zfsdist - Summarize ZFS operation latency. Uses Linux eBPF/bcc.
Contents
Description
This tool summarizes time (latency) spent in common ZFS file operations: reads, writes, opens, and syncs,
and presents it as a power-of-2 histogram. It uses an in-kernel eBPF map to store the histogram for
efficiency.
This uses kernel dynamic tracing of the ZPL interface (ZFS POSIX Layer), and will need updates to match
any changes to this interface.
This is intended to work with the ZFS on Linux project:
http://zfsonlinux.org
Since this uses BPF, only the root user can use this tool.
Examples
Trace ZFS operation time, and print a summary on Ctrl-C:
# zfsdist
Trace PID 181 only:
# zfsdist-p181
Print 1 second summaries, 10 times:
# zfsdist110
1 second summaries, printed in milliseconds
# zfsdist-m1Fields
msecs Range of milliseconds for this bucket.
usecs Range of microseconds for this bucket.
count Number of operations in this time range.
distribution
ASCII representation of the distribution (the count column).
Name
zfsdist - Summarize ZFS operation latency. Uses Linux eBPF/bcc.
Options
-h Print usage message.
-T Don't include timestamps on interval output.
-m Output in milliseconds.
-p PID Trace this PID only.
Os
Linux
Overhead
This adds low-overhead instrumentation to these ZFS operations, including reads and writes from the file
system cache. Such reads and writes can be very frequent (depending on the workload; eg, 1M/sec), at
which point the overhead of this tool may become noticeable. Measure and quantify before use.
Requirements
CONFIG_BPF and bcc.
See Also
zfssnoop(8) USER COMMANDS 2016-02-12 zfsdist(8)
Source
This is from bcc.
https://github.com/iovisor/bcc
Also look in the bcc distribution for a companion _examples.txt file containing example usage, output,
and commentary for this tool.
Stability
Unstable - in development.
Synopsis
zfsdist[-h][-T][-m][-pPID][interval][count]
