feat(algorithms): add Breaking of the Hash Table

Signed-off-by: Matej Focko <mfocko@redhat.com>

static/files/algorithms/hash-tables/breaking/benchmark.cpp

@@ -0,0 +1,133 @@
+#include <bit>
+#include <cassert>
+#include <chrono>
+#include <cstdint>
+#include <functional>
+#include <iostream>
+#include <ranges>
+#include <set>
+#include <string>
+#include <unordered_set>
+
+using elem_t = std::uint64_t;
+
+const elem_t N_ELEMENTS = 10000000;
+#define LOOPS 10
+
+template <typename T> struct strategy {
+  virtual std::string name() const = 0;
+  virtual T elements() = 0;
+
+  template <typename C> void run(C &&s) {
+    using namespace std;
+
+    cout << "\nBenchmarking:\t\t" << name() << '\n';
+
+    auto start = chrono::steady_clock::now();
+    for (auto x : elements()) {
+      s.insert(x);
+    }
+    auto after_insertion = chrono::steady_clock::now();
+
+    auto insertion_time =
+        chrono::duration_cast<chrono::milliseconds>(after_insertion - start);
+    cout << "Insertion phase:\t" << insertion_time << "\n";
+
+    start = chrono::steady_clock::now();
+    for (int i = 0; i < LOOPS; ++i) {
+      for (auto x : elements()) {
+        assert(s.contains(x));
+      }
+    }
+    auto after_lookups = chrono::steady_clock::now();
+
+    auto lookup_time =
+        chrono::duration_cast<chrono::milliseconds>(after_lookups - start);
+    cout << "Lookup phase:\t\t" << lookup_time << "\n";
+  }
+
+  virtual ~strategy() = default;
+};
+
+using iota_t =
+    decltype(std::views::iota(static_cast<elem_t>(0), static_cast<elem_t>(0)));
+
+struct ascending_ordered_sequence : public strategy<iota_t> {
+  std::string name() const override { return "ordered sequence (ascending)"; }
+  iota_t elements() override {
+    return std::views::iota(static_cast<elem_t>(0), N_ELEMENTS);
+  }
+};
+
+static elem_t reverse(elem_t x) { return static_cast<elem_t>(N_ELEMENTS) - x; }
+using reversed_iota_t =
+    decltype(std::views::iota(static_cast<elem_t>(0), static_cast<elem_t>(0)) |
+             std::views::transform(reverse));
+
+struct descending_ordered_sequence : public strategy<reversed_iota_t> {
+  std::string name() const override { return "ordered sequence (descending)"; }
+  reversed_iota_t elements() override {
+    return std::views::iota(static_cast<elem_t>(1), N_ELEMENTS + 1) |
+           std::views::transform(reverse);
+  }
+};
+
+static elem_t attack(elem_t x) { return x << (5 + std::bit_width(x)); }
+using attacked_iota_t =
+    decltype(std::views::iota(static_cast<elem_t>(0), static_cast<elem_t>(0)) |
+             std::views::transform(attack));
+
+struct progressive_ascending_attack : public strategy<attacked_iota_t> {
+  std::string name() const override {
+    return "progressive sequence that self-heals on resize";
+  }
+  attacked_iota_t elements() override {
+    return std::views::iota(static_cast<elem_t>(0), N_ELEMENTS) |
+           std::views::transform(attack);
+  }
+};
+
+using reversed_attacked_iota_t =
+    decltype(std::views::iota(static_cast<elem_t>(0), static_cast<elem_t>(0)) |
+             std::views::transform(reverse) | std::views::transform(attack));
+
+struct progressive_descending_attack
+    : public strategy<reversed_attacked_iota_t> {
+  std::string name() const override {
+    return "progressive sequence that self-heals in the end";
+  }
+  reversed_attacked_iota_t elements() override {
+    return std::views::iota(static_cast<elem_t>(1), N_ELEMENTS + 1) |
+           std::views::transform(reverse) | std::views::transform(attack);
+  }
+};
+
+static elem_t shift(elem_t x) { return x << 32; }
+using shifted_iota_t =
+    decltype(std::views::iota(static_cast<elem_t>(0), static_cast<elem_t>(0)) |
+             std::views::transform(shift));
+
+struct hard_attack : public strategy<shifted_iota_t> {
+  std::string name() const override { return "carefully chosen numbers"; }
+  shifted_iota_t elements() override {
+    return std::views::iota(static_cast<elem_t>(0), N_ELEMENTS) |
+           std::views::transform(shift);
+  }
+};
+
+template <typename C> void run_all(const std::string &note) {
+  std::cout << "\n«" << note << "»\n";
+
+  ascending_ordered_sequence{}.run(C{});
+  descending_ordered_sequence{}.run(C{});
+  progressive_ascending_attack{}.run(C{});
+  progressive_descending_attack{}.run(C{});
+  hard_attack{}.run(C{});
+}
+
+int main() {
+  run_all<std::unordered_set<elem_t>>("hash table");
+  run_all<std::set<elem_t>>("red-black tree");
+
+  return 0;
+}

static/files/algorithms/hash-tables/breaking/benchmark.py

@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+
+from functools import cached_property
+from time import monotonic_ns
+
+N_ELEMENTS = 10_000_000
+LOOPS = 10
+
+
+class Strategy:
+    def __init__(self, data_structure=set):
+        self._table = data_structure()
+
+    @cached_property
+    def elements(self):
+        raise NotImplementedError("Implement for each strategy")
+
+    @property
+    def name(self):
+        raise NotImplementedError("Implement for each strategy")
+
+    def run(self):
+        print(f"\nBenchmarking:\t\t{self.name}")
+
+        # Extract the elements here, so that the evaluation of them does not
+        # slow down the relevant part of benchmark
+        elements = self.elements
+
+        # Insertion phase
+        start = monotonic_ns()
+        for x in elements:
+            self._table.add(x)
+        after_insertion = monotonic_ns()
+
+        print(f"Insertion phase:\t{(after_insertion - start) / 1000000:.2f}ms")
+
+        # Lookup phase
+        start = monotonic_ns()
+        for _ in range(LOOPS):
+            for x in elements:
+                assert x in self._table
+        after_lookups = monotonic_ns()
+
+        print(f"Lookup phase:\t\t{(after_lookups - start) / 1000000:.2f}ms")
+
+
+class AscendingOrderedSequence(Strategy):
+    @property
+    def name(self):
+        return "ordered sequence (ascending)"
+
+    @cached_property
+    def elements(self):
+        return [x for x in range(N_ELEMENTS)]
+
+
+class DescendingOrderedSequence(Strategy):
+    @property
+    def name(self):
+        return "ordered sequence (descending)"
+
+    @cached_property
+    def elements(self):
+        return [x for x in reversed(range(N_ELEMENTS))]
+
+
+class ProgressiveAttack(Strategy):
+    @staticmethod
+    def _break(n):
+        return n << max(5, n.bit_length())
+
+
+class ProgressiveAscendingAttack(ProgressiveAttack):
+    @property
+    def name(self):
+        return "progressive sequence that self-heals on resize"
+
+    @cached_property
+    def elements(self):
+        return [self._break(x) for x in range(N_ELEMENTS)]
+
+
+class ProgressiveDescendingAttack(ProgressiveAttack):
+    @property
+    def name(self):
+        return "progressive sequence that self-heals in the end"
+
+    @cached_property
+    def elements(self):
+        return [self._break(x) for x in reversed(range(N_ELEMENTS))]
+
+
+class HardAttack(Strategy):
+    @property
+    def name(self):
+        return "carefully chosen numbers"
+
+    @cached_property
+    def elements(self):
+        return [x << 32 for x in range(N_ELEMENTS)]
+
+
+STRATEGIES = [
+    AscendingOrderedSequence,
+    DescendingOrderedSequence,
+    ProgressiveAscendingAttack,
+    ProgressiveDescendingAttack,
+    HardAttack,
+]
+
+
+def main():
+    for strategy in STRATEGIES:
+        strategy().run()
+
+
+if __name__ == "__main__":
+    main()