Opt-in to rpm/deb default package filenames

Closes #13

Bench.cpp

@@ -34,7 +34,7 @@ ConflictSet::ReadRange singleton(Arena &arena, std::span<const uint8_t> key) {
       std::span<uint8_t>(new (arena) uint8_t[key.size() + 1], key.size() + 1);
   memcpy(r.data(), key.data(), key.size());
   r[key.size()] = 0;
-  return {key.data(), int(key.size()), r.data(), int(r.size())};
+  return {{key.data(), int(key.size())}, {r.data(), int(r.size())}, 0};
 }
 
 ConflictSet::ReadRange prefixRange(Arena &arena, std::span<const uint8_t> key) {
@@ -52,7 +52,7 @@ ConflictSet::ReadRange prefixRange(Arena &arena, std::span<const uint8_t> key) {
   auto r = std::span<uint8_t>(new (arena) uint8_t[index + 1], index + 1);
   memcpy(r.data(), key.data(), index + 1);
   r[r.size() - 1]++;
-  return {key.data(), int(key.size()), r.data(), int(r.size())};
+  return {{key.data(), int(key.size())}, {r.data(), int(r.size())}, 0};
 }
 
 void benchConflictSet() {
@@ -258,4 +258,4 @@ void benchConflictSet() {
   }
 }
 
-int main(void) { benchConflictSet(); }
+int main(void) { benchConflictSet(); }

CMakeLists.txt

@@ -25,6 +25,9 @@ endif()
 add_compile_options(-fdata-sections -ffunction-sections -Wswitch-enum
                     -Werror=switch-enum)
 
+option(USE_SIMD_FALLBACK
+       "Use fallback implementations of functions that use SIMD" OFF)
+
 # This is encouraged according to
 # https://valgrind.org/docs/manual/manual-core-adv.html#manual-core-adv.clientreq
 include_directories(SYSTEM ${CMAKE_SOURCE_DIR}/third_party/valgrind)
@@ -43,18 +46,20 @@ endif()
 include(CheckIncludeFileCXX)
 include(CMakePushCheckState)
 
-cmake_push_check_state()
+if(NOT USE_SIMD_FALLBACK)
-list(APPEND CMAKE_REQUIRED_FLAGS -mavx)
+  cmake_push_check_state()
-check_include_file_cxx("immintrin.h" HAS_AVX)
+  list(APPEND CMAKE_REQUIRED_FLAGS -mavx)
-if(HAS_AVX)
+  check_include_file_cxx("immintrin.h" HAS_AVX)
-  add_compile_options(-mavx)
+  if(HAS_AVX)
-  add_compile_definitions(HAS_AVX)
+    add_compile_options(-mavx)
-endif()
+    add_compile_definitions(HAS_AVX)
-cmake_pop_check_state()
+  endif()
+  cmake_pop_check_state()
 
-check_include_file_cxx("arm_neon.h" HAS_ARM_NEON)
+  check_include_file_cxx("arm_neon.h" HAS_ARM_NEON)
-if(HAS_ARM_NEON)
+  if(HAS_ARM_NEON)
-  add_compile_definitions(HAS_ARM_NEON)
+    add_compile_definitions(HAS_ARM_NEON)
+  endif()
 endif()
 
 set(CMAKE_CXX_IMPLICIT_LINK_LIBRARIES "")
@@ -267,6 +272,10 @@ set(CPACK_RESOURCE_FILE_README "${CMAKE_CURRENT_SOURCE_DIR}/README.md")
 set(CPACK_RPM_PACKAGE_ARCHITECTURE ${CMAKE_SYSTEM_PROCESSOR})
 set(CPACK_RPM_SPEC_INSTALL_POST "/bin/true") # avoid stripping
 set(CPACK_RPM_PACKAGE_LICENSE "Apache 2.0")
+set(CPACK_RPM_FILE_NAME RPM-DEFAULT)
+
+# deb
+set(CPACK_DEBIAN_FILE_NAME DEB-DEFAULT)
 
 include(CPack)
 

ConflictSet.cpp

@@ -29,6 +29,7 @@ limitations under the License.
 #include <span>
 #include <string>
 #include <string_view>
+#include <type_traits>
 #include <utility>
 
 #ifdef HAS_AVX
@@ -39,6 +40,8 @@ limitations under the License.
 
 #include <memcheck.h>
 
+using namespace weaselab;
+
 // Use assert for checking potentially complex properties during tests.
 // Use assume to hint simple properties to the optimizer.
 
@@ -558,7 +561,6 @@ template <class T> struct BoundedFreeListAllocator {
   }
 
   void release(T *p) {
-    static_assert(std::is_trivially_destructible_v<T>);
     if (freeListBytes >= kFreeListMaxMemory) {
       removeNode(p);
       return safe_free(p, sizeof(T) + p->partialKeyCapacity);
@@ -953,6 +955,42 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
     assert(self->getType() == Type_Node16);
 
     ++self->numChildren;
+#ifdef HAS_AVX
+    __m128i key_vec = _mm_set1_epi8(index);
+    __m128i indices;
+    memcpy(&indices, self16->index, sizeof(self16->index));
+    __m128i results = _mm_cmpeq_epi8(key_vec, _mm_min_epu8(key_vec, indices));
+    int mask = (1 << (self->numChildren - 1)) - 1;
+    uint32_t bitfield = _mm_movemask_epi8(results) & mask;
+    bitfield |= uint32_t(1) << (self->numChildren - 1);
+    int i = std::countr_zero(bitfield);
+    if (i < self->numChildren - 1) {
+      memmove(self16->index + i + 1, self16->index + i,
+              self->numChildren - (i + 1));
+      memmove(self16->children + i + 1, self16->children + i,
+              (self->numChildren - (i + 1)) * sizeof(Child));
+    }
+#elif defined(HAS_ARM_NEON)
+    uint8x16_t indices;
+    memcpy(&indices, self16->index, sizeof(self16->index));
+    // 0xff for each leq
+    auto results = vcleq_u8(vdupq_n_u8(index), indices);
+    uint64_t mask = (uint64_t(1) << ((self->numChildren - 1) * 4)) - 1;
+    // 0xf for each 0xff (within mask)
+    uint64_t bitfield =
+        vget_lane_u64(
+            vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(results), 4)),
+            0) &
+        mask;
+    bitfield |= uint64_t(0xf) << ((self->numChildren - 1) * 4);
+    int i = std::countr_zero(bitfield) / 4;
+    if (i < self->numChildren - 1) {
+      memmove(self16->index + i + 1, self16->index + i,
+              self->numChildren - (i + 1));
+      memmove(self16->children + i + 1, self16->children + i,
+              (self->numChildren - (i + 1)) * sizeof(Child));
+    }
+#else
     int i = 0;
     for (; i < int(self->numChildren) - 1; ++i) {
       if (int(self16->index[i]) > int(index)) {
@@ -963,6 +1001,7 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
         break;
       }
     }
+#endif
     self16->index[i] = index;
     auto &result = self16->children[i].child;
     result = nullptr;
@@ -978,8 +1017,8 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
       self = newSelf;
       goto insert256;
     }
-  insert48:
 
+  insert48:
     auto *self48 = static_cast<Node48 *>(self);
     self48->bitSet.set(index);
     ++self->numChildren;
@@ -991,6 +1030,7 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
     return result;
   }
   case Type_Node256: {
+
   insert256:
     auto *self256 = static_cast<Node256 *>(self);
     ++self->numChildren;
@@ -2607,16 +2647,25 @@ ConflictSet_check(void *cs, const ConflictSet_ReadRange *reads,
 __attribute__((__visibility__("default"))) void
 ConflictSet_addWrites(void *cs, const ConflictSet_WriteRange *writes, int count,
                       int64_t writeVersion) {
-  ((ConflictSet::Impl *)cs)->addWrites(writes, count, writeVersion);
+  auto *impl = ((ConflictSet::Impl *)cs);
+  mallocBytesDelta = 0;
+  impl->addWrites(writes, count, writeVersion);
+  impl->totalBytes += mallocBytesDelta;
 }
 __attribute__((__visibility__("default"))) void
 ConflictSet_setOldestVersion(void *cs, int64_t oldestVersion) {
-  ((ConflictSet::Impl *)cs)->setOldestVersion(oldestVersion);
+  auto *impl = ((ConflictSet::Impl *)cs);
+  mallocBytesDelta = 0;
+  impl->setOldestVersion(oldestVersion);
+  impl->totalBytes += mallocBytesDelta;
 }
 __attribute__((__visibility__("default"))) void *
 ConflictSet_create(int64_t oldestVersion) {
-  return new (safe_malloc(sizeof(ConflictSet::Impl)))
+  mallocBytesDelta = 0;
+  auto *result = new (safe_malloc(sizeof(ConflictSet::Impl)))
       ConflictSet::Impl{oldestVersion};
+  result->totalBytes += mallocBytesDelta;
+  return result;
 }
 __attribute__((__visibility__("default"))) void ConflictSet_destroy(void *cs) {
   using Impl = ConflictSet::Impl;
@@ -2630,6 +2679,12 @@ ConflictSet_getBytes(void *cs) {
 }
 }
 
+// Make sure abi is well-defined
+static_assert(std::is_standard_layout_v<ConflictSet::Result>);
+static_assert(std::is_standard_layout_v<ConflictSet::Key>);
+static_assert(std::is_standard_layout_v<ConflictSet::ReadRange>);
+static_assert(std::is_standard_layout_v<ConflictSet::WriteRange>);
+
 namespace {
 
 std::string getSearchPathPrintable(Node *n) {
@@ -2842,8 +2897,8 @@ Iterator firstGeq(Node *n, std::string_view key) {
   }
 }
 
-bool checkCorrectness(Node *node, int64_t oldestVersion,
+[[maybe_unused]] bool checkCorrectness(Node *node, int64_t oldestVersion,
-                      ConflictSet::Impl *impl) {
+                                       ConflictSet::Impl *impl) {
   bool success = true;
 
   checkParentPointers(node, success);

Internal.h

@@ -2,6 +2,8 @@
 
 #include "ConflictSet.h"
 
+using namespace weaselab;
+
 #include <bit>
 #include <cassert>
 #include <compare>
@@ -60,6 +62,10 @@ inline int64_t peakMallocBytes = 0;
 
 inline thread_local int64_t mallocBytesDelta = 0;
 
+#ifndef NDEBUG
+constexpr auto kMallocHeaderSize = 16;
+#endif
+
 // malloc that aborts on OOM and thus always returns a non-null pointer. Must be
 // paired with `safe_free`.
 __attribute__((always_inline)) inline void *safe_malloc(size_t s) {
@@ -69,18 +75,20 @@ __attribute__((always_inline)) inline void *safe_malloc(size_t s) {
   if (mallocBytes > peakMallocBytes) {
     peakMallocBytes = mallocBytes;
   }
-  void *p = malloc(s);
-  if (p == nullptr) {
-    abort();
-  }
-  return p;
-#else
-  void *p = malloc(s);
-  if (p == nullptr) {
-    abort();
-  }
-  return p;
 #endif
+  void *p = malloc(s
+#ifndef NDEBUG
+                   + kMallocHeaderSize
+#endif
+  );
+  if (p == nullptr) {
+    abort();
+  }
+#ifndef NDEBUG
+  memcpy(p, &s, sizeof(s));
+  (char *&)p += kMallocHeaderSize;
+#endif
+  return p;
 }
 
 // Must be paired with `safe_malloc`.
@@ -93,6 +101,12 @@ __attribute__((always_inline)) inline void safe_free(void *p, size_t s) {
   mallocBytes -= s;
   free(p);
 #else
+#ifndef NDEBUG
+  (char *&)p -= kMallocHeaderSize;
+  size_t expected;
+  memcpy(&expected, p, sizeof(expected));
+  assert(s == expected);
+#endif
   free(p);
 #endif
 }

Jenkinsfile

@@ -48,6 +48,17 @@ pipeline {
                 recordIssues(tools: [clang()])
             }
         }
+        stage('SIMD fallback') {
+            agent {
+                dockerfile {
+                    args '-v /home/jenkins/ccache:/ccache'
+                    reuseNode true
+                }
+            }
+            steps {
+                CleanBuildAndTest("-DUSE_SIMD_FALLBACK=ON")
+            }
+        }
         stage('Release [gcc]') {
             agent {
                 dockerfile {

README.md

@@ -9,49 +9,49 @@ Hardware for all benchmarks is a mac m1 2020.
 ## Skip list
 
 ```
-New conflict set: 1.964 sec
+New conflict set: 1.957 sec
-                  0.637 Mtransactions/sec
+                  0.639 Mtransactions/sec
-                  2.546 Mkeys/sec
+                  2.555 Mkeys/sec
-Detect only:      1.859 sec
+Detect only:      1.845 sec
-                  0.672 Mtransactions/sec
+                  0.678 Mtransactions/sec
-                  2.690 Mkeys/sec
+                  2.710 Mkeys/sec
-Skiplist only:    1.275 sec
+Skiplist only:    1.263 sec
-                  0.980 Mtransactions/sec
+                  0.990 Mtransactions/sec
-                  3.921 Mkeys/sec
+                  3.960 Mkeys/sec
 Performance counters:
-               Build: 0.0496
+               Build: 0.0546
-                 Add: 0.0539
+                 Add: 0.0563
-              Detect: 1.86
+              Detect: 1.84
               D.Sort: 0.412
-           D.Combine: 0.0139
+           D.Combine: 0.0141
-         D.CheckRead: 0.682
+         D.CheckRead: 0.671
-   D.CheckIntraBatch: 0.00673
+   D.CheckIntraBatch: 0.0068
-        D.MergeWrite: 0.593
+        D.MergeWrite: 0.592
-      D.RemoveBefore: 0.148
+      D.RemoveBefore: 0.146
 ```
 
 ## Radix tree (this implementation)
 
 ```
-New conflict set: 1.289 sec
+New conflict set: 1.366 sec
-                  0.970 Mtransactions/sec
+                  0.915 Mtransactions/sec
-                  3.879 Mkeys/sec
+                  3.660 Mkeys/sec
-Detect only:      1.199 sec
+Detect only:      1.248 sec
-                  1.043 Mtransactions/sec
+                  1.002 Mtransactions/sec
-                  4.170 Mkeys/sec
+                  4.007 Mkeys/sec
-Skiplist only:    0.542 sec
+Skiplist only:    0.573 sec
-                  2.305 Mtransactions/sec
+                  2.182 Mtransactions/sec
-                  9.220 Mkeys/sec
+                  8.730 Mkeys/sec
 Performance counters:
-               Build: 0.0395
+               Build: 0.0594
-                 Add: 0.0492
+                 Add: 0.0572
-              Detect: 1.2
+              Detect: 1.25
-              D.Sort: 0.411
+              D.Sort: 0.418
-           D.Combine: 0.0135
+           D.Combine: 0.0149
-         D.CheckRead: 0.22
+         D.CheckRead: 0.232
-   D.CheckIntraBatch: 0.00652
+   D.CheckIntraBatch: 0.0067
-        D.MergeWrite: 0.322
+        D.MergeWrite: 0.341
-      D.RemoveBefore: 0.223
+      D.RemoveBefore: 0.232
 ```
 
 # Our benchmark
@@ -60,25 +60,25 @@ Performance counters:
 
 |               ns/op |                op/s |    err% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------:|:----------
-|              249.47 |        4,008,533.72 |    0.5% |      0.01 | `point reads`
+|              246.99 |        4,048,700.59 |    0.2% |      0.01 | `point reads`
-|              236.78 |        4,223,252.12 |    0.4% |      0.01 | `prefix reads`
+|              260.16 |        3,843,784.65 |    0.1% |      0.01 | `prefix reads`
-|              432.76 |        2,310,737.74 |    0.1% |      0.01 | `range reads`
+|              493.35 |        2,026,953.19 |    0.1% |      0.01 | `range reads`
-|              449.42 |        2,225,105.96 |    0.5% |      0.01 | `point writes`
+|              462.05 |        2,164,289.23 |    0.6% |      0.01 | `point writes`
-|              438.47 |        2,280,674.39 |    0.3% |      0.01 | `prefix writes`
+|              448.19 |        2,231,205.25 |    0.9% |      0.01 | `prefix writes`
-|              242.92 |        4,116,581.59 |    3.7% |      0.02 | `range writes`
+|              255.83 |        3,908,845.72 |    1.5% |      0.02 | `range writes`
-|              553.31 |        1,807,319.60 |    0.7% |      0.01 | `monotonic increasing point writes`
+|              582.63 |        1,716,349.02 |    1.3% |      0.01 | `monotonic increasing point writes`
 
 ## Radix tree (this implementation)
 
 |               ns/op |                op/s |    err% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------:|:----------
-|               19.35 |       51,669,510.11 |    0.2% |      0.01 | `point reads`
+|               19.42 |       51,483,206.67 |    0.3% |      0.01 | `point reads`
-|               56.64 |       17,655,057.00 |    0.2% |      0.01 | `prefix reads`
+|               58.43 |       17,115,612.57 |    0.1% |      0.01 | `prefix reads`
-|              217.04 |        4,607,450.05 |    0.2% |      0.01 | `range reads`
+|              216.09 |        4,627,766.60 |    0.2% |      0.01 | `range reads`
-|               26.31 |       38,012,015.29 |    0.0% |      0.01 | `point writes`
+|               28.35 |       35,267,567.72 |    0.2% |      0.01 | `point writes`
-|               41.45 |       24,124,003.19 |    0.2% |      0.01 | `prefix writes`
+|               43.43 |       23,026,226.17 |    0.2% |      0.01 | `prefix writes`
-|               48.33 |       20,691,082.14 |    0.0% |      0.01 | `range writes`
+|               50.00 |       20,000,000.00 |    0.0% |      0.01 | `range writes`
-|               84.92 |       11,775,856.81 |    4.0% |      0.01 | `monotonic increasing point writes`
+|               92.38 |       10,824,863.69 |    4.1% |      0.01 | `monotonic increasing point writes`
 
 # "Real data" test
 
@@ -87,13 +87,13 @@ Point queries only, best of three runs. Gc ratio is the ratio of time spent doin
 ## skip list
 
 ```
-Check: 11.267 seconds, 331.812 MB/s, Add: 5.33323 seconds, 131.635 MB/s, Gc ratio: 45.4671%
+Check: 11.3385 seconds, 329.718 MB/s, Add: 5.35612 seconds, 131.072 MB/s, Gc ratio: 45.7173%
 ```
 
 ## radix tree
 
 ```
-Check: 2.48508 seconds, 1504.38 MB/s, Add: 2.07295 seconds, 338.666 MB/s, Gc ratio: 42.2825%
+Check: 2.48583 seconds, 1503.93 MB/s, Add: 2.12768 seconds, 329.954 MB/s, Gc ratio: 41.7943%
 ```
 
 ## hash table
@@ -101,5 +101,5 @@ Check: 2.48508 seconds, 1504.38 MB/s, Add: 2.07295 seconds, 338.666 MB/s, Gc rat
 (The hash table implementation doesn't work on range queries, and its purpose is to provide an idea of how fast point queries can be)
 
 ```
-Check: 1.83931 seconds, 2032.56 MB/s, Add: 0.607861 seconds, 1154.93 MB/s, Gc ratio: 48.7142%
+Check: 1.83386 seconds, 2038.6 MB/s, Add: 0.601411 seconds, 1167.32 MB/s, Gc ratio: 48.9776%
 ```

RealDataBench.cpp

@@ -8,6 +8,8 @@
 #include <unistd.h>
 #include <vector>
 
+using namespace weaselab;
+
 double now() {
   return std::chrono::duration_cast<std::chrono::nanoseconds>(
              std::chrono::steady_clock::now().time_since_epoch())
@@ -28,7 +30,7 @@ constexpr inline size_t rightAlign(size_t offset, size_t alignment) {
 
 int main(int argc, const char **argv) {
   // Use with this dataset https://snap.stanford.edu/data/memetracker9.html
-  // Preprocess the files with `sed -i '' '/^Q/d'`
+  // Preprocess the files with `sed -i'' '/^Q/d'`
 
   double checkTime = 0;
   double addTime = 0;

conflict_set_c_api_test.c

@@ -7,6 +7,7 @@ int main(void) {
   ConflictSet_WriteRange w;
   ConflictSet_Result result;
   ConflictSet_ReadRange r;
+  int64_t bytes;
   w.begin.p = (const uint8_t *)"0000";
   w.begin.len = 4;
   w.end.len = 0;
@@ -17,6 +18,8 @@ int main(void) {
   r.readVersion = 0;
   ConflictSet_check(cs, &r, &result, 1);
   assert(result == ConflictSet_Conflict);
+  bytes = ConflictSet_getBytes(cs);
+  assert(bytes > 0);
   ConflictSet_destroy(cs);
   return 0;
 }

conflict_set_cxx_api_test.cpp

@@ -2,6 +2,8 @@
 
 #include <cassert>
 
+using namespace weaselab;
+
 int main(void) {
   ConflictSet cs(0);
   ConflictSet::WriteRange w;
@@ -17,4 +19,6 @@ int main(void) {
   r.readVersion = 0;
   cs.check(&r, &result, 1);
   assert(result == ConflictSet::Conflict);
+  int64_t bytes = cs.getBytes();
+  assert(bytes > 0);
 }

fdb-patch.txt

@@ -1,32 +1,19 @@
-giff --git a/fdbserver/CMakeLists.txt b/fdbserver/CMakeLists.txt
+diff --git a/fdbserver/CMakeLists.txt b/fdbserver/CMakeLists.txt
-index 3f353c2ef..cd0834761 100644
+index 3f353c2ef..074a18628 100644
 --- a/fdbserver/CMakeLists.txt
 +++ b/fdbserver/CMakeLists.txt
 @@ -22,6 +22,9 @@ file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/workloads)
  
  add_flow_target(EXECUTABLE NAME fdbserver SRCS ${FDBSERVER_SRCS})
  
-+find_package(ConflictSet)
++find_package(conflict-set)
-+target_link_libraries(fdbserver PRIVATE conflict_set_static)
++target_link_libraries(fdbserver PRIVATE conflict-set-static)
 +
  if (WITH_SWIFT)
    # Setup the Swift sources in FDBServer.
    include(FindSwiftLibs)
-diff --git a/fdbserver/Resolver.actor.cpp b/fdbserver/Resolver.actor.cpp
-index bf4118f5f..d3b4eaad8 100644
---- a/fdbserver/Resolver.actor.cpp
-+++ b/fdbserver/Resolver.actor.cpp
-@@ -132,7 +132,7 @@ struct Resolver : ReferenceCounted<Resolver> {
- 	AsyncVar<int64_t> totalStateBytes;
- 	AsyncTrigger checkNeededVersion;
- 	std::map<NetworkAddress, ProxyRequestsInfo> proxyInfoMap;
--	ConflictSet* conflictSet;
-+	ConflictSet2* conflictSet;
- 	TransientStorageMetricSample iopsSample;
- 
- 	// Use LogSystem as backend for txnStateStore. However, the real commit
 diff --git a/fdbserver/SkipList.cpp b/fdbserver/SkipList.cpp
-index b48d32c6b..da106b5d2 100644
+index b48d32c6b..da99e03aa 100644
 --- a/fdbserver/SkipList.cpp
 +++ b/fdbserver/SkipList.cpp
 @@ -25,6 +25,7 @@
@@ -46,50 +33,35 @@ index b48d32c6b..da106b5d2 100644
  static std::vector<PerfDoubleCounter*> skc;
  
  static thread_local uint32_t g_seed = 0;
-@@ -782,26 +785,34 @@ private:
+@@ -783,10 +786,14 @@ private:
- 	}
  };
  
--struct ConflictSet {
+ struct ConflictSet {
 -	ConflictSet() : removalKey(makeString(0)), oldestVersion(0) {}
--	~ConflictSet() {}
++	ConflictSet() : versionHistory(0), removalKey(makeString(0)), oldestVersion(0) {}
-+struct ConflictSet2 {
+ 	~ConflictSet() {}
-+	ConflictSet2() : versionHistory(0), removalKey(makeString(0)), oldestVersion(0) {}
-+	~ConflictSet2() {}
  
 +#if USE_RADIX_TREE
-+	ConflictSet versionHistory;
++	weaselab::ConflictSet versionHistory;
 +#else
  	SkipList versionHistory;
 +#endif
  	Key removalKey;
  	Version oldestVersion;
  };
- 
+@@ -795,7 +802,11 @@ ConflictSet* newConflictSet() {
--ConflictSet* newConflictSet() {
+ 	return new ConflictSet;
--	return new ConflictSet;
-+ConflictSet2* newConflictSet() {
-+	return new ConflictSet2;
  }
--void clearConflictSet(ConflictSet* cs, Version v) {
+ void clearConflictSet(ConflictSet* cs, Version v) {
 -	SkipList(v).swap(cs->versionHistory);
-+void clearConflictSet(ConflictSet2* cs, Version v) {
 +#if USE_RADIX_TREE
-+	cs->versionHistory = ConflictSet{ 0 };
++	cs->versionHistory = weaselab::ConflictSet{ 0 };
 +#else
 +	SkipList().swap(cs->versionHistory);
 +#endif
  }
--void destroyConflictSet(ConflictSet* cs) {
+ void destroyConflictSet(ConflictSet* cs) {
-+void destroyConflictSet(ConflictSet2* cs) {
  	delete cs;
- }
- 
--ConflictBatch::ConflictBatch(ConflictSet* cs,
-+ConflictBatch::ConflictBatch(ConflictSet2* cs,
-                              std::map<int, VectorRef<int>>* conflictingKeyRangeMap,
-                              Arena* resolveBatchReplyArena)
-   : cs(cs), transactionCount(0), conflictingKeyRangeMap(conflictingKeyRangeMap),
 @@ -971,11 +982,15 @@ void ConflictBatch::detectConflicts(Version now,
  	t = timer();
  	if (newOldestVersion > cs->oldestVersion) {
@@ -112,7 +84,7 @@ index b48d32c6b..da106b5d2 100644
  
 +#if USE_RADIX_TREE
 +	Arena arena;
-+	auto* reads = new (arena) ConflictSet::ReadRange[combinedReadConflictRanges.size()];
++	auto* reads = new (arena) weaselab::ConflictSet::ReadRange[combinedReadConflictRanges.size()];
 +
 +	for (int i = 0; i < combinedReadConflictRanges.size(); ++i) {
 +		auto& read = reads[i];
@@ -122,11 +94,11 @@ index b48d32c6b..da106b5d2 100644
 +		read.end.p = combinedReadConflictRanges[i].end.begin();
 +		read.end.len = combinedReadConflictRanges[i].end.size();
 +	}
-+	auto* results = new (arena) ConflictSet::Result[combinedReadConflictRanges.size()];
++	auto* results = new (arena) weaselab::ConflictSet::Result[combinedReadConflictRanges.size()];
 +	cs->versionHistory.check(reads, results, combinedReadConflictRanges.size());
 +
 +	for (int i = 0; i < combinedReadConflictRanges.size(); ++i) {
-+		if (results[i] == ConflictSet::Conflict) {
++		if (results[i] == weaselab::ConflictSet::Conflict) {
 +			transactionConflictStatus[combinedReadConflictRanges[i].transaction] = true;
 +			if (combinedReadConflictRanges[i].conflictingKeyRange != nullptr) {
 +				combinedReadConflictRanges[i].conflictingKeyRange->push_back(*combinedReadConflictRanges[i].cKRArena,
@@ -147,7 +119,7 @@ index b48d32c6b..da106b5d2 100644
  
 +#if USE_RADIX_TREE
 +	Arena arena;
-+	auto* writes = new (arena) ConflictSet::WriteRange[combinedWriteConflictRanges.size()];
++	auto* writes = new (arena) weaselab::ConflictSet::WriteRange[combinedWriteConflictRanges.size()];
 +
 +	for (int i = 0; i < combinedWriteConflictRanges.size(); ++i) {
 +		auto& write = writes[i];
@@ -164,15 +136,6 @@ index b48d32c6b..da106b5d2 100644
  }
  
  void ConflictBatch::combineWriteConflictRanges() {
-@@ -1115,7 +1171,7 @@ void skipListTest() {
- 
- 	double start;
- 
--	ConflictSet* cs = newConflictSet();
-+	ConflictSet2* cs = newConflictSet();
- 
- 	Arena testDataArena;
- 	VectorRef<VectorRef<KeyRangeRef>> testData;
 @@ -1197,6 +1253,4 @@ void skipListTest() {
  	for (const auto& counter : skc) {
  		printf("%20s: %s\n", counter->getMetric().name().c_str(), counter->getMetric().formatted().c_str());
@@ -180,35 +143,3 @@ index b48d32c6b..da106b5d2 100644
 -
 -	printf("%d entries in version history\n", cs->versionHistory.count());
  }
-diff --git a/fdbserver/include/fdbserver/ConflictSet.h b/fdbserver/include/fdbserver/ConflictSet.h
-index 90ed2c406..b7e31217c 100644
---- a/fdbserver/include/fdbserver/ConflictSet.h
-+++ b/fdbserver/include/fdbserver/ConflictSet.h
-@@ -28,13 +28,13 @@
- #include "fdbclient/CommitTransaction.h"
- #include "fdbserver/ResolverBug.h"
- 
--struct ConflictSet;
--ConflictSet* newConflictSet();
--void clearConflictSet(ConflictSet*, Version);
--void destroyConflictSet(ConflictSet*);
-+struct ConflictSet2;
-+ConflictSet2* newConflictSet();
-+void clearConflictSet(ConflictSet2*, Version);
-+void destroyConflictSet(ConflictSet2*);
- 
- struct ConflictBatch {
--	explicit ConflictBatch(ConflictSet*,
-+	explicit ConflictBatch(ConflictSet2*,
- 	                       std::map<int, VectorRef<int>>* conflictingKeyRangeMap = nullptr,
- 	                       Arena* resolveBatchReplyArena = nullptr);
- 	~ConflictBatch();
-@@ -54,7 +54,7 @@ struct ConflictBatch {
- 	void GetTooOldTransactions(std::vector<int>& tooOldTransactions);
- 
- private:
--	ConflictSet* cs;
-+	ConflictSet2* cs;
- 	Standalone<VectorRef<struct TransactionInfo*>> transactionInfo;
- 	std::vector<struct KeyInfo> points;
- 	int transactionCount;

include/ConflictSet.h

@@ -19,6 +19,7 @@ limitations under the License.
 #include <stdint.h>
 
 #ifdef __cplusplus
+namespace weaselab {
 /** A data structure for optimistic concurrency control on ranges of
  * bitwise-lexicographically-ordered keys.
  *
@@ -26,7 +27,7 @@ limitations under the License.
  *   - It's safe to operate on two different ConflictSets in two different
  * threads concurrently
  *   - It's safe to have multiple threads operating on the same ConflictSet
- * concurrently if and only if all threads only call `check`.
+ * concurrently if and only if all threads only call const methods
  */
 struct __attribute__((__visibility__("default"))) ConflictSet {
   enum Result {
@@ -100,6 +101,7 @@ struct __attribute__((__visibility__("default"))) ConflictSet {
 private:
   Impl *impl;
 };
+} /* namespace weaselab */
 
 #else
 
@@ -110,7 +112,8 @@ private:
  *   - It's safe to operate on two different ConflictSets in two different
  * threads concurrently
  *   - It's safe to have multiple threads operating on the same ConflictSet
- * concurrently if and only if all threads only call `check`.
+ * concurrently if and only if all threads only call functions that accept a
+ * const ConflictSet pointer
  */
 typedef struct ConflictSet ConflictSet;
 
@@ -150,7 +153,8 @@ typedef struct {
 } ConflictSet_WriteRange;
 
 /** The result of checking reads[i] is written in results[i] */
-void ConflictSet_check(ConflictSet *cs, const ConflictSet_ReadRange *reads,
+void ConflictSet_check(const ConflictSet *cs,
+                       const ConflictSet_ReadRange *reads,
                        ConflictSet_Result *results, int count);
 
 /** `writes` must be sorted ascending, and must not have adjacent or
@@ -173,6 +177,6 @@ ConflictSet *ConflictSet_create(int64_t oldestVersion);
 void ConflictSet_destroy(ConflictSet *cs);
 
 /** Returns the total bytes in use by this ConflictSet */
-int64_t ConflictSet_getBytes(ConflictSet *cs);
+int64_t ConflictSet_getBytes(const ConflictSet *cs);
 
 #endif

symbols.txt

@@ -4,14 +4,14 @@ ConflictSet_create
 ConflictSet_destroy
 ConflictSet_getBytes
 ConflictSet_setOldestVersion
-_ZN11ConflictSet16setOldestVersionEl
+_ZN8weaselab11ConflictSet16setOldestVersionEl
-_ZN11ConflictSet9addWritesEPKNS_10WriteRangeEil
+_ZN8weaselab11ConflictSet9addWritesEPKNS0_10WriteRangeEil
-_ZN11ConflictSetaSEOS_
+_ZN8weaselab11ConflictSetaSEOS0_
-_ZN11ConflictSetC1El
+_ZN8weaselab11ConflictSetC1El
-_ZN11ConflictSetC1EOS_
+_ZN8weaselab11ConflictSetC1EOS0_
-_ZN11ConflictSetC2El
+_ZN8weaselab11ConflictSetC2El
-_ZN11ConflictSetC2EOS_
+_ZN8weaselab11ConflictSetC2EOS0_
-_ZN11ConflictSetD1Ev
+_ZN8weaselab11ConflictSetD1Ev
-_ZN11ConflictSetD2Ev
+_ZN8weaselab11ConflictSetD2Ev
-_ZNK11ConflictSet5checkEPKNS_9ReadRangeEPNS_6ResultEi
+_ZNK8weaselab11ConflictSet5checkEPKNS0_9ReadRangeEPNS0_6ResultEi
-_ZNK11ConflictSet8getBytesEv
+_ZNK8weaselab11ConflictSet8getBytesEv