Remove unnecessary branch for interleaved range writes

Do it in a simpler, more robust/type safe way

CMakeLists.txt

@@ -102,8 +102,6 @@ option(DISABLE_TSAN "Disable TSAN" OFF)
 # https://valgrind.org/docs/manual/manual-core-adv.html#manual-core-adv.clientreq
 include_directories(SYSTEM ${CMAKE_CURRENT_SOURCE_DIR}/third_party/valgrind)
 
-add_compile_options($<$<COMPILE_LANGUAGE:CXX>:-Wno-invalid-offsetof>)
-
 if(APPLE)
   add_link_options(-Wl,-dead_strip)
 else()

README.md

@@ -7,7 +7,7 @@ Hardware for all benchmarks is an AMD Ryzen 9 7900 with (2x32GB) 5600MT/s CL28-3
 ```
 $ clang++ --version
 
-Ubuntu clang version 20.0.0 (++20241119082716+7e85cb8a8a9d-1~exp1~20241119082825.551)
+Ubuntu clang version 20.0.0 (++20241120082228+86734c857724-1~exp1~20241120202359.554)
 Target: x86_64-pc-linux-gnu
 Thread model: posix
 InstalledDir: /usr/lib/llvm-20/bin
@@ -19,30 +19,30 @@ InstalledDir: /usr/lib/llvm-20/bin
 
 |               ns/op |                op/s |    err% |          ins/op |          cyc/op |    IPC |         bra/op |   miss% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
-|              175.88 |        5,685,575.81 |    0.0% |        3,014.03 |          883.13 |  3.413 |         504.59 |    0.0% |      2.10 | `point reads`
-|              173.35 |        5,768,718.52 |    0.0% |        2,954.16 |          869.59 |  3.397 |         490.17 |    0.0% |      2.07 | `prefix reads`
-|              251.74 |        3,972,274.68 |    0.1% |        3,592.41 |        1,265.71 |  2.838 |         629.31 |    0.0% |      3.01 | `range reads`
-|              472.13 |        2,118,079.83 |    0.2% |        4,450.57 |        2,377.84 |  1.872 |         707.92 |    2.3% |      5.60 | `point writes`
-|              471.34 |        2,121,609.91 |    0.0% |        4,410.22 |        2,372.55 |  1.859 |         694.74 |    2.3% |      5.61 | `prefix writes`
-|              306.69 |        3,260,650.68 |    0.0% |        2,315.38 |        1,550.33 |  1.493 |         396.69 |    3.3% |      3.68 | `range writes`
-|              502.70 |        1,989,277.15 |    0.9% |        6,999.33 |        2,527.47 |  2.769 |       1,251.74 |    1.3% |      0.06 | `monotonic increasing point writes`
-|          138,097.67 |            7,241.25 |    0.7% |      807,445.67 |      699,899.00 |  1.154 |     144,584.50 |    0.8% |      0.01 | `worst case for radix tree`
-|               46.29 |       21,605,126.00 |    1.0% |          902.00 |          230.73 |  3.909 |         132.00 |    0.0% |      0.01 | `create and destroy`
+|              161.29 |        6,200,056.17 |    0.1% |        3,014.03 |          831.04 |  3.627 |         504.59 |    0.0% |      1.93 | `point reads`
+|              158.32 |        6,316,160.64 |    0.1% |        2,954.16 |          815.80 |  3.621 |         490.17 |    0.0% |      1.89 | `prefix reads`
+|              237.39 |        4,212,409.50 |    0.2% |        3,592.41 |        1,233.96 |  2.911 |         629.31 |    0.0% |      2.84 | `range reads`
+|              442.11 |        2,261,878.94 |    0.0% |        4,450.57 |        2,314.25 |  1.923 |         707.92 |    2.1% |      5.28 | `point writes`
+|              439.89 |        2,273,308.53 |    0.1% |        4,410.22 |        2,302.29 |  1.916 |         694.74 |    2.1% |      5.25 | `prefix writes`
+|              290.96 |        3,436,936.78 |    0.0% |        2,315.38 |        1,528.68 |  1.515 |         396.69 |    3.3% |      3.49 | `range writes`
+|              476.93 |        2,096,762.02 |    0.6% |        6,999.33 |        2,484.94 |  2.817 |       1,251.73 |    1.3% |      0.06 | `monotonic increasing point writes`
+|          131,736.57 |            7,590.91 |    1.1% |      807,444.50 |      704,941.71 |  1.145 |     144,584.60 |    0.9% |      0.01 | `worst case for radix tree`
+|               45.50 |       21,978,369.95 |    1.1% |          902.00 |          232.36 |  3.882 |         132.00 |    0.0% |      0.01 | `create and destroy`
 
 ## Radix tree (this implementation)
 
 
 |               ns/op |                op/s |    err% |          ins/op |          cyc/op |    IPC |         bra/op |   miss% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
-|               14.04 |       71,216,855.01 |    0.1% |          245.98 |           70.38 |  3.495 |          31.49 |    0.6% |      0.17 | `point reads`
-|               14.57 |       68,630,592.89 |    0.1% |          297.83 |           72.93 |  4.084 |          40.34 |    0.5% |      0.17 | `prefix reads`
-|               35.28 |       28,347,588.39 |    0.2% |          783.70 |          176.57 |  4.438 |         107.65 |    0.2% |      0.42 | `range reads`
-|               20.64 |       48,453,280.08 |    0.0% |          378.97 |          103.31 |  3.668 |          49.92 |    0.7% |      0.25 | `point writes`
-|               39.14 |       25,551,096.17 |    0.0% |          672.00 |          196.08 |  3.427 |         101.28 |    0.3% |      0.47 | `prefix writes`
-|               39.88 |       25,075,121.85 |    0.0% |          738.26 |          199.71 |  3.697 |         111.59 |    0.1% |      0.49 | `range writes`
-|               79.36 |       12,601,312.65 |    0.5% |        1,447.65 |          398.77 |  3.630 |         275.61 |    0.1% |      0.01 | `monotonic increasing point writes`
-|          307,037.33 |            3,256.93 |    0.3% |    4,043,060.50 |    1,549,199.33 |  2.610 |     714,828.00 |    0.1% |      0.01 | `worst case for radix tree`
-|               97.00 |       10,309,246.47 |    0.2% |        1,986.00 |          487.06 |  4.078 |         315.00 |    0.0% |      0.01 | `create and destroy`
+|               12.36 |       80,885,626.43 |    0.2% |          243.56 |           63.62 |  3.828 |          31.07 |    0.6% |      0.15 | `point reads`
+|               14.18 |       70,502,196.81 |    0.1% |          297.72 |           73.13 |  4.071 |          40.31 |    0.5% |      0.17 | `prefix reads`
+|               33.44 |       29,901,623.04 |    0.1% |          767.90 |          172.42 |  4.454 |         101.32 |    0.2% |      0.40 | `range reads`
+|               19.48 |       51,342,564.70 |    0.3% |          374.45 |          100.43 |  3.728 |          48.92 |    0.5% |      0.23 | `point writes`
+|               37.46 |       26,694,471.44 |    0.1% |          672.00 |          193.14 |  3.479 |         101.28 |    0.3% |      0.45 | `prefix writes`
+|               38.78 |       25,784,784.34 |    0.0% |          738.26 |          199.93 |  3.693 |         111.59 |    0.1% |      0.47 | `range writes`
+|               76.05 |       13,148,995.74 |    0.7% |        1,450.77 |          397.16 |  3.653 |         275.72 |    0.0% |      0.01 | `monotonic increasing point writes`
+|          286,920.33 |            3,485.29 |    0.4% |    4,117,948.00 |    1,521,352.00 |  2.707 |     714,833.00 |    0.1% |      0.01 | `worst case for radix tree`
+|               95.66 |       10,453,798.72 |    0.5% |        1,986.00 |          495.04 |  4.012 |         315.00 |    0.0% |      0.01 | `create and destroy`
 
 # "Real data" test
 
@@ -51,13 +51,13 @@ Point queries only. Gc ratio is the ratio of time spent doing garbage collection
 ## skip list
 
 ```
-Check: 4.66163 seconds, 361.716 MB/s, Add: 3.97534 seconds, 144.726 MB/s, Gc ratio: 33.3998%, Peak idle memory: 5.61007e+06
+Check: 4.53508 seconds, 371.81 MB/s, Add: 3.81222 seconds, 150.919 MB/s, Gc ratio: 33.66%, Peak idle memory: 5.61007e+06
 ```
 
 ## radix tree
 
 ```
-Check: 1.01776 seconds, 1656.77 MB/s, Add: 1.2718 seconds, 452.38 MB/s, Gc ratio: 38.626%, Peak idle memory: 2.05667e+06
+Check: 0.957735 seconds, 1760.6 MB/s, Add: 1.19942 seconds, 479.678 MB/s, Gc ratio: 38.6069%, Peak idle memory: 2.05667e+06
 ```
 
 ## hash table
@@ -65,6 +65,6 @@ Check: 1.01776 seconds, 1656.77 MB/s, Add: 1.2718 seconds, 452.38 MB/s, Gc ratio
 (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: 0.859188 seconds, 1962.54 MB/s, Add: 0.714174 seconds, 805.596 MB/s, Gc ratio: 34.9552%, Peak idle memory: 0
+Check: 0.804598 seconds, 2095.69 MB/s, Add: 0.671221 seconds, 857.147 MB/s, Gc ratio: 35.0034%, Peak idle memory: 0
 ```
 

ServerBench.cpp

@@ -161,8 +161,8 @@ template <class... Ts> std::string tupleKey(const Ts &...ts) {
 
 constexpr int kTotalKeyRange = 1'000'000'000;
 constexpr int kWindowSize = 1'000'000;
-constexpr int kNumReadKeysPerTx = 10;
-constexpr int kNumWriteKeysPerTx = 5;
+constexpr int kNumReadKeysPerTx = 5;
+constexpr int kNumWriteKeysPerTx = 10;
 
 struct Transaction {
   std::vector<std::string> keys;