Update README benchmark after adding getBytes

ConflictSet.cpp

@@ -2607,16 +2607,25 @@ 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 +2639,12 @@ 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) {

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: 1.962 sec
                   0.637 Mtransactions/sec
-                  2.546 Mkeys/sec
+                  2.548 Mkeys/sec
-Detect only:      1.859 sec
+Detect only:      1.842 sec
-                  0.672 Mtransactions/sec
+                  0.679 Mtransactions/sec
-                  2.690 Mkeys/sec
+                  2.714 Mkeys/sec
-Skiplist only:    1.275 sec
+Skiplist only:    1.261 sec
-                  0.980 Mtransactions/sec
+                  0.991 Mtransactions/sec
-                  3.921 Mkeys/sec
+                  3.964 Mkeys/sec
 Performance counters:
-               Build: 0.0496
+               Build: 0.0597
-                 Add: 0.0539
+                 Add: 0.0587
-              Detect: 1.86
+              Detect: 1.84
-              D.Sort: 0.412
+              D.Sort: 0.411
-           D.Combine: 0.0139
+           D.Combine: 0.0136
-         D.CheckRead: 0.682
+         D.CheckRead: 0.67
-   D.CheckIntraBatch: 0.00673
+   D.CheckIntraBatch: 0.00671
-        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: 1.285 sec
-                  0.970 Mtransactions/sec
+                  0.973 Mtransactions/sec
-                  3.879 Mkeys/sec
+                  3.892 Mkeys/sec
-Detect only:      1.199 sec
+Detect only:      1.196 sec
-                  1.043 Mtransactions/sec
+                  1.045 Mtransactions/sec
-                  4.170 Mkeys/sec
+                  4.180 Mkeys/sec
-Skiplist only:    0.542 sec
+Skiplist only:    0.539 sec
-                  2.305 Mtransactions/sec
+                  2.320 Mtransactions/sec
-                  9.220 Mkeys/sec
+                  9.281 Mkeys/sec
 Performance counters:
-               Build: 0.0395
+               Build: 0.0377
-                 Add: 0.0492
+                 Add: 0.0493
               Detect: 1.2
-              D.Sort: 0.411
+              D.Sort: 0.41
            D.Combine: 0.0135
-         D.CheckRead: 0.22
+         D.CheckRead: 0.219
-   D.CheckIntraBatch: 0.00652
+   D.CheckIntraBatch: 0.00654
-        D.MergeWrite: 0.322
+        D.MergeWrite: 0.319
-      D.RemoveBefore: 0.223
+      D.RemoveBefore: 0.224
 ```
 
 # 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%
 ```

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

@@ -17,4 +17,6 @@ int main(void) {
   r.readVersion = 0;
   cs.check(&r, &result, 1);
   assert(result == ConflictSet::Conflict);
+  int64_t bytes = cs.getBytes();
+  assert(bytes > 0);
 }

include/ConflictSet.h

@@ -26,7 +26,7 @@ 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 {
@@ -110,7 +110,8 @@ 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 +151,8 @@ 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 +175,6 @@ 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