bench: measure block (size)serialization speed

The SizeComputer is a special serializer which returns what the exact final size will be of the serialized content.

> cmake -B build -DBUILD_BENCH=ON -DCMAKE_BUILD_TYPE=Release && cmake --build build -j$(nproc) && build/bin/bench_bitcoin -filter='SizeComputerBlock|SerializeBlock' --min-time=10000

> C compiler ............................ AppleClang 16.0.0.16000026

|            ns/block |             block/s |    err% |     total | benchmark
|--------------------:|--------------------:|--------:|----------:|:----------
|          195,610.62 |            5,112.20 |    0.3% |     11.00 | `SerializeBlock`
|           12,061.83 |           82,906.19 |    0.1% |     11.01 | `SizeComputerBlock`

> C++ compiler .......................... GNU 13.3.0

|            ns/block |             block/s |    err% |       ins/block |       cyc/block |    IPC |      bra/block |   miss% |     total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
|          867,857.55 |            1,152.26 |    0.0% |    8,015,883.90 |    3,116,099.08 |  2.572 |   1,517,035.87 |    0.5% |     10.81 | `SerializeBlock`
|           30,928.27 |           32,332.88 |    0.0% |      221,683.03 |      111,055.84 |  1.996 |      53,037.03 |    0.8% |     11.03 | `SizeComputerBlock`

src/bench/checkblock.cpp

@@ -21,11 +21,34 @@
 #include <optional>
 #include <vector>
 
+static void SizeComputerBlock(benchmark::Bench& bench) {
+    CBlock block;
+    DataStream(benchmark::data::block413567) >> TX_WITH_WITNESS(block);
+
+    bench.unit("block").run([&] {
+        SizeComputer size_computer;
+        size_computer << TX_WITH_WITNESS(block);
+        assert(size_computer.size() == benchmark::data::block413567.size());
+    });
+}
+
+static void SerializeBlock(benchmark::Bench& bench) {
+    CBlock block;
+    DataStream(benchmark::data::block413567) >> TX_WITH_WITNESS(block);
+
+    // Create output stream and verify first serialization matches input
+    bench.unit("block").run([&] {
+        DataStream output_stream(benchmark::data::block413567.size());
+        output_stream << TX_WITH_WITNESS(block);
+        assert(output_stream.size() == benchmark::data::block413567.size());
+    });
+}
+
 // These are the two major time-sinks which happen after we have fully received
 // a block off the wire, but before we can relay the block on to peers using
 // compact block relay.
 
-static void DeserializeBlockTest(benchmark::Bench& bench)
+static void DeserializeBlock(benchmark::Bench& bench)
 {
     DataStream stream(benchmark::data::block413567);
     std::byte a{0};
@@ -39,7 +62,7 @@ static void DeserializeBlockTest(benchmark::Bench& bench)
     });
 }
 
-static void DeserializeAndCheckBlockTest(benchmark::Bench& bench)
+static void DeserializeAndCheckBlock(benchmark::Bench& bench)
 {
     DataStream stream(benchmark::data::block413567);
     std::byte a{0};
@@ -60,5 +83,7 @@ static void DeserializeAndCheckBlockTest(benchmark::Bench& bench)
     });
 }
 
-BENCHMARK(DeserializeBlockTest, benchmark::PriorityLevel::HIGH);
-BENCHMARK(DeserializeAndCheckBlockTest, benchmark::PriorityLevel::HIGH);
+BENCHMARK(SizeComputerBlock, benchmark::PriorityLevel::HIGH);
+BENCHMARK(SerializeBlock, benchmark::PriorityLevel::HIGH);
+BENCHMARK(DeserializeBlock, benchmark::PriorityLevel::HIGH);
+BENCHMARK(DeserializeAndCheckBlock, benchmark::PriorityLevel::HIGH);

src/streams.h

@@ -141,6 +141,7 @@ public:
     typedef vector_type::reverse_iterator reverse_iterator;
 
     explicit DataStream() = default;
+    explicit DataStream(size_type n) { reserve(n); }
     explicit DataStream(std::span<const uint8_t> sp) : DataStream{std::as_bytes(sp)} {}
     explicit DataStream(std::span<const value_type> sp) : vch(sp.data(), sp.data() + sp.size()) {}