NAME¶
systemd-cgtop - Show top control groups by their resource
usage
SYNOPSIS¶
systemd-cgtop [OPTIONS...] [GROUP]
DESCRIPTION¶
systemd-cgtop shows the top control groups of the local
Linux control group hierarchy, ordered by their CPU, memory, or disk I/O
load. The display is refreshed in regular intervals (by default every 1s),
similar in style to top(1). If a control group path is specified,
shows only the services of the specified control group.
If systemd-cgtop is not connected to a tty, no column
headers are printed and the default is to only run one iteration. The
--iterations= argument, if given, is honored. This mode is suitable
for scripting.
Resource usage is only accounted for control groups with the
appropriate controllers turned on: "cpu" controller for CPU usage,
"memory" controller for memory usage, and "io"
controller for disk I/O consumption. If resource monitoring for these
resources is required, it is recommended to add the CPUAccounting=1,
MemoryAccounting=1 and IOAccounting=1 settings in the unit
files in question. See systemd.resource-control(5) for details.
The CPU load value can be between 0 and 100 times the number of
processors the system has. For example, if the system has 8 processors, the
CPU load value is going to be between 0% and 800%. The number of processors
can be found in "/proc/cpuinfo".
To emphasize: unless "CPUAccounting=1",
"MemoryAccounting=1", and "IOAccounting=1" are enabled
for the services in question, no resource accounting will be available for
system services and the data shown by systemd-cgtop will be
incomplete.
OPTIONS¶
The following options are understood:
-p, --order=path
Order by control group path name.
-t, --order=tasks
Order by number of tasks/processes in the control
group.
-c, --order=cpu
Order by CPU load.
-m, --order=memory
Order by memory usage.
-i, --order=io
Order by disk I/O load.
-b, --batch
Run in "batch" mode: do not accept input and
run until the iteration limit set with --iterations= is exhausted or
until killed. This mode could be useful for sending output from
systemd-cgtop to other programs or to a file.
-r, --raw
Format byte counts (as in memory usage and I/O metrics)
and CPU time with raw numeric values rather than human-readable numbers.
--cpu=percentage, --cpu=time
Controls whether the CPU usage is shown as percentage or
time. By default, the CPU usage is shown as percentage. This setting may also
be toggled at runtime by pressing the % key.
-P
Count only userspace processes instead of all tasks. By
default, all tasks are counted: each kernel thread and each userspace thread
individually. With this setting, kernel threads are excluded from the count
and each userspace process only counts as one task, regardless of how many
threads it consists of. This setting may also be toggled at runtime by
pressing the P key. This option may not be combined with -k.
-k
Count only userspace processes and kernel threads instead
of all tasks. By default, all tasks are counted: each kernel thread and each
userspace thread individually. With this setting, kernel threads are included
in the count and each userspace process only counts as one task, regardless of
how many threads it consists of. This setting may also be toggled at runtime
by pressing the k key. This option may not be combined with -P.
--recursive=
Controls whether the number of processes shown for a
control group shall include all processes that are contained in any of the
child control groups as well. Takes a boolean argument, which defaults to
"yes". If enabled, the processes in child control groups are
included, if disabled, only the processes in the control group itself are
counted. This setting may also be toggled at runtime by pressing the r key.
Note that this setting only applies to process counting, i.e. when the
-P or -k options are used. It has not effect if all tasks are
counted, in which case the counting is always recursive.
-n, --iterations=
Perform only this many iterations. A value of 0 indicates
that the program should run indefinitely.
-1
A shortcut for --iterations=1.
-d, --delay=
Specify refresh delay in seconds (or if one of
"ms", "us", "min" is specified as unit in this
time unit). This setting may also be increased and decreased at runtime by
pressing the + and - keys.
--depth=
Maximum control group tree traversal depth. Specifies how
deep systemd-cgtop shall traverse the control group hierarchies. If 0
is specified, only the root group is monitored. For 1, only the first level of
control groups is monitored, and so on. Defaults to 3.
-M MACHINE,
--machine=MACHINE
Limit control groups shown to the part corresponding to
the container MACHINE. This option may not be used when a control group
path is specified.
-h, --help
Print a short help text and exit.
--version
Print a short version string and exit.
KEYS¶
systemd-cgtop is an interactive tool and may be controlled
via user input using the following keys:
h
Shows a short help text.
Space
Immediately refresh output.
q
Terminate the program.
p, t, c, m, i
Sort the control groups by path, number of tasks, CPU
load, memory usage, or I/O load, respectively. This setting may also be
controlled using the --order= command line switch.
%
Toggle between showing CPU time as time or percentage.
This setting may also be controlled using the --cpu= command line
switch.
+, -
Increase or decrease refresh delay, respectively. This
setting may also be controlled using the --delay= command line
switch.
P
Toggle between counting all tasks, or only userspace
processes. This setting may also be controlled using the -P command
line switch (see above).
k
Toggle between counting all tasks, or only userspace
processes and kernel threads. This setting may also be controlled using the
-k command line switch (see above).
r
Toggle between recursively including or excluding
processes in child control groups in control group process counts. This
setting may also be controlled using the --recursive= command line
switch. This key is not available if all tasks are counted, it is only
available if processes are counted, as enabled with the P or k keys.
EXIT STATUS¶
On success, 0 is returned, a non-zero failure code otherwise.
