perf: Stream comparison
v6 cover perf: Stream comparison
Sometimes, a small change in a hot function reducing the cycles of this function, but the overall workload doesn't get faster. It is interesting where the cycles are moved to.
What it would like is to diff before/after streams. The stream is the branch history which is aggregated by the branch records from perf samples. For example, the callchains aggregated from the branch records. By browsing the hot stream, we can understand the hot code path.
By browsing the hot streams, we can understand the hot code path. By comparing the cycles variation of same streams between old perf data and new perf data, we can understand if the cycles are moved to other codes.
The before stream is the stream in perf.data.old. The after stream is the stream in perf.data.
Diffing before/after streams compares top N hottest streams between two perf data files.
If all entries of one stream in perf.data.old are fully matched with all entries of another stream in perf.data, we think two streams are matched, otherwise the streams are not matched.
For example,
cycles: 1, hits: 26.80% cycles: 1, hits: 27.30%
-------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44
The above streams are matched and we can see for the same streams the cycles (1) are equal and the callchain hit percents are slightly changed (26.80% vs. 27.30%). That's expected.
Now let's see examples.
perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream
[ Matched hot streams ]
hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44
hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98%
--------------------------- --------------------------
__random_r random_r.c:360 __random_r random_r.c:360
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:380 __random_r random_r.c:380
__random_r random_r.c:357 __random_r random_r.c:357
__random random.c:293 __random random.c:293
__random random.c:293 __random random.c:293
__random random.c:291 __random random.c:291
__random random.c:291 __random random.c:291
__random random.c:291 __random random.c:291
__random random.c:288 __random random.c:288
rand rand.c:27 rand rand.c:27
rand rand.c:26 rand rand.c:26
rand@plt rand@plt
rand@plt rand@plt
compute_flag div.c:25 compute_flag div.c:25
compute_flag div.c:22 compute_flag div.c:22
main div.c:40 main div.c:40
main div.c:40 main div.c:40
main div.c:39 main div.c:39
hot chain pair 3:
cycles: 9, hits: 4.48% cycles: 6, hits: 4.51%
--------------------------- --------------------------
__random_r random_r.c:360 __random_r random_r.c:360
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:380 __random_r random_r.c:380[ Hot streams in old perf data only ]
hot chain 1:
cycles: 18, hits: 6.75%
--------------------------
__random_r random_r.c:360
__random_r random_r.c:388
__random_r random_r.c:388
__random_r random_r.c:380
__random_r random_r.c:357
__random random.c:293
__random random.c:293
__random random.c:291
__random random.c:291
__random random.c:291
__random random.c:288
rand rand.c:27
rand rand.c:26
rand@plt
rand@plt
compute_flag div.c:25
compute_flag div.c:22
main div.c:40hot chain 2:
cycles: 29, hits: 2.78%
--------------------------
compute_flag div.c:22
main div.c:40
main div.c:40
main div.c:39[ Hot streams in new perf data only ]
hot chain 1:
cycles: 4, hits: 4.54%
--------------------------
main div.c:42
compute_flag div.c:28hot chain 2:
cycles: 5, hits: 3.51%
--------------------------
main div.c:39
main div.c:44
main div.c:42
compute_flag div.c:28 v6:
---
Rebase to perf/core
v5:
---
1. Remove enum stream_type
2. Rebase to perf/core
v4:
---
The previous version is too big and very hard for review.
1. v4 removes the code which supports the source line mapping table and remove the source line based comparison. Now we only supports the basic functionality of stream comparison.
2. Refactor the code in a generic way.
v3:
---
v2 has 14 patches, it's hard to review. v3 is only 7 patches for basic stream comparison.
Jin Yao (7):
perf util: Create streams
perf util: Get the evsel_streams by evsel_idx perf util: Compare two streams
perf util: Link stream pair
perf util: Calculate the sum of total streams hits perf util: Report hot streams
perf diff: Support hot streams comparison
tools/perf/Documentation/perf-diff.txt | 4 + tools/perf/builtin-diff.c | 133 +++++++++- tools/perf/util/Build | 1 + tools/perf/util/callchain.c | 99 ++++++++ tools/perf/util/callchain.h | 9 + tools/perf/util/stream.c | 324 +++++++++++++++++++++++++ tools/perf/util/stream.h | 34 +++ 7 files changed, 591 insertions(+), 13 deletions(-) create mode 100644 tools/perf/util/stream.c create mode 100644 tools/perf/util/stream.h
Signature · 1 line
2.17.1
PATCH v6 1/7 perf util: Create streams
We define the stream is the branch history which is aggregated by the branch records from perf samples. For example, the callchains aggregated from the branch records are considered as streams. By browsing the hot stream, we can understand the hot code path.
Now we only support the callchain for stream. For measuring the hot level for a stream, we use the callchain_node->hit, higher is hotter.
There may be many callchains sampled so we only focus on the top N hottest callchains. N is a user defined parameter or predefined default value (nr_streams_max).
This patch creates an evsel_streams array per event, and saves the top N hottest streams in a stream array.
So now we can get the per-event top N hottest streams.
---
v6:
- Rebase to perf/core
v5:
- Remove enum stram_type
- Rebase to perf/core
v4:
- Refactor the code
- Rename patch name from 'perf util: Create streams for managing top N hottest callchains' to 'perf util: Create streams'
v2:
- Use zfree in free_evsel_streams().
tools/perf/util/Build | 1 + tools/perf/util/stream.c | 148 +++++++++++++++++++++++++++++++++++++++ tools/perf/util/stream.h | 23 ++++++ 3 files changed, 172 insertions(+) create mode 100644 tools/perf/util/stream.c create mode 100644 tools/perf/util/stream.h
tools/perf/util/Build +1 -0
@@ -101,6 +101,7 @@ perf-y += call-path.o perf-y += rwsem.o perf-y += thread-stack.o perf-y += spark.o +perf-y += stream.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ perf-$(CONFIG_AUXTRACE) += intel-pt.o
tools/perf/util/stream.c new file +148 -0
148 lines not on this page · raw message
tools/perf/util/stream.h new file +23 -0
@@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_STREAM_H +#define __PERF_STREAM_H + +#include "callchain.h" + +struct stream { +struct callchain_node *cnode; +}; + +struct evsel_streams { +struct stream *streams; +int nr_streams_max; +int nr_streams; +int evsel_idx; +}; + +struct evlist ; + +struct evsel_streams *perf_evlist__create_streams (struct evlist *evlist, +int nr_streams_max); + +#endif /* __PERF_STREAM_H */
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v6 1/7] perf util: Create streams
Em Fri, Sep 11, 2020 at 04:03:47PM +0800, Jin Yao escreveu:
Quoted 67 lines
We define the stream is the branch history which is aggregated by the branch records from perf samples. For example, the callchains aggregated from the branch records are considered as streams. By browsing the hot stream, we can understand the hot code path.
Now we only support the callchain for stream. For measuring the hot level for a stream, we use the
callchain_node->hit, higher is hotter.There may be many callchains sampled so we only focus on the top N hottest callchains. N is a user defined parameter or predefined default value (
nr_streams_max).This patch creates an
evsel_streamsarray per event, and saves the top N hottest streams in a stream array.So now we can get the per-event top N hottest streams.
Signed-off-by Jin Yao <[email protected]>---
v6:
- Rebase to perf/corev5:
- Remove enumstram_type
- Rebase to perf/corev4:
- Refactor the code
- Rename patch name from 'perf util: Create streams for managing top N hottest callchains' to 'perf util: Create streams'v2:
- Use zfree infree_evsel_streams().tools/perf/util/Build | 1 + tools/perf/util/stream.c | 148 +++++++++++++++++++++++++++++++++++++++ tools/perf/util/stream.h | 23 ++++++ 3 files changed, 172 insertions(+) create mode 100644 tools/perf/util/stream.c create mode 100644 tools/perf/util/stream.htools/perf/util/Build +1
-0@@ -101,6 +101,7 @@ perf-y += call-path.o perf-y += rwsem.o perf-y += thread-stack.o perf-y += spark.o +perf-y += stream.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ perf-$(CONFIG_AUXTRACE) += intel-pt.otools/perf/util/stream.c new file +7
-0@@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Compare and figure out the top N hottest streams +* Copyright (c) 2020, Intel Corporation. +* Author: Jin Yao +*/ +
tools/perf/util/stream.c line 17
Quoted 10 lines
tools/perf/util/stream.c new file +10
-0+#include <inttypes.h> +#include <stdlib.h> +#include <linux/zalloc.h> +#include "debug.h" +#include "hist.h" +#include "sort.h" +#include "stream.h" +#include "evlist.h" + +static void free_evsel_streams (struct evsel_streams *es,int nr_evsel)
Please name the functions with the struct name first, followed by __ and then the method name, i.e. for this one:
static void evsel_streams__delete(struct evsel_streams *es, int nr_evsels)
One thing that made me curious is why nr_evsels (plural please) isn't in 'struct evsel_streams', why?
tools/perf/util/stream.c line 26
Quoted 9 lines
tools/perf/util/stream.c new file +9
-0+{ +for (int i =0 ; i < nr_evsel; i++) +zfree (&es[i].streams); + +free (es); +} + +static struct evsel_streams *create_evsel_streams (int nr_evsel, +int nr_streams_max)
Oh, I see, you create just an array :-\
Please rename it to:
evsel_streams__new(int nr_evsels, int nr_streams_max)
Quoted 20 lines
tools/perf/util/stream.c new file +20
-0+{ +struct evsel_streams *es; + + es =calloc (nr_evsel,sizeof (struct evsel_streams )); +if (!es) +return NULL ; + +for (int i =0 ; i < nr_evsel; i++) { +struct evsel_streams *s = &es[i]; + + s->streams =calloc (nr_streams_max,sizeof (struct stream )); +if (!s->streams) + goto err; + + s->nr_streams_max = nr_streams_max; + s->evsel_idx =-1 ; + } + +return es; +
tools/perf/util/stream.c line 56
Quoted 10 lines
tools/perf/util/stream.c new file +10
-0+err: +free_evsel_streams (es, nr_evsel); +return NULL ; +} + +/* +* The cnodes with high hit number are hot callchains. +*/ +static void set_hot_cnode (struct evsel_streams *es, +struct callchain_node *cnode)
Since it is static its kinda ok not to have the prefix, but I'd do it as:
static void evsel_streams__set_hot_cnode(...)
For ctags sake, for instance, i.e. navigate in vim using ctags.
Quoted 46 lines
tools/perf/util/stream.c new file +46
-0+{ +int i, idx =0 ; +u64 hit; + +if (es->nr_streams < es->nr_streams_max) { + i = es->nr_streams; + es->streams[i].cnode = cnode; + es->nr_streams++; +return ; + } + +/* +* Considering a few number of hot streams, only use simple +* way to find the cnode with smallest hit number and replace. +*/ + hit = (es->streams[0 ].cnode)->hit; +for (i =1 ; i < es->nr_streams; i++) { +if ((es->streams[i].cnode)->hit < hit) { + hit = (es->streams[i].cnode)->hit; + idx = i; + } + } + +if (cnode->hit > hit) + es->streams[idx].cnode = cnode; +} + +static void update_hot_callchain (struct hist_entry *he, +struct evsel_streams *es) +{ +struct rb_root *root = &he->sorted_chain; +struct rb_node *rb_node =rb_first (root); +struct callchain_node *cnode; + +while (rb_node) { + cnode = rb_entry(rb_node, struct callchain_node, rb_node); +set_hot_cnode (es, cnode); + rb_node =rb_next (rb_node); + } +} + +static void init_hot_callchain (struct hists *hists,struct evsel_streams *es) +{ +struct rb_node *next =rb_first_cached (&hists->entries); + +while (next) {
tools/perf/util/stream.c line 112
Quoted 10 lines
tools/perf/util/stream.c new file +10
-0+struct hist_entry *he; + + he = rb_entry(next, struct hist_entry, rb_node); +update_hot_callchain (he, es); + next =rb_next (&he->rb_node); + } +} + +static int evlist_init_callchain_streams (struct evlist *evlist, +struct evsel_streams *es,int nr_es)
So here we miss just one extra _, i.e.:
+static int evlist__init_callchain_streams(struct evlist *evlist,
+ struct evsel_streams *es, int nr_es)
Quoted 10 lines
tools/perf/util/stream.c new file +10
-0+{ +struct evsel *pos; +int i =0 ; + +BUG_ON (nr_es < evlist->core.nr_entries); + +evlist__for_each_entry (evlist, pos) { +struct hists *hists =evsel__hists (pos); + +hists__output_resort (hists,NULL );
tools/perf/util/stream.c line 132
Quoted 10 lines
tools/perf/util/stream.c new file +10
-0+init_hot_callchain (hists, &es[i]); + es[i].evsel_idx = pos->idx; + i++; + } + +return 0 ; +} + +struct evsel_streams *perf_evlist__create_streams (struct evlist *evlist, +int nr_streams_max)
And here it should be:
+struct evsel_streams *evlist__create_streams(struct evlist *evlist,
+ int nr_streams_max)
I.e. without the perf_ prefix, since that is for 'struct perf_evlist' methods, that are in tools/lib/perf/, aka libperf
tools/perf/util/stream.c line 137
Quoted 5 lines
tools/perf/util/stream.c new file +5
-0+{ +struct evsel_streams *es; +int nr_evsel = evlist->core.nr_entries, ret =-1 ; + + es =create_evsel_streams (nr_evsel, nr_streams_max);
Minor nitpick, usually combine declaration with first attribution, if possible, i.e.:
+ struct evsel_streams *es = create_evsel_streams(nr_evsel, nr_streams_max);
Quoted 29 lines
tools/perf/util/stream.c new file +11
-0+if (!es) +return NULL ; + + ret =evlist_init_callchain_streams (evlist, es, nr_evsel); +if (ret) { +free_evsel_streams (es, nr_evsel); +return NULL ; + } + +return es; +}tools/perf/util/stream.h new file +12
-0@@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_STREAM_H +#define __PERF_STREAM_H + +#include "callchain.h" + +struct stream { + struct callchain_node *cnode; +}; + +struct evsel_streams { + struct stream *streams;
tools/perf/util/stream.h line 22
Quoted 10 lines
tools/perf/util/stream.h new file +10
-0+int nr_streams_max; +int nr_streams; +int evsel_idx; +}; + +struct evlist ; + +struct evsel_streams *perf_evlist__create_streams (struct evlist *evlist, +int nr_streams_max); +
evlist__create_streams()
Quoted 4 lines
tools/perf/util/stream.h new file +1
-0+#endif /* __PERF_STREAM_H */ Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
PATCH v6 2/7 perf util: Get the evsel_streams by evsel_idx
In reply to Jin YaoIn previous patch, we have created evsel_streams array
This patch returns the specified evsel_streams according to the evsel_idx.
---
v6:
- Rebase to perf/core
v5:
- Rebase to perf/core
v4:
- Rename the patch from 'perf util: Return per-event callchain streams' to 'perf util: Get the evsel_streams by evsel_idx'
tools/perf/util/stream.c | 11 +++++++++++ tools/perf/util/stream.h | 3 +++ 2 files changed, 14 insertions(+)
tools/perf/util/stream.c +11 -0
@@ -146,3 +146,14 @@ struct evsel_streams *perf_evlist__create_streams(struct evlist *evlist,return es; } + +struct evsel_streams *evsel_streams_get (struct evsel_streams *es, +int nr_evsel,int evsel_idx) +{ +for (int i =0 ; i < nr_evsel; i++) { +if (es[i].evsel_idx == evsel_idx) +return &es[i]; + } + +return NULL ; +}
tools/perf/util/stream.h +3 -0
@@ -20,4 +20,7 @@ struct evlist;struct evsel_streams *perf_evlist__create_streams (struct evlist *evlist,int nr_streams_max); +struct evsel_streams *evsel_streams_get (struct evsel_streams *es, +int nr_evsel,int evsel_idx); +#endif /* __PERF_STREAM_H */
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v6 2/7] perf util: Get the evsel_streams by evsel_idx
Em Fri, Sep 11, 2020 at 04:03:48PM +0800, Jin Yao escreveu:
Quoted 26 lines
In previous patch, we have created
evsel_streamsarrayThis patch returns the specified
evsel_streamsaccording to theevsel_idx.Signed-off-by Jin Yao <[email protected]>---
v6:
- Rebase to perf/corev5:
- Rebase to perf/corev4:
- Rename the patch from 'perf util: Return per-event callchain streams' to 'perf util: Get theevsel_streamsbyevsel_idx'tools/perf/util/stream.c | 11 +++++++++++ tools/perf/util/stream.h | 3 +++ 2 files changed, 14 insertions(+)tools/perf/util/stream.c +0
-0
tools/perf/util/stream.c struct evsel_streams *perf_evlist__create_streams(struct evlist *evlist, · line 151
Quoted 6 lines
tools/perf/util/stream.c +3
-0@@ -146,3 +146,14 @@ struct evsel_streams *perf_evlist__create_streams(struct evlist *evlist,return es; } + +struct evsel_streams *evsel_streams_get (struct evsel_streams *es, +int nr_evsel,int evsel_idx)
foo__get() is the idiom for refcount_t method to bump the refcount for 'struct foo', so please rename it to:
struct evsel_streams__entry(struct evsel_streams *es, int nr_evsel, int evsel_idx)
Also please consider having the array and the number of entries in 'struct evsel_streams', so that you don't have to always pass the number of entries around.
Quoted 23 lines
tools/perf/util/stream.c +8
-0+{ +for (int i =0 ; i < nr_evsel; i++) { +if (es[i].evsel_idx == evsel_idx) +return &es[i]; + } + +return NULL ; +}tools/perf/util/stream.h +3
-0@@ -20,4 +20,7 @@ struct evlist;struct evsel_streams *perf_evlist__create_streams (struct evlist *evlist,int nr_streams_max); +struct evsel_streams *evsel_streams_get (struct evsel_streams *es, +int nr_evsel,int evsel_idx); +#endif /* __PERF_STREAM_H */ Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
PATCH v6 3/7 perf util: Compare two streams
In reply to Jin YaoStream is the branch history which is aggregated by the branch records from perf samples. Now we support the callchain as stream.
If the callchain entries of one stream are fully matched with the callchain entries of another stream, we think two streams are matched.
For example,
cycles: 1, hits: 26.80% cycles: 1, hits: 27.30%
----------------------- -----------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44
Above two streams are matched (we don't consider the case that source code is changed).
The matching logic is, compare the chain string first. If it's not matched, fallback to dso address comparison.
---
v6:
- Rebase to perf/core
v5:
- Remove enum stream_type
- Rebase to perf/core
v4:
- Remove original source line comparison code.
tools/perf/util/callchain.c | 54 +++++++++++++++++++++++++++++++++++++ tools/perf/util/callchain.h | 4 +++ 2 files changed, 58 insertions(+)
tools/perf/util/callchain.c +54 -0
@@ -1613,3 +1613,57 @@ void callchain_param_setup(u64 sample_type) callchain_param.record_mode =CALLCHAIN_FP ; } } + +static bool chain_match (struct callchain_list *base_chain, +struct callchain_list *pair_chain) +{ +enum match_result match; + + match =match_chain_strings (base_chain->srcline, + pair_chain->srcline); +if (match !=MATCH_ERROR ) +return match ==MATCH_EQ ; + + match =match_chain_dso_addresses (base_chain->ms.map, + base_chain->ip, + pair_chain->ms.map, + pair_chain->ip); + +return match ==MATCH_EQ ; +} + +bool callchain_cnode_matched (struct callchain_node *base_cnode, +struct callchain_node *pair_cnode) +{ +struct callchain_list *base_chain, *pair_chain; +bool match = false; + + pair_chain =list_first_entry (&pair_cnode->val, + struct callchain_list, + list); + +list_for_each_entry (base_chain, &base_cnode->val, list) { +if (&pair_chain->list == &pair_cnode->val) +return false; + +if (!base_chain->srcline || !pair_chain->srcline) { + pair_chain =list_next_entry (pair_chain, list); +continue ; + } + + match =chain_match (base_chain, pair_chain); +if (!match) +return false; + + pair_chain =list_next_entry (pair_chain, list); + } + +/* +* Say chain1 is ABC, chain2 is ABCD, we consider they are +* not fully matched. +*/ +if (pair_chain && (&pair_chain->list != &pair_cnode->val)) +return false; + +return match; +}
tools/perf/util/callchain.h +4 -0
@@ -298,4 +298,8 @@ int callchain_branch_counts(struct callchain_root *root, u64 *abort_count, u64 *cycles_count);void callchain_param_setup (u64 sample_type); + +bool callchain_cnode_matched (struct callchain_node *base_cnode, +struct callchain_node *pair_cnode); +#endif /* __PERF_CALLCHAIN_H */
Signature · 1 line
2.17.1
PATCH v6 4/7 perf util: Link stream pair
In reply to Jin YaoIn previous patch, we have created an evsel_streams for one event, and top N hottest streams will be saved in a stream array in evsel_streams.
This patch compares total streams among two evsel_streams.
Once two streams are fully matched, they will be linked as a pair. From the pair, we can know which streams are matched.
---
v6:
- Rebase to perf/core
v5:
- Remove enum stream_type
v4:
- New patch in v4.
tools/perf/util/stream.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/stream.h | 4 ++++ 2 files changed, 44 insertions(+)
tools/perf/util/stream.c +40 -0
@@ -157,3 +157,43 @@ struct evsel_streams *evsel_streams_get(struct evsel_streams *es,return NULL ; } + +static struct stream *stream_callchain_match (struct stream *base_stream, +struct evsel_streams *es_pair) +{ +for (int i =0 ; i < es_pair->nr_streams; i++) { +struct stream *pair_stream = &es_pair->streams[i]; + +if (callchain_cnode_matched (base_stream->cnode, + pair_stream->cnode)) { +return pair_stream; + } + } + +return NULL ; +} + +static struct stream *stream_match (struct stream *base_stream, +struct evsel_streams *es_pair) +{ +return stream_callchain_match (base_stream, es_pair); +} + +static void stream_link (struct stream *base_stream,struct stream *pair_stream) +{ + base_stream->pair_cnode = pair_stream->cnode; + pair_stream->pair_cnode = base_stream->cnode; +} + +void match_evsel_streams (struct evsel_streams *es_base, +struct evsel_streams *es_pair) +{ +for (int i =0 ; i < es_base->nr_streams; i++) { +struct stream *base_stream = &es_base->streams[i]; +struct stream *pair_stream; + + pair_stream =stream_match (base_stream, es_pair); +if (pair_stream) +stream_link (base_stream, pair_stream); + } +}
tools/perf/util/stream.h +4 -0
@@ -6,6 +6,7 @@struct stream {struct callchain_node *cnode; +struct callchain_node *pair_cnode; };struct evsel_streams {
@@ -23,4 +24,7 @@ struct evsel_streams *perf_evlist__create_streams(struct evlist *evlist,struct evsel_streams *evsel_streams_get (struct evsel_streams *es,int nr_evsel,int evsel_idx); +void match_evsel_streams (struct evsel_streams *es_base, +struct evsel_streams *es_pair); +#endif /* __PERF_STREAM_H */
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v6 4/7] perf util: Link stream pair
Em Fri, Sep 11, 2020 at 04:03:50PM +0800, Jin Yao escreveu:
Quoted 29 lines
In previous patch, we have created an
evsel_streamsfor one event, and top N hottest streams will be saved in a stream array inevsel_streams.This patch compares total streams among two
evsel_streams.Once two streams are fully matched, they will be linked as a pair. From the pair, we can know which streams are matched.
Signed-off-by Jin Yao <[email protected]>---
v6:
- Rebase to perf/corev5:
- Remove enumstream_typev4:
- New patch in v4.tools/perf/util/stream.c | 40 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/stream.h | 4 ++++ 2 files changed, 44 insertions(+)tools/perf/util/stream.c +0
-0
tools/perf/util/stream.c struct evsel_streams *evsel_streams_get(struct evsel_streams *es, · line 162
Quoted 6 lines
tools/perf/util/stream.c +3
-0@@ -157,3 +157,43 @@ struct evsel_streams *evsel_streams_get(struct evsel_streams *es,return NULL ; } + +static struct stream *stream_callchain_match (struct stream *base_stream, +struct evsel_streams *es_pair)
Please use stream__
Quoted 60 lines
tools/perf/util/stream.c +37
-0+{ +for (int i =0 ; i < es_pair->nr_streams; i++) { +struct stream *pair_stream = &es_pair->streams[i]; + +if (callchain_cnode_matched (base_stream->cnode, + pair_stream->cnode)) { +return pair_stream; + } + } + +return NULL ; +} + +static struct stream *stream_match (struct stream *base_stream, +struct evsel_streams *es_pair) +{ +return stream_callchain_match (base_stream, es_pair); +} + +static void stream_link (struct stream *base_stream,struct stream *pair_stream) +{ + base_stream->pair_cnode = pair_stream->cnode; + pair_stream->pair_cnode = base_stream->cnode; +} + +void match_evsel_streams (struct evsel_streams *es_base, +struct evsel_streams *es_pair) +{ +for (int i =0 ; i < es_base->nr_streams; i++) { +struct stream *base_stream = &es_base->streams[i]; +struct stream *pair_stream; + + pair_stream =stream_match (base_stream, es_pair); +if (pair_stream) +stream_link (base_stream, pair_stream); + } +}tools/perf/util/stream.h +4
-0@@ -6,6 +6,7 @@struct stream {struct callchain_node *cnode; +struct callchain_node *pair_cnode; };struct evsel_streams {@@ -23,4 +24,7 @@ struct evsel_streams *perf_evlist__create_streams(struct evlist *evlist,struct evsel_streams *evsel_streams_get (struct evsel_streams *es,int nr_evsel,int evsel_idx); +void match_evsel_streams (struct evsel_streams *es_base, +struct evsel_streams *es_pair); +#endif /* __PERF_STREAM_H */ Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
PATCH v6 5/7 perf util: Calculate the sum of total streams hits
In reply to Jin YaoWe have used callchain_node->hit to measure the hot level of one stream. This patch calculates the sum of hits of total streams.
Thus in next patch, we can use following formula to report hot percent for one stream.
hot percent = callchain_node->hit / sum of total hits
---
v6:
- Rebase to perf/core
v5:
- Rebase to perf/core
v4:
- No functional change.
v2:
- Combine the variable decl line with its initial assignment in total_callchain_hits().
tools/perf/util/callchain.c | 32 ++++++++++++++++++++++++++++++++ tools/perf/util/callchain.h | 3 +++ tools/perf/util/stream.c | 2 ++ tools/perf/util/stream.h | 1 + 4 files changed, 38 insertions(+)
tools/perf/util/callchain.c +32 -0
@@ -1667,3 +1667,35 @@ bool callchain_cnode_matched(struct callchain_node *base_cnode,return match; } + +static u64 count_callchain_hits (struct hist_entry *he) +{ +struct rb_root *root = &he->sorted_chain; +struct rb_node *rb_node =rb_first (root); +struct callchain_node *node; +u64 chain_hits =0 ; + +while (rb_node) { + node = rb_entry(rb_node, struct callchain_node, rb_node); + chain_hits += node->hit; + rb_node =rb_next (rb_node); + } + +return chain_hits; +} + +u64 callchain_total_hits (struct hists *hists) +{ +struct rb_node *next =rb_first_cached (&hists->entries); +u64 chain_hits =0 ; + +while (next) { + struct hist_entry *he = rb_entry(next, struct hist_entry, + rb_node); + + chain_hits +=count_callchain_hits (he); + next =rb_next (&he->rb_node); + } + +return chain_hits; +}
tools/perf/util/callchain.h +3 -0
@@ -13,6 +13,7 @@ struct ip_callchain;struct map ;struct perf_sample ;struct thread ; +struct hists ;#define HELP_PAD "\t\t\t\t"
@@ -302,4 +303,6 @@ void callchain_param_setup(u64 sample_type);bool callchain_cnode_matched (struct callchain_node *base_cnode,struct callchain_node *pair_cnode); +u64 callchain_total_hits (struct hists *hists); +#endif /* __PERF_CALLCHAIN_H */
tools/perf/util/stream.c +2 -0
@@ -106,6 +106,8 @@ static void init_hot_callchain(struct hists *hists, struct evsel_streams *es)update_hot_callchain (he, es); next =rb_next (&he->rb_node); } + + es->streams_hits =callchain_total_hits (hists); } static int evlist_init_callchain_streams(struct evlist *evlist,
tools/perf/util/stream.h +1 -0
@@ -14,6 +14,7 @@ struct evsel_streams {int nr_streams_max;int nr_streams;int evsel_idx; +u64 streams_hits; };struct evlist ;
Signature · 1 line
2.17.1
PATCH v6 6/7 perf util: Report hot streams
In reply to Jin YaoWe show the streams separately. They are divided into different sections.
1. "Matched hot streams"
2. "Hot streams in old perf data only"
3. "Hot streams in new perf data only".
For each stream, we report the cycles and hot percent (hits%).
For example,
cycles: 2, hits: 4.08%
--------------------------
main div.c:42
compute_flag div.c:28---
v6:
- Rebase to perf/core
v5:
- Rebase to perf/core
v4:
- Remove "Hot chains in old perf data but source line changed in new perf data"
tools/perf/util/callchain.c | 13 ++++ tools/perf/util/callchain.h | 2 + tools/perf/util/stream.c | 123 ++++++++++++++++++++++++++++++++++++ tools/perf/util/stream.h | 3 + 4 files changed, 141 insertions(+)
tools/perf/util/callchain.c +13 -0
@@ -1699,3 +1699,16 @@ u64 callchain_total_hits(struct hists *hists)return chain_hits; } + +s64 callchain_avg_cycles (struct callchain_node *cnode) +{ +struct callchain_list *chain; +s64 cycles =0 ; + +list_for_each_entry (chain, &cnode->val, list) { +if (chain->srcline && chain->branch_count) + cycles += chain->cycles_count / chain->branch_count; + } + +return cycles; +}
tools/perf/util/callchain.h +2 -0
@@ -305,4 +305,6 @@ bool callchain_cnode_matched(struct callchain_node *base_cnode,u64 callchain_total_hits (struct hists *hists); +s64 callchain_avg_cycles (struct callchain_node *cnode); +#endif /* __PERF_CALLCHAIN_H */
tools/perf/util/stream.c +123 -0
126 lines not on this page · raw message
tools/perf/util/stream.h +3 -0
@@ -28,4 +28,7 @@ struct evsel_streams *evsel_streams_get(struct evsel_streams *es,void match_evsel_streams (struct evsel_streams *es_base,struct evsel_streams *es_pair); +void evsel_streams_report (struct evsel_streams *es_base, +struct evsel_streams *es_pair); +#endif /* __PERF_STREAM_H */
Signature · 1 line
2.17.1
PATCH v6 7/7 perf diff: Support hot streams comparison
In reply to Jin YaoThis patch enables perf-diff with "--stream" option.
"--stream": Enable hot streams comparison
Now let's see examples.
perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream
[ Matched hot streams ]
hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44
hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98%
--------------------------- --------------------------
__random_r random_r.c:360 __random_r random_r.c:360
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:380 __random_r random_r.c:380
__random_r random_r.c:357 __random_r random_r.c:357
__random random.c:293 __random random.c:293
__random random.c:293 __random random.c:293
__random random.c:291 __random random.c:291
__random random.c:291 __random random.c:291
__random random.c:291 __random random.c:291
__random random.c:288 __random random.c:288
rand rand.c:27 rand rand.c:27
rand rand.c:26 rand rand.c:26
rand@plt rand@plt
rand@plt rand@plt
compute_flag div.c:25 compute_flag div.c:25
compute_flag div.c:22 compute_flag div.c:22
main div.c:40 main div.c:40
main div.c:40 main div.c:40
main div.c:39 main div.c:39
hot chain pair 3:
cycles: 9, hits: 4.48% cycles: 6, hits: 4.51%
--------------------------- --------------------------
__random_r random_r.c:360 __random_r random_r.c:360
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:388 __random_r random_r.c:388
__random_r random_r.c:380 __random_r random_r.c:380[ Hot streams in old perf data only ]
hot chain 1:
cycles: 18, hits: 6.75%
--------------------------
__random_r random_r.c:360
__random_r random_r.c:388
__random_r random_r.c:388
__random_r random_r.c:380
__random_r random_r.c:357
__random random.c:293
__random random.c:293
__random random.c:291
__random random.c:291
__random random.c:291
__random random.c:288
rand rand.c:27
rand rand.c:26
rand@plt
rand@plt
compute_flag div.c:25
compute_flag div.c:22
main div.c:40hot chain 2:
cycles: 29, hits: 2.78%
--------------------------
compute_flag div.c:22
main div.c:40
main div.c:40
main div.c:39[ Hot streams in new perf data only ]
hot chain 1:
cycles: 4, hits: 4.54%
--------------------------
main div.c:42
compute_flag div.c:28hot chain 2:
cycles: 5, hits: 3.51%
--------------------------
main div.c:39
main div.c:44
main div.c:42
compute_flag div.c:28---
v6:
- Rebase to perf/core
v5:
- Remove enum stream_type
- Rebase to perf/core
v4:
- Remove the "--before" and "--after" options since they are for source line based comparison. In this patchset, we will not support source line based comparison.
tools/perf/Documentation/perf-diff.txt | 4 + tools/perf/builtin-diff.c | 133 ++++++++++++++++++++++--- 2 files changed, 124 insertions(+), 13 deletions(-)
tools/perf/Documentation/perf-diff.txt +4 -0
@@ -182,6 +182,10 @@ OPTIONS --tid=:: Only diff samples for given thread ID (comma separated list). +--stream:: + Enable hot streams comparison. Stream can be a callchain which is + aggregated by the branch records from samples. + COMPARISON ---------- The comparison is governed by the baseline file. The baseline perf.data
tools/perf/builtin-diff.c +120 -13
216 lines not on this page · raw message
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v6 7/7] perf diff: Support hot streams comparison
Em Fri, Sep 11, 2020 at 04:03:53PM +0800, Jin Yao escreveu:
Quoted 18 lines
This patch enables perf-diff with "--stream" option.
"--stream": Enable hot streams comparison
Now let's see examples.
perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream[ Matched hot streams ]
hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44
Quoted 4 lines
hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360
Would it be interesting to get the associated source code and show right below these file:number lines?
- Arnaldo
Quoted 345 lines
__random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288rand rand.c:27 rand rand.c:27
rand rand.c:26 rand rand.c:26
rand@plt rand@plt
rand@plt rand@plt
compute_flagdiv.c:25compute_flagdiv.c:25
compute_flagdiv.c:22compute_flagdiv.c:22
main div.c:40 main div.c:40
main div.c:40 main div.c:40
main div.c:39 main div.c:39hot chain pair 3:
cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380[ Hot streams in old perf data only ]
hot chain 1:
cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40hot chain 2:
cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39[ Hot streams in new perf data only ]
hot chain 1:
cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28hot chain 2:
cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28Signed-off-by Jin Yao <[email protected]>---
v6:
- Rebase to perf/corev5:
- Remove enumstream_type
- Rebase to perf/corev4:
- Remove the "--before" and "--after" options since they are for source line based comparison. In this patchset, we will not support source line based comparison.tools/perf/Documentation/perf-diff.txt | 4 + tools/perf/builtin-diff.c | 133 ++++++++++++++++++++++--- 2 files changed, 124 insertions(+), 13 deletions(-)tools/perf/Documentation/perf-diff.txt +4
-0@@ -182,6 +182,10 @@ OPTIONS --tid=:: Only diff samples for given thread ID (comma separated list). +--stream:: + Enable hot streams comparison. Stream can be a callchain which is + aggregated by the branch records from samples. + COMPARISON ---------- The comparison is governed by the baseline file. The baseline perf.datatools/perf/builtin-diff.c +120
-13@@ -25,6 +25,7 @@#include "util/map.h" #include "util/spark.h" #include "util/block-info.h" +#include "util/stream.h" #include <linux/err.h> #include <linux/zalloc.h> #include <subcmd/pager.h> @@ -42,6 +43,7 @@ struct perf_diff {int range_size;int range_num;bool has_br_stack; +bool stream; };/* Diff command specific HPP columns. */ @@ -72,6 +74,8 @@ struct data__file {struct perf_data data;int idx;struct hists *hists; +struct evsel_streams *evsel_streams; +int nr_evsel_streams;struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX ]; };@@ -106,6 +110,7 @@ enum {COMPUTE_DELTA_ABS ,COMPUTE_CYCLES ,COMPUTE_MAX , + COMPUTE_STREAM, /* After COMPUTE_MAX to avoid use current compute arrays */ }; const char *compute_names[COMPUTE_MAX] = {@@ -393,6 +398,11 @@ static int diff__process_sample_event(struct perf_tool *tool, struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool);struct addr_location al;struct hists *hists =evsel__hists (evsel); +struct hist_entry_iter iter = { + .evsel = evsel, + .sample = sample, + .ops = &hist_iter_normal, + };int ret =-1 ; if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num,@@ -411,14 +421,8 @@ static int diff__process_sample_event(struct perf_tool *tool, goto out_put; } -if (compute !=COMPUTE_CYCLES ) { -if (!hists__add_entry (hists, &al,NULL ,NULL ,NULL , sample, - true)) { -pr_warning ("problem incrementing symbol period, " -"skipping event\n" ); - goto out_put; - } - }else { +switch (compute) { +case COMPUTE_CYCLES :if (!hists__add_entry_ops (hists, &block_hist_ops, &al,NULL ,NULL ,NULL , sample, true)) { pr_warning("problem incrementing symbol period, "@@ -428,6 +432,23 @@ static int diff__process_sample_event(struct perf_tool *tool,hist__account_cycles (sample->branch_stack, &al, sample, false,NULL ); +break ; + +case COMPUTE_STREAM : +if (hist_entry_iter__add (&iter, &al,PERF_MAX_STACK_DEPTH , +NULL )) { +pr_debug ("problem adding hist entry, skipping event\n" ); + goto out_put; + } +break ; + +default : +if (!hists__add_entry (hists, &al,NULL ,NULL ,NULL , sample, + true)) { +pr_warning ("problem incrementing symbol period, " +"skipping event\n" ); + goto out_put; + } }/* @@ -996,6 +1017,50 @@ static void data_process(void) } } +static int process_base_stream (struct data__file *data_base, +struct data__file *data_pair, +const char *title__maybe_unused ) +{ +struct evlist *evlist_base = data_base->session->evlist; +struct evlist *evlist_pair = data_pair->session->evlist; +struct evsel *evsel_base, *evsel_pair; +struct evsel_streams *es_base, *es_pair; + +evlist__for_each_entry (evlist_base, evsel_base) { + evsel_pair =evsel_match (evsel_base, evlist_pair); +if (!evsel_pair) +continue ; + + es_base =evsel_streams_get (data_base->evsel_streams, + data_base->nr_evsel_streams, + evsel_base->idx); +if (!es_base) +return -1 ; + + es_pair =evsel_streams_get (data_pair->evsel_streams, + data_pair->nr_evsel_streams, + evsel_pair->idx); +if (!es_pair) +return -1 ; + +match_evsel_streams (es_base, es_pair); +evsel_streams_report (es_base, es_pair); + } + +return 0 ; +} + +static void stream_process (void ) +{ +/* +* Stream comparison only supports two data files. +* perf.data.old and perf.data. data__files[0] is perf.data.old, +* data__files[1] is perf.data. +*/ +process_base_stream (&data__files[0 ], &data__files[1 ], +"# Output based on old perf data:\n#\n" ); +} +static void data__free (struct data__file *d) {int col;@@ -1109,6 +1174,18 @@ static int check_file_brstack(void)return 0 ; } +static struct evsel_streams *create_evsel_streams (struct evlist *evlist, +int nr_streams_max, +int *nr_evsel_streams) +{ +struct evsel_streams *es; + + es =perf_evlist__create_streams (evlist, nr_streams_max); + *nr_evsel_streams = evlist->core.nr_entries; + +return es; +} +static int __cmd_diff (void ) {struct data__file *d;@@ -1153,9 +1230,21 @@ static int __cmd_diff(void)if (pdiff.ptime_range)zfree (&pdiff.ptime_range); + +if (compute ==COMPUTE_STREAM ) { + d->evsel_streams =create_evsel_streams ( + d->session->evlist, +5 , + &d->nr_evsel_streams); +if (!d->evsel_streams) + goto out_delete; + } } -data_process (); +if (compute ==COMPUTE_STREAM ) +stream_process (); +else +data_process (); out_delete:data__for_each_file (i, d) {@@ -1228,6 +1317,8 @@ static const struct option options[] = { "only consider symbols in these pids"),OPT_STRING (0 ,"tid" , &symbol_conf.tid_list_str,"tid[,tid...]" ,"only consider symbols in these tids" ), +OPT_BOOLEAN (0 ,"stream" , &pdiff.stream, +"Enable hot streams comparison." ), OPT_END() };@@ -1887,6 +1978,9 @@ int cmd_diff(int argc, const char **argv)if (cycles_hist && (compute !=COMPUTE_CYCLES ))usage_with_options (diff_usage, options); +if (pdiff.stream) + compute =COMPUTE_STREAM ; +symbol__annotation_init ();if (symbol__init (NULL ) <0 )@@ -1898,13 +1992,26 @@ int cmd_diff(int argc, const char **argv)if (check_file_brstack () <0 )return -1 ; -if (compute ==COMPUTE_CYCLES && !pdiff.has_br_stack) +if ((compute ==COMPUTE_CYCLES || compute ==COMPUTE_STREAM ) + && !pdiff.has_br_stack) {return -1 ; + } -if (ui_init () <0 ) -return -1 ; +if (compute ==COMPUTE_STREAM ) { + symbol_conf.show_branchflag_count = true; + symbol_conf.disable_add2line_warn = true; + callchain_param.mode =CHAIN_FLAT ; + callchain_param.key =CCKEY_SRCLINE ; + callchain_param.branch_callstack =1 ; + symbol_conf.use_callchain = true; +callchain_register_param (&callchain_param); + sort_order ="srcline,symbol,dso" ; + }else { +if (ui_init () <0 ) +return -1 ; - sort__mode =SORT_MODE__DIFF ; + sort__mode =SORT_MODE__DIFF ; + }if (setup_sorting (NULL ) <0 )usage_with_options (diff_usage, options);Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Re: [PATCH v6 7/7] perf diff: Support hot streams comparison
Hi Arnaldo,
Quoted 24 lines · Arnaldo Carvalho de Melo
Em Fri, Sep 11, 2020 at 04:03:53PM +0800, Jin Yao escreveu:
Quoted 18 lines
This patch enables perf-diff with "--stream" option.
"--stream": Enable hot streams comparison
Now let's see examples.
perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream[ Matched hot streams ]
hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44Quoted 4 lines
hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360
Quoted 5 lines
Would it be interesting to get the associated source code and show right below these file:number lines?
- Arnaldo
Yes, that would be better. Let me think about the implementation.
Thanks
Jin Yao
Re: [PATCH v6 7/7] perf diff: Support hot streams comparison
In reply to Arnaldo Carvalho de MeloHi Arnaldo,
Quoted 24 lines · Arnaldo Carvalho de Melo
Em Fri, Sep 11, 2020 at 04:03:53PM +0800, Jin Yao escreveu:
Quoted 18 lines
This patch enables perf-diff with "--stream" option.
"--stream": Enable hot streams comparison
Now let's see examples.
perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream[ Matched hot streams ]
hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44Quoted 4 lines
hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360
Quoted 5 lines
Would it be interesting to get the associated source code and show right below these file:number lines?
- Arnaldo
I'm thinking we can implement this function in callchain_list__sym_name(), and then all callchain functionality will benefit from it. While that looks to be another patchset. :)
Thanks
Jin Yao
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v6 7/7] perf diff: Support hot streams comparison
Em Sat, Sep 19, 2020 at 12:41:35PM +0800, Jin, Yao escreveu:
Quoted 30 lines
Hi Arnaldo,
Quoted 27 lines · Arnaldo Carvalho de Melo
Em Fri, Sep 11, 2020 at 04:03:53PM +0800, Jin Yao escreveu:
Quoted 18 lines
This patch enables perf-diff with "--stream" option.
"--stream": Enable hot streams comparison
Now let's see examples.
perf record -b ... Generate perf.data.old with branch data
perf record -b ... Generate perf.data with branch data
perf diff --stream[ Matched hot streams ]
hot chain pair 1:
cycles: 1, hits: 27.77% cycles: 1, hits: 9.24%
--------------------------- --------------------------
main div.c:39 main div.c:39
main div.c:44 main div.c:44Quoted 4 lines
hot chain pair 2:
cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360Would it be interesting to get the associated source code and show right below these file:number lines?
Quoted 6 lines
Quoted 2 lines
- Arnaldo
I'm thinking we can implement this function in
callchain_list__sym_name(), and then all callchain functionality will benefit from it. While that looks to be another patchset. :)
Sure, after we go thru the process of merging the current one.
Quoted 2 lines
Thanks
Jin Yao
Signature · 1 line
- Arnaldo
On Fri, Sep 11, 2020 at 04:03:46PM +0800, Jin Yao wrote:
SNIP
Quoted 20 lines
main div.c:40 main div.c:40 main div.c:39[ Hot streams in new perf data only ]
hot chain 1:
cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28hot chain 2:
cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28
Quoted 3 lines
v6:
---
Rebase to perf/core
it looks good to me
thanks,
jirka
Arnaldo Carvalho de Melo
maintainerEm Thu, Sep 17, 2020 at 03:05:56PM +0200, Jiri Olsa escreveu:
Quoted 24 lines · Jin Yao
SNIP
Quoted 20 lines
main div.c:40 main div.c:40 main div.c:39[ Hot streams in new perf data only ]
hot chain 1:
cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28hot chain 2:
cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28
Quoted 7 lines
Quoted 3 lines
v6:
---
Rebase to perf/coreit looks good to me
Acked-by Jiri Olsa <[email protected]>
Jin,
I'm sorry I only got to look at this now, there are some issues,
I'll try to point them out patch by patch,
Thanks,
- Arnaldo
Hi Arnaldo,
Quoted 33 lines · Arnaldo Carvalho de Melo
Em Thu, Sep 17, 2020 at 03:05:56PM +0200, Jiri Olsa escreveu:
Quoted 24 lines · Jin Yao
SNIP
Quoted 20 lines
main div.c:40 main div.c:40 main div.c:39[ Hot streams in new perf data only ]
hot chain 1:
cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28hot chain 2:
cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28Quoted 7 lines
Quoted 3 lines
v6:
---
Rebase to perf/coreit looks good to me
Acked-by Jiri Olsa <[email protected]>
Quoted 9 lines
Jin,
I'm sorry I only got to look at this now, there are some issues,
I'll try to point them out patch by patch,Thanks,
- Arnaldo
Thanks so much for looking at this patchset! :)
I will fix the issues which you point out in other mail threads. Once the fixes are done, I will post v7.
Thanks
Jin Yao