Hystor : Making the Best Use of Solid State Drivers in High Performance Storage Systems Presenter : Dong Chang

Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

Introduction Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

Introduction Data-intensive computing are in high demand for high-performance storage systems. HDD disadvantages: low random access performance and high power consumption. SSD : semiconductor chips without moving parts, providing higher performance. SSD should not be a replacement but an enhancement of HDD.

Introduction DRAM300K$120K + Disk250$30 + Random reads/sec Cost (128 GB) Flash-SSD10K*$225 + Random writes/sec K 5K* Too slow Too expensive * Derived from latencies on Intel M-18 SSD in experiments 2.5 ops/sec/$ Slow writes + Price statistics from

Introduction  Finding the fittest position of SSDs in storage system? Critical Issues:  Effectively identifying the most performance-critical blocks and fully exploiting the unique performance potential of SSDs.  Efficiently maintaining data access history with low overhead for accurately characterizing access patterns.  Avoiding major kernel changes in existing systems while effectively implementing the hybrid storage management policies

Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

Contributions Identify an effective metric to represent the performance-critical blocks. Design an efficient mechanism to profile and maintain detailed data access history for a long-term optimization. Design and implementation of a high performance hybrid storage system,Hystor.

Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

SSD Performance Advantages  Performance benefits are dependent on workload access patterns.  High write performance on the SSD (up to 194MB/sec).  Write performance on the SSD is largely independent of access patterns, and random writes can achieve almost identical performance as sequential writes.

SSD Performance Advantages The consideration in the design of Hystor: workload access patterns 1. Recognize workload access patterns to identify the most high-cost data blocks, especially those blocks being randomly accessed by small requests, which cause the worst performance for HDDs. write-back 2. Leverage the SSD as a write-back buffer to handle writes, which often raise high latencies in HDDs. we do not have to treat random writes specifically, since random writes on SSD can perform as fast as sequential writes.

Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

System High-cost data block How to identify it? indicator metrics: frequency/size

System Manage data access history Maintain history information---block table

System Manage data access history inverse bitmap Represent the metric: inverse bitmap (to encode the request size and frequency ) A block is accessed by a request of N sectors, an inverse bitmap, b, is calculated using the following equation:

System Main Architecture

System Hystor Design ： Logical Block Mapping SSD Space Management Managing the Remap Area Identifying High-Cost Data Blocks Reorganizing Data Layout across Devices User-level Monitor Identifying Metadata Blocks Managing the Write-back Area

Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

Experiments Intel ® D975BX system 2.66GHz Intel ® Core™ 2 Quad CPU and 4GB main memory

Experiments Performance of Hystor

Experiments Performance of Hystor

Introduction Contributions SSD Performance Advantages System Experiments Conclusions Outline

Conclusions Identify the data that are best suitable to be held in SSD by using a simple yet effective metric SSDs should play a major role in the storage hierarchy retaining performance- and semantically-critical data, and it can also be as a write-back buffer