Update some of the invariant checks to account for leaves

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

CMakeLists.txt

@@ -32,12 +32,8 @@ if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
 endif()
 
 add_compile_options(
-  -Werror=switch-enum
-  -Wswitch-enum
-  -Wunused-variable
-  -fPIC
-  -fdata-sections
-  -ffunction-sections
+  # -Werror=switch-enum
+  -Wswitch-enum -Wunused-variable -fPIC -fdata-sections -ffunction-sections
   -fno-jump-tables # https://github.com/llvm/llvm-project/issues/54247
 )
 
@@ -102,8 +98,6 @@ 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
 |--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
-|              169.16 |        5,911,582.44 |    0.0% |        3,014.03 |          855.12 |  3.525 |         504.59 |    0.0% |      2.02 | `point reads`
-|              167.17 |        5,981,796.19 |    0.0% |        2,954.16 |          845.14 |  3.495 |         490.17 |    0.0% |      2.00 | `prefix reads`
-|              250.44 |        3,992,954.35 |    0.1% |        3,592.41 |        1,265.18 |  2.839 |         629.31 |    0.0% |      2.99 | `range reads`
-|              467.10 |        2,140,846.36 |    0.0% |        4,450.57 |        2,488.36 |  1.789 |         707.92 |    2.1% |      5.62 | `point writes`
-|              465.18 |        2,149,723.11 |    0.2% |        4,410.22 |        2,474.92 |  1.782 |         694.74 |    2.1% |      5.55 | `prefix writes`
-|              297.45 |        3,361,954.05 |    0.1% |        2,315.38 |        1,581.64 |  1.464 |         396.69 |    3.3% |      3.57 | `range writes`
-|              476.56 |        2,098,370.82 |    1.0% |        6,999.33 |        2,492.26 |  2.808 |       1,251.74 |    1.3% |      0.06 | `monotonic increasing point writes`
-|          129,455.00 |            7,724.69 |    1.0% |      807,446.67 |      698,559.40 |  1.156 |     144,584.60 |    0.8% |      0.01 | `worst case for radix tree`
-|               44.67 |       22,384,996.63 |    0.5% |          902.00 |          235.18 |  3.835 |         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
 |--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
-|               14.11 |       70,857,435.19 |    0.1% |          247.13 |           71.03 |  3.479 |          32.64 |    0.8% |      0.17 | `point reads`
-|               15.63 |       63,997,306.79 |    0.0% |          299.99 |           78.59 |  3.817 |          42.50 |    0.4% |      0.19 | `prefix reads`
-|               36.24 |       27,590,266.59 |    0.1% |          782.70 |          182.21 |  4.296 |         106.65 |    0.2% |      0.43 | `range reads`
-|               22.72 |       44,004,627.40 |    0.1% |          376.04 |          114.33 |  3.289 |          49.97 |    0.8% |      0.27 | `point writes`
-|               40.83 |       24,494,110.04 |    0.0% |          666.07 |          205.35 |  3.244 |         101.33 |    0.3% |      0.49 | `prefix writes`
-|               43.45 |       23,016,324.00 |    0.0% |          732.33 |          218.41 |  3.353 |         111.64 |    0.1% |      0.53 | `range writes`
-|               81.46 |       12,276,650.63 |    3.6% |        1,458.85 |          411.52 |  3.545 |         280.42 |    0.1% |      0.01 | `monotonic increasing point writes`
-|          314,217.00 |            3,182.51 |    1.2% |    4,043,063.50 |    1,593,715.00 |  2.537 |     714,828.00 |    0.1% |      0.01 | `worst case for radix tree`
-|              106.79 |        9,364,602.60 |    0.5% |        2,046.00 |          539.75 |  3.791 |         329.00 |    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: 4.62434 seconds, 364.633 MB/s, Add: 3.90399 seconds, 147.371 MB/s, Gc ratio: 33.6898%, 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: 0.956689 seconds, 1762.52 MB/s, Add: 1.35744 seconds, 423.84 MB/s, Gc ratio: 35.0946%, Peak idle memory: 2.32922e+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: 0.956689 seconds, 1762.52 MB/s, Add: 1.35744 seconds, 423.84 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: 0.799863 seconds, 2108.09 MB/s, Add: 0.667736 seconds, 861.621 MB/s, Gc ratio: 35.0666%, 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;