R&D: SSD-Based Workload Characteristics and Performance Implications

ACM Transactions on Storage has published an article written by Gala Yadgar, Computer Science Department, Technion, Haifa, Israel, Moshe Gabel, Shehbaz Jaffer, and Bianca Schroeder, Department of Computer Science, University of Toronto, Toronto, ON, Canada.

Abstract: “Storage systems are designed and optimized relying on wisdom derived from analysis studies of file-system and block-level workloads. However, while SSDs are becoming a dominant building block in many storage systems, their design continues to build on knowledge derived from analysis targeted at hard disk optimization. Though still valuable, it does not cover important aspects relevant for SSD performance. In a sense, we are ‘searching under the streetlight,’ possibly missing important opportunities for optimizing storage system design.“

“We present the first I/O workload analysis designed with SSDs in mind. We characterize traces from four repositories and examine their ‘temperature’ ranges, sensitivity to page size, and ‘logical locality.’ We then take the first step towards correlating these characteristics with three standard performance metrics: write amplification, read amplification, and flash read costs. Our results show that SSD-specific characteristics strongly affect performance, often in surprising ways.“