txgraph: make number of acceptable iterations configurable (feature)

Author: sipa

src/bench/txgraph.cpp

@@ -46,6 +46,9 @@ void BenchTxGraphTrim(benchmark::Bench& bench)
     static constexpr int NUM_DEPS_PER_BOTTOM_TX = 100;
     /** Set a very large cluster size limit so that only the count limit is triggered. */
     static constexpr int32_t MAX_CLUSTER_SIZE = 100'000 * 100;
+    /** Set a very high number for acceptable iterations, so that we certainly benchmark optimal
+     *  linearization. */
+    static constexpr uint64_t NUM_ACCEPTABLE_ITERS = 100'000'000;
 
     /** Refs to all top transactions. */
     std::vector<TxGraph::Ref> top_refs;
@@ -57,7 +60,7 @@ void BenchTxGraphTrim(benchmark::Bench& bench)
     std::vector<size_t> top_components;
 
     InsecureRandomContext rng(11);
-    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE);
+    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE, NUM_ACCEPTABLE_ITERS);
 
     // Construct the top chains.
     for (int chain = 0; chain < NUM_TOP_CHAINS; ++chain) {

src/test/fuzz/txgraph.cpp

@@ -309,9 +309,11 @@ FUZZ_TARGET(txgraph)
     auto max_cluster_count = provider.ConsumeIntegralInRange<DepGraphIndex>(1, MAX_CLUSTER_COUNT_LIMIT);
     /** The maximum total size of transactions in a (non-oversized) cluster. */
     auto max_cluster_size = provider.ConsumeIntegralInRange<uint64_t>(1, 0x3fffff * MAX_CLUSTER_COUNT_LIMIT);
+    /** The number of iterations to consider a cluster acceptably linearized. */
+    auto acceptable_iters = provider.ConsumeIntegralInRange<uint64_t>(0, 10000);
 
     // Construct a real graph, and a vector of simulated graphs (main, and possibly staging).
-    auto real = MakeTxGraph(max_cluster_count, max_cluster_size);
+    auto real = MakeTxGraph(max_cluster_count, max_cluster_size, acceptable_iters);
     std::vector<SimTxGraph> sims;
     sims.reserve(2);
     sims.emplace_back(max_cluster_count, max_cluster_size);

src/test/txgraph_tests.cpp

@@ -13,6 +13,10 @@
 
 BOOST_AUTO_TEST_SUITE(txgraph_tests)
 
+/** The number used as acceptable_iters argument in these tests. High enough that everything
+ *  should be optimal, always. */
+static constexpr uint64_t NUM_ACCEPTABLE_ITERS = 100'000'000;
+
 BOOST_AUTO_TEST_CASE(txgraph_trim_zigzag)
 {
     // T     T     T     T     T     T     T     T     T     T     T     T     T     T (50 T's)
@@ -35,7 +39,7 @@ BOOST_AUTO_TEST_CASE(txgraph_trim_zigzag)
     static constexpr int32_t MAX_CLUSTER_SIZE = 100'000 * 100;
 
     // Create a new graph for the test.
-    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE);
+    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE, NUM_ACCEPTABLE_ITERS);
 
     // Add all transactions and store their Refs.
     std::vector<TxGraph::Ref> refs;
@@ -98,7 +102,7 @@ BOOST_AUTO_TEST_CASE(txgraph_trim_flower)
     /** Set a very large cluster size limit so that only the count limit is triggered. */
     static constexpr int32_t MAX_CLUSTER_SIZE = 100'000 * 100;
 
-    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE);
+    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE, NUM_ACCEPTABLE_ITERS);
 
     // Add all transactions and store their Refs.
     std::vector<TxGraph::Ref> refs;
@@ -184,7 +188,7 @@ BOOST_AUTO_TEST_CASE(txgraph_trim_huge)
     std::vector<size_t> top_components;
 
     FastRandomContext rng;
-    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE);
+    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE, NUM_ACCEPTABLE_ITERS);
 
     // Construct the top chains.
     for (int chain = 0; chain < NUM_TOP_CHAINS; ++chain) {
@@ -256,7 +260,7 @@ BOOST_AUTO_TEST_CASE(txgraph_trim_big_singletons)
     static constexpr int NUM_TOTAL_TX = 100;
 
     // Create a new graph for the test.
-    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE);
+    auto graph = MakeTxGraph(MAX_CLUSTER_COUNT, MAX_CLUSTER_SIZE, NUM_ACCEPTABLE_ITERS);
 
     // Add all transactions and store their Refs.
     std::vector<TxGraph::Ref> refs;

src/txgraph.cpp

@@ -255,6 +255,9 @@ class TxGraphImpl final : public TxGraph
     const DepGraphIndex m_max_cluster_count;
     /** This TxGraphImpl's maximum cluster size limit. */
     const uint64_t m_max_cluster_size;
+    /** The number of linearization improvement steps needed per cluster to be considered
+     *  acceptable. */
+    const uint64_t m_acceptable_iters;
 
     /** Information about one group of Clusters to be merged. */
     struct GroupEntry
@@ -456,9 +459,10 @@ class TxGraphImpl final : public TxGraph
 
 public:
     /** Construct a new TxGraphImpl with the specified limits. */
-    explicit TxGraphImpl(DepGraphIndex max_cluster_count, uint64_t max_cluster_size) noexcept :
+    explicit TxGraphImpl(DepGraphIndex max_cluster_count, uint64_t max_cluster_size, uint64_t acceptable_iters) noexcept :
         m_max_cluster_count(max_cluster_count),
         m_max_cluster_size(max_cluster_size),
+        m_acceptable_iters(acceptable_iters),
         m_main_chunkindex(ChunkOrder(this))
     {
         Assume(max_cluster_count >= 1);
@@ -1677,7 +1681,7 @@ void TxGraphImpl::MakeAcceptable(Cluster& cluster) noexcept
 {
     // Relinearize the Cluster if needed.
     if (!cluster.NeedsSplitting() && !cluster.IsAcceptable() && !cluster.IsOversized()) {
-        cluster.Relinearize(*this, 10000);
+        cluster.Relinearize(*this, m_acceptable_iters);
     }
 }
 
@@ -2892,7 +2896,7 @@ TxGraph::Ref::Ref(Ref&& other) noexcept
     std::swap(m_index, other.m_index);
 }
 
-std::unique_ptr<TxGraph> MakeTxGraph(unsigned max_cluster_count, uint64_t max_cluster_size) noexcept
+std::unique_ptr<TxGraph> MakeTxGraph(unsigned max_cluster_count, uint64_t max_cluster_size, uint64_t acceptable_iters) noexcept
 {
-    return std::make_unique<TxGraphImpl>(max_cluster_count, max_cluster_size);
+    return std::make_unique<TxGraphImpl>(max_cluster_count, max_cluster_size, acceptable_iters);
 }

src/txgraph.h

@@ -247,7 +247,8 @@ class TxGraph
 
 /** Construct a new TxGraph with the specified limit on the number of transactions within a cluster,
  *  and on the sum of transaction sizes within a cluster. max_cluster_count cannot exceed
- *  MAX_CLUSTER_COUNT_LIMIT. */
-std::unique_ptr<TxGraph> MakeTxGraph(unsigned max_cluster_count, uint64_t max_cluster_size) noexcept;
+ *  MAX_CLUSTER_COUNT_LIMIT. acceptable_iters controls how many linearization optimization
+ *  steps will be performed per cluster before they are considered to be of acceptable quality. */
+std::unique_ptr<TxGraph> MakeTxGraph(unsigned max_cluster_count, uint64_t max_cluster_size, uint64_t acceptable_iters) noexcept;
 
 #endif // BITCOIN_TXGRAPH_H