Lines Matching refs:e
52 Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
54 perf record -e intel_pt//u ls
56 And profiled with 'perf report' e.g.
67 ~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
76 selected for reporting. e.g. sample every microsecond
94 perf record -e intel_pt//u ls
133 An enhancement has been made to allow default "config" e.g. the option
135 -e intel_pt//
139 -e intel_pt/tsc,noretcomp=0/
143 -e intel_pt/tsc=1,noretcomp=0/
161 Note that the default config must be overridden for each term i.e.
163 -e intel_pt/noretcomp=0/
167 -e intel_pt/tsc=1,noretcomp=0/
171 -e intel_pt/tsc=0/
175 -e intel_pt/config=0x400/
190 perf_event_attr is displayed if the -vv option is used e.g.
227 The default config selects tsc (i.e. tsc=1).
233 The default config does not select noretcomp (i.e. noretcomp=0).
252 valid values e.g. bit 2 set means value 2 is valid.
259 e.g. value 3 means 16KiB bytes between PSBs
262 will give a list of valid values e.g.
264 $ perf record -e intel_pt/psb_period=15/u uname
268 of 3 (i.e. psb_period=3) or the nearest lower value that is
302 valid values e.g. bit 2 set means value 2 is valid.
308 e.g. value 3 means one eighth of CTC-frequency
314 will give a list of valid values e.g.
316 $ perf record -e intel_pt/mtc_period=15/u uname
347 valid values e.g. bit 2 set means value 2 is valid.
355 e.g. value 4 means 8 CPU cycles must pass before a CYC packet
357 packet is sent, not at, e.g. every 8 CPU cycles.
360 will give a list of valid values e.g.
362 $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
382 Optionally it can be followed by the snapshot size e.g.
392 The snapshot size is displayed if the option -vv is used e.g.
400 Intel PT buffer size is specified by an addition to the -m option e.g.
404 selects a buffer size of 16 pages i.e. 64KiB.
424 The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
437 Full-trace mode traces continuously e.g.
439 perf record -e intel_pt//u uname
441 Snapshot mode captures the available data when a signal is sent e.g.
443 perf record -v -e intel_pt//u -S ./loopy 1000000000 &
458 There may be buffer limitations (i.e. single ToPa entry) which means that actual
532 command to run (i.e. the workload).
537 In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
567 decoding. sched_switch events are automatically added. e.g. the second event
570 $ perf record -vv -e intel_pt//u uname
671 e synthesize tracing error events
676 "Instructions" events look like they were recorded by "perf record -e
679 "Branches" events look like they were recorded by "perf record -e branches". "c"
694 In addition, the period of the "instructions" event can be specified. e.g.
698 sets the period to 10us i.e. one instruction sample is synthesized for each 10
714 'instructions' (i.e. --itrace=i1i).
717 transactions events can be specified. e.g.
723 transactions events can be specified. e.g.
737 perf script has an option (-D) to "dump" the events i.e. display the binary
764 removed and replaced with the synthesized events. e.g.
782 $ perf record -e intel_pt//u ./sort 3000