New RPC and daemon command to get output histogram

This is a list of existing output amounts along with the number
of outputs of that amount in the blockchain.

The daemon command takes:
- no parameters: all outputs with at least 3 instances
- one parameter: all outputs with at least that many instances
- two parameters: all outputs within that many instances

The default starts at 3 to avoid massive spamming of all dust
outputs in the blockchain, and is the current minimum mixin
requirement.

An optional vector of amounts may be passed, to request
histogram only for those outputs.

2 files changed, 67 insertions, 0 deletions

diff --git a/src/blockchain_db/lmdb/db_lmdb.cpp b/src/blockchain_db/lmdb/db_lmdb.cpp
index e928ab803..9b99520a1 100644
--- a/src/blockchain_db/lmdb/db_lmdb.cpp
+++ b/src/blockchain_db/lmdb/db_lmdb.cpp
@@ -2692,6 +2692,63 @@ void BlockchainLMDB::get_output_tx_and_index(const uint64_t& amount, const std::
   LOG_PRINT_L3("db3: " << db3);
 }
 
+std::map<uint64_t, uint64_t> BlockchainLMDB::get_output_histogram(const std::vector<uint64_t> &amounts) const
+{
+  LOG_PRINT_L3("BlockchainLMDB::" << __func__);
+  check_open();
+
+  TXN_PREFIX_RDONLY();
+  RCURSOR(output_amounts);
+
+  std::map<uint64_t, uint64_t> histogram;
+  MDB_val k;
+  MDB_val v;
+
+  if (amounts.empty())
+  {
+    MDB_cursor_op op = MDB_FIRST;
+    while (1)
+    {
+      int ret = mdb_cursor_get(m_cur_output_amounts, &k, &v, op);
+      op = MDB_NEXT_NODUP;
+      if (ret == MDB_NOTFOUND)
+        break;
+      if (ret)
+        throw0(DB_ERROR(lmdb_error("Failed to enumerate outputs: ", ret).c_str()));
+      mdb_size_t num_elems = 0;
+      mdb_cursor_count(m_cur_output_amounts, &num_elems);
+      uint64_t amount = *(const uint64_t*)k.mv_data;
+      histogram[amount] = num_elems;
+    }
+  }
+  else
+  {
+    for (const auto &amount: amounts)
+    {
+      MDB_val_copy<uint64_t> k(amount);
+      int ret = mdb_cursor_get(m_cur_output_amounts, &k, &v, MDB_SET);
+      if (ret == MDB_NOTFOUND)
+      {
+        histogram[amount] = 0;
+      }
+      else if (ret == MDB_SUCCESS)
+      {
+        mdb_size_t num_elems = 0;
+        mdb_cursor_count(m_cur_output_amounts, &num_elems);
+        histogram[amount] = num_elems;
+      }
+      else
+      {
+        throw0(DB_ERROR(lmdb_error("Failed to enumerate outputs: ", ret).c_str()));
+      }
+    }
+  }
+
+  TXN_POSTFIX_RDONLY();
+
+  return histogram;
+}
+
 void BlockchainLMDB::check_hard_fork_info()
 {
   LOG_PRINT_L3("BlockchainLMDB::" << __func__);
diff --git a/src/blockchain_db/lmdb/db_lmdb.h b/src/blockchain_db/lmdb/db_lmdb.h
index a3f32ffaa..6cd3e0e8f 100644
--- a/src/blockchain_db/lmdb/db_lmdb.h
+++ b/src/blockchain_db/lmdb/db_lmdb.h
@@ -280,6 +280,16 @@ public:
   virtual void pop_block(block& blk, std::vector<transaction>& txs);
 
   virtual bool can_thread_bulk_indices() const { return true; }
+
+  /**
+   * @brief return a histogram of outputs on the blockchain
+   *
+   * @param amounts optional set of amounts to lookup
+   *
+   * @return a set of amount/instances
+   */
+  std::map<uint64_t, uint64_t> get_output_histogram(const std::vector<uint64_t> &amounts) const;
+
 private:
   void do_resize(uint64_t size_increase=0);