mirror of https://github.com/facebook/rocksdb.git
e63350e726
Summary: Currently, deadlock cycles are held in std::unordered_map. The problem with it is that it allocates/deallocates memory on every insertion/deletion. This limits throughput since we're doing this expensive operation while holding a global mutex. Fix this by using a vector which caches memory instead. Running the deadlock stress test, this change increased throughput from 39k txns/s -> 49k txns/s. The effect is more noticeable in MyRocks. Closes https://github.com/facebook/rocksdb/pull/1545 Differential Revision: D4205662 Pulled By: lth fbshipit-source-id: ff990e4 |
||
|---|---|---|
| .. | ||
| optimistic_transaction_db_impl.cc | ||
| optimistic_transaction_db_impl.h | ||
| optimistic_transaction_impl.cc | ||
| optimistic_transaction_impl.h | ||
| optimistic_transaction_test.cc | ||
| transaction_base.cc | ||
| transaction_base.h | ||
| transaction_db_impl.cc | ||
| transaction_db_impl.h | ||
| transaction_db_mutex_impl.cc | ||
| transaction_db_mutex_impl.h | ||
| transaction_impl.cc | ||
| transaction_impl.h | ||
| transaction_lock_mgr.cc | ||
| transaction_lock_mgr.h | ||
| transaction_test.cc | ||
| transaction_util.cc | ||
| transaction_util.h | ||