Try to detect internal corruption of histogram instances....

base/metrics/histogram.h

 // Copyright (c) 2010 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.
 
 // Histogram is an object that aggregates statistics, and can summarize them in
 // various forms, including ASCII graphical, HTML, and numerically (as a
 // vector of numbers corresponding to each of the aggregating buckets).
 
 // It supports calls to accumulate either time intervals (which are processed
 // as integral number of milliseconds), or arbitrary integral units.
@@ skipping 18 matching lines @@
 // gigantic range with the addition of very few buckets.
 
 #ifndef BASE_METRICS_HISTOGRAM_H_
 #define BASE_METRICS_HISTOGRAM_H_
 #pragma once
 
 #include <map>
 #include <string>
 #include <vector>
 
+#include "base/gtest_prod_util.h"
 #include "base/ref_counted.h"
 #include "base/logging.h"
 #include "base/time.h"
 
 class Lock;
 class Pickle;
 
 namespace base {
 
 //------------------------------------------------------------------------------
@@ skipping 187 matching lines @@
 
 class Histogram : public base::RefCountedThreadSafe<Histogram> {
  public:
   typedef int Sample;  // Used for samples (and ranges of samples).
   typedef int Count;  // Used to count samples in a bucket.
   static const Sample kSampleType_MAX = INT_MAX;
 
   typedef std::vector<Count> Counts;
   typedef std::vector<Sample> Ranges;
 
-  /* These enums are meant to facilitate deserialization of renderer histograms
-     into the browser. */
+  // These enums are used to facilitate deserialization of renderer histograms
+  // into the browser.
   enum ClassType {
     HISTOGRAM,
     LINEAR_HISTOGRAM,
     BOOLEAN_HISTOGRAM,
     CUSTOM_HISTOGRAM,
     NOT_VALID_IN_RENDERER
   };
 
   enum BucketLayout {
     EXPONENTIAL,
     LINEAR,
     CUSTOM
   };
 
   enum Flags {
     kNoFlags = 0,
     kUmaTargetedHistogramFlag = 0x1,  // Histogram should be UMA uploaded.
 
     // Indicate that the histogram was pickled to be sent across an IPC Channel.
     // If we observe this flag on a histogram being aggregated into after IPC,
     // then we are running in a single process mode, and the aggregation should
     // not take place (as we would be aggregating back into the source
     // histogram!).
     kIPCSerializationSourceFlag = 0x10,
 
     kHexRangePrintingFlag = 0x8000,  // Fancy bucket-naming supported.
   };
 
+  enum Inconsistencies {
+    NO_INCONSISTENCIES = 0x0,
+    RANGE_CHECKSUM_ERROR = 0x1,
+    BUCKET_ORDER_ERROR = 0x2,
+    COUNT_HIGH_ERROR = 0x4,
+    COUNT_LOW_ERROR = 0x8,
+
+    NEVER_EXCEEDED_VALUE = 0x10
+  };
+
   struct DescriptionPair {
     Sample sample;
     const char* description;  // Null means end of a list of pairs.
   };
 
   //----------------------------------------------------------------------------
   // Statistic values, developed over the life of the histogram.
 
   class SampleSet {
    public:
     explicit SampleSet();
     ~SampleSet();
 
     // Adjust size of counts_ for use with given histogram.
     void Resize(const Histogram& histogram);
     void CheckSize(const Histogram& histogram) const;
 
     // Accessor for histogram to make routine additions.
     void Accumulate(Sample value, Count count, size_t index);
 
     // Accessor methods.
     Count counts(size_t i) const { return counts_[i]; }
     Count TotalCount() const;
     int64 sum() const { return sum_; }
     int64 square_sum() const { return square_sum_; }
+    int64 redundant_count() const { return redundant_count_; }
 
     // Arithmetic manipulation of corresponding elements of the set.
     void Add(const SampleSet& other);
     void Subtract(const SampleSet& other);
 
     bool Serialize(Pickle* pickle) const;
     bool Deserialize(void** iter, const Pickle& pickle);
 
    protected:
     // Actual histogram data is stored in buckets, showing the count of values
     // that fit into each bucket.
     Counts counts_;
 
     // Save simple stats locally.  Note that this MIGHT get done in base class
     // without shared memory at some point.
     int64 sum_;         // sum of samples.
     int64 square_sum_;  // sum of squares of samples.
+
+   private:
+    // Allow tests to corrupt our innards for testing purposes.
+    FRIEND_TEST(HistogramTest, CorruptSampleCounts);
+
+    // To help identify memory corruption, we reduntantly save the number of
+    // samples we've accumulated into all of our buckets.  We can compare this
+    // count to the sum of the counts in all buckets, and detect problems.  Note
+    // that due to races in histogram accumulation (if a histogram is indeed
+    // updated on several threads simultaneously), the tallies might mismatch,
+    // and also the snapshotting code may asynchronously get a mismatch (though
+    // generally either race based mismatch cause is VERY rare).
+    int64 redundant_count_;
   };
+
   //----------------------------------------------------------------------------
   // minimum should start from 1. 0 is invalid as a minimum. 0 is an implicit
   // default underflow bucket.
   static scoped_refptr<Histogram> FactoryGet(const std::string& name,
       Sample minimum, Sample maximum, size_t bucket_count, Flags flags);
   static scoped_refptr<Histogram> FactoryTimeGet(const std::string& name,
       base::TimeDelta minimum, base::TimeDelta maximum, size_t bucket_count,
       Flags flags);
 
   void Add(int value);
@@ skipping 31 matching lines @@
 
   // Serialize the given snapshot of a Histogram into a String. Uses
   // Pickle class to flatten the object.
   static std::string SerializeHistogramInfo(const Histogram& histogram,
                                             const SampleSet& snapshot);
   // The following method accepts a list of pickled histograms and
   // builds a histogram and updates shadow copy of histogram data in the
   // browser process.
   static bool DeserializeHistogramInfo(const std::string& histogram_info);
 
+  // Check to see if bucket ranges, counts and tallies in the snapshot are
+  // consistent with the bucket ranges and checksums in our histogram.  This can
+  // produce a false-alarm if a race occurred in the reading of the data during
+  // a SnapShot process, but should otherwise be false at all times (unless we
+  // have memory over-writes, or DRAM failures).
+  Inconsistencies FindCorruption(const SampleSet& snapshot) const;
+
   //----------------------------------------------------------------------------
   // Accessors for factory constuction, serialization and testing.
   //----------------------------------------------------------------------------
   virtual ClassType histogram_type() const { return HISTOGRAM; }
   const std::string& histogram_name() const { return histogram_name_; }
   Sample declared_min() const { return declared_min_; }
   Sample declared_max() const { return declared_max_; }
   virtual Sample ranges(size_t i) const { return ranges_[i];}
+  Sample range_checksum() const { return range_checksum_; }
   virtual size_t bucket_count() const { return bucket_count_; }
   // Snapshot the current complete set of sample data.
   // Override with atomic/locked snapshot if needed.
   virtual void SnapshotSample(SampleSet* sample) const;
 
   virtual bool HasConstructorArguments(Sample minimum, Sample maximum,
                                        size_t bucket_count);
 
   virtual bool HasConstructorTimeDeltaArguments(TimeDelta minimum,
                                                 TimeDelta maximum,
@@ skipping 14 matching lines @@
   //----------------------------------------------------------------------------
   // Methods to override to create histogram with different bucket widths.
   //----------------------------------------------------------------------------
   // Initialize ranges_ mapping.
   virtual void InitializeBucketRange();
   // Find bucket to increment for sample value.
   virtual size_t BucketIndex(Sample value) const;
   // Get normalized size, relative to the ranges_[i].
   virtual double GetBucketSize(Count current, size_t i) const;
 
+  // Recalculate range_checksum_.
+  void ResetRangeChecksum();
+
   // Return a string description of what goes in a given bucket.
   // Most commonly this is the numeric value, but in derived classes it may
   // be a name (or string description) given to the bucket.
   virtual const std::string GetAsciiBucketRange(size_t it) const;
 
   //----------------------------------------------------------------------------
   // Methods to override to create thread safe histogram.
   //----------------------------------------------------------------------------
   // Update all our internal data, including histogram
   virtual void Accumulate(Sample value, Count count, size_t index);
 
   //----------------------------------------------------------------------------
   // Accessors for derived classes.
   //----------------------------------------------------------------------------
   void SetBucketRange(size_t i, Sample value);
 
   // Validate that ranges_ was created sensibly (top and bottom range
   // values relate properly to the declared_min_ and declared_max_)..
   bool ValidateBucketRanges() const;
 
  private:
+  // Allow tests to corrupt our innards for testing purposes.
+  FRIEND_TEST(HistogramTest, CorruptBucketBounds);
+  FRIEND_TEST(HistogramTest, CorruptSampleCounts);
+
   // Post constructor initialization.
   void Initialize();
 
+  // Return true iff the range_checksum_ matches current ranges_ vector.
+  bool HasValidRangeChecksum() const;
+
+  Sample CalculateRangeChecksum() const;
+
   //----------------------------------------------------------------------------
   // Helpers for emitting Ascii graphic.  Each method appends data to output.
 
   // Find out how large the (graphically) the largest bucket will appear to be.
   double GetPeakBucketSize(const SampleSet& snapshot) const;
 
   // Write a common header message describing this histogram.
   void WriteAsciiHeader(const SampleSet& snapshot,
                         Count sample_count, std::string* output) const;
 
@@ skipping 24 matching lines @@
 
   // Flag the histogram for recording by UMA via metric_services.h.
   Flags flags_;
 
   // For each index, show the least value that can be stored in the
   // corresponding bucket. We also append one extra element in this array,
   // containing kSampleType_MAX, to make calculations easy.
   // The dimension of ranges_ is bucket_count + 1.
   Ranges ranges_;
 
+  // For redundancy, we store the sum of all the sample ranges when ranges are
+  // generated.  If ever there is ever a difference, then the histogram must
+  // have been corrupted.
+  Sample range_checksum_;
+
   // Finally, provide the state that changes with the addition of each new
   // sample.
   SampleSet sample_;
 
   DISALLOW_COPY_AND_ASSIGN(Histogram);
 };
 
 //------------------------------------------------------------------------------
 
 // LinearHistogram is a more traditional histogram, with evenly spaced
@@ skipping 64 matching lines @@
 };
 
 //------------------------------------------------------------------------------
 
 // CustomHistogram is a histogram for a set of custom integers.
 class CustomHistogram : public Histogram {
  public:
   virtual ClassType histogram_type() const;
 
   static scoped_refptr<Histogram> FactoryGet(const std::string& name,
-      const std::vector<int>& custom_ranges, Flags flags);
+      const std::vector<Sample>& custom_ranges, Flags flags);
 
  protected:
   CustomHistogram(const std::string& name,
-                  const std::vector<int>& custom_ranges);
+                  const std::vector<Sample>& custom_ranges);
 
   // Initialize ranges_ mapping.
   virtual void InitializeBucketRange();
   virtual double GetBucketSize(Count current, size_t i) const;
 
  private:
   // Temporary pointer used during construction/initialization, and then NULLed.
-  const std::vector<int>* ranges_vector_;
+  const std::vector<Sample>* ranges_vector_;
 
   DISALLOW_COPY_AND_ASSIGN(CustomHistogram);
 };
 
 //------------------------------------------------------------------------------
 // StatisticsRecorder handles all histograms in the system.  It provides a
 // general place for histograms to register, and supports a global API for
 // accessing (i.e., dumping, or graphing) the data in all the histograms.
 
 class StatisticsRecorder {
@@ skipping 47 matching lines @@
 
   // Dump all known histograms to log.
   static bool dump_on_exit_;
 
   DISALLOW_COPY_AND_ASSIGN(StatisticsRecorder);
 };
 
 }  // namespace base
 
 #endif  // BASE_METRICS_HISTOGRAM_H_