1 perf-mem(1)
2 ===========
3
4 NAME
5 ----
6 perf-mem - Profile memory accesses
7
8 SYNOPSIS
9 --------
10 [verse]
11 'perf mem' [<options>] (record [<command>] | r
12
13 DESCRIPTION
14 -----------
15 "perf mem record" runs a command and gathers m
16 from it, into perf.data. Perf record options a
17
18 "perf mem report" displays the result. It invo
19 right set of options to display a memory acces
20 and stores are sampled. Use the -t option to l
21
22 Note that on Intel systems the memory latency
23 not the pure load (or store latency). Use late
24 queuing delays in addition to the memory subsy
25
26 On Arm64 this uses SPE to sample load and stor
27 and kernel support is required. See linkperf:p
28 Due to the statistical nature of SPE sampling,
29 be sampled.
30
31 COMMON OPTIONS
32 --------------
33 -f::
34 --force::
35 Don't do ownership validation
36
37 -t::
38 --type=<type>::
39 Select the memory operation type: load
40
41 -v::
42 --verbose::
43 Be more verbose (show counter open err
44
45 -p::
46 --phys-data::
47 Record/Report sample physical addresse
48
49 --data-page-size::
50 Record/Report sample data address page
51
52 RECORD OPTIONS
53 --------------
54 <command>...::
55 Any command you can specify in a shell
56
57 -e::
58 --event <event>::
59 Event selector. Use 'perf mem record -
60
61 -K::
62 --all-kernel::
63 Configure all used events to run in ke
64
65 -U::
66 --all-user::
67 Configure all used events to run in us
68
69 --ldlat <n>::
70 Specify desired latency for loads even
71 processors only. Ignored on other arch
72
73 REPORT OPTIONS
74 --------------
75 -i::
76 --input=<file>::
77 Input file name.
78
79 -C::
80 --cpu=<cpu>::
81 Monitor only on the list of CPUs provi
82 comma-separated list with no space: 0,
83 like 0-2. Default is to monitor all CP
84
85 -D::
86 --dump-raw-samples::
87 Dump the raw decoded samples on the sc
88 one sample per line.
89
90 -s::
91 --sort=<key>::
92 Group result by given key(s) - multipl
93 in CSV format. The keys are specific
94 symbol_daddr, symbol_iaddr, dso_daddr,
95 dcacheline, phys_daddr, data_page_size
96
97 - symbol_daddr: name of data symbol be
98 - symbol_iaddr: name of code symbol be
99 - dso_daddr: name of library or module
100 on at the time of the sam
101 - locked: whether the bus was locked a
102 - tlb: type of tlb access for the data
103 - mem: type of memory access for the d
104 - snoop: type of snoop (if any) for th
105 - dcacheline: the cacheline the data a
106 - phys_daddr: physical address of data
107 - data_page_size: the data page size o
108 - blocked: reason of blocked load acce
109
110 And the default sort keys are changed
111 symbol_daddr, dso_daddr, snoop, tlb, l
112
113 -T::
114 --type-profile::
115 Show data-type profile result instead
116 the debug information and it will chan
117 mem, snoop, tlb, type.
118
119 -U::
120 --hide-unresolved::
121 Only display entries resolved to a sym
122
123 -x::
124 --field-separator=<separator>::
125 Specify the field separator used when
126 The separator is the space character.
127
128 In addition, for report all perf report option
129 all perf record options.
130
131 SEE ALSO
132 --------
133 linkperf:perf-record[1], linkperf:perf-report[
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.