Disk IO
From DTraceBook
This chapter uses DTrace for analyzing the disk subsystem, including block device I/O, SCSI, SATA, IDE and SAS.
Contents |
Sample One-Liners
See the DTrace book for more one-liners.
io Provider
Show disk I/O size as distribution plots, by process name
dtrace -n 'io:::start { @size[execname] = quantize(args[0]->b_bcount); }'
Identify kernel stacks calling disk I/O
dtrace -n 'io:::start { @[stack()] = count(); }'
Trace errors along with disk and error number
dtrace -n 'io:::done /args[0]->b_flags & B_ERROR/ { printf("%s err: %d", args[1]->dev_statname, args[0]->b_error); }'
fbt Provider
Identify kernel stacks calling disk I/O (FreeBSD)
dtrace -n 'fbt::bufstrategy:entry { @[stack()] = count(); }'
Scripts
- iolatency.d
- disklatency.d
- iotypes.d
- rwtime.d
- bitesize.d
- seeksize.d
- iosnoop
- iotop
- iopattern
- geomiosnoop.d
- sdqueue.d
- sdretry.d
- scsicmds.d
- scsilatency.d
- scsirw.d
- scsireasons.d
- scsi.d
- satacmds.d
- satarw.d
- satareasons.d
- satalatency.d
- idelatency.d
- iderw.d
- ideerr.d
- mptsasscsi.d
- mptevents.d
- mptlatency.d
Errata
1st printing:
- p231, 2nd para: "scripts is this book": "is" -> "in"
