为什么TimesTen比使用内存缓存的Oracle还要快

Oracle可以把整个表置于内存缓存中，为什么还是不如Oracle快呢?
Oracle TimesTen Application-Tier Database Cache Introduction中第一章中Why is Oracle TimesTen In-Memory Database fast?做出了解释：

Much of the work that is done by a conventional, disk-optimized RDBMS is done under the assumption that data primarily resides on disk. Optimization algorithms, buffer pool management, and indexed retrieval techniques are designed based on this fundamental assumption.

Even when a disk-based RDBMS has been configured to hold all of its data in main memory, its performance is hobbled by assumptions of disk-based data residency. These assumptions cannot be easily reversed because they are hard-coded in processing logic, indexing schemes, and data access mechanisms.

TimesTen is designed with the knowledge that data resides in main memory and can take more direct routes to data, reducing the length of the code path and simplifying algorithms and structure.

When the assumption of disk-residency is removed, complexity is dramatically reduced. The number of machine instructions drops, buffer pool management disappears, extra data copies are not needed, index pages shrink, and their structure is simplified. The design becomes simple and more compact, and requests are executed faster.

两者的对比如下图：

In a conventional disk-based RDBMS, client applications communicate with a database server process over some type of IPC connection, which adds performance overhead to all SQL operations. An application can link TimesTen directly into its address space to eliminate the IPC overhead and streamline query processing. This is accomplished through a direct connection to TimesTen.

这里提到了TimesTen的direct模式，不过即使是C/S模式，还是会比Oracle快

另一篇文章的解释也可以作为补充， Oracle’s In-Memory Database Strategy for OLTP and Analytics

Another over-arching design principle is the use of memory-based addressing rather than logical addressing. For instance, indexes in TimesTen contain pointers to the tuples in the base table. The metadata describing the layout of a table contains pointers to the pages comprising the table. Therefore both index scans and tablescans can operate via pointer traversal. This design approach is repeated over and over again in the storage manager, with the result that TimesTen is significantly faster than a disk-oriented database even one that is completely cached – since there is no overhead from having to translate logical rowids to physical memory addresses of buffers in a buffer cache.