foundationdb/flowbench
FDB Formatster 2c788c233d apply clang-format to *.c, *.cpp, *.h, *.hpp files 2021-08-27 17:07:47 -07:00
..
BenchEncrypt.cpp apply clang-format to *.c, *.cpp, *.h, *.hpp files 2021-08-27 17:07:47 -07:00
BenchHash.cpp Add custom memcpy for aarch64 2021-06-16 14:35:04 +00:00
BenchIterate.cpp Renamed fdbbench to flowbench 2020-08-03 15:45:47 -07:00
BenchMetadataCheck.cpp Add include to BenchMetadataCheck.cpp 2021-06-02 21:28:37 -07:00
BenchPopulate.cpp Renamed fdbbench to flowbench 2020-08-03 15:45:47 -07:00
BenchRandom.cpp Added flowbench/README.md 2020-08-04 14:53:46 -07:00
BenchRef.cpp Add benchmark and document entities touched 2021-04-26 17:46:35 +00:00
BenchStream.actor.cpp Added flowbench/README.md 2020-08-04 14:53:46 -07:00
BenchTimer.cpp Added flowbench/README.md 2020-08-04 14:53:46 -07:00
CMakeLists.txt Added BenchEncrypt 2021-01-25 13:44:55 -08:00
GlobalData.cpp Replace xxhash64 with xxhash3 2020-11-21 18:25:35 -08:00
GlobalData.h Renamed fdbbench to flowbench 2020-08-03 15:45:47 -07:00
README.md Exclude flowbench target from all 2020-10-10 15:03:53 -07:00
benchmark.cmake Renamed fdbbench to flowbench 2020-08-03 15:45:47 -07:00
flowbench.actor.cpp Renamed fdbbench to flowbench 2020-08-03 15:45:47 -07:00

README.md

Summary

flowbench is an executable that can be used to microbenchmark parts of the FoundationDB code. The goal is to make it easy to test the performance of various sub-millisecond operations using flow and fdbrpc. Specifically, this tool can be used to:

  • Test the performance effects of changes to the actor compiler or to the flow and fdbrpc libraries
  • Test the performance of various uses of the flow and fdbrpc libraries
  • Find areas for improvement in the flow and fdbrpc libraries
  • Compare flow/fdbrpc primitives to alternatives provided by the standard library or other third-party libraries.

Usage

  • To build the flowbench executable, run ninja flowbench or make flowbench depending on which build system you're using.
  • Then you can run bin/flowbench --help to see possible uses of flowbench.
  • Running bin/flowbench directly will run all registered benchmarks, but you may want to limit your run to a subset of benchmarks. This can be done by running bin/flowbench --benchmark_filter=<regex>
  • All benchmark names can be listed with bin/flowbench --benchmark_list_tests
  • Example output:
$ bin/flowbench --benchmark_filter=bench_ref
2020-08-04 21:49:40
Running bin/flowbench
Run on (7 X 2904 MHz CPU s)
CPU Caches:
  L1 Data 32 KiB (x7)
  L1 Instruction 32 KiB (x7)
  L2 Unified 256 KiB (x7)
  L3 Unified 12288 KiB (x1)
Load Average: 0.15, 0.15, 0.72
---------------------------------------------------------------------------------------------------------------
Benchmark                                                     Time             CPU   Iterations UserCounters...
---------------------------------------------------------------------------------------------------------------
bench_ref_create_and_destroy<RefType::RawPointer>          4.90 ns         4.90 ns    116822124 items_per_second=203.88M/s
bench_ref_create_and_destroy<RefType::UniquePointer>       4.94 ns         4.94 ns    141101924 items_per_second=202.555M/s
bench_ref_create_and_destroy<RefType::SharedPointer>       42.5 ns         42.5 ns     13802909 items_per_second=23.531M/s
bench_ref_create_and_destroy<RefType::FlowReference>       5.05 ns         5.05 ns    100000000 items_per_second=197.955M/s
bench_ref_copy<RefType::RawPointer>                        1.15 ns         1.15 ns    612121585 items_per_second=871.218M/s
bench_ref_copy<RefType::SharedPointer>                     10.0 ns         10.0 ns     67553102 items_per_second=99.8113M/s
bench_ref_copy<RefType::FlowReference>                     2.33 ns         2.33 ns    292317474 items_per_second=428.507M/s

Existing Benchmarks

  • bench_populate measures the population of a vector of mutations
  • bench_ref compares the performance of the flow Reference type to other pointer types
  • bench_iterate measures iteration over a list of mutations
  • bench_stream measures the performance of writing to and reading from a PromiseStream
  • bench_random measures the performance of DeterministicRandom.
  • bench_timer measures the perforamnce of FoundationDB timers.

Future use cases

  • Benchmark the overhead of sending and receiving messages through FlowTransport
  • Benchmark the performance of serializing/deserializing various types