sar.1

linux下查看系统工具原码,如IOSTAT等

.TH SAR 1 "APRIL 2006" Linux "Linux User's Manual" -*- nroff -*-
.SH NAME
sar \- Collect, report, or save system activity information.
.SH SYNOPSIS
.B sar [ -A ] [ -b ] [ -B ] [ -c ] [ -d ] [ -i
.I interval
.B ] [ -p ] [ -q ] [ -r ] [ -R ] [ -t ] [ -u ] [ -v ] [ -V ] [ -w ] [ -W ] [ -y ]
.B [ -n { DEV | EDEV | NFS | NFSD | SOCK | ALL } ]
.B [ -x {
.I pid
.B | SELF | ALL } ] [ -X {
.I pid
.B | SELF | ALL } ] [ -I {
.I irq
.B | SUM | ALL | XALL } ] [ -P {
.I cpu
.B | ALL } ] [ -o [
.I filename
.B ] | -f [
.I filename
.B ] ] [ -s [
.I hh:mm:ss
.B ] ] [ -e [
.I hh:mm:ss
.B ] ] [
.I interval
.B [
.I count
.B ] ]
.SH DESCRIPTION
The
.B sar
command writes to standard output the contents of selected
cumulative activity counters in the operating system. The accounting
system, based on the values in the
.I count
and
.I interval
parameters, writes information the specified number of times spaced
at the specified intervals in seconds.
If the
.I interval
parameter is set to zero, the
.B sar
command displays the average statistics for the time
since the system was started. The default value for the
.I count
parameter is 1. If its value is set to zero, then reports are
generated continuously.
The collected data can also
be saved in the file specified by the
.B -o
.I filename
flag, in addition to being displayed onto the screen. If
.I filename
is omitted, sar uses the standard system activity daily data file,
the
.IR /var/log/sa/sa dd
file, where the dd parameter indicates the current day.
By default all the data available from the kernel are saved in the
data file. Exceptions are interrupts and disks data, for which the
relevant options must be explicitly passed to sar (or to its backend
.B sadc
) when the data file is created (see options below).

The
.B sar
command extracts and writes to standard output records previously
saved in a file. This file can be either the one specified by the
.B -f
flag or, by default, the standard system activity daily data file.

Without the
.B -P
flag, the
.B sar
command reports system-wide (global among all processors) statistics,
which are calculated as averages for values expressed as percentages,
and as sums otherwise. If the
.B -P
flag is given, the
.B sar
command reports activity which relates to the specified processor or
processors. If
.B -P ALL
is given, the
.B sar
command reports statistics for each individual processor and global
statistics among all processors.

You can select information about specific system activities using
flags. Not specifying any flags selects only CPU activity.
Specifying the
.B -A
flag is equivalent to specifying
.BR "-bBcdqrRuvwWy -I SUM -I XALL -n ALL -P ALL".

The default version of the
.B sar
command (CPU utilization report) might be one of the first facilities
the user runs to begin system activity investigation, because it
monitors major system resources. If CPU utilization is near 100 percent
(user + nice + system), the workload sampled is CPU-bound.

If multiple samples and multiple reports are desired, it is convenient
to specify an output file for the
.B sar
command. 
Run the
.B sar
command as a background process. The syntax for this is:

.B sar -o datafile interval count >/dev/null 2>&1 &

All data is captured in binary form and saved to a file (datafile).
The data can then be selectively displayed with the
.B sar
command using the
.B -f
option. Set the
.I interval
and
.I count
parameters to select
.I count
records at
.I interval
second intervals. If the
.I count
parameter is not set, all the records saved in the
file will be selected.
Collection of data in this manner is useful to characterize
system usage over a period of time and determine peak usage hours.

Note:	The
.B sar
command only reports on local activities.

.SH OPTIONS
.IP -A
This is equivalent to specifying
.BR "-bBcdqrRuvwWy -I SUM -I XALL -n ALL -P ALL".
.IP -b
Report I/O and transfer rate statistics.
The following values are displayed:

.B tps
.RS
.RS
Total number of transfers per second that were issued to physical devices.
A transfer is an I/O request to a physical device. Multiple logical
requests can be combined into a single I/O request to the device.
A transfer is of indeterminate size.
.RE

.B rtps
.RS
Total number of read requests per second issued to physical devices.
.RE

.B wtps
.RS
Total number of write requests per second issued to physical devices.
.RE

.B bread/s
.RS
Total amount of data read from the devices in blocks per second.
Blocks are equivalent to sectors with 2.4 kernels and newer
and therefore have a size of 512 bytes. With older kernels, a block is of
indeterminate size.
.RE

.B bwrtn/s
.RS
Total amount of data written to devices in blocks per second.
.RE
.RE
.IP -B
Report paging statistics. The following values are displayed:

.B pgpgin/s
.RS
.RS
Total number of kilobytes the system paged in from disk per second.
Note: With old kernels (2.2.x) this value is a number of blocks per
second (and not kilobytes).
.RE

.B pgpgout/s
.RS
Total number of kilobytes the system paged out to disk per second.
Note: With old kernels (2.2.x) this value is a number of blocks per
second (and not kilobytes).
.RE

.B fault/s
.RS
Number of page faults (major + minor) made by the system per second
(post 2.5 kernels only).
This is not a count of page faults that generate I/O, because some page
faults can be resolved without I/O.
.RE

.B majflt/s
.RS
Number of major faults the system has made per second, those which
have required loading a memory page from disk
(post 2.5 kernels only).
.RE
.RE
.IP -c
Report process creation activity.

.B proc/s
.RS
.RS
Total number of processes created per second.
.RE
.RE
.IP -d
Report activity for each block device (kernels 2.4 and newer only).
When data is displayed, the device specification
.I dev m-n
is generally used (
.B DEV
column).
.B m
is the major number of the device.
With recent kernels (post 2.5),
.B n
is the minor number of the device, but is only a sequence number with
pre 2.5 kernels. Device names may also be pretty-printed if option -p
is used (see below). Values for fields avgqu-sz, await, svctm and %util
may be unavailable and displayed as 0.00 with some 2.4 kernels.

.B tps
.RS
.RS
Indicate the number of transfers per second that were issued to the device.
Multiple logical requests can be combined into a single I/O request to the
device. A transfer is of indeterminate size.
.RE

.B rd_sec/s
.RS
Number of sectors read from the device. The size of a sector is 512 bytes.
.RE

.B wr_sec/s
.RS
Number of sectors written to the device. The size of a sector is 512 bytes.
.RE

.B avgrq-sz
.RS
The average size (in sectors) of the requests that were issued to the device.
.RE

.B avgqu-sz
.RS
The average queue length of the requests that were issued to the device.
.RE

.B await
.RS
The average time (in milliseconds) for I/O requests issued to the device
to be served. This includes the time spent by the requests in queue and
the time spent servicing them.
.RE

.B svctm
.RS
The average service time (in milliseconds) for I/O requests that were issued
to the device.
.RE

.B %util
.RS
Percentage of CPU time during which I/O requests were issued to the device
(bandwidth utilization for the device). Device saturation occurs when this
value is close to 100%.
.RE
.RE
.IP "-e [ hh:mm:ss ]"
Set the ending time of the report. The default ending time is
18:00:00. Hours must be given in 24-hour format.
This option can be used only when data are read from
or written to a file (options
.B -f
or
.B -o
).
.IP "-f [ filename ]"
Extract records from
.I filename
(created by the
.B -o filename
flag). The default value of the
.B filename
parameter is the current daily data file, the
.IR /var/log/sa/sa dd
file. The -f option is exclusive of the -o option.
.IP "-i interval"
Select data records at seconds as close as possible to the number specified
by the
.I interval
parameter.
.IP "-I { irq | SUM | ALL | XALL }"
Report statistics for a given interrupt.
.B irq
is the interrupt number. Specifying multiple
.B -I irq
parameters on the command line will look at multiple independent interrupts.
The
.B SUM
keyword indicates that the total number of interrupts received per second
is to be displayed. The
.B ALL
keyword indicates that statistics from
the first 16 interrupts are to be reported, whereas the
.B XALL
keyword indicates that statistics from all interrupts, including potential
APIC interrupt sources, are to be reported.
.IP "-n { DEV | EDEV | NFS | NFSD | SOCK | ALL }"
Report network statistics.

With the
.B DEV
keyword, statistics from the network devices are reported.
The following values are displayed:

.B IFACE
.RS
.RS
Name of the network interface for which statistics are reported.
.RE

.B rxpck/s
.RS
Total number of packets received per second.
.RE

.B txpck/s
.RS
Total number of packets transmitted per second.
.RE

.B rxbyt/s
.RS
Total number of bytes received per second.
.RE

.B txbyt/s
.RS
Total number of bytes transmitted per second.
.RE

.B rxcmp/s
.RS
Number of compressed packets received per second (for cslip etc.).
.RE

.B txcmp/s
.RS
Number of compressed packets transmitted per second.
.RE

.B rxmcst/s
.RS
Number of multicast packets received per second.
.RE

With the
.B EDEV
keyword, statistics on failures (errors) from the network devices are reported.
The following values are displayed:

.B IFACE
.RS
Name of the network interface for which statistics are reported.
.RE

.B rxerr/s
.RS
Total number of bad packets received per second.
.RE

.B txerr/s
.RS
Total number of errors that happened per second while transmitting packets.
.RE

.B coll/s
.RS
Number of collisions that happened per second while transmitting packets.
.RE

.B rxdrop/s
.RS
Number of received packets dropped per second because of a lack of space in linux buffers.
.RE

.B txdrop/s
.RS
Number of transmitted packets dropped per second because of a lack of space in linux buffers.
.RE

.B txcarr/s
.RS
Number of carrier-errors that happened per second while transmitting packets.
.RE

.B rxfram/s
.RS
Number of frame alignment errors that happened per second on received packets.
.RE

.B rxfifo/s
.RS
Number of FIFO overrun errors that happened per second on received packets.
.RE

.B txfifo/s
.RS
Number of FIFO overrun errors that happened per second on transmitted packets.
.RE

With the
.B NFS
keyword, statistics about NFS client activity are reported.
The following values are displayed:

.B call/s
.RS
Number of RPC requests made per second.
.RE

.B retrans/s
.RS
Number of RPC requests per second, those which needed to be retransmitted (for
example because of a server timeout).
.RE

.B read/s
.RS
Number of 'read' RPC calls made per second.
.RE

.B write/s
.RS
Number of 'write' RPC calls made per second.
.RE

.B access/s
.RS
Number of 'access' RPC calls made per second.
.RE

.B getatt/s
.RS
Number of 'getattr' RPC calls made per second.
.RE

With the
.B NFSD
keyword, statistics about NFS server activity are reported.
The following values are displayed:

.B scall/s
.RS
Number of RPC requests received per second.
.RE

.B badcall/s
.RS
Number of bad RPC requests received per second, those whose
processing generated an error.
.RE

.B packet/s
.RS
Number of network packets received per second.
.RE

.B udp/s
.RS
Number of UDP packets received per second.
.RE

.B tcp/s
.RS
Number of TCP packets received per second.
.RE

.B hit/s
.RS
Number of reply cache hits per second.
.RE

.B miss/s
.RS
Number of reply cache misses per second.
.RE

.B sread/s
.RS
Number of 'read' RPC calls received per second.
.RE

.B swrite/s
.RS
Number of 'write' RPC calls received per second.
.RE

.B saccess/s
.RS
Number of 'access' RPC calls received per second.
.RE

.B sgetatt/s
.RS