/Users/brunogarcia/projects/bitcoin-core-dev/src/cluster_linearize.h

Source
// Copyright (c) The Bitcoin Core developers
// Distributed under the MIT software license, see the accompanying
// file COPYING or http://www.opensource.org/licenses/mit-license.php.

#ifndef BITCOIN_CLUSTER_LINEARIZE_H
#define BITCOIN_CLUSTER_LINEARIZE_H

#include <algorithm>
#include <cstdint>
#include <numeric>
#include <optional>
#include <utility>
#include <vector>

#include <memusage.h>
#include <random.h>
#include <span.h>
#include <util/feefrac.h>
#include <util/vecdeque.h>

namespace cluster_linearize {

/** Data type to represent transaction indices in DepGraphs and the clusters they represent. */
using DepGraphIndex = uint32_t;

/** Data structure that holds a transaction graph's preprocessed data (fee, size, ancestors,
 *  descendants). */
template<typename SetType>
class DepGraph
{
    /** Information about a single transaction. */
    struct Entry
    {
        /** Fee and size of transaction itself. */
        FeeFrac feerate;
        /** All ancestors of the transaction (including itself). */
        SetType ancestors;
        /** All descendants of the transaction (including itself). */
        SetType descendants;

        /** Equality operator (primarily for for testing purposes). */
        friend bool operator==(const Entry&, const Entry&) noexcept = default;

        /** Construct an empty entry. */
        Entry() noexcept = default;
        /** Construct an entry with a given feerate, ancestor set, descendant set. */
        Entry(const FeeFrac& f, const SetType& a, const SetType& d) noexcept : feerate(f), ancestors(a), descendants(d) {}
    };

    /** Data for each transaction. */
    std::vector<Entry> entries;

    /** Which positions are used. */
    SetType m_used;

public:
    /** Equality operator (primarily for testing purposes). */
    friend bool operator==(const DepGraph& a, const DepGraph& b) noexcept
    {
        if (a.m_used != b.m_used) return false;
        // Only compare the used positions within the entries vector.
        for (auto idx : a.m_used) {
            if (a.entries[idx] != b.entries[idx]) return false;
        }
        return true;
    }

    // Default constructors.
    DepGraph() noexcept = default;
    DepGraph(const DepGraph&) noexcept = default;
    DepGraph(DepGraph&&) noexcept = default;
    DepGraph& operator=(const DepGraph&) noexcept = default;
    DepGraph& operator=(DepGraph&&) noexcept = default;

    /** Construct a DepGraph object given another DepGraph and a mapping from old to new.
     *
     * @param depgraph   The original DepGraph that is being remapped.
     *
     * @param mapping    A span such that mapping[i] gives the position in the new DepGraph
     *                   for position i in the old depgraph. Its size must be equal to
     *                   depgraph.PositionRange(). The value of mapping[i] is ignored if
     *                   position i is a hole in depgraph (i.e., if !depgraph.Positions()[i]).
     *
     * @param pos_range  The PositionRange() for the new DepGraph. It must equal the largest
     *                   value in mapping for any used position in depgraph plus 1, or 0 if
     *                   depgraph.TxCount() == 0.
     *
     * Complexity: O(N^2) where N=depgraph.TxCount().
     */
    DepGraph(const DepGraph<SetType>& depgraph, std::span<const DepGraphIndex> mapping, DepGraphIndex pos_range) noexcept : entries(pos_range)
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        for (DepGraphIndex i : depgraph.Positions()) {
            auto new_idx = mapping[i];
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            // Add transaction.
            entries[new_idx].ancestors = SetType::Singleton(new_idx);
            entries[new_idx].descendants = SetType::Singleton(new_idx);
            m_used.Set(new_idx);
            // Fill in fee and size.
            entries[new_idx].feerate = depgraph.entries[i].feerate;
        }
        for (DepGraphIndex i : depgraph.Positions()) {
            // Fill in dependencies by mapping direct parents.
            SetType parents;
            for (auto j : depgraph.GetReducedParents(i)) parents.Set(mapping[j]);
            AddDependencies(parents, mapping[i]);
        }
        // Verify that the provided pos_range was correct (no unused positions at the end).
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
    }

    /** Get the set of transactions positions in use. Complexity: O(1). */
    const SetType& Positions() const noexcept { return m_used; }
    /** Get the range of positions in this DepGraph. All entries in Positions() are in [0, PositionRange() - 1]. */
    DepGraphIndex PositionRange() const noexcept { return entries.size(); }
    /** Get the number of transactions in the graph. Complexity: O(1). */
    auto TxCount() const noexcept { return m_used.Count(); }
    /** Get the feerate of a given transaction i. Complexity: O(1). */
    const FeeFrac& FeeRate(DepGraphIndex i) const noexcept { return entries[i].feerate; }
    /** Get the mutable feerate of a given transaction i. Complexity: O(1). */
    FeeFrac& FeeRate(DepGraphIndex i) noexcept { return entries[i].feerate; }
    /** Get the ancestors of a given transaction i. Complexity: O(1). */
    const SetType& Ancestors(DepGraphIndex i) const noexcept { return entries[i].ancestors; }
    /** Get the descendants of a given transaction i. Complexity: O(1). */
    const SetType& Descendants(DepGraphIndex i) const noexcept { return entries[i].descendants; }

    /** Add a new unconnected transaction to this transaction graph (in the first available
     *  position), and return its DepGraphIndex.
     *
     * Complexity: O(1) (amortized, due to resizing of backing vector).
     */
    DepGraphIndex AddTransaction(const FeeFrac& feefrac) noexcept
    {
        static constexpr auto ALL_POSITIONS = SetType::Fill(SetType::Size());
        auto available = ALL_POSITIONS - m_used;
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        DepGraphIndex new_idx = available.First();
        if (new_idx == entries.size()) {
            entries.emplace_back(feefrac, SetType::Singleton(new_idx), SetType::Singleton(new_idx));
        } else {
            entries[new_idx] = Entry(feefrac, SetType::Singleton(new_idx), SetType::Singleton(new_idx));
        }
        m_used.Set(new_idx);
        return new_idx;
    }

    /** Remove the specified positions from this DepGraph.
     *
     * The specified positions will no longer be part of Positions(), and dependencies with them are
     * removed. Note that due to DepGraph only tracking ancestors/descendants (and not direct
     * dependencies), if a parent is removed while a grandparent remains, the grandparent will
     * remain an ancestor.
     *
     * Complexity: O(N) where N=TxCount().
     */
    void RemoveTransactions(const SetType& del) noexcept
    {
        m_used -= del;
        // Remove now-unused trailing entries.
        while (!entries.empty() && !m_used[entries.size() - 1]) {
            entries.pop_back();
        }
        // Remove the deleted transactions from ancestors/descendants of other transactions. Note
        // that the deleted positions will retain old feerate and dependency information. This does
        // not matter as they will be overwritten by AddTransaction if they get used again.
        for (auto& entry : entries) {
            entry.ancestors &= m_used;
            entry.descendants &= m_used;
        }
    }

    /** Modify this transaction graph, adding multiple parents to a specified child.
     *
     * Complexity: O(N) where N=TxCount().
     */
    void AddDependencies(const SetType& parents, DepGraphIndex child) noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        // Compute the ancestors of parents that are not already ancestors of child.
        SetType par_anc;
        for (auto par : parents - Ancestors(child)) {
            par_anc |= Ancestors(par);
        }
        par_anc -= Ancestors(child);
        // Bail out if there are no such ancestors.
        if (par_anc.None()) return;
        // To each such ancestor, add as descendants the descendants of the child.
        const auto& chl_des = entries[child].descendants;
        for (auto anc_of_par : par_anc) {
            entries[anc_of_par].descendants |= chl_des;
        }
        // To each descendant of the child, add those ancestors.
        for (auto dec_of_chl : Descendants(child)) {
            entries[dec_of_chl].ancestors |= par_anc;
        }
    }

    /** Compute the (reduced) set of parents of node i in this graph.
     *
     * This returns the minimal subset of the parents of i whose ancestors together equal all of
     * i's ancestors (unless i is part of a cycle of dependencies). Note that DepGraph does not
     * store the set of parents; this information is inferred from the ancestor sets.
     *
     * Complexity: O(N) where N=Ancestors(i).Count() (which is bounded by TxCount()).
     */
    SetType GetReducedParents(DepGraphIndex i) const noexcept
    {
        SetType parents = Ancestors(i);
        parents.Reset(i);
        for (auto parent : parents) {
            if (parents[parent]) {
                parents -= Ancestors(parent);
                parents.Set(parent);
            }
        }
        return parents;
    }

    /** Compute the (reduced) set of children of node i in this graph.
     *
     * This returns the minimal subset of the children of i whose descendants together equal all of
     * i's descendants (unless i is part of a cycle of dependencies). Note that DepGraph does not
     * store the set of children; this information is inferred from the descendant sets.
     *
     * Complexity: O(N) where N=Descendants(i).Count() (which is bounded by TxCount()).
     */
    SetType GetReducedChildren(DepGraphIndex i) const noexcept
    {
        SetType children = Descendants(i);
        children.Reset(i);
        for (auto child : children) {
            if (children[child]) {
                children -= Descendants(child);
                children.Set(child);
            }
        }
        return children;
    }

    /** Compute the aggregate feerate of a set of nodes in this graph.
     *
     * Complexity: O(N) where N=elems.Count().
     **/
    FeeFrac FeeRate(const SetType& elems) const noexcept
    {
        FeeFrac ret;
        for (auto pos : elems) ret += entries[pos].feerate;
        return ret;
    }

    /** Get the connected component within the subset "todo" that contains tx (which must be in
     *  todo).
     *
     * Two transactions are considered connected if they are both in `todo`, and one is an ancestor
     * of the other in the entire graph (so not just within `todo`), or transitively there is a
     * path of transactions connecting them. This does mean that if `todo` contains a transaction
     * and a grandparent, but misses the parent, they will still be part of the same component.
     *
     * Complexity: O(ret.Count()).
     */
    SetType GetConnectedComponent(const SetType& todo, DepGraphIndex tx) const noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        auto to_add = SetType::Singleton(tx);
        SetType ret;
        do {
            SetType old = ret;
            for (auto add : to_add) {
                ret |= Descendants(add);
                ret |= Ancestors(add);
            }
            ret &= todo;
            to_add = ret - old;
        } while (to_add.Any());
        return ret;
    }

    /** Find some connected component within the subset "todo" of this graph.
     *
     * Specifically, this finds the connected component which contains the first transaction of
     * todo (if any).
     *
     * Complexity: O(ret.Count()).
     */
    SetType FindConnectedComponent(const SetType& todo) const noexcept
    {
        if (todo.None()) return todo;
        return GetConnectedComponent(todo, todo.First());
    }

    /** Determine if a subset is connected.
     *
     * Complexity: O(subset.Count()).
     */
    bool IsConnected(const SetType& subset) const noexcept
    {
        return FindConnectedComponent(subset) == subset;
    }

    /** Determine if this entire graph is connected.
     *
     * Complexity: O(TxCount()).
     */
    bool IsConnected() const noexcept { return IsConnected(m_used); }

    /** Append the entries of select to list in a topologically valid order.
     *
     * Complexity: O(select.Count() * log(select.Count())).
     */
    void AppendTopo(std::vector<DepGraphIndex>& list, const SetType& select) const noexcept
    {
        DepGraphIndex old_len = list.size();
        for (auto i : select) list.push_back(i);
        std::sort(list.begin() + old_len, list.end(), [&](DepGraphIndex a, DepGraphIndex b) noexcept {
            const auto a_anc_count = entries[a].ancestors.Count();
            const auto b_anc_count = entries[b].ancestors.Count();
            if (a_anc_count != b_anc_count) return a_anc_count < b_anc_count;
            return a < b;
        });
    }

    /** Check if this graph is acyclic. */
    bool IsAcyclic() const noexcept
    {
        for (auto i : Positions()) {
            if ((Ancestors(i) & Descendants(i)) != SetType::Singleton(i)) {
                return false;
            }
        }
        return true;
    }

    /** Reduce memory usage if possible. No observable effect. */
    void Compact() noexcept
    {
        entries.shrink_to_fit();
    }

    size_t DynamicMemoryUsage() const noexcept
    {
        return memusage::DynamicUsage(entries);
    }
};

/** A set of transactions together with their aggregate feerate. */
template<typename SetType>
struct SetInfo
{
    /** The transactions in the set. */
    SetType transactions;
    /** Their combined fee and size. */
    FeeFrac feerate;

    /** Construct a SetInfo for the empty set. */
    SetInfo() noexcept = default;

    /** Construct a SetInfo for a specified set and feerate. */
    SetInfo(const SetType& txn, const FeeFrac& fr) noexcept : transactions(txn), feerate(fr) {}

    /** Construct a SetInfo for a given transaction in a depgraph. */
    explicit SetInfo(const DepGraph<SetType>& depgraph, DepGraphIndex pos) noexcept :
        transactions(SetType::Singleton(pos)), feerate(depgraph.FeeRate(pos)) {}

    /** Construct a SetInfo for a set of transactions in a depgraph. */
    explicit SetInfo(const DepGraph<SetType>& depgraph, const SetType& txn) noexcept :
        transactions(txn), feerate(depgraph.FeeRate(txn)) {}

    /** Add a transaction to this SetInfo (which must not yet be in it). */
    void Set(const DepGraph<SetType>& depgraph, DepGraphIndex pos) noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        transactions.Set(pos);
        feerate += depgraph.FeeRate(pos);
    }

    /** Add the transactions of other to this SetInfo (no overlap allowed). */
    SetInfo& operator|=(const SetInfo& other) noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        transactions |= other.transactions;
        feerate += other.feerate;
        return *this;
    }

    /** Construct a new SetInfo equal to this, with more transactions added (which may overlap
     *  with the existing transactions in the SetInfo). */
    [[nodiscard]] SetInfo Add(const DepGraph<SetType>& depgraph, const SetType& txn) const noexcept
    {
        return {transactions | txn, feerate + depgraph.FeeRate(txn - transactions)};
    }

    /** Swap two SetInfo objects. */
    friend void swap(SetInfo& a, SetInfo& b) noexcept
    {
        swap(a.transactions, b.transactions);
        swap(a.feerate, b.feerate);
    }

    /** Permit equality testing. */
    friend bool operator==(const SetInfo&, const SetInfo&) noexcept = default;
};

/** Compute the feerates of the chunks of linearization. */
template<typename SetType>
std::vector<FeeFrac> ChunkLinearization(const DepGraph<SetType>& depgraph, std::span<const DepGraphIndex> linearization) noexcept
{
    std::vector<FeeFrac> ret;
    for (DepGraphIndex i : linearization) {
        /** The new chunk to be added, initially a singleton. */
        auto new_chunk = depgraph.FeeRate(i);
        // As long as the new chunk has a higher feerate than the last chunk so far, absorb it.
        while (!ret.empty() && new_chunk >> ret.back()) {
            new_chunk += ret.back();
            ret.pop_back();
        }
        // Actually move that new chunk into the chunking.
        ret.push_back(std::move(new_chunk));
    }
    return ret;
}

/** Data structure encapsulating the chunking of a linearization, permitting removal of subsets. */
template<typename SetType>
class LinearizationChunking
{
    /** The depgraph this linearization is for. */
    const DepGraph<SetType>& m_depgraph;

    /** The linearization we started from, possibly with removed prefix stripped. */
    std::span<const DepGraphIndex> m_linearization;

    /** Chunk sets and their feerates, of what remains of the linearization. */
    std::vector<SetInfo<SetType>> m_chunks;

    /** How large a prefix of m_chunks corresponds to removed transactions. */
    DepGraphIndex m_chunks_skip{0};

    /** Which transactions remain in the linearization. */
    SetType m_todo;

    /** Fill the m_chunks variable, and remove the done prefix of m_linearization. */
    void BuildChunks() noexcept
    {
        // Caller must clear m_chunks.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)

        // Chop off the initial part of m_linearization that is already done.
        while (!m_linearization.empty() && !m_todo[m_linearization.front()]) {
            m_linearization = m_linearization.subspan(1);
        }

        // Iterate over the remaining entries in m_linearization. This is effectively the same
        // algorithm as ChunkLinearization, but supports skipping parts of the linearization and
        // keeps track of the sets themselves instead of just their feerates.
        for (auto idx : m_linearization) {
            if (!m_todo[idx]) continue;
            // Start with an initial chunk containing just element idx.
            SetInfo add(m_depgraph, idx);
            // Absorb existing final chunks into add while they have lower feerate.
            while (!m_chunks.empty() && add.feerate >> m_chunks.back().feerate) {
                add |= m_chunks.back();
                m_chunks.pop_back();
            }
            // Remember new chunk.
            m_chunks.push_back(std::move(add));
        }
    }

public:
    /** Initialize a LinearizationSubset object for a given length of linearization. */
    explicit LinearizationChunking(const DepGraph<SetType>& depgraph LIFETIMEBOUND, std::span<const DepGraphIndex> lin LIFETIMEBOUND) noexcept :
        m_depgraph(depgraph), m_linearization(lin)
    {
        // Mark everything in lin as todo still.
        for (auto i : m_linearization) m_todo.Set(i);
        // Compute the initial chunking.
        m_chunks.reserve(depgraph.TxCount());
        BuildChunks();
    }

    /** Determine how many chunks remain in the linearization. */
    DepGraphIndex NumChunksLeft() const noexcept { return m_chunks.size() - m_chunks_skip; }

    /** Access a chunk. Chunk 0 is the highest-feerate prefix of what remains. */
    const SetInfo<SetType>& GetChunk(DepGraphIndex n) const noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        return m_chunks[n + m_chunks_skip];
    }

    /** Remove some subset of transactions from the linearization. */
    void MarkDone(SetType subset) noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        m_todo -= subset;
        if (GetChunk(0).transactions == subset) {
            // If the newly done transactions exactly match the first chunk of the remainder of
            // the linearization, we do not need to rechunk; just remember to skip one
            // additional chunk.
            ++m_chunks_skip;
            // With subset marked done, some prefix of m_linearization will be done now. How long
            // that prefix is depends on how many done elements were interspersed with subset,
            // but at least as many transactions as there are in subset.
            m_linearization = m_linearization.subspan(subset.Count());
        } else {
            // Otherwise rechunk what remains of m_linearization.
            m_chunks.clear();
            m_chunks_skip = 0;
            BuildChunks();
        }
    }

    /** Find the shortest intersection between subset and the prefixes of remaining chunks
     *  of the linearization that has a feerate not below subset's.
     *
     * This is a crucial operation in guaranteeing improvements to linearizations. If subset has
     * a feerate not below GetChunk(0)'s, then moving IntersectPrefixes(subset) to the front of
     * (what remains of) the linearization is guaranteed not to make it worse at any point.
     *
     * See https://delvingbitcoin.org/t/introduction-to-cluster-linearization/1032 for background.
     */
    SetInfo<SetType> IntersectPrefixes(const SetInfo<SetType>& subset) const noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        SetInfo<SetType> accumulator;
        // Iterate over all chunks of the remaining linearization.
        for (DepGraphIndex i = 0; i < NumChunksLeft(); ++i) {
            // Find what (if any) intersection the chunk has with subset.
            const SetType to_add = GetChunk(i).transactions & subset.transactions;
            if (to_add.Any()) {
                // If adding that to accumulator makes us hit all of subset, we are done as no
                // shorter intersection with higher/equal feerate exists.
                accumulator.transactions |= to_add;
                if (accumulator.transactions == subset.transactions) break;
                // Otherwise update the accumulator feerate.
                accumulator.feerate += m_depgraph.FeeRate(to_add);
                // If that does result in something better, or something with the same feerate but
                // smaller, return that. Even if a longer, higher-feerate intersection exists, it
                // does not hurt to return the shorter one (the remainder of the longer intersection
                // will generally be found in the next call to Intersect, but even if not, it is not
                // required for the improvement guarantee this function makes).
                if (!(accumulator.feerate << subset.feerate)) return accumulator;
            }
        }
        return subset;
    }
};

/** Class encapsulating the state needed to find the best remaining ancestor set.
 *
 * It is initialized for an entire DepGraph, and parts of the graph can be dropped by calling
 * MarkDone.
 *
 * As long as any part of the graph remains, FindCandidateSet() can be called which will return a
 * SetInfo with the highest-feerate ancestor set that remains (an ancestor set is a single
 * transaction together with all its remaining ancestors).
 */
template<typename SetType>
class AncestorCandidateFinder
{
    /** Internal dependency graph. */
    const DepGraph<SetType>& m_depgraph;
    /** Which transaction are left to include. */
    SetType m_todo;
    /** Precomputed ancestor-set feerates (only kept up-to-date for indices in m_todo). */
    std::vector<FeeFrac> m_ancestor_set_feerates;

public:
    /** Construct an AncestorCandidateFinder for a given cluster.
     *
     * Complexity: O(N^2) where N=depgraph.TxCount().
     */
    AncestorCandidateFinder(const DepGraph<SetType>& depgraph LIFETIMEBOUND) noexcept :
        m_depgraph(depgraph),
        m_todo{depgraph.Positions()},
        m_ancestor_set_feerates(depgraph.PositionRange())
    {
        // Precompute ancestor-set feerates.
        for (DepGraphIndex i : m_depgraph.Positions()) {
            /** The remaining ancestors for transaction i. */
            SetType anc_to_add = m_depgraph.Ancestors(i);
            FeeFrac anc_feerate;
            // Reuse accumulated feerate from first ancestor, if usable.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            DepGraphIndex first = anc_to_add.First();
            if (first < i) {
                anc_feerate = m_ancestor_set_feerates[first];
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
                anc_to_add -= m_depgraph.Ancestors(first);
            }
            // Add in other ancestors (which necessarily include i itself).
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            anc_feerate += m_depgraph.FeeRate(anc_to_add);
            // Store the result.
            m_ancestor_set_feerates[i] = anc_feerate;
        }
    }

    /** Remove a set of transactions from the set of to-be-linearized ones.
     *
     * The same transaction may not be MarkDone()'d twice.
     *
     * Complexity: O(N*M) where N=depgraph.TxCount(), M=select.Count().
     */
    void MarkDone(SetType select) noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        m_todo -= select;
        for (auto i : select) {
            auto feerate = m_depgraph.FeeRate(i);
            for (auto j : m_depgraph.Descendants(i) & m_todo) {
                m_ancestor_set_feerates[j] -= feerate;
            }
        }
    }

    /** Check whether any unlinearized transactions remain. */
    bool AllDone() const noexcept
    {
        return m_todo.None();
    }

    /** Count the number of remaining unlinearized transactions. */
    DepGraphIndex NumRemaining() const noexcept
    {
        return m_todo.Count();
    }

    /** Find the best (highest-feerate, smallest among those in case of a tie) ancestor set
     *  among the remaining transactions. Requires !AllDone().
     *
     * Complexity: O(N) where N=depgraph.TxCount();
     */
    SetInfo<SetType> FindCandidateSet() const noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        std::optional<DepGraphIndex> best;
        for (auto i : m_todo) {
            if (best.has_value()) {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
                if (!(m_ancestor_set_feerates[i] > m_ancestor_set_feerates[*best])) continue;
            }
            best = i;
        }
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        return {m_depgraph.Ancestors(*best) & m_todo, m_ancestor_set_feerates[*best]};
    }
};

/** Class encapsulating the state needed to perform search for good candidate sets.
 *
 * It is initialized for an entire DepGraph, and parts of the graph can be dropped by calling
 * MarkDone().
 *
 * As long as any part of the graph remains, FindCandidateSet() can be called to perform a search
 * over the set of topologically-valid subsets of that remainder, with a limit on how many
 * combinations are tried.
 */
template<typename SetType>
class SearchCandidateFinder
{
    /** Internal RNG. */
    InsecureRandomContext m_rng;
    /** m_sorted_to_original[i] is the original position that sorted transaction position i had. */
    std::vector<DepGraphIndex> m_sorted_to_original;
    /** m_original_to_sorted[i] is the sorted position original transaction position i has. */
    std::vector<DepGraphIndex> m_original_to_sorted;
    /** Internal dependency graph for the cluster (with transactions in decreasing individual
     *  feerate order). */
    DepGraph<SetType> m_sorted_depgraph;
    /** Which transactions are left to do (indices in m_sorted_depgraph's order). */
    SetType m_todo;

    /** Given a set of transactions with sorted indices, get their original indices. */
    SetType SortedToOriginal(const SetType& arg) const noexcept
    {
        SetType ret;
        for (auto pos : arg) ret.Set(m_sorted_to_original[pos]);
        return ret;
    }

    /** Given a set of transactions with original indices, get their sorted indices. */
    SetType OriginalToSorted(const SetType& arg) const noexcept
    {
        SetType ret;
        for (auto pos : arg) ret.Set(m_original_to_sorted[pos]);
        return ret;
    }

public:
    /** Construct a candidate finder for a graph.
     *
     * @param[in] depgraph   Dependency graph for the to-be-linearized cluster.
     * @param[in] rng_seed   A random seed to control the search order.
     *
     * Complexity: O(N^2) where N=depgraph.Count().
     */
    SearchCandidateFinder(const DepGraph<SetType>& depgraph, uint64_t rng_seed) noexcept :
        m_rng(rng_seed),
        m_sorted_to_original(depgraph.TxCount()),
        m_original_to_sorted(depgraph.PositionRange())
    {
        // Determine reordering mapping, by sorting by decreasing feerate. Unused positions are
        // not included, as they will never be looked up anyway.
        DepGraphIndex sorted_pos{0};
        for (auto i : depgraph.Positions()) {
            m_sorted_to_original[sorted_pos++] = i;
        }
        std::sort(m_sorted_to_original.begin(), m_sorted_to_original.end(), [&](auto a, auto b) {
            auto feerate_cmp = depgraph.FeeRate(a) <=> depgraph.FeeRate(b);
            if (feerate_cmp == 0) return a < b;
            return feerate_cmp > 0;
        });
        // Compute reverse mapping.
        for (DepGraphIndex i = 0; i < m_sorted_to_original.size(); ++i) {
            m_original_to_sorted[m_sorted_to_original[i]] = i;
        }
        // Compute reordered dependency graph.
        m_sorted_depgraph = DepGraph(depgraph, m_original_to_sorted, m_sorted_to_original.size());
        m_todo = m_sorted_depgraph.Positions();
    }

    /** Check whether any unlinearized transactions remain. */
    bool AllDone() const noexcept
    {
        return m_todo.None();
    }

    /** Find a high-feerate topologically-valid subset of what remains of the cluster.
     *  Requires !AllDone().
     *
     * @param[in] max_iterations  The maximum number of optimization steps that will be performed.
     * @param[in] best            A set/feerate pair with an already-known good candidate. This may
     *                            be empty.
     * @return                    A pair of:
     *                            - The best (highest feerate, smallest size as tiebreaker)
     *                              topologically valid subset (and its feerate) that was
     *                              encountered during search. It will be at least as good as the
     *                              best passed in (if not empty).
     *                            - The number of optimization steps that were performed. This will
     *                              be <= max_iterations. If strictly < max_iterations, the
     *                              returned subset is optimal.
     *
     * Complexity: possibly O(N * min(max_iterations, sqrt(2^N))) where N=depgraph.TxCount().
     */
    std::pair<SetInfo<SetType>, uint64_t> FindCandidateSet(uint64_t max_iterations, SetInfo<SetType> best) noexcept
    {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)

        // Convert the provided best to internal sorted indices.
        best.transactions = OriginalToSorted(best.transactions);

        /** Type for work queue items. */
        struct WorkItem
        {
            /** Set of transactions definitely included (and its feerate). This must be a subset
             *  of m_todo, and be topologically valid (includes all in-m_todo ancestors of
             *  itself). */
            SetInfo<SetType> inc;
            /** Set of undecided transactions. This must be a subset of m_todo, and have no overlap
             *  with inc. The set (inc | und) must be topologically valid. */
            SetType und;
            /** (Only when inc is not empty) The best feerate of any superset of inc that is also a
             *  subset of (inc | und), without requiring it to be topologically valid. It forms a
             *  conservative upper bound on how good a set this work item can give rise to.
             *  Transactions whose feerate is below best's are ignored when determining this value,
             *  which means it may technically be an underestimate, but if so, this work item
             *  cannot result in something that beats best anyway. */
            FeeFrac pot_feerate;

            /** Construct a new work item. */
            WorkItem(SetInfo<SetType>&& i, SetType&& u, FeeFrac&& p_f) noexcept :
                inc(std::move(i)), und(std::move(u)), pot_feerate(std::move(p_f))
            {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            }

            /** Swap two WorkItems. */
            void Swap(WorkItem& other) noexcept
            {
                swap(inc, other.inc);
                swap(und, other.und);
                swap(pot_feerate, other.pot_feerate);
            }
        };

        /** The queue of work items. */
        VecDeque<WorkItem> queue;
        queue.reserve(std::max<size_t>(256, 2 * m_todo.Count()));

        // Create initial entries per connected component of m_todo. While clusters themselves are
        // generally connected, this is not necessarily true after some parts have already been
        // removed from m_todo. Without this, effort can be wasted on searching "inc" sets that
        // span multiple components.
        auto to_cover = m_todo;
        do {
            auto component = m_sorted_depgraph.FindConnectedComponent(to_cover);
            to_cover -= component;
            // If best is not provided, set it to the first component, so that during the work
            // processing loop below, and during the add_fn/split_fn calls, we do not need to deal
            // with the best=empty case.
            if (best.feerate.IsEmpty()) best = SetInfo(m_sorted_depgraph, component);
            queue.emplace_back(/*inc=*/SetInfo<SetType>{},
                               /*und=*/std::move(component),
                               /*pot_feerate=*/FeeFrac{});
        } while (to_cover.Any());

        /** Local copy of the iteration limit. */
        uint64_t iterations_left = max_iterations;

        /** The set of transactions in m_todo which have feerate > best's. */
        SetType imp = m_todo;
        while (imp.Any()) {
            DepGraphIndex check = imp.Last();
            if (m_sorted_depgraph.FeeRate(check) >> best.feerate) break;
            imp.Reset(check);
        }

        /** Internal function to add an item to the queue of elements to explore if there are any
         *  transactions left to split on, possibly improving it before doing so, and to update
         *  best/imp.
         *
         * - inc: the "inc" value for the new work item (must be topological).
         * - und: the "und" value for the new work item ((inc | und) must be topological).
         */
        auto add_fn = [&](SetInfo<SetType> inc, SetType und) noexcept {
            /** SetInfo object with the set whose feerate will become the new work item's
             *  pot_feerate. It starts off equal to inc. */
            auto pot = inc;
            if (!inc.feerate.IsEmpty()) {
                // Add entries to pot. We iterate over all undecided transactions whose feerate is
                // higher than best. While undecided transactions of lower feerate may improve pot,
                // the resulting pot feerate cannot possibly exceed best's (and this item will be
                // skipped in split_fn anyway).
                for (auto pos : imp & und) {
                    // Determine if adding transaction pos to pot (ignoring topology) would improve
                    // it. If not, we're done updating pot. This relies on the fact that
                    // m_sorted_depgraph, and thus the transactions iterated over, are in decreasing
                    // individual feerate order.
                    if (!(m_sorted_depgraph.FeeRate(pos) >> pot.feerate)) break;
                    pot.Set(m_sorted_depgraph, pos);
                }

                // The "jump ahead" optimization: whenever pot has a topologically-valid subset,
                // that subset can be added to inc. Any subset of (pot - inc) has the property that
                // its feerate exceeds that of any set compatible with this work item (superset of
                // inc, subset of (inc | und)). Thus, if T is a topological subset of pot, and B is
                // the best topologically-valid set compatible with this work item, and (T - B) is
                // non-empty, then (T | B) is better than B and also topological. This is in
                // contradiction with the assumption that B is best. Thus, (T - B) must be empty,
                // or T must be a subset of B.
                //
                // See https://delvingbitcoin.org/t/how-to-linearize-your-cluster/303 section 2.4.
                const auto init_inc = inc.transactions;
                for (auto pos : pot.transactions - inc.transactions) {
                    // If the transaction's ancestors are a subset of pot, we can add it together
                    // with its ancestors to inc. Just update the transactions here; the feerate
                    // update happens below.
                    auto anc_todo = m_sorted_depgraph.Ancestors(pos) & m_todo;
                    if (anc_todo.IsSubsetOf(pot.transactions)) inc.transactions |= anc_todo;
                }
                // Finally update und and inc's feerate to account for the added transactions.
                und -= inc.transactions;
                inc.feerate += m_sorted_depgraph.FeeRate(inc.transactions - init_inc);

                // If inc's feerate is better than best's, remember it as our new best.
                if (inc.feerate > best.feerate) {
                    best = inc;
                    // See if we can remove any entries from imp now.
                    while (imp.Any()) {
                        DepGraphIndex check = imp.Last();
                        if (m_sorted_depgraph.FeeRate(check) >> best.feerate) break;
                        imp.Reset(check);
                    }
                }

                // If no potential transactions exist beyond the already included ones, no
                // improvement is possible anymore.
                if (pot.feerate.size == inc.feerate.size) return;
                // At this point und must be non-empty. If it were empty then pot would equal inc.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            } else {
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
                // If inc is empty, we just make sure there are undecided transactions left to
                // split on.
                if (und.None()) return;
            }

            // Actually construct a new work item on the queue. Due to the switch to DFS when queue
            // space runs out (see below), we know that no reallocation of the queue should ever
            // occur.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            queue.emplace_back(/*inc=*/std::move(inc),
                               /*und=*/std::move(und),
                               /*pot_feerate=*/std::move(pot.feerate));
        };

        /** Internal process function. It takes an existing work item, and splits it in two: one
         *  with a particular transaction (and its ancestors) included, and one with that
         *  transaction (and its descendants) excluded. */
        auto split_fn = [&](WorkItem&& elem) noexcept {
            // Any queue element must have undecided transactions left, otherwise there is nothing
            // to explore anymore.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            // The included and undecided set are all subsets of m_todo.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            // Included transactions cannot be undecided.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            // If pot is empty, then so is inc.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)

            const DepGraphIndex first = elem.und.First();
            if (!elem.inc.feerate.IsEmpty()) {
                // If no undecided transactions remain with feerate higher than best, this entry
                // cannot be improved beyond best.
                if (!elem.und.Overlaps(imp)) return;
                // We can ignore any queue item whose potential feerate isn't better than the best
                // seen so far.
                if (elem.pot_feerate <= best.feerate) return;
            } else {
                // In case inc is empty use a simpler alternative check.
                if (m_sorted_depgraph.FeeRate(first) <= best.feerate) return;
            }

            // Decide which transaction to split on. Splitting is how new work items are added, and
            // how progress is made. One split transaction is chosen among the queue item's
            // undecided ones, and:
            // - A work item is (potentially) added with that transaction plus its remaining
            //   descendants excluded (removed from the und set).
            // - A work item is (potentially) added with that transaction plus its remaining
            //   ancestors included (added to the inc set).
            //
            // To decide what to split on, consider the undecided ancestors of the highest
            // individual feerate undecided transaction. Pick the one which reduces the search space
            // most. Let I(t) be the size of the undecided set after including t, and E(t) the size
            // of the undecided set after excluding t. Then choose the split transaction t such
            // that 2^I(t) + 2^E(t) is minimal, tie-breaking by highest individual feerate for t.
            DepGraphIndex split = 0;
            const auto select = elem.und & m_sorted_depgraph.Ancestors(first);
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            std::optional<std::pair<DepGraphIndex, DepGraphIndex>> split_counts;
            for (auto t : select) {
                // Call max = max(I(t), E(t)) and min = min(I(t), E(t)). Let counts = {max,min}.
                // Sorting by the tuple counts is equivalent to sorting by 2^I(t) + 2^E(t). This
                // expression is equal to 2^max + 2^min = 2^max * (1 + 1/2^(max - min)). The second
                // factor (1 + 1/2^(max - min)) there is in (1,2]. Thus increasing max will always
                // increase it, even when min decreases. Because of this, we can first sort by max.
                std::pair<DepGraphIndex, DepGraphIndex> counts{
                    (elem.und - m_sorted_depgraph.Ancestors(t)).Count(),
                    (elem.und - m_sorted_depgraph.Descendants(t)).Count()};
                if (counts.first < counts.second) std::swap(counts.first, counts.second);
                // Remember the t with the lowest counts.
                if (!split_counts.has_value() || counts < *split_counts) {
                    split = t;
                    split_counts = counts;
                }
            }
            // Since there was at least one transaction in select, we must always find one.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)

            // Add a work item corresponding to exclusion of the split transaction.
            const auto& desc = m_sorted_depgraph.Descendants(split);
            add_fn(/*inc=*/elem.inc,
                   /*und=*/elem.und - desc);

            // Add a work item corresponding to inclusion of the split transaction.
            const auto anc = m_sorted_depgraph.Ancestors(split) & m_todo;
            add_fn(/*inc=*/elem.inc.Add(m_sorted_depgraph, anc),
                   /*und=*/elem.und - anc);

            // Account for the performed split.
            --iterations_left;
        };

        // Work processing loop.
        //
        // New work items are always added at the back of the queue, but items to process use a
        // hybrid approach where they can be taken from the front or the back.
        //
        // Depth-first search (DFS) corresponds to always taking from the back of the queue. This
        // is very memory-efficient (linear in the number of transactions). Breadth-first search
        // (BFS) corresponds to always taking from the front, which potentially uses more memory
        // (up to exponential in the transaction count), but seems to work better in practice.
        //
        // The approach here combines the two: use BFS (plus random swapping) until the queue grows
        // too large, at which point we temporarily switch to DFS until the size shrinks again.
        while (!queue.empty()) {
            // Randomly swap the first two items to randomize the search order.
            if (queue.size() > 1 && m_rng.randbool()) {
                queue[0].Swap(queue[1]);
            }

            // Processing the first queue item, and then using DFS for everything it gives rise to,
            // may increase the queue size by the number of undecided elements in there, minus 1
            // for the first queue item being removed. Thus, only when that pushes the queue over
            // its capacity can we not process from the front (BFS), and should we use DFS.
            while (queue.size() - 1 + queue.front().und.Count() > queue.capacity()) {
                if (!iterations_left) break;
                auto elem = queue.back();
                queue.pop_back();
                split_fn(std::move(elem));
            }

            // Process one entry from the front of the queue (BFS exploration)
            if (!iterations_left) break;
            auto elem = queue.front();
            queue.pop_front();
            split_fn(std::move(elem));
        }

        // Return the found best set (converted to the original transaction indices), and the
        // number of iterations performed.
        best.transactions = SortedToOriginal(best.transactions);
        return {std::move(best), max_iterations - iterations_left};
    }

    /** Remove a subset of transactions from the cluster being linearized.
     *
     * Complexity: O(N) where N=done.Count().
     */
    void MarkDone(const SetType& done) noexcept
    {
        const auto done_sorted = OriginalToSorted(done);
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        m_todo -= done_sorted;
    }
};

/** Find or improve a linearization for a cluster.
 *
 * @param[in] depgraph            Dependency graph of the cluster to be linearized.
 * @param[in] max_iterations      Upper bound on the number of optimization steps that will be done.
 * @param[in] rng_seed            A random number seed to control search order. This prevents peers
 *                                from predicting exactly which clusters would be hard for us to
 *                                linearize.
 * @param[in] old_linearization   An existing linearization for the cluster (which must be
 *                                topologically valid), or empty.
 * @return                        A tuple of:
 *                                - The resulting linearization. It is guaranteed to be at least as
 *                                  good (in the feerate diagram sense) as old_linearization.
 *                                - A boolean indicating whether the result is guaranteed to be
 *                                  optimal.
 *                                - How many optimization steps were actually performed.
 *
 * Complexity: possibly O(N * min(max_iterations + N, sqrt(2^N))) where N=depgraph.TxCount().
 */
template<typename SetType>
std::tuple<std::vector<DepGraphIndex>, bool, uint64_t> Linearize(const DepGraph<SetType>& depgraph, uint64_t max_iterations, uint64_t rng_seed, std::span<const DepGraphIndex> old_linearization = {}) noexcept
{
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
    if (depgraph.TxCount() == 0) return {{}, true, 0};

    uint64_t iterations_left = max_iterations;
    std::vector<DepGraphIndex> linearization;

    AncestorCandidateFinder anc_finder(depgraph);
    std::optional<SearchCandidateFinder<SetType>> src_finder;
    linearization.reserve(depgraph.TxCount());
    bool optimal = true;

    // Treat the initialization of SearchCandidateFinder as taking N^2/64 (rounded up) iterations
    // (largely due to the cost of constructing the internal sorted-by-feerate DepGraph inside
    // SearchCandidateFinder), a rough approximation based on benchmark. If we don't have that
    // many, don't start it.
    uint64_t start_iterations = (uint64_t{depgraph.TxCount()} * depgraph.TxCount() + 63) / 64;
    if (iterations_left > start_iterations) {
        iterations_left -= start_iterations;
        src_finder.emplace(depgraph, rng_seed);
    }

    /** Chunking of what remains of the old linearization. */
    LinearizationChunking old_chunking(depgraph, old_linearization);

    while (true) {
        // Find the highest-feerate prefix of the remainder of old_linearization.
        SetInfo<SetType> best_prefix;
        if (old_chunking.NumChunksLeft()) best_prefix = old_chunking.GetChunk(0);

        // Then initialize best to be either the best remaining ancestor set, or the first chunk.
        auto best = anc_finder.FindCandidateSet();
        if (!best_prefix.feerate.IsEmpty() && best_prefix.feerate >= best.feerate) best = best_prefix;

        uint64_t iterations_done_now = 0;
        uint64_t max_iterations_now = 0;
        if (src_finder) {
            // Treat the invocation of SearchCandidateFinder::FindCandidateSet() as costing N/4
            // up-front (rounded up) iterations (largely due to the cost of connected-component
            // splitting), a rough approximation based on benchmarks.
            uint64_t base_iterations = (anc_finder.NumRemaining() + 3) / 4;
            if (iterations_left > base_iterations) {
                // Invoke bounded search to update best, with up to half of our remaining
                // iterations as limit.
                iterations_left -= base_iterations;
                max_iterations_now = (iterations_left + 1) / 2;
                std::tie(best, iterations_done_now) = src_finder->FindCandidateSet(max_iterations_now, best);
                iterations_left -= iterations_done_now;
            }
        }

        if (iterations_done_now == max_iterations_now) {
            optimal = false;
            // If the search result is not (guaranteed to be) optimal, run intersections to make
            // sure we don't pick something that makes us unable to reach further diagram points
            // of the old linearization.
            if (old_chunking.NumChunksLeft() > 0) {
                best = old_chunking.IntersectPrefixes(best);
            }
        }

        // Add to output in topological order.
        depgraph.AppendTopo(linearization, best.transactions);

        // Update state to reflect best is no longer to be linearized.
        anc_finder.MarkDone(best.transactions);
        if (anc_finder.AllDone()) break;
        if (src_finder) src_finder->MarkDone(best.transactions);
        if (old_chunking.NumChunksLeft() > 0) {
            old_chunking.MarkDone(best.transactions);
        }
    }

    return {std::move(linearization), optimal, max_iterations - iterations_left};
}

/** Improve a given linearization.
 *
 * @param[in]     depgraph       Dependency graph of the cluster being linearized.
 * @param[in,out] linearization  On input, an existing linearization for depgraph. On output, a
 *                               potentially better linearization for the same graph.
 *
 * Postlinearization guarantees:
 * - The resulting chunks are connected.
 * - If the input has a tree shape (either all transactions have at most one child, or all
 *   transactions have at most one parent), the result is optimal.
 * - Given a linearization L1 and a leaf transaction T in it. Let L2 be L1 with T moved to the end,
 *   optionally with its fee increased. Let L3 be the postlinearization of L2. L3 will be at least
 *   as good as L1. This means that replacing transactions with same-size higher-fee transactions
 *   will not worsen linearizations through a "drop conflicts, append new transactions,
 *   postlinearize" process.
 */
template<typename SetType>
void PostLinearize(const DepGraph<SetType>& depgraph, std::span<DepGraphIndex> linearization)
{
    // This algorithm performs a number of passes (currently 2); the even ones operate from back to
    // front, the odd ones from front to back. Each results in an equal-or-better linearization
    // than the one started from.
    // - One pass in either direction guarantees that the resulting chunks are connected.
    // - Each direction corresponds to one shape of tree being linearized optimally (forward passes
    //   guarantee this for graphs where each transaction has at most one child; backward passes
    //   guarantee this for graphs where each transaction has at most one parent).
    // - Starting with a backward pass guarantees the moved-tree property.
    //
    // During an odd (forward) pass, the high-level operation is:
    // - Start with an empty list of groups L=[].
    // - For every transaction i in the old linearization, from front to back:
    //   - Append a new group C=[i], containing just i, to the back of L.
    //   - While L has at least one group before C, and the group immediately before C has feerate
    //     lower than C:
    //     - If C depends on P:
    //       - Merge P into C, making C the concatenation of P+C, continuing with the combined C.
    //     - Otherwise:
    //       - Swap P with C, continuing with the now-moved C.
    // - The output linearization is the concatenation of the groups in L.
    //
    // During even (backward) passes, i iterates from the back to the front of the existing
    // linearization, and new groups are prepended instead of appended to the list L. To enable
    // more code reuse, both passes append groups, but during even passes the meanings of
    // parent/child, and of high/low feerate are reversed, and the final concatenation is reversed
    // on output.
    //
    // In the implementation below, the groups are represented by singly-linked lists (pointing
    // from the back to the front), which are themselves organized in a singly-linked circular
    // list (each group pointing to its predecessor, with a special sentinel group at the front
    // that points back to the last group).
    //
    // Information about transaction t is stored in entries[t + 1], while the sentinel is in
    // entries[0].

    /** Index of the sentinel in the entries array below. */
    static constexpr DepGraphIndex SENTINEL{0};
    /** Indicator that a group has no previous transaction. */
    static constexpr DepGraphIndex NO_PREV_TX{0};


    /** Data structure per transaction entry. */
    struct TxEntry
    {
        /** The index of the previous transaction in this group; NO_PREV_TX if this is the first
         *  entry of a group. */
        DepGraphIndex prev_tx;

        // The fields below are only used for transactions that are the last one in a group
        // (referred to as tail transactions below).

        /** Index of the first transaction in this group, possibly itself. */
        DepGraphIndex first_tx;
        /** Index of the last transaction in the previous group. The first group (the sentinel)
         *  points back to the last group here, making it a singly-linked circular list. */
        DepGraphIndex prev_group;
        /** All transactions in the group. Empty for the sentinel. */
        SetType group;
        /** All dependencies of the group (descendants in even passes; ancestors in odd ones). */
        SetType deps;
        /** The combined fee/size of transactions in the group. Fee is negated in even passes. */
        FeeFrac feerate;
    };

    // As an example, consider the state corresponding to the linearization [1,0,3,2], with
    // groups [1,0,3] and [2], in an odd pass. The linked lists would be:
    //
    //                                        +-----+
    //                                 0<-P-- | 0 S | ---\     Legend:
    //                                        +-----+    |
    //                                           ^       |     - digit in box: entries index
    //             /--------------F---------+    G       |       (note: one more than tx value)
    //             v                         \   |       |     - S: sentinel group
    //          +-----+        +-----+        +-----+    |          (empty feerate)
    //   0<-P-- | 2   | <--P-- | 1   | <--P-- | 4 T |    |     - T: tail transaction, contains
    //          +-----+        +-----+        +-----+    |          fields beyond prev_tv.
    //                                           ^       |     - P: prev_tx reference
    //                                           G       G     - F: first_tx reference
    //                                           |       |     - G: prev_group reference
    //                                        +-----+    |
    //                                 0<-P-- | 3 T | <--/
    //                                        +-----+
    //                                         ^   |
    //                                         \-F-/
    //
    // During an even pass, the diagram above would correspond to linearization [2,3,0,1], with
    // groups [2] and [3,0,1].

    std::vector<TxEntry> entries(depgraph.PositionRange() + 1);

    // Perform two passes over the linearization.
    for (int pass = 0; pass < 2; ++pass) {
        int rev = !(pass & 1);
        // Construct a sentinel group, identifying the start of the list.
        entries[SENTINEL].prev_group = SENTINEL;
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)

        // Iterate over all elements in the existing linearization.
        for (DepGraphIndex i = 0; i < linearization.size(); ++i) {
            // Even passes are from back to front; odd passes from front to back.
            DepGraphIndex idx = linearization[rev ? linearization.size() - 1 - i : i];
            // Construct a new group containing just idx. In even passes, the meaning of
            // parent/child and high/low feerate are swapped.
            DepGraphIndex cur_group = idx + 1;
            entries[cur_group].group = SetType::Singleton(idx);
            entries[cur_group].deps = rev ? depgraph.Descendants(idx): depgraph.Ancestors(idx);
            entries[cur_group].feerate = depgraph.FeeRate(idx);
            if (rev) entries[cur_group].feerate.fee = -entries[cur_group].feerate.fee;
            entries[cur_group].prev_tx = NO_PREV_TX; // No previous transaction in group.
            entries[cur_group].first_tx = cur_group; // Transaction itself is first of group.
            // Insert the new group at the back of the groups linked list.
            entries[cur_group].prev_group = entries[SENTINEL].prev_group;
            entries[SENTINEL].prev_group = cur_group;

            // Start merge/swap cycle.
            DepGraphIndex next_group = SENTINEL; // We inserted at the end, so next group is sentinel.
            DepGraphIndex prev_group = entries[cur_group].prev_group;
            // Continue as long as the current group has higher feerate than the previous one.
            while (entries[cur_group].feerate >> entries[prev_group].feerate) {
                // prev_group/cur_group/next_group refer to (the last transactions of) 3
                // consecutive entries in groups list.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
                // The sentinel has empty feerate, which is neither higher or lower than other
                // feerates. Thus, the while loop we are in here guarantees that cur_group and
                // prev_group are not the sentinel.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
                if (entries[cur_group].deps.Overlaps(entries[prev_group].group)) {
                    // There is a dependency between cur_group and prev_group; merge prev_group
                    // into cur_group. The group/deps/feerate fields of prev_group remain unchanged
                    // but become unused.
                    entries[cur_group].group |= entries[prev_group].group;
                    entries[cur_group].deps |= entries[prev_group].deps;
                    entries[cur_group].feerate += entries[prev_group].feerate;
                    // Make the first of the current group point to the tail of the previous group.
                    entries[entries[cur_group].first_tx].prev_tx = prev_group;
                    // The first of the previous group becomes the first of the newly-merged group.
                    entries[cur_group].first_tx = entries[prev_group].first_tx;
                    // The previous group becomes whatever group was before the former one.
                    prev_group = entries[prev_group].prev_group;
                    entries[cur_group].prev_group = prev_group;
                } else {
                    // There is no dependency between cur_group and prev_group; swap them.
                    DepGraphIndex preprev_group = entries[prev_group].prev_group;
                    // If PP, P, C, N were the old preprev, prev, cur, next groups, then the new
                    // layout becomes [PP, C, P, N]. Update prev_groups to reflect that order.
                    entries[next_group].prev_group = prev_group;
                    entries[prev_group].prev_group = cur_group;
                    entries[cur_group].prev_group = preprev_group;
                    // The current group remains the same, but the groups before/after it have
                    // changed.
                    next_group = prev_group;
                    prev_group = preprev_group;
                }
            }
        }

        // Convert the entries back to linearization (overwriting the existing one).
        DepGraphIndex cur_group = entries[0].prev_group;
        DepGraphIndex done = 0;
        while (cur_group != SENTINEL) {
            DepGraphIndex cur_tx = cur_group;
            // Traverse the transactions of cur_group (from back to front), and write them in the
            // same order during odd passes, and reversed (front to back) in even passes.
            if (rev) {
                do {
                    *(linearization.begin() + (done++)) = cur_tx - 1;
                    cur_tx = entries[cur_tx].prev_tx;
                } while (cur_tx != NO_PREV_TX);
            } else {
                do {
                    *(linearization.end() - (++done)) = cur_tx - 1;
                    cur_tx = entries[cur_tx].prev_tx;
                } while (cur_tx != NO_PREV_TX);
            }
            cur_group = entries[cur_group].prev_group;
        }
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
    }
}

/** Merge two linearizations for the same cluster into one that is as good as both.
 *
 * Complexity: O(N^2) where N=depgraph.TxCount(); O(N) if both inputs are identical.
 */
template<typename SetType>
std::vector<DepGraphIndex> MergeLinearizations(const DepGraph<SetType>& depgraph, std::span<const DepGraphIndex> lin1, std::span<const DepGraphIndex> lin2)
{
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)

    /** Chunkings of what remains of both input linearizations. */
    LinearizationChunking chunking1(depgraph, lin1), chunking2(depgraph, lin2);
    /** Output linearization. */
    std::vector<DepGraphIndex> ret;
    if (depgraph.TxCount() == 0) return ret;
    ret.reserve(depgraph.TxCount());

    while (true) {
        // As long as we are not done, both linearizations must have chunks left.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
        // Find the set to output by taking the best remaining chunk, and then intersecting it with
        // prefixes of remaining chunks of the other linearization.
        SetInfo<SetType> best;
        const auto& lin1_firstchunk = chunking1.GetChunk(0);
        const auto& lin2_firstchunk = chunking2.GetChunk(0);
        if (lin2_firstchunk.feerate >> lin1_firstchunk.feerate) {
            best = chunking1.IntersectPrefixes(lin2_firstchunk);
        } else {
            best = chunking2.IntersectPrefixes(lin1_firstchunk);
        }
        // Append the result to the output and mark it as done.
        depgraph.AppendTopo(ret, best.transactions);
        chunking1.MarkDone(best.transactions);
        if (chunking1.NumChunksLeft() == 0) break;
        chunking2.MarkDone(best.transactions);
    }

#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
    return ret;
}

/** Make linearization topological, retaining its ordering where possible. */
template<typename SetType>
void FixLinearization(const DepGraph<SetType>& depgraph, std::span<DepGraphIndex> linearization) noexcept
{
    // This algorithm can be summarized as moving every element in the linearization backwards
    // until it is placed after all its ancestors.
    SetType done;
    const auto len = linearization.size();
    // Iterate over the elements of linearization from back to front (i is distance from back).
    for (DepGraphIndex i = 0; i < len; ++i) {
        /** The element at that position. */
        DepGraphIndex elem = linearization[len - 1 - i];
        /** j represents how far from the back of the linearization elem should be placed. */
        DepGraphIndex j = i;
        // Figure out which elements need to be moved before elem.
        SetType place_before = done & depgraph.Ancestors(elem);
        // Find which position to place elem in (updating j), continuously moving the elements
        // in between forward.
        while (place_before.Any()) {
            // j cannot be 0 here; if it was, then there was necessarily nothing earlier which
            // elem needs to be placed before anymore, and place_before would be empty.
#define Assume(val) inline_assertion_check<false>(val, std::source_location::current(), #val)
            auto to_swap = linearization[len - 1 - (j - 1)];
            place_before.Reset(to_swap);
            linearization[len - 1 - (j--)] = to_swap;
        }
        // Put elem in its final position and mark it as done.
        linearization[len - 1 - j] = elem;
        done.Set(elem);
    }
}

} // namespace cluster_linearize

#endif // BITCOIN_CLUSTER_LINEARIZE_H

Bitcoin Core Fuzz Coverage Report for wallet_tx_can_be_bumped

Coverage Report

Created: 2025-11-19 11:20