• Corpus ID: 2812114

Optimize write performance for DBMS on Solid State Drive

@inproceedings{Li2009OptimizeWP,
  title={Optimize write performance for DBMS on Solid State Drive},
  author={Yu Li},
  year={2009}
}
  • Yu Li
  • Published 2009
  • Computer Science
Solid State Drive (SSD) is believed to be the replacement for magnetic disk in computer systems. SSD is a complex storage device composed of flash chips, controller hardware, and proprietary software that together provide a block device interface via a standard interconnect. Comparing to its fast sequential read/write and random read operations, the random write on SSD is generally believed to be poor. DBMS applications such as online transaction processing (OLTP) will suffer from it because of… 

Figures from this paper

References

SHOWING 1-10 OF 14 REFERENCES
A case for flash memory ssd in enterprise database applications
TLDR
It is shown empirically that up to more than an order of magnitude improvement can be achieved in transaction processing by replacing magnetic disk with flash memory SSD for transaction log, rollback segments, and temporary table spaces.
Understanding intrinsic characteristics and system implications of flash memory based solid state drives
TLDR
This study reveals several unanticipated aspects in the performance dynamics of SSD technology that must be addressed by system designers and data-intensive application users in order to effectively place it in the storage hierarchy.
Query processing techniques for solid state drives
TLDR
This paper investigates data structures and algorithms that leverage fast random reads to speed up selection, projection, and join operations in relational query processing, and introduces FlashJoin, a general pipelined join algorithm that minimizes accesses to base and intermediate relational data.
Design of flash-based DBMS: an in-page logging approach
TLDR
It is shown empirically that the IPL approach can yield considerable performance benefit over traditional design for disk-based database servers, and that the basic design of IPL can be elegantly extended to support transactional database recovery.
FlashLogging: exploiting flash devices for synchronous logging performance
TLDR
This paper proposes FlashLogging, a logging solution that exploits multiple (USB) flash drives for synchronous logging that achieves up to 5.7X improvements over magnetic-disk-based logging, and obtains up to 98.6% of the ideal performance.
Design Tradeoffs for SSD Performance
TLDR
It is found that SSD performance and lifetime is highly workload-sensitive, and that complex systems problems that normally appear higher in the storage stack, or even in distributed systems, are relevant to device firmware.
FlashDB: dynamic self-tuning database for NAND flash
TLDR
This work formalizes the self-tuning nature of an index as a two-state task system and proposes a 3-competitive online algorithm that achieves the theoretical optimum, and prototype and compare different indexing schemes on multiple flash devices and workloads, and shows that the indexing scheme outperforms existing schemes under all workloads and flash devices the authors consider.
A new flash memory management for flash storage system
  • Han-joon Kim, Sang-goo Lee
  • Computer Science
    Proceedings. Twenty-Third Annual International Computer Software and Applications Conference (Cat. No.99CB37032)
  • 1999
TLDR
A new way of managing flash memory space for flash memory-specific file systems based on a log-structured file system that has a maximum of 35% reduction in the cleaning cost with evenly-spread writes across segments.
An efficient B-tree layer implementation for flash-memory storage systems
TLDR
It is demonstrated that when index structures are adopted over flash memory, the proposed methodology can significantly improve the system performance and, at the same time, reduce both the overhead of flash-memory management and the energy dissipation.
A Flash-Memory Based File System
TLDR
A flash memory device driver that supports a conventional UNIX file system transparently writes data to the flash memory system sequentially as a Log-structured File System does and uses a cleaner to collect valid data blocks and reclaim invalid ones by erasing the corresponding flash memory regions.
...
...