Lines Matching refs:mutex

12 … writer and multiple readers. There is only one single major lock, the DB mutex (DBImpl.mutex_) pr…
25 This DB mutex used to be scalability bottleneck preventing us from scaling to more than 16 threads.…
27 1. Consolidate reference counters and introduce "super version". For every read operation, mutex wa…
31 … that decreasing reference count of an object usually doesn’t need to be inside the mutex any more.
33 …he locking for decreasing reference counts, in read case, we only acquire mutex for one thing: fet…
35 …mutex. As we know, each disk I/O to hard drives takes several milliseconds. It can be even longer …
36 We identified in two situations, we might do disk I/O inside mutex and we removed them:
37 (1) Opening and closing transactional log files. We moved those operations out of the mutex.
38 …mutex. There is a chance that file write will wait for disk I/O to finish before finishing, even i…
40 5. Reduce object creation inside the mutex.
41 …tructors. For these reasons, we try to reduce object creations inside the mutex. Here are two exam…
43 …or manipulating those meta data structures. Those meta operations are often locked inside DB mutex.
45 …mutex and a merging iterator on top of them. Besides malloc, some of those iterators can be quite …
48 …a structures. Lock contention of these two locks are as intense as the DB mutex. Even if LRU cache…