From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: Clark Williams <williams@redhat.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Jin Yao <yao.jin@linux.intel.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>,
Kan Liang <kan.liang@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 23/75] perf annotate: Compute average IPC and IPC coverage per symbol
Date: Thu, 6 Dec 2018 18:25:10 -0300 [thread overview]
Message-ID: <20181206212602.20474-24-acme@kernel.org> (raw)
In-Reply-To: <20181206212602.20474-1-acme@kernel.org>
From: Jin Yao <yao.jin@linux.intel.com>
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/annotate.c | 41 +++++++++++++++++++++++++++++++++++---
tools/perf/util/annotate.h | 5 +++++
2 files changed, 43 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 6936daf89ddd..4b2b1b09b8f1 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1000,6 +1000,7 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
{
unsigned n_insn;
+ unsigned int cover_insn = 0;
u64 offset;
n_insn = annotation__count_insn(notes, start, end);
@@ -1013,21 +1014,34 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
for (offset = start; offset <= end; offset++) {
struct annotation_line *al = notes->offsets[offset];
- if (al)
+ if (al && al->ipc == 0.0) {
al->ipc = ipc;
+ cover_insn++;
+ }
+ }
+
+ if (cover_insn) {
+ notes->hit_cycles += ch->cycles;
+ notes->hit_insn += n_insn * ch->num;
+ notes->cover_insn += cover_insn;
}
}
}
void annotation__compute_ipc(struct annotation *notes, size_t size)
{
- u64 offset;
+ s64 offset;
if (!notes->src || !notes->src->cycles_hist)
return;
+ notes->total_insn = annotation__count_insn(notes, 0, size - 1);
+ notes->hit_cycles = 0;
+ notes->hit_insn = 0;
+ notes->cover_insn = 0;
+
pthread_mutex_lock(¬es->lock);
- for (offset = 0; offset < size; ++offset) {
+ for (offset = size - 1; offset >= 0; --offset) {
struct cyc_hist *ch;
ch = ¬es->src->cycles_hist[offset];
@@ -2563,6 +2577,22 @@ static void disasm_line__write(struct disasm_line *dl, struct annotation *notes,
disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset);
}
+static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
+{
+ double ipc = 0.0, coverage = 0.0;
+
+ if (notes->hit_cycles)
+ ipc = notes->hit_insn / ((double)notes->hit_cycles);
+
+ if (notes->total_insn) {
+ coverage = notes->cover_insn * 100.0 /
+ ((double)notes->total_insn);
+ }
+
+ scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
+ ipc, coverage);
+}
+
static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
bool first_line, bool current_entry, bool change_color, int width,
void *obj, unsigned int percent_type,
@@ -2658,6 +2688,11 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
"Cycle(min/max)");
}
+
+ if (show_title && !*al->line) {
+ ipc_coverage_string(bf, sizeof(bf), notes);
+ obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf);
+ }
}
obj__printf(obj, " ");
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 5399ba2321bb..fb6463730ba4 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -64,6 +64,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
#define ANNOTATION__IPC_WIDTH 6
#define ANNOTATION__CYCLES_WIDTH 6
#define ANNOTATION__MINMAX_CYCLES_WIDTH 19
+#define ANNOTATION__AVG_IPC_WIDTH 36
struct annotation_options {
bool hide_src_code,
@@ -262,6 +263,10 @@ struct annotation {
pthread_mutex_t lock;
u64 max_coverage;
u64 start;
+ u64 hit_cycles;
+ u64 hit_insn;
+ unsigned int total_insn;
+ unsigned int cover_insn;
struct annotation_options *options;
struct annotation_line **offsets;
int nr_events;
--
2.19.2
next prev parent reply other threads:[~2018-12-06 21:25 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-06 21:24 [GIT PULL 00/75] perf/core improvements and fixes Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 01/75] perf build: Give better hint about devel package for libssl Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 02/75] perf stat: Fix shadow stats for clock events Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 03/75] perf stat: Fix CSV mode column output for non-cgroup events Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 04/75] perf map: Remove extra indirection from map__find() Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 05/75] perf env: Also consider env->arch == NULL as local operation Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 06/75] perf machine: Record if a arch has a single user/kernel address space Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 07/75] perf thread: Add fallback functions for cases where cpumode is insufficient Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 08/75] perf tools: Use fallback for sample_addr_correlates_sym() cases Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 09/75] perf script: Use fallbacks for branch stacks Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 10/75] tools lib traceevent: Fix compile warnings in tools/lib/traceevent/event-parse.c Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 11/75] perf tests record: Allow for 'sleep' being 'coreutils' Arnaldo Carvalho de Melo
2018-12-06 21:24 ` [PATCH 12/75] perf test: Fix perf_event_attr test failure Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 13/75] tools include: Adopt ERR_CAST() from the kernel err.h header Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 14/75] perf bpf: Use ERR_CAST instead of ERR_PTR(PTR_ERR()) Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 15/75] perf top: Allow passing a kallsyms file Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 16/75] perf intel-pt: Fix error with config term "pt=0" Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 17/75] tools build feature: Check if libaio is available Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 18/75] perf mmap: Map data buffer for preserving collected data Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 19/75] perf record: Enable asynchronous trace writing Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 20/75] perf record: Extend trace writing to multi AIO Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 21/75] perf beauty mmap_flags: Check if the arch has a mmap.h file Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 22/75] tools lib traceevent: Add sanity check to is_timestamp_in_us() Arnaldo Carvalho de Melo
2018-12-06 21:25 ` Arnaldo Carvalho de Melo [this message]
2018-12-06 21:25 ` [PATCH 24/75] perf annotate: Create a annotate2 flag in struct symbol Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 25/75] perf report: Display average IPC and IPC coverage per symbol Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 26/75] perf report: Documentation average IPC and IPC coverage Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 27/75] tools lib traceevent: Implement new API tep_get_ref() Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 28/75] tools lib traceevent: Added support for pkg-config Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 29/75] tools lib traceevent: Install trace-seq.h API header file Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 30/75] tools lib traceevent, perf tools: Rename 'struct tep_event_format' to 'struct tep_event' Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 31/75] tools lib traceevent: Rename tep_free_format() to tep_free_event() Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 32/75] perf tools: traceevent API cleanup, remove __tep_data2host*() Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 33/75] tools lib traceevent: traceevent API cleanup Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 34/75] perf beauty mmap_flags: Fixed syntax error Fixed missing ']' error Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 35/75] perf cs-etm: Support for ARM A32/T32 instruction sets in CoreSight trace Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 36/75] perf tests ARM: Disable breakpoint tests 32-bit Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 37/75] perf vendor events intel: Fix diverse typos Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 38/75] tools lib traceevent: Fix diverse typos in comments Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 39/75] perf tools Documentation: Fix diverse typos Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 40/75] perf bpf-loader: Fix debugging message typo Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 41/75] perf tools: Fix diverse comment typos Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 42/75] tools lib subcmd: Fix a few source code " Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 43/75] perf tools: Allow specifying proc-map-timeout in config file Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 44/75] perf trace: We need to consider "nr" if "__syscall_nr" is not there Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 45/75] perf tools: Support 'srccode' output Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 46/75] perf ordered_events: Rework show_progress for __ordered_events__flush Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 47/75] perf ordered_events: Add private data member Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 48/75] perf top: Save and display the lost count stats Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 49/75] perf top: Move lost events warning to helpline Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 50/75] perf top: Add processing thread Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 51/75] perf top: Use cond variable instead of a lock Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 52/75] perf top: Set the 'session_done' volatile variable when exiting Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 53/75] perf top: Drop samples which are behind the refresh rate Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 54/75] perf top: Save and display the drop count stats Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 55/75] perf top: Display slow reader warning when droping samples Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 56/75] perf top: Move perf_top__reset_sample_counters() to after counts display Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 57/75] perf cs-etm: Add configuration for ETMv3 trace protocol Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 58/75] perf cs-etm: Add support for ETMv3 trace decoding Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 59/75] perf cs-etm: Add support for PTMv1.1 decoding Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 60/75] perf dso: Fix unchecked usage of strncpy() Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 61/75] perf header: " Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 62/75] " Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 63/75] perf help: Remove needless use " Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 64/75] perf svghelper: Fix unchecked usage " Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 65/75] perf ui helpline: Use strlcpy() as a shorter form of strncpy() + explicit set nul Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 66/75] perf probe: Fix unchecked usage of strncpy() Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 67/75] perf parse-events: " Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 68/75] perf vendor events intel: Fix Load_Miss_Real_Latency on SKL/SKX Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 69/75] perf record: Fix memory leak on AIO objects deallocation Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 70/75] perf config: Modify size factor of snprintf Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 71/75] perf annotate: Introduce basic support for ARC Arnaldo Carvalho de Melo
2018-12-06 21:25 ` [PATCH 72/75] perf ordered_events: Add ordered_events__flush_time interface Arnaldo Carvalho de Melo
2018-12-06 21:26 ` [PATCH 73/75] perf trace: Move event delivery to a new deliver_event() function Arnaldo Carvalho de Melo
2018-12-06 21:26 ` [PATCH 74/75] perf ordered_events: Add first_time() method Arnaldo Carvalho de Melo
2018-12-06 21:26 ` [PATCH 75/75] perf trace: Add ordered processing Arnaldo Carvalho de Melo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181206212602.20474-24-acme@kernel.org \
--to=acme@kernel.org \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=williams@redhat.com \
--cc=yao.jin@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).