Merge bitcoin/bitcoin#24832: index: Verify the block filter hash when reading the filter from disk.

e734228d8585c0870c71ce8ba8c037f8cf8b249a Update GCSFilter benchmarks (Calvin Kim)
aee9a8140b3a58b744766f9e89572f1d953a808b Add GCSFilterDecodeSkipCheck benchmark (Patrick Strateman)
299023c1d9962628d158fac0306f8531506a0123 Add GCSFilterDecode and GCSBlockFilterGetHash benchmarks. (Patrick Strateman)
b0a53d50d9142bed51a8372eeb848816bfa94da8 Make sanity check in GCSFilter constructor optional (Patrick Strateman)

Pull request description:

  This PR picks up the abandoned #19280

  BlockFilterIndex was depending on `GolombRiceDecode()` during the filter decode to sanity check that the filter wasn't corrupt. However, we can check for corruption by ensuring that the encoded blockfilter's hash matches up with the one stored in the index database.

  Benchmarks that were added in #19280 showed that checking the hash is much faster.

  The benchmarks were changed to nanobench and the relevant benchmarks were like below, showing a clear win for the hash check method.

  ```
  |             ns/elem |              elem/s |    err% |        ins/elem |       bra/elem |   miss% |     total | benchmark
  |--------------------:|--------------------:|--------:|----------------:|---------------:|--------:|----------:|:----------
  |              531.40 |        1,881,819.43 |    0.3% |        3,527.01 |         411.00 |    0.2% |      0.01 | `DecodeCheckedGCSFilter`
  |          258,220.50 |            3,872.66 |    0.1% |    2,990,092.00 |     586,706.00 |    1.7% |      0.01 | `DecodeGCSFilter`
  |           13,036.77 |           76,706.09 |    0.3% |       64,238.24 |         513.04 |    0.2% |      0.01 | `BlockFilterGetHash`
  ```

ACKs for top commit:
  mzumsande:
    Code Review ACK e734228d8585c0870c71ce8ba8c037f8cf8b249a
  theStack:
    Code-review ACK e734228d8585c0870c71ce8ba8c037f8cf8b249a
  stickies-v:
    ACK e734228d8585c0870c71ce8ba8c037f8cf8b249a
  ryanofsky:
    Code review ACK e734228d8585c0870c71ce8ba8c037f8cf8b249a, with caveat that I mostly paid attention to the main code, not the changes to the benchmark. Only changes since last review were changes to the benchmark code.

Tree-SHA512: 02b86eab7b554e1a57a15b17a4d6d71faa91b556c637b0da29f0c9ee76597a110be8e3b4d0c158d4cab04af0623de18b764837be0ec2a72afcfe1ad9c78a83c6

1 files changed, 62 insertions, 17 deletions

diff --git a/src/bench/gcs_filter.cpp b/src/bench/gcs_filter.cpp
index 607e4392b7..80babb213b 100644
--- a/src/bench/gcs_filter.cpp
+++ b/src/bench/gcs_filter.cpp
@@ -5,39 +5,84 @@
 #include <bench/bench.h>
 #include <blockfilter.h>
 
-static void ConstructGCSFilter(benchmark::Bench& bench)
+static const GCSFilter::ElementSet GenerateGCSTestElements()
 {
     GCSFilter::ElementSet elements;
-    for (int i = 0; i < 10000; ++i) {
+
+    // Testing the benchmarks with different number of elements show that a filter
+    // with at least 100,000 elements results in benchmarks that have the same
+    // ns/op. This makes it easy to reason about how long (in nanoseconds) a single
+    // filter element takes to process.
+    for (int i = 0; i < 100000; ++i) {
         GCSFilter::Element element(32);
         element[0] = static_cast<unsigned char>(i);
         element[1] = static_cast<unsigned char>(i >> 8);
         elements.insert(std::move(element));
     }
 
+    return elements;
+}
+
+static void GCSBlockFilterGetHash(benchmark::Bench& bench)
+{
+    auto elements = GenerateGCSTestElements();
+
+    GCSFilter filter({0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, elements);
+    BlockFilter block_filter(BlockFilterType::BASIC, {}, filter.GetEncoded(), /*skip_decode_check=*/false);
+
+    bench.run([&] {
+        block_filter.GetHash();
+    });
+}
+
+static void GCSFilterConstruct(benchmark::Bench& bench)
+{
+    auto elements = GenerateGCSTestElements();
+
     uint64_t siphash_k0 = 0;
-    bench.batch(elements.size()).unit("elem").run([&] {
-        GCSFilter filter({siphash_k0, 0, 20, 1 << 20}, elements);
+    bench.run([&]{
+        GCSFilter filter({siphash_k0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, elements);
 
         siphash_k0++;
     });
 }
 
-static void MatchGCSFilter(benchmark::Bench& bench)
+static void GCSFilterDecode(benchmark::Bench& bench)
 {
-    GCSFilter::ElementSet elements;
-    for (int i = 0; i < 10000; ++i) {
-        GCSFilter::Element element(32);
-        element[0] = static_cast<unsigned char>(i);
-        element[1] = static_cast<unsigned char>(i >> 8);
-        elements.insert(std::move(element));
-    }
-    GCSFilter filter({0, 0, 20, 1 << 20}, elements);
+    auto elements = GenerateGCSTestElements();
 
-    bench.unit("elem").run([&] {
-        filter.Match(GCSFilter::Element());
+    GCSFilter filter({0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, elements);
+    auto encoded = filter.GetEncoded();
+
+    bench.run([&] {
+        GCSFilter filter({0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, encoded, /*skip_decode_check=*/false);
     });
 }
 
-BENCHMARK(ConstructGCSFilter);
-BENCHMARK(MatchGCSFilter);
+static void GCSFilterDecodeSkipCheck(benchmark::Bench& bench)
+{
+    auto elements = GenerateGCSTestElements();
+
+    GCSFilter filter({0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, elements);
+    auto encoded = filter.GetEncoded();
+
+    bench.run([&] {
+        GCSFilter filter({0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, encoded, /*skip_decode_check=*/true);
+    });
+}
+
+static void GCSFilterMatch(benchmark::Bench& bench)
+{
+    auto elements = GenerateGCSTestElements();
+
+    GCSFilter filter({0, 0, BASIC_FILTER_P, BASIC_FILTER_M}, elements);
+
+    bench.run([&] {
+        filter.Match(GCSFilter::Element());
+    });
+}
+BENCHMARK(GCSBlockFilterGetHash);
+BENCHMARK(GCSFilterConstruct);
+BENCHMARK(GCSFilterDecode);
+BENCHMARK(GCSFilterDecodeSkipCheck);
+BENCHMARK(GCSFilterMatch);