xref: /linux/tools/perf/Documentation/itrace.txt (revision 26fbb4c8c7c3ee9a4c3b4de555a8587b5a19154e)
1		i	synthesize instructions events
2		b	synthesize branches events (branch misses for Arm SPE)
3		c	synthesize branches events (calls only)
4		r	synthesize branches events (returns only)
5		x	synthesize transactions events
6		w	synthesize ptwrite events
7		p	synthesize power events
8		o	synthesize other events recorded due to the use
9			of aux-output (refer to perf record)
10		e	synthesize error events
11		d	create a debug log
12		f	synthesize first level cache events
13		m	synthesize last level cache events
14		M	synthesize memory events
15		t	synthesize TLB events
16		a	synthesize remote access events
17		g	synthesize a call chain (use with i or x)
18		G	synthesize a call chain on existing event records
19		l	synthesize last branch entries (use with i or x)
20		L	synthesize last branch entries on existing event records
21		s       skip initial number of events
22		q	quicker (less detailed) decoding
23
24	The default is all events i.e. the same as --itrace=ibxwpe,
25	except for perf script where it is --itrace=ce
26
27	In addition, the period (default 100000, except for perf script where it is 1)
28	for instructions events can be specified in units of:
29
30		i	instructions
31		t	ticks
32		ms	milliseconds
33		us	microseconds
34		ns	nanoseconds (default)
35
36	Also the call chain size (default 16, max. 1024) for instructions or
37	transactions events can be specified.
38
39	Also the number of last branch entries (default 64, max. 1024) for
40	instructions or transactions events can be specified.
41
42	Similar to options g and l, size may also be specified for options G and L.
43	On x86, note that G and L work poorly when data has been recorded with
44	large PEBS. Refer linkperf:perf-intel-pt[1] man page for details.
45
46	It is also possible to skip events generated (instructions, branches, transactions,
47	ptwrite, power) at the beginning. This is useful to ignore initialization code.
48
49	--itrace=i0nss1000000
50
51	skips the first million instructions.
52
53	The 'e' option may be followed by flags which affect what errors will or
54	will not be reported. Each flag must be preceded by either '+' or '-'.
55	The flags are:
56		o	overflow
57		l	trace data lost
58
59	If supported, the 'd' option may be followed by flags which affect what
60	debug messages will or will not be logged. Each flag must be preceded
61	by either '+' or '-'. The flags are:
62		a	all perf events
63
64	If supported, the 'q' option may be repeated to increase the effect.
65