Add one-time randomization support for FieldTrial, and the ability to

base/metrics/field_trial.cc

-// Copyright (c) 2010 The Chromium Authors. All rights reserved.
+// Copyright (c) 2011 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 "base/metrics/field_trial.h"
 
 #include "base/logging.h"
 #include "base/rand_util.h"
+#include "base/sha1.h"
+#include "base/string_util.h"
 #include "base/stringprintf.h"
 #include "base/utf_string_conversions.h"
 
 namespace base {
 
 // static
 const int FieldTrial::kNotFinalized = -1;
 
 // static
 const int FieldTrial::kDefaultGroupNumber = 0;
@@ skipping 11 matching lines @@
 
 FieldTrial::FieldTrial(const std::string& name,
                        const Probability total_probability,
                        const std::string& default_group_name,
                        const int year,
                        const int month,
                        const int day_of_month)
   : name_(name),
     divisor_(total_probability),
     default_group_name_(default_group_name),
-    random_(static_cast<Probability>(divisor_ * base::RandDouble())),
+    random_(static_cast<Probability>(divisor_ * RandDouble())),
     accumulated_group_probability_(0),
     next_group_number_(kDefaultGroupNumber+1),
-    group_(kNotFinalized) {
+    group_(kNotFinalized),
+    enable_field_trial_(true) {
   DCHECK_GT(total_probability, 0);
   DCHECK(!default_group_name_.empty());
   FieldTrialList::Register(this);
 
   DCHECK_GT(year, 1970);
   DCHECK_GT(month, 0);
   DCHECK_LT(month, 13);
   DCHECK_GT(day_of_month, 0);
   DCHECK_LT(day_of_month, 32);
 
-  base::Time::Exploded exploded;
+  Time::Exploded exploded;
   exploded.year = year;
   exploded.month = month;
   exploded.day_of_week = 0;  // Should be unused.
   exploded.day_of_month = day_of_month;
   exploded.hour = 0;
   exploded.minute = 0;
   exploded.second = 0;
   exploded.millisecond = 0;
 
-  base::Time expiration_time = Time::FromLocalExploded(exploded);
-  disable_field_trial_ = (GetBuildTime() > expiration_time) ? true : false;
+  Time expiration_time = Time::FromLocalExploded(exploded);
+  if (GetBuildTime() > expiration_time)
+    Disable();
+}
+
+void FieldTrial::UseOneTimeRandomization() {
+  DCHECK_EQ(group_, kNotFinalized);
+  if (!FieldTrialList::IsOneTimeRandomizationEnabled()) {
+    NOTREACHED();
+    Disable();
+    return;
+  }
+
+  random_ = static_cast<Probability>(
+      divisor_ * HashClientId(FieldTrialList::client_id(), name_));
+}
+
+void FieldTrial::Disable() {
+  enable_field_trial_ = false;
+
+  // In case we are disabled after initialization, we need to switch
+  // the trial to the default group.
+  if (group_ != kNotFinalized) {
+    group_ = kDefaultGroupNumber;
+    group_name_ = default_group_name_;
+  }
 }
 
 int FieldTrial::AppendGroup(const std::string& name,
                             Probability group_probability) {
   DCHECK(group_probability <= divisor_);
   DCHECK_GE(group_probability, 0);
 
-  if (enable_benchmarking_ || disable_field_trial_)
+  if (enable_benchmarking_ || !enable_field_trial_)
     group_probability = 0;
 
   accumulated_group_probability_ += group_probability;
 
   DCHECK(accumulated_group_probability_ <= divisor_);
   if (group_ == kNotFinalized && accumulated_group_probability_ > random_) {
     // This is the group that crossed the random line, so we do the assignment.
     group_ = next_group_number_;
     if (name.empty())
-      base::StringAppendF(&group_name_, "%d", group_);
+      StringAppendF(&group_name_, "%d", group_);
     else
       group_name_ = name;
   }
   return next_group_number_++;
 }
 
 int FieldTrial::group() {
   if (group_ == kNotFinalized) {
     accumulated_group_probability_ = divisor_;
     group_ = kDefaultGroupNumber;
     group_name_ = default_group_name_;
   }
   return group_;
 }
 
 std::string FieldTrial::group_name() {
   group();  // call group() to make group assignment was done.
+  DCHECK(!group_name_.empty());
   return group_name_;
 }
 
 // static
 std::string FieldTrial::MakeName(const std::string& name_prefix,
                                  const std::string& trial_name) {
   std::string big_string(name_prefix);
   big_string.append(1, kHistogramFieldTrialSeparator);
   return big_string.append(FieldTrialList::FindFullName(trial_name));
 }
 
 // static
 void FieldTrial::EnableBenchmarking() {
   DCHECK_EQ(0u, FieldTrialList::GetFieldTrialCount());
   enable_benchmarking_ = true;
 }
 
 FieldTrial::~FieldTrial() {}
 
 // static
 Time FieldTrial::GetBuildTime() {
   Time integral_build_time;
   const char* kDateTime = __DATE__ " " __TIME__;
   bool result = Time::FromString(ASCIIToWide(kDateTime).c_str(),
                                  &integral_build_time);
   DCHECK(result);
   return integral_build_time;
 }
 
+// static
+double FieldTrial::HashClientId(const std::string& client_id,
+                                const std::string& trial_name) {
+  // SHA-1 is designed to produce a uniformly random spread in its output space,
+  // even for nearly-identical inputs, so it helps massage whatever client_id
+  // and trial_name we get into something with a uniform distribution, which
+  // is desirable so that we don't skew any part of the 0-100% spectrum.
+  std::string input(client_id + trial_name);
+  unsigned char sha1_hash[SHA1_LENGTH];
+  SHA1HashBytes(reinterpret_cast<const unsigned char*>(input.c_str()),
+                input.size(),
+                sha1_hash);
+
+  COMPILE_ASSERT(sizeof(uint64) < sizeof(sha1_hash), need_more_data);
+  uint64* bits = reinterpret_cast<uint64*>(&sha1_hash[0]);
+
+  return BitsToRandLikeDouble(*bits);
+}
+
 //------------------------------------------------------------------------------
 // FieldTrialList methods and members.
 
 // static
 FieldTrialList* FieldTrialList::global_ = NULL;
 
 // static
 bool FieldTrialList::register_without_global_ = false;
 
 FieldTrialList::FieldTrialList() : application_start_time_(TimeTicks::Now()) {
@@ skipping 116 matching lines @@
 }
 
 // static
 size_t FieldTrialList::GetFieldTrialCount() {
   if (!global_)
     return 0;
   AutoLock auto_lock(global_->lock_);
   return global_->registered_.size();
 }
 
+// static
+void FieldTrialList::EnableOneTimeRandomization(const std::string& client_id) {
+  DCHECK(global_);
+  if (!global_)
+    return;
+
+  DCHECK(!global_->IsOneTimeRandomizationEnabled());
+  DCHECK(!client_id.empty());
+
+  global_->client_id_ = client_id;
+}
+
+// static
+bool FieldTrialList::IsOneTimeRandomizationEnabled() {
+  DCHECK(global_);
+  if (!global_)
+    return false;
+
+  return !global_->client_id_.empty();
+}
+
+// static
+const std::string& FieldTrialList::client_id() {
+  DCHECK(global_);
+  if (!global_)
+    return EmptyString();

[jar (doing other things), 2011/04/21 22:10:02]

If you switch over to using a detectable uninitialized value for client_id, you
could return it here rather than empty string.

[jar (doing other things), 2011/04/29 00:57:11]

In fact.... I'd argument that the EmptyString() would be a great way to say that
there is no client_id().

+
+  return global_->client_id_;
+}
+
 FieldTrial* FieldTrialList::PreLockedFind(const std::string& name) {
   RegistrationList::iterator it = registered_.find(name);
   if (registered_.end() == it)
     return NULL;
   return it->second;
 }
 
 }  // namespace base