SPEK: A Storage Performance Evaluation Kernel Module for Block-Level Storage Systems under Faulty Conditions

Xubin He Tennessee Technological University ; Ming Zhang University of Rhode Island ; Qing Yang University of Rhode Island

Abstract

This paper introduces a new benchmark tool, SPEK (storage performance evaluation kernel module), for evaluating the performance of block-level storage systems in the presence of faults as well as under normal operations. SPEK can work on both direct attached storage (DAS) and block level networked storage systems such as storage area networks (SAN). Each SPEK consists of a controller, several workers, one or more probers, and several fault injection modules. Since it runs at kernel level and eliminates skews and overheads caused by file systems, SPEK is highly accurate and efficient. It allows a storage architect to generate configurable workloads to a system under test and to inject different faults into various system components such as network devices, storage devices, and controllers. Available performance measurements under different workloads and faulty conditions are dynamically collected and recorded in SPEK over a spectrum of time. To demonstrate its functionality, we apply SPEK to evaluate the performance of two direct attached storage systems and two typical SANs under Linux with different fault injections. Our experiments show that SPEK is highly efficient and accurate to measure performance for block-level storage systems.

Journal
IEEE Transactions on Professional Communication
Published
2005-02-01
DOI
10.1109/tdsc.2005.27
CompPile
Open Access
OA PDF Green
Topics
Export

Citation Context

Cited by in this index (0)

No articles in this index cite this work.

References (49)

  1. 10.1145/176979.176981
  2. 10.1006/jpdc.1993.1013
  3. Appia: Automatic Storage Area Network Fabric Design
  4. PostMark: A New File System Benchmark
  5. Iozone Filesystem Benchmark
Show all 49 →
  1. Bonnie++ Benchmark Tool
  2. Performance Analysis Tool
  3. 10.1145/258612.258689
  4. 10.1007/BF02187098
  5. 10.1109/24.24588
  6. Composite Performance and Availability Analysis Using a Hierarchy of Stochastic Reward Nets
  7. 10.1109/25.950322
  8. Towards Availability Benchmarks: A Case Study of Software RAID Systems
  9. UNH, iSCSI Reference Implementation
  10. 10.1016/j.jpdc.2004.05.005
  11. SCSI Block Commands, NCITS Working Draft Proposed Standard, Rev. 8c
  12. 10.1109/12.238482
  13. ORCHESTRA: A Fault Injection Environment for Distributed Systems
  14. Fault-Tolerant Computer System Design
  15. Mendosus: A SAN-Based Fault-Injection Test-Bed for the Construction of Highly Available N…
  16. 10.1002/047122460X
  17. Using Fault Injection and Modeling to Evaluate the Performability of Cluster-Based Services
  18. 10.1145/251007.251012
  19. Obtaining High Performance for Storage Outsourcing
  20. Timing-Accurate Storage Emulation
  21. DTB: Linux Disk Trace Buffer, Performance Evaluation Laboratory, Brigham Young University
  22. SPC, Storage Performance Council I/O Traces
  23. Observing the Effects of Multi-Zone Disks
  24. Dell/EMC, CX200 RAID Storage System
  25. 10.1145/258612.258690
  26. iSCSI Draft Standard
  27. 10.1109/IPCCC.2001.918661
  28. iSCSI Initiator Design and Implementation Experience
  29. Reliability, Availability, Dependability and Performability: A User-Centered View
  30. 10.1109/HPCA.2003.1183541
  31. 10.1109/TC.1980.1675654
  32. 10.1016/0166-5316(92)90002-X
  33. Efficient Verification of Performability Guarantees
  34. 10.1109/12.2184
  35. Probability and Statistics with Reliability, Queuing, and Computer Science Applications
  36. 10.1145/88237.88242
  37. LADDIS: The Next Generation in NFS File Server Benchmarking
  38. SPEC, SPEC SFS benchmark
  39. VeriTest, Netbench File System Benchmark
  40. Structure and Performance of the Direct Access File System (DAFS)
  41. NHT-1 I/O Benchmarks
  42. 10.1177/109434209801200305
  43. 10.1145/511334.511382
  44. 10.1145/346152.346263