for that matter.
@@ skipping 82 matching lines @@
 
 void PrecacheDatabase::DeleteUnfinishedWork() {
   precache_session_table_.DeleteUnfinishedWork();
 }
 
 base::WeakPtr<PrecacheDatabase> PrecacheDatabase::GetWeakPtr() {
   return weak_factory_.GetWeakPtr();
 }
 
 }  // namespace precache