2009-06-06 20:56:33 +08:00
|
|
|
|
perf-list(1)
|
2008-04-16 04:39:31 +08:00
|
|
|
|
============
|
2009-06-06 20:56:33 +08:00
|
|
|
|
|
|
|
|
|
|
NAME
|
|
|
|
|
|
----
|
|
|
|
|
|
perf-list - List all symbolic event types
|
|
|
|
|
|
|
|
|
|
|
|
SYNOPSIS
|
|
|
|
|
|
--------
|
|
|
|
|
|
[verse]
|
2013-04-21 02:02:29 +08:00
|
|
|
|
'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
|
2009-06-06 20:56:33 +08:00
|
|
|
|
|
|
|
|
|
|
DESCRIPTION
|
|
|
|
|
|
-----------
|
|
|
|
|
|
This command displays the symbolic event types which can be selected in the
|
|
|
|
|
|
various perf commands with the -e option.
|
|
|
|
|
|
|
2012-08-08 01:43:15 +08:00
|
|
|
|
[[EVENT_MODIFIERS]]
|
2010-10-15 09:51:00 +08:00
|
|
|
|
EVENT MODIFIERS
|
|
|
|
|
|
---------------
|
|
|
|
|
|
|
2014-09-09 23:18:50 +08:00
|
|
|
|
Events can optionally have a modifier by appending a colon and one or
|
2012-08-08 01:43:16 +08:00
|
|
|
|
more modifiers. Modifiers allow the user to restrict the events to be
|
|
|
|
|
|
counted. The following modifiers exist:
|
|
|
|
|
|
|
|
|
|
|
|
u - user-space counting
|
|
|
|
|
|
k - kernel counting
|
|
|
|
|
|
h - hypervisor counting
|
|
|
|
|
|
G - guest counting (in KVM guests)
|
|
|
|
|
|
H - host counting (not in KVM guests)
|
|
|
|
|
|
p - precise level
|
2012-10-10 23:39:03 +08:00
|
|
|
|
S - read sample value (PERF_SAMPLE_READ)
|
perf tools: Add support for pinned modifier
This commit adds support for a new modifier "D", which requests that the
event, or group of events, be pinned to the PMU.
The "p" modifier is already taken for precise, and "P" may be used in
future to mean "fully precise".
So we use "D", which stands for pinneD - and looks like a padlock, or if
you're using the ":D" syntax perf smiles at you.
This is an oft-requested feature from our HW folks, who want to be able
to run a large number of events, but also want 100% accurate results for
instructions per cycle.
Comparison of results with and without pinning:
$ perf stat -e '{cycles,instructions}:D' -e cycles,instructions,...
79,590,480,683 cycles # 0.000 GHz
166,123,716,524 instructions # 2.09 insns per cycle
# 0.11 stalled cycles per insn
79,352,134,463 cycles # 0.000 GHz [11.11%]
165,178,301,818 instructions # 2.08 insns per cycle
# 0.11 stalled cycles per insn [11.13%]
As you can see although perf does a very good job of scaling the values
in the non-pinned case, there is some small discrepancy.
The patch is fairly straight forward, the one detail is that we need to
make sure we only request pinning for the group leader when we have a
group.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1375795686-4226-1-git-send-email-michael@ellerman.id.au
[ Use perf_evsel__is_group_leader instead of open coded equivalent, as
suggested by Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-06 21:28:05 +08:00
|
|
|
|
D - pin the event to the PMU
|
2010-10-15 09:51:00 +08:00
|
|
|
|
|
|
|
|
|
|
The 'p' modifier can be used for specifying how precise the instruction
|
2012-08-08 01:43:16 +08:00
|
|
|
|
address should be. The 'p' modifier can be specified multiple times:
|
|
|
|
|
|
|
|
|
|
|
|
0 - SAMPLE_IP can have arbitrary skid
|
|
|
|
|
|
1 - SAMPLE_IP must have constant skid
|
|
|
|
|
|
2 - SAMPLE_IP requested to have 0 skid
|
|
|
|
|
|
3 - SAMPLE_IP must have 0 skid
|
|
|
|
|
|
|
|
|
|
|
|
For Intel systems precise event sampling is implemented with PEBS
|
|
|
|
|
|
which supports up to precise-level 2.
|
|
|
|
|
|
|
|
|
|
|
|
On AMD systems it is implemented using IBS (up to precise-level 2).
|
|
|
|
|
|
The precise modifier works with event types 0x76 (cpu-cycles, CPU
|
|
|
|
|
|
clocks not halted) and 0xC1 (micro-ops retired). Both events map to
|
|
|
|
|
|
IBS execution sampling (IBS op) with the IBS Op Counter Control bit
|
|
|
|
|
|
(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
|
|
|
|
|
|
Manual Volume 2: System Programming, 13.3 Instruction-Based
|
|
|
|
|
|
Sampling). Examples to use IBS:
|
2010-10-15 09:51:00 +08:00
|
|
|
|
|
2012-08-08 01:43:16 +08:00
|
|
|
|
perf record -a -e cpu-cycles:p ... # use ibs op counting cycles
|
|
|
|
|
|
perf record -a -e r076:p ... # same as -e cpu-cycles:p
|
|
|
|
|
|
perf record -a -e r0C1:p ... # use ibs op counting micro-ops
|
2010-10-15 09:51:00 +08:00
|
|
|
|
|
2010-05-05 22:20:05 +08:00
|
|
|
|
RAW HARDWARE EVENT DESCRIPTOR
|
|
|
|
|
|
-----------------------------
|
|
|
|
|
|
Even when an event is not available in a symbolic form within perf right now,
|
2010-05-08 01:07:05 +08:00
|
|
|
|
it can be encoded in a per processor specific way.
|
|
|
|
|
|
|
|
|
|
|
|
For instance For x86 CPUs NNN represents the raw register encoding with the
|
|
|
|
|
|
layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
|
|
|
|
|
|
of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
|
|
|
|
|
|
Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
|
|
|
|
|
|
|
2012-08-08 01:43:15 +08:00
|
|
|
|
Note: Only the following bit fields can be set in x86 counter
|
|
|
|
|
|
registers: event, umask, edge, inv, cmask. Esp. guest/host only and
|
|
|
|
|
|
OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT
|
|
|
|
|
|
MODIFIERS>>.
|
|
|
|
|
|
|
2010-05-08 01:07:05 +08:00
|
|
|
|
Example:
|
|
|
|
|
|
|
|
|
|
|
|
If the Intel docs for a QM720 Core i7 describe an event as:
|
2010-05-05 22:20:05 +08:00
|
|
|
|
|
|
|
|
|
|
Event Umask Event Mask
|
|
|
|
|
|
Num. Value Mnemonic Description Comment
|
|
|
|
|
|
|
|
|
|
|
|
A8H 01H LSD.UOPS Counts the number of micro-ops Use cmask=1 and
|
|
|
|
|
|
delivered by loop stream detector invert to count
|
|
|
|
|
|
cycles
|
|
|
|
|
|
|
|
|
|
|
|
raw encoding of 0x1A8 can be used:
|
|
|
|
|
|
|
|
|
|
|
|
perf stat -e r1a8 -a sleep 1
|
|
|
|
|
|
perf record -e r1a8 ...
|
|
|
|
|
|
|
2010-05-08 01:07:05 +08:00
|
|
|
|
You should refer to the processor specific documentation for getting these
|
|
|
|
|
|
details. Some of them are referenced in the SEE ALSO section below.
|
|
|
|
|
|
|
2009-06-06 20:56:33 +08:00
|
|
|
|
OPTIONS
|
|
|
|
|
|
-------
|
2011-02-18 01:38:58 +08:00
|
|
|
|
|
|
|
|
|
|
Without options all known events will be listed.
|
|
|
|
|
|
|
|
|
|
|
|
To limit the list use:
|
|
|
|
|
|
|
|
|
|
|
|
. 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
|
|
|
|
|
|
|
|
|
|
|
|
. 'sw' or 'software' to list software events such as context switches, etc.
|
|
|
|
|
|
|
|
|
|
|
|
. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
|
|
|
|
|
|
|
|
|
|
|
|
. 'tracepoint' to list all tracepoint events, alternatively use
|
|
|
|
|
|
'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
|
|
|
|
|
|
block, etc.
|
|
|
|
|
|
|
2013-04-21 02:02:29 +08:00
|
|
|
|
. 'pmu' to print the kernel supplied PMU events.
|
|
|
|
|
|
|
2011-02-18 01:38:58 +08:00
|
|
|
|
. If none of the above is matched, it will apply the supplied glob to all
|
|
|
|
|
|
events, printing the ones that match.
|
|
|
|
|
|
|
|
|
|
|
|
One or more types can be used at the same time, listing the events for the
|
|
|
|
|
|
types specified.
|
2009-06-06 20:56:33 +08:00
|
|
|
|
|
|
|
|
|
|
SEE ALSO
|
|
|
|
|
|
--------
|
|
|
|
|
|
linkperf:perf-stat[1], linkperf:perf-top[1],
|
2010-05-08 01:07:05 +08:00
|
|
|
|
linkperf:perf-record[1],
|
|
|
|
|
|
http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
|
2012-08-08 01:43:16 +08:00
|
|
|
|
http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
|
