Update corpus

This is the default now

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.18)
 project(
   conflict-set
-  VERSION 0.0.7
+  VERSION 0.0.8
   DESCRIPTION
     "A data structure for optimistic concurrency control on ranges of bitwise-lexicographically-ordered keys."
   HOMEPAGE_URL "https://git.weaselab.dev/weaselab/conflict-set"

Internal.h

@@ -664,6 +664,44 @@ template <class ConflictSetImpl> struct TestDriver {
       fprintf(stderr, "Write @ %" PRId64 "\n", v);
 #endif
 
+      // Test non-canonical writes
+      if (numPointWrites > 0) {
+        int overlaps = arbitrary.bounded(numPointWrites);
+        for (int i = 0; i < numPointWrites + numRangeWrites && overlaps > 0;
+             ++i) {
+          if (writes[i].end.len == 0) {
+            int keyLen = prefixLen + arbitrary.bounded(kMaxKeySuffixLen);
+            auto *begin = new (arena) uint8_t[keyLen];
+            memset(begin, prefixByte, prefixLen);
+            arbitrary.randomBytes(begin + prefixLen, keyLen - prefixLen);
+            writes[i].end.len = keyLen;
+            writes[i].end.p = begin;
+            auto c =
+                std::span<const uint8_t>(writes[i].begin.p,
+                                         writes[i].begin.len) <=>
+                std::span<const uint8_t>(writes[i].end.p, writes[i].end.len);
+            if (c > 0) {
+              using std::swap;
+              swap(writes[i].begin, writes[i].end);
+            } else if (c == 0) {
+              // It's a point write after all, I guess
+              writes[i].end.len = 0;
+            }
+            --overlaps;
+          }
+        }
+      }
+      if (arbitrary.bounded(2)) {
+        // Shuffle writes
+        for (int i = numPointWrites + numRangeWrites - 1; i > 0; --i) {
+          int j = arbitrary.bounded(i + 1);
+          if (i != j) {
+            using std::swap;
+            swap(writes[i], writes[j]);
+          }
+        }
+      }
+
       CALLGRIND_START_INSTRUMENTATION;
       cs.addWrites(writes, numPointWrites + numRangeWrites, v);
       CALLGRIND_STOP_INSTRUMENTATION;

Jenkinsfile

@@ -59,17 +59,6 @@ pipeline {
                 CleanBuildAndTest("-DUSE_SIMD_FALLBACK=ON")
             }
         }
-        stage('32-bit versions') {
-            agent {
-                dockerfile {
-                    args '-v /home/jenkins/ccache:/ccache'
-                    reuseNode true
-                }
-            }
-            steps {
-                CleanBuildAndTest("-DUSE_32_BIT_VERSIONS=ON")
-            }
-        }
         stage('Release [gcc]') {
             agent {
                 dockerfile {

README.md

@@ -60,27 +60,27 @@ Performance counters:
 
 |               ns/op |                op/s |    err% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------:|:----------
-|              256.89 |        3,892,784.92 |    0.3% |      0.01 | `point reads`
-|              272.90 |        3,664,395.04 |    0.2% |      0.01 | `prefix reads`
-|              507.22 |        1,971,549.50 |    0.7% |      0.01 | `range reads`
-|              452.66 |        2,209,181.91 |    0.5% |      0.01 | `point writes`
-|              438.09 |        2,282,619.96 |    0.4% |      0.01 | `prefix writes`
-|              253.33 |        3,947,420.36 |    2.5% |      0.02 | `range writes`
-|              574.07 |        1,741,936.71 |    0.3% |      0.01 | `monotonic increasing point writes`
-|          151,562.50 |            6,597.94 |    1.5% |      0.01 | `worst case for radix tree`
+|              245.99 |        4,065,232.81 |    0.3% |      0.01 | `point reads`
+|              265.93 |        3,760,430.49 |    0.2% |      0.01 | `prefix reads`
+|              485.30 |        2,060,569.50 |    0.2% |      0.01 | `range reads`
+|              449.60 |        2,224,195.17 |    0.4% |      0.01 | `point writes`
+|              441.76 |        2,263,688.18 |    1.1% |      0.01 | `prefix writes`
+|              245.42 |        4,074,647.54 |    2.4% |      0.02 | `range writes`
+|              572.80 |        1,745,810.06 |    1.3% |      0.01 | `monotonic increasing point writes`
+|          154,819.33 |            6,459.14 |    0.9% |      0.01 | `worst case for radix tree`
 
 ## Radix tree (this implementation)
 
 |               ns/op |                op/s |    err% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------:|:----------
-|               19.83 |       50,420,955.28 |    0.1% |      0.01 | `point reads`
-|               55.95 |       17,872,542.40 |    0.5% |      0.01 | `prefix reads`
-|               88.28 |       11,327,709.50 |    0.4% |      0.01 | `range reads`
-|               29.15 |       34,309,531.64 |    0.5% |      0.01 | `point writes`
-|               42.36 |       23,607,424.27 |    1.1% |      0.01 | `prefix writes`
-|               50.00 |       20,000,000.00 |    0.0% |      0.01 | `range writes`
-|               93.52 |       10,692,413.79 |    3.3% |      0.01 | `monotonic increasing point writes`
-|        2,388,417.00 |              418.69 |    0.4% |      0.03 | `worst case for radix tree`
+|               19.17 |       52,163,930.66 |    0.1% |      0.01 | `point reads`
+|               23.68 |       42,224,388.21 |    0.7% |      0.01 | `prefix reads`
+|               63.30 |       15,797,506.06 |    0.9% |      0.01 | `range reads`
+|               29.66 |       33,720,994.74 |    0.3% |      0.01 | `point writes`
+|               43.50 |       22,987,781.25 |    1.0% |      0.01 | `prefix writes`
+|               50.00 |       20,000,000.00 |    0.8% |      0.01 | `range writes`
+|              103.25 |        9,684,786.47 |    2.9% |      0.01 | `monotonic increasing point writes`
+|        1,181,500.00 |              846.38 |    2.3% |      0.01 | `worst case for radix tree`
 
 # "Real data" test
 

SkipList.cpp

@@ -22,6 +22,8 @@
 
 #include "ConflictSet.h"
 #include "Internal.h"
+
+#include <algorithm>
 #include <span>
 
 std::span<const uint8_t> keyAfter(Arena &arena, std::span<const uint8_t> key) {
@@ -52,6 +54,135 @@ struct KeyRangeRef {
       : begin(begin), end(keyAfter(arena, begin)) {}
 };
 
+struct KeyInfo {
+  StringRef key;
+  bool begin;
+  bool write;
+
+  KeyInfo() = default;
+  KeyInfo(StringRef key, bool begin, bool write)
+      : key(key), begin(begin), write(write) {}
+};
+
+force_inline int extra_ordering(const KeyInfo &ki) {
+  return ki.begin * 2 + (ki.write ^ ki.begin);
+}
+
+// returns true if done with string
+force_inline bool getCharacter(const KeyInfo &ki, int character,
+                               int &outputCharacter) {
+  // normal case
+  if (character < ki.key.size()) {
+    outputCharacter = 5 + ki.key.begin()[character];
+    return false;
+  }
+
+  // termination
+  if (character == ki.key.size()) {
+    outputCharacter = 0;
+    return false;
+  }
+
+  if (character == ki.key.size() + 1) {
+    // end/begin+read/write relative sorting
+    outputCharacter = extra_ordering(ki);
+    return false;
+  }
+
+  outputCharacter = 0;
+  return true;
+}
+
+bool operator<(const KeyInfo &lhs, const KeyInfo &rhs) {
+  int i = std::min(lhs.key.size(), rhs.key.size());
+  int c = memcmp(lhs.key.data(), rhs.key.data(), i);
+  if (c != 0)
+    return c < 0;
+
+  // Always sort shorter keys before longer keys.
+  if (lhs.key.size() < rhs.key.size()) {
+    return true;
+  }
+  if (lhs.key.size() > rhs.key.size()) {
+    return false;
+  }
+
+  // When the keys are the same length, use the extra ordering constraint.
+  return extra_ordering(lhs) < extra_ordering(rhs);
+}
+
+bool operator==(const KeyInfo &lhs, const KeyInfo &rhs) {
+  return !(lhs < rhs || rhs < lhs);
+}
+
+void swapSort(std::vector<KeyInfo> &points, int a, int b) {
+  if (points[b] < points[a]) {
+    KeyInfo temp;
+    temp = points[a];
+    points[a] = points[b];
+    points[b] = temp;
+  }
+}
+
+struct SortTask {
+  int begin;
+  int size;
+  int character;
+  SortTask(int begin, int size, int character)
+      : begin(begin), size(size), character(character) {}
+};
+
+void sortPoints(std::vector<KeyInfo> &points) {
+  std::vector<SortTask> tasks;
+  std::vector<KeyInfo> newPoints;
+  std::vector<int> counts;
+
+  tasks.emplace_back(0, points.size(), 0);
+
+  while (tasks.size()) {
+    SortTask st = tasks.back();
+    tasks.pop_back();
+
+    if (st.size < 10) {
+      std::sort(points.begin() + st.begin, points.begin() + st.begin + st.size);
+      continue;
+    }
+
+    newPoints.resize(st.size);
+    counts.assign(256 + 5, 0);
+
+    // get counts
+    int c;
+    bool allDone = true;
+    for (int i = st.begin; i < st.begin + st.size; i++) {
+      allDone &= getCharacter(points[i], st.character, c);
+      counts[c]++;
+    }
+    if (allDone)
+      continue;
+
+    // calculate offsets from counts and build next level of tasks
+    int total = 0;
+    for (int i = 0; i < counts.size(); i++) {
+      int temp = counts[i];
+      if (temp > 1)
+        tasks.emplace_back(st.begin + total, temp, st.character + 1);
+      counts[i] = total;
+      total += temp;
+    }
+
+    // put in their places
+    for (int i = st.begin; i < st.begin + st.size; i++) {
+      getCharacter(points[i], st.character, c);
+      newPoints[counts[c]++] = points[i];
+    }
+
+    // copy back into original points array
+    for (int i = 0; i < st.size; i++)
+      points[st.begin + i] = newPoints[i];
+  }
+}
+
 static thread_local uint32_t g_seed = 0;
 
 static inline int skfastrand() {
@@ -602,10 +733,40 @@ struct __attribute__((visibility("hidden"))) ConflictSet::Impl {
 
   void addWrites(const ConflictSet::WriteRange *writes, int count,
                  int64_t writeVersion) {
+    auto points = std::vector<KeyInfo>(count * 2);
+    Arena arena;
+
+    for (int r = 0; r < count; r++) {
+      points.emplace_back(StringRef(writes[r].begin.p, writes[r].begin.len),
+                          true, true);
+      points.emplace_back(
+          writes[r].end.len > 0
+              ? StringRef{writes[r].end.p, size_t(writes[r].end.len)}
+              : keyAfter(arena, points.back().key),
+          false, true);
+    }
+
+    sortPoints(points);
+
+    int activeWriteCount = 0;
+    std::vector<std::pair<StringRef, StringRef>> combinedWriteConflictRanges;
+    for (const KeyInfo &point : points) {
+      if (point.write) {
+        if (point.begin) {
+          activeWriteCount++;
+          if (activeWriteCount == 1)
+            combinedWriteConflictRanges.emplace_back(point.key, StringRef());
+        } else /*if (point.end)*/ {
+          activeWriteCount--;
+          if (activeWriteCount == 0)
+            combinedWriteConflictRanges.back().second = point.key;
+        }
+      }
+    }
+
     assert(writeVersion >= newestVersion);
     newestVersion = writeVersion;
-    Arena arena;
-    const int stringCount = count * 2;
+    const int stringCount = combinedWriteConflictRanges.size() * 2;
 
     const int stripeSize = 16;
     SkipList::Finger fingers[stripeSize];
@@ -616,15 +777,13 @@ struct __attribute__((visibility("hidden"))) ConflictSet::Impl {
     int ss = stringCount - (stripes - 1) * stripeSize;
     for (int s = stripes - 1; s >= 0; s--) {
       for (int i = 0; i * 2 < ss; ++i) {
-        const auto &w = writes[s * stripeSize / 2 + i];
+        const auto &w = combinedWriteConflictRanges[s * stripeSize / 2 + i];
 #if DEBUG_VERBOSE
         printf("Write begin: %s\n", printable(w.begin).c_str());
         fflush(stdout);
 #endif
-        values[i * 2] = {w.begin.p, size_t(w.begin.len)};
-        values[i * 2 + 1] = w.end.len > 0
-                                ? StringRef{w.end.p, size_t(w.end.len)}
-                                : keyAfter(arena, values[i * 2]);
+        values[i * 2] = w.first;
+        values[i * 2 + 1] = w.second;
         keyUpdates += 3;
       }
       skipList.find(values, fingers, temp, ss);

corpus/0e410d4488defd877d2c9690a26970f57ab78b0c

@@ -1,4 +0,0 @@
-*
-
-
-

corpus/22c23c2418773edaaff055ed387f82c8ad078f9f

@@ -1,2 +0,0 @@
-*
-