1drsnoop(8)                  System Manager's Manual                 drsnoop(8)
2
3
4

NAME

6       drsnoop - Trace direct reclaim events. Uses Linux eBPF/bcc.
7

SYNOPSIS

9       drsnoop.py  [-h] [-T] [-U] [-p PID] [-t TID] [-u UID] [-d DURATION] [-n
10       name] [-v]
11

DESCRIPTION

13       drsnoop trace direct reclaim events, showing which processes are alloc‐
14       ing  pages  with  direct reclaiming. This can be useful for discovering
15       when allocstall (/p- roc/vmstat) continues to increase, whether  it  is
16       caused by some critical proc- esses or not.
17
18       This  works  by  tracing  the direct reclaim events using kernel trace‐
19       points.
20
21       This makes use of a Linux 4.4  feature  (bpf_perf_event_output());  for
22       kernels  older than 4.4, see the version under tools/old, which uses an
23       older mechanism.
24
25       Since this uses BPF, only the root user can use this tool.
26

REQUIREMENTS

28       CONFIG_BPF and bcc.
29

OPTIONS

31       -h     Print usage message.
32
33       -T     Include a timestamp column.
34
35       -U     Show UID.
36
37       -p PID Trace this process ID only (filtered in-kernel).
38
39       -t TID Trace this thread ID only (filtered in-kernel).
40
41       -u UID Trace this UID only (filtered in-kernel).
42
43       -d DURATION
44              Total duration of trace in seconds.
45
46       -n name
47              Only print processes where its name partially matches 'name'  -v
48              verbose Run in verbose mode. Will output system memory state
49

EXAMPLES

51       Trace all direct reclaim events:
52              # drsnoop
53
54       Trace all direct reclaim events, for 10 seconds only:
55              # drsnoop -d 10
56
57       Trace all direct reclaim events, and include timestamps:
58              # drsnoop -T
59
60       Show UID:
61              # drsnoop -U
62
63       Trace PID 181 only:
64              # drsnoop -p 181
65
66       Trace UID 1000 only:
67              # drsnoop -u 1000
68
69       Trace all direct reclaim events from processes where its name partially
70       match-
71              es 'mond': # drnsnoop -n mond
72

FIELDS

74       TIME(s)
75              Time of the call, in seconds.
76
77       UID    User ID
78
79       PID    Process ID
80
81       TID    Thread ID
82
83       COMM   Process name
84

OVERHEAD

86       This traces the kernel direct reclaim tracepoints and prints output for
87       each  event.  As  the  rate  of this is generally expected to be low (<
88       1000/s), the overhead is also expected to be negligible.
89

SOURCE

91       This is from bcc.
92
93              https://github.com/iovisor/bcc
94
95       Also look in the bcc distribution for a  companion  _examples.txt  file
96       containing example usage, output, and commentary for this tool.
97

OS

99       Linux
100

STABILITY

102       Unstable - in development.
103

AUTHOR

105       Wenbo Zhang
106
107
108
109USER COMMANDS                     2019-02-20                        drsnoop(8)