iopending(1m) [osx man page]

iopending(1m)							   USER COMMANDS						     iopending(1m)

NAME

       iopending - plot number of pending disk events. Uses DTrace.

SYNOPSIS

       iopending [-c] [-d device] [-f filename] [-m mount_point] [interval [count]]

DESCRIPTION

       This samples the number of disk events that are pending and plots a distribution graph. By doing this the "serialness" or "parallelness" of
       disk behaviour can be distinguished.  A high occurance of a pending value of more than 1 is an indication of saturation.

       Since this uses DTrace, only users with root privileges can run this command.

OPTIONS

       -c     clear screen

       -d device
	      instance name to snoop (eg, dad0)

       -f filename
	      full pathname of file to snoop

       -m mount_point
	      mountpoint for filesystem to snoop

EXAMPLES

       Default output, print I/O summary every 1 second,
	      # iopending

       Print 10 second samples,
	      # iopending 10

       Print 12 x 5 second samples,
	      # iopending 5 12

       Snoop events on the root filesystem only,
	      # iopending -m /

FIELDS

       value  number of pending events, 0 == idle

       count  number of samples @ 1000 Hz

       load   1 min load average

       disk_r total disk read Kb for sample

       disk_w total disk write Kb for sample

IDEA

       Dr Rex di Bona

DOCUMENTATION

       See the DTraceToolkit for further documentation under the Docs directory. The DTraceToolkit docs may include full worked examples with ver-
       bose descriptions explaining the output.

EXIT

       iopending will run forever until Ctrl-C is hit, or the specified count is reached.

AUTHOR

       Brendan Gregg [Sydney, Australia]

SEE ALSO

       iosnoop(1M), iotop(1M), dtrace(1M)

version 0.60							   Nov 01, 2005 						     iopending(1m)

iopattern(1m)							   USER COMMANDS						     iopattern(1m)

NAME

       iopattern - print disk I/O pattern. Uses DTrace.

SYNOPSIS

       iopattern [-v] [-d device] [-f filename] [-m mount_point] [interval [count]]

DESCRIPTION

       This  prints  details on the I/O access pattern for the disks, such as percentage of events that were of a random or sequential nature.	By
       default totals for all disks are printed.

       An event is considered random when the heads seek. This program prints the percentage of events that are random. The size of  the  seek	is
       not measured - it's either random or not.

       Since this uses DTrace, only users with root privileges can run this command.

OPTIONS

       -v     print timestamp, string

       -d device
	      instance name to snoop (eg, dad0)

       -f filename
	      full pathname of file to snoop

       -m mount_point
	      mountpoint for filesystem to snoop

EXAMPLES

       Default output, print I/O summary every 1 second,
	      # iopattern

       Print 10 second samples,
	      # iopattern 10

       Print 12 x 5 second samples,
	      # iopattern 5 12

       Snoop events on the root filesystem only,
	      # iopattern -m /

FIELDS

       %RAN   percentage of events of a random nature

       %SEQ   percentage of events of a sequential nature

       COUNT  number of I/O events

       MIN    minimum I/O event size

       MAX    maximum I/O event size

       AVG    average I/O event size

       KR     total kilobytes read during sample

       KW     total kilobytes written during sample

       DEVICE device name

       MOUNT  mount point

       FILE   filename (basename) for I/O operation

       TIME   timestamp, string

IDEA

       Ryan Matteson

DOCUMENTATION

       See the DTraceToolkit for further documentation under the Docs directory. The DTraceToolkit docs may include full worked examples with ver-
       bose descriptions explaining the output.

EXIT

       iopattern will run forever until Ctrl-C is hit, or the specified count is reached.

AUTHOR

       Brendan Gregg [Sydney, Australia]

SEE ALSO

       iosnoop(1M), iotop(1M), dtrace(1M)

version 0.70							   Jul 25, 2005 						     iopattern(1m)