Project

General

Profile

Bug #3794

Sequential IO on ZFS exhibits factor >13 slowdown when not aligned to record boundaries.

Added by Richard Yao over 6 years ago. Updated over 6 years ago.

Status:
New
Priority:
Normal
Assignee:
-
Category:
zfs - Zettabyte File System
Start date:
2013-05-28
Due date:
% Done:

0%

Estimated time:
Difficulty:
Hard
Tags:
needs-triage

Description

It seems that using dd to write a large sequential file with bs=131072 is quick while bs=65536 exhibits a factor of >13 slowdown. This has been observed on both Linux and Solaris 10u10. This appears to be a write-hole caused by an absence of write coalescing. Full details are available at the ZFSOnLinux issue:

https://github.com/zfsonlinux/zfs/issues/361

This is not something that the ZFSOnLinux project should tackle by itself, so I decided to file an upstream issue.

History

#1

Updated by Rich Lowe over 6 years ago

  • Project changed from site to illumos gate
#2

Updated by Rich Lowe over 6 years ago

  • Category set to zfs - Zettabyte File System

Also available in: Atom PDF