direct fuse removing the middleman for high performance
play

Direct-FUSE: Removing the Middleman for High-Performance FUSE File - PowerPoint PPT Presentation

Direct-FUSE: Removing the Middleman for High-Performance FUSE File System Support Yue Zhu*, Teng Wang*, Kathryn Mohror + , Adam Moody + , Kento Sato + , Muhib Khan*, Weikuan Yu* Florida State University* Lawrence Livermore National Laboratory +


  1. Direct-FUSE: Removing the Middleman for High-Performance FUSE File System Support Yue Zhu*, Teng Wang*, Kathryn Mohror + , Adam Moody + , Kento Sato + , Muhib Khan*, Weikuan Yu* Florida State University* Lawrence Livermore National Laboratory +

  2. Introduction n An efficient file system is important for high-performance computing (HPC) systems in supporting large-scale scientific applications. Ø User-level file systems are more designed for particular I/O workloads with special-purpose, due to development complexity, reliability, and portability. Ø Different file systems are used for different kinds of data in a single job. n Filesystem in Userspace (FUSE) Ø A software interface for Unix-like computer operating systems. Ø It allows non-privileged users to create their own file systems without editing kernel code. Ø User defined file system run as a separate process in user-space. PDSW-WIP’17 S-2

  3. Breakdown of Metadata & Data Latency n The create() and close(), and write() are taken as examples to show the percentage of real operation time in a complete FUSE metadata and data operation, respectively. Ø Tests are on tmpfs and FUSE-tmpfs. Ø Real Operation in metadata operation: the time of conducting operation. Ø Data Movement : the actual time of write in a complete write function call. Ø Overhead : the cost besides the above two, e.g. the time of context switches. 250 600 11.18% Data Movement Real Operation 38.12% 500 200 Overhead Overhead Latency (ns) 400 Latency (ns) 150 300 37.86% 100 200 33.7% 2.17% 50 100 34.8% 15.82% 10.08% 0 0 tmpfs FUSE-tmpfs tmpfs FUSE-tmpfs Create Close 1 4 16 64 128 256 Metadata Operations Transfer Sizes (KB) Fig. 1. The time Expense in Metadata Operations Fig. 2. The time Expense in Data Operations PDSW-WIP’17 S-3

  4. The Overview of Direct-FUSE n Direct-FUSE contains the Application Program adapted libsysio , lightweight- libfuse , and backend Direct-FUSE services . adapted-libsysio Ø Adapted-libsysio o Support multiple backends lightweight-libfuse Ø lightweight-libfuse o Not real libfuse Backend Services o Exposes file system operation to under layer backend services with SSHFS FTPFS FUSE-ext4 supporting FUSE library. … FusionFS GlusterFS Ø Backend services o Provide defined FUSE operations. PDSW-WIP’17 S-4

  5. Sequential Write Bandwidth n The bandwidth of Direct-FUSE is very close to the native file system. Ø Ext4(tmpfs)-fuse : FUSE file system overlying Ext4 (tmpfs); Ext4(tmpfs)-direct : Direct-FUSE on Ext4 (tmpfs); Ext4(tmpfs)- native : original Ext4 (tmpfs). Ø Ext4-direct outperforms Ext4-fuse by 11.9% on average Ø tmpfs-direct outperforms tmpfs-fuse at least 2.26x. Ext4-fuse Ext4-direct Ext4-native tmpfs-fuse tmpfs-direct tmpfs-native 10000 Bandwidth (MB/s) 1000 100 10 1 4 16 64 256 1024 Write Transfer Sizes (KB) PDSW-WIP’17 S-5

  6. Sponsors of This Research PDSW-WIP’17 S-6

Recommend


More recommend