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

NAME

6       dbstat - Collect histograms of MySQL/PostgreSQL query latencies.
7

SYNOPSIS

9       dbstat  [-v]  [-p  PID  [PID  ...]]  [-m  THRESHOLD] [-u] [-i INTERVAL]
10       {mysql,postgres}
11

DESCRIPTION

13       This traces queries served by a MySQL or PostgreSQL  server,  and  col‐
14       lects  a  histogram of query latencies. The histogram is printed at the
15       end of collection, or at specified intervals.
16
17       This uses User Statically-Defined  Tracing  (USDT)  probes,  a  feature
18       added  to MySQL and PostgreSQL for DTrace support, but which may not be
19       enabled on a given installation. See requirements.
20
21       Since this uses BPF, only the root user can use this tool.
22

REQUIREMENTS

24       CONFIG_BPF, bcc, and MySQL server with USDT probe support (when config‐
25       uring  the  build:  -DENABLE_DTRACE=1)  or  PostgreSQL server with USDT
26       probe support (when configuring the build: --enable-dtrace).
27

OPTIONS

29       -h Print usage message.
30
31       -p PID Trace this PID. If no PID is specified, the tool will attempt to
32              automatically  detect  the MySQL or PostgreSQL processes running
33              on the system.
34
35       -m THRESHOLD
36              Minimum query latency  (duration)  to  trace,  in  milliseconds.
37              Default is all queries.
38
39       -u     Display query latencies in microseconds (default: milliseconds).
40
41       -i INTERVAL
42              Print summaries (histograms) at this interval, specified in sec‐
43              onds.
44
45       {mysql,postgres}
46              The database engine to trace.
47

EXAMPLES

49       Display histogram of MySQL query latencies:
50              # dbstat mysql
51
52       Display histogram of PostgreSQL query latencies slower than 10ms in pid
53       408:
54              # dbstat postgres -p 408 -m 10
55
56       Display histogram of PostgreSQL query latencies at 3-second intervals:
57              # dbstat postgres -i 3
58

OVERHEAD

60       This  adds low-overhead instrumentation to queries, and only emits out‐
61       put data from kernel to user-level if they query exceeds the threshold.
62       If  the  server  query  rate  is  less  than 1,000/sec, the overhead is
63       expected to be negligible. If the query rate is higher, test  to  gauge
64       overhead.
65

SOURCE

67       This is from bcc.
68
69              https://github.com/iovisor/bcc
70
71       Also  look  in  the bcc distribution for a companion _examples.txt file
72       containing example usage, output, and commentary for this tool.
73

OS

75       Linux
76

STABILITY

78       Unstable - in development.
79

AUTHOR

81       Sasha Goldshtein
82

SEE ALSO

84       dbslower(8)
85
86
87
88USER COMMANDS                     2017-02-15                         dbstat(8)
Impressum