3 stats \- display graphs of system activity
15 displays a rolling graph of various statistics collected by the operating
16 system and updated once per second.
17 The statistics may be from a remote
21 whose graphs will appear in adjacent columns.
22 The columns are labeled by the machine names and the number
23 of processors on the machine if it is a multiprocessor.
25 The right mouse button presents a menu to enable and disable the display
26 of various statistics; by default,
28 begins by showing the load average on the executing machine.
33 choose the initial set to display:
37 percentage battery life remaining.
40 number of process context switches per second.
44 total number of packets sent and received per second.
48 number of packets sent and received per second, displayed as separate graphs.
51 number of page faults per second.
54 number of interrupts per second.
57 system load, % time in idle, and % time in interrupts.
58 The last two are averaged over all processors on a
62 (default) system load average.
63 The load is computed as a running average of
64 the number of processes ready to run, multiplied by 1000.
67 total pages of active memory.
68 The graph displays the fraction
69 of the machine's total memory in use.
72 kernel memory allocation size in bytes.
75 draw memory allocation size in bytes.
79 number of packets sent and received per second, and total number of errors, displayed as separate graphs.
82 number of translation lookaside buffer flushes per second.
85 number of system calls per second.
88 number of translation lookaside buffer misses per second.
91 number of valid pages on the swap device.
92 The swap is displayed as a
93 fraction of the number of swap pages configured by the machine.
96 display the signal strength detected by the 802.11b wireless ether card; the value
97 is usually below 50% unless the receiver is in the same room as the transmitter, so
98 a midrange value represents a strong signal.
101 The graphs are plotted with time on the horizontal axis.
102 The vertical axes range from 0 to 1000*sleepsecs,
103 multiplied by the number of processors on the machine
105 The only exceptions are
108 which display fractions of the total available,
109 system load, which displays a number between 0 and 1000,
110 idle and intr, which display percentages and the Ethernet error count,
111 which goes from 0 to 10..
112 If the value of the parameter is too large for the visible range, its value is shown
113 in decimal in the upper left corner of the graph.
115 Upper-case options control details of the display.
116 All graphs are affected; there is no mechanism to
117 affect only one graph.
120 Set the number of seconds between samples to
122 (default one second).
124 may be a floating-point number.
127 Sets a scale factor for the displays. A value of 2, for example,
128 means that the highest value plotted will be twice as large as the default.
131 Plot all graphs with logarithmic
134 The graph is plotted so the maximum value that would be displayed on
135 a linear graph is 2/3 of the way up the
137 axis and the total range of the graph is a factor of 1000; thus the
139 origin is 1/100 of the default maximum value and the top of the graph is
140 10 times the default maximum.
143 If the display is large enough to show them,
144 place value markers along the
147 Since one set of markers serves for all machines across the display,
148 the values in the markers disregard scaling factors due to multiple processors
149 on the machines. On a graph for a multiprocessor,
150 the displayed values will be larger
151 than the markers indicate.
152 The markers appear along the right, and the markers
153 show values appropriate to the rightmost machine; this only
154 matters for graphs such as memory that have machine-specific
158 .B /net/ether0/0/stats
164 .B /sys/src/cmd/stats.c
166 Some machines do not have TLB hardware.