1dbslower(8) System Manager's Manual dbslower(8)
2
3
4
6 dbslower - Trace MySQL/PostgreSQL server queries slower than a thresh‐
7 old.
8
10 dbslower [-v] [-p PID [PID ...]] [-x PATH] [-m THRESHOLD] {mysql,post‐
11 gres}
12
14 This traces queries served by a MySQL or PostgreSQL server, and prints
15 those that exceed a latency (query time) threshold. By default a
16 threshold of 1 ms is used.
17
18 This uses User Statically-Defined Tracing (USDT) probes, a feature
19 added to MySQL and PostgreSQL for DTrace support, but which may not be
20 enabled on a given installation. See requirements. Alternativly, MySQL
21 queries can be traced without the USDT support using the -x option.
22
23 Since this uses BPF, only the root user can use this tool.
24
26 CONFIG_BPF, bcc, and MySQL server with USDT probe support (when config‐
27 uring the build: -DENABLE_DTRACE=1) or PostgreSQL server with USDT
28 probe support (when configuring the build: --enable-dtrace).
29
31 -h Print usage message.
32
33 -p PID Trace this PID. If no PID is specified, the tool will attempt to
34 automatically detect the MySQL or PostgreSQL processes running
35 on the system.
36
37 -x PATH
38 Path to MySQL binary. This option allow to MySQL queries even
39 when USDT probes aren't enabled on the MySQL server.
40
41 -m THRESHOLD
42 Minimum query latency (duration) to trace, in milliseconds.
43 Default is 1 ms.
44
45 {mysql,postgres}
46 The database engine to trace.
47
49 Trace MySQL server queries slower than 1 ms:
50 # dbslower mysql
51
52 Trace slower than 10 ms for PostgreSQL in process 408:
53 # dbslower postgres -p 408 -m 10
54
56 TIME(s)
57 Time of query start, in seconds.
58
59 PID Process ID of the traced server.
60
61 MS Milliseconds for the query, from start to end.
62
63 QUERY Query string, truncated to 256 characters.
64
66 This adds low-overhead instrumentation to queries, and only emits out‐
67 put data from kernel to user-level if they query exceeds the threshold.
68 If the server query rate is less than 1,000/sec, the overhead is
69 expected to be negligible. If the query rate is higher, test to gauge
70 overhead.
71
73 This is from bcc.
74
75 https://github.com/iovisor/bcc
76
77 Also look in the bcc distribution for a companion _examples.txt file
78 containing example usage, output, and commentary for this tool.
79
81 Linux
82
84 Unstable - in development.
85
87 Sasha Goldshtein, Brendan Gregg
88
90 biosnoop(8), mysqld_qslower(8), dbstat(8)
91
92
93
94USER COMMANDS 2017-02-15 dbslower(8)