1PW-TOP(1) General Commands Manual PW-TOP(1)
2
6 pw-top - The PipeWire process viewer
7
9 pw-top [options]
10
13 The pw-top program provides a dynamic real-time view of the pipewire
14 node and device statistics.
15 A hierarchical view is shown of Driver nodes and follower nodes. The
17 Driver nodes are actively using a timer to schedule dataflow in the
18 followers. The followers of a driver node as shown below their driver
19 with a + sign in a tree-like representation.
20 The columns presented are as follows:
22 S Measurement status. ! representing inactive - no connections
24 Blank representing active
26 ID The ID of the pipewire node/device, as found in pw-dump
28 QUANT The current quantum (for drivers) and the suggested quantum for
30 follower nodes.
31 The quantum by itself needs to be divided by the RATE column to
33 calculate the duration of a scheduling period in fractions of a
34 second.
35 For a QUANT of 1024 and a RATE of 48000, the duration of one pe‐
37 riod in the graph is 1024/48000 or 21.3 milliseconds.
38 Follower nodes can have a 0 QUANT field, which means that the
40 node does not have a suggestion for the quantum and thus uses
41 what the driver selected.
42 The driver will use the lowest quantum of any of the followers.
44 If none of the followers select a quantum, the default quantum
45 in the pipewire configuration file will be used.
46 The QUANT on the drivers usually translates directly into the
48 number of audio samples processed per processing cycle of the
49 graph.
50 See also
52 https://gitlab.freedesktop.org/pipewire/pipewire/-/wikis/FAQ#pipewire-buffering-explained
53 RATE The current rate (for drivers) and the suggested rate for fol‐
55 lower nodes.
56 This is the rate at which the graph processes data and needs to
58 be combined with the QUANT value to derive the duration of a
59 processing cycle in the graph.
60 Some nodes can have a 0 RATE, which means that they don't have
62 any rate suggestion for the graph. Nodes that suggest a rate can
63 make the graph switch rates if the graph is otherwise idle and
64 the new rate is allowed as a possible graph rate (see the
65 pipewire configuration file).
66 The RATE on (audio) driver nodes usually also translates di‐
68 rectly to the samplerate used by the device. Although some de‐
69 vices might not be able to operate at the given samplerate, in
70 which case resampling will need to be done.
71 WAIT The waiting time of a node is the elapsed time between when the
73 node is ready to start processing and when it actually started
74 processing.
75 For Driver nodes, this is the time between when the node wakes
77 up to start processing the graph and when the driver (and thus
78 also the graph) completes a cycle. The WAIT time for driver is
79 thus the elapsed time processing the graph.
80 For follower nodes, it is the time spent between being woken up
82 (when all dependencies of the node are satisfied) and when pro‐
83 cessing starts. The WAIT time for follower nodes is thus mostly
84 caused by context switching.
85 A value of --- means that the node was not signaled. A value of
87 +++ means that the node was signaled but not awake.
88 BUSY The processing time is started when the node starts processing
90 until it completes and wakes up the next nodes in the graph.
91 A value of --- means that the node was not started. A value of
93 +++ means that the node was started but did not complete.
94 W/Q Ratio of WAIT / QUANT.
96 The W/Q time of the driver node is a good measure of the graph
98 load. The running averages of the driver W/Q ratios are used as
99 the DSP load in other (JACK) tools.
100 Values of --- and +++ are copied from the WAIT column.
102 B/Q Ratio of BUSY / QUANT
104 This is a good measure of the load of a particular driver or
106 follower node.
107 Values of --- and +++ are copied from the BUSY column.
109 ERR Total of Xruns and Errors
111 Xruns for drivers are when the graph did not complete a cycle.
113 This can be because a node in the graph also has an Xrun. It can
114 also be caused when scheduling delays cause a deadline to be
115 missed, causing a hardware Xrun.
116 Xruns for followers are incremented when the node started pro‐
118 cessing but did not complete before the end of the graph cycle
119 deadline.
120 NAME Name assigned to the device/node, as found in pw-dump node.name
122 Names are prefixed by + when they are linked to a driver (entry
124 above with no +)
125
127 -h | --help
128 Show help.
129 -r | --remote=NAME
131 The name the remote instance to monitor. If left unspecified, a
132 connection is made to the default PipeWire instance.
133 --version
135 Show version information.
136
138 The PipeWire Developers <‐
139 https://gitlab.freedesktop.org/pipewire/pipewire/issues>; PipeWire is
140 available from https://pipewire.org
141
143 pipewire(1),
144 PW-TOP(1)