Overwriting is much faster than appendingWriting small volume of data (Bytes-MBs) with sync (fsync()/fdatasync()/O_SYNC/O_DSYNC) is very common for RDBMS and is needed to guarantee durability. For transactional log files, sync happens per commit. For data files, sync happens at checkpoint etc. Typically RDBMS does syncing data very frequently. In this case, overwriting is much faster than appending for most filesystems/storages. Overwrit
The Design of A Big, Fast, and Persistent Queue - Abstraction Builder
ファイル入出力の基本 (IO モデル) を勉強する - フリーフォーム フリークアウト
mmap (メモリマップトファイル) : kei@sodan
