From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Nick Terrell <terrelln@fb.com>,
Kan Liang <kan.liang@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>, Leo Yan <leo.yan@linaro.org>,
Song Liu <song@kernel.org>, Sandipan Das <sandipan.das@amd.com>,
James Clark <james.clark@arm.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Miguel Ojeda <ojeda@kernel.org>,
Liam Howlett <liam.howlett@oracle.com>,
Yang Jihong <yangjihong1@huawei.com>,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
Kajol Jain <kjain@linux.ibm.com>,
K Prateek Nayak <kprateek.nayak@amd.com>,
Sean Christopherson <seanjc@google.com>,
Yanteng Si <siyanteng@loongson.cn>,
Ravi Bangoria <ravi.bangoria@amd.com>,
German Gomez <german.gomez@arm.com>,
Changbin Du <changbin.du@huawei.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Masami Hiramatsu <mhiramat@kernel.org>,
liuwenyu <liuwenyu7@huawei.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: [PATCH v3 09/50] perf callchain: Make brtype_stat in callchain_list optional
Date: Tue, 24 Oct 2023 15:23:12 -0700 [thread overview]
Message-ID: <20231024222353.3024098-10-irogers@google.com> (raw)
In-Reply-To: <20231024222353.3024098-1-irogers@google.com>
struct callchain_list is 352bytes in size, 232 of which are
brtype_stat. brtype_stat is only used for certain callchain_list
items so make it optional, allocating when necessary. So that
printing doesn't need to deal with an optional brtype_stat, pass
an empty/zero version.
Before:
```
struct callchain_list {
u64 ip; /* 0 8 */
struct map_symbol ms; /* 8 24 */
struct {
_Bool unfolded; /* 32 1 */
_Bool has_children; /* 33 1 */
}; /* 32 2 */
/* XXX 6 bytes hole, try to pack */
u64 branch_count; /* 40 8 */
u64 from_count; /* 48 8 */
u64 predicted_count; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
u64 abort_count; /* 64 8 */
u64 cycles_count; /* 72 8 */
u64 iter_count; /* 80 8 */
u64 iter_cycles; /* 88 8 */
struct branch_type_stat brtype_stat; /* 96 232 */
/* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */
const char * srcline; /* 328 8 */
struct list_head list; /* 336 16 */
/* size: 352, cachelines: 6, members: 13 */
/* sum members: 346, holes: 1, sum holes: 6 */
/* last cacheline: 32 bytes */
};
```
After:
```
struct callchain_list {
u64 ip; /* 0 8 */
struct map_symbol ms; /* 8 24 */
struct {
_Bool unfolded; /* 32 1 */
_Bool has_children; /* 33 1 */
}; /* 32 2 */
/* XXX 6 bytes hole, try to pack */
u64 branch_count; /* 40 8 */
u64 from_count; /* 48 8 */
u64 predicted_count; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
u64 abort_count; /* 64 8 */
u64 cycles_count; /* 72 8 */
u64 iter_count; /* 80 8 */
u64 iter_cycles; /* 88 8 */
struct branch_type_stat * brtype_stat; /* 96 8 */
const char * srcline; /* 104 8 */
struct list_head list; /* 112 16 */
/* size: 128, cachelines: 2, members: 13 */
/* sum members: 122, holes: 1, sum holes: 6 */
};
```
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/callchain.c | 41 +++++++++++++++++++++++++++++--------
tools/perf/util/callchain.h | 2 +-
2 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index cde4860e6f28..5349c6a21849 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -586,7 +586,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
call = zalloc(sizeof(*call));
if (!call) {
perror("not enough memory for the code path tree");
- return -1;
+ return -ENOMEM;
}
call->ip = cursor_node->ip;
call->ms = cursor_node->ms;
@@ -602,7 +602,15 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
* branch_from is set with value somewhere else
* to imply it's "to" of a branch.
*/
- call->brtype_stat.branch_to = true;
+ if (!call->brtype_stat) {
+ call->brtype_stat = zalloc(sizeof(*call->brtype_stat));
+ if (!call->brtype_stat) {
+ perror("not enough memory for the code path branch statisitcs");
+ free(call->brtype_stat);
+ return -ENOMEM;
+ }
+ }
+ call->brtype_stat->branch_to = true;
if (cursor_node->branch_flags.predicted)
call->predicted_count = 1;
@@ -610,7 +618,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
if (cursor_node->branch_flags.abort)
call->abort_count = 1;
- branch_type_count(&call->brtype_stat,
+ branch_type_count(call->brtype_stat,
&cursor_node->branch_flags,
cursor_node->branch_from,
cursor_node->ip);
@@ -618,7 +626,8 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
/*
* It's "from" of a branch
*/
- call->brtype_stat.branch_to = false;
+ if (call->brtype_stat && call->brtype_stat->branch_to)
+ call->brtype_stat->branch_to = false;
call->cycles_count =
cursor_node->branch_flags.cycles;
call->iter_count = cursor_node->nr_loop_iter;
@@ -652,6 +661,7 @@ add_child(struct callchain_node *parent,
list_del_init(&call->list);
map__zput(call->ms.map);
maps__zput(call->ms.maps);
+ zfree(&call->brtype_stat);
free(call);
}
free(new);
@@ -762,7 +772,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
/*
* It's "to" of a branch
*/
- cnode->brtype_stat.branch_to = true;
+ if (!cnode->brtype_stat) {
+ cnode->brtype_stat = zalloc(sizeof(*cnode->brtype_stat));
+ if (!cnode->brtype_stat) {
+ perror("not enough memory for the code path branch statisitcs");
+ return MATCH_ERROR;
+ }
+ }
+ cnode->brtype_stat->branch_to = true;
if (node->branch_flags.predicted)
cnode->predicted_count++;
@@ -770,7 +787,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
if (node->branch_flags.abort)
cnode->abort_count++;
- branch_type_count(&cnode->brtype_stat,
+ branch_type_count(cnode->brtype_stat,
&node->branch_flags,
node->branch_from,
node->ip);
@@ -778,7 +795,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
/*
* It's "from" of a branch
*/
- cnode->brtype_stat.branch_to = false;
+ if (cnode->brtype_stat && cnode->brtype_stat->branch_to)
+ cnode->brtype_stat->branch_to = false;
cnode->cycles_count += node->branch_flags.cycles;
cnode->iter_count += node->nr_loop_iter;
cnode->iter_cycles += node->iter_cycles;
@@ -1026,6 +1044,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
maps__zput(ms.maps);
map__zput(list->ms.map);
maps__zput(list->ms.maps);
+ zfree(&list->brtype_stat);
free(list);
}
@@ -1447,11 +1466,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
int callchain_list_counts__printf_value(struct callchain_list *clist,
FILE *fp, char *bf, int bfsize)
{
+ static const struct branch_type_stat empty_brtype_stat = {};
+ const struct branch_type_stat *brtype_stat;
u64 branch_count, predicted_count;
u64 abort_count, cycles_count;
u64 iter_count, iter_cycles;
u64 from_count;
+ brtype_stat = clist->brtype_stat ?: &empty_brtype_stat;
branch_count = clist->branch_count;
predicted_count = clist->predicted_count;
abort_count = clist->abort_count;
@@ -1463,7 +1485,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
return callchain_counts_printf(fp, bf, bfsize, branch_count,
predicted_count, abort_count,
cycles_count, iter_count, iter_cycles,
- from_count, &clist->brtype_stat);
+ from_count, brtype_stat);
}
static void free_callchain_node(struct callchain_node *node)
@@ -1476,6 +1498,7 @@ static void free_callchain_node(struct callchain_node *node)
list_del_init(&list->list);
map__zput(list->ms.map);
maps__zput(list->ms.maps);
+ zfree(&list->brtype_stat);
free(list);
}
@@ -1483,6 +1506,7 @@ static void free_callchain_node(struct callchain_node *node)
list_del_init(&list->list);
map__zput(list->ms.map);
maps__zput(list->ms.maps);
+ zfree(&list->brtype_stat);
free(list);
}
@@ -1569,6 +1593,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
list_del_init(&chain->list);
map__zput(chain->ms.map);
maps__zput(chain->ms.maps);
+ zfree(&chain->brtype_stat);
free(chain);
}
return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index d2618a47deca..86e8a9e81456 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -129,7 +129,7 @@ struct callchain_list {
u64 cycles_count;
u64 iter_count;
u64 iter_cycles;
- struct branch_type_stat brtype_stat;
+ struct branch_type_stat *brtype_stat;
const char *srcline;
struct list_head list;
};
--
2.42.0.758.gaed0368e0e-goog
next prev parent reply other threads:[~2023-10-24 22:25 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-24 22:23 [PATCH v3 00/50] Improvements to memory use Ian Rogers
2023-10-24 22:23 ` [PATCH v3 01/50] perf rwsem: Add debug mode that uses a mutex Ian Rogers
2023-10-24 22:23 ` [PATCH v3 02/50] perf machine: Avoid out of bounds LBR memory read Ian Rogers
2023-10-24 22:23 ` [PATCH v3 03/50] libperf rc_check: Make implicit enabling work for GCC Ian Rogers
2023-10-24 22:23 ` [PATCH v3 04/50] libperf rc_check: Add RC_CHK_EQUAL Ian Rogers
2023-10-24 22:23 ` [PATCH v3 05/50] perf hist: Add missing puts to hist__account_cycles Ian Rogers
2023-10-24 22:23 ` [PATCH v3 06/50] perf threads: Remove unused dead thread list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 07/50] perf offcpu: Add missed btf_free Ian Rogers
2023-10-24 22:23 ` [PATCH v3 08/50] perf callchain: Make display use of branch_type_stat const Ian Rogers
2023-10-24 22:23 ` Ian Rogers [this message]
2023-10-24 22:23 ` [PATCH v3 10/50] perf callchain: Minor layout changes to callchain_list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 11/50] perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit Ian Rogers
2023-10-24 22:23 ` [PATCH v3 12/50] perf record: Lazy load kernel symbols Ian Rogers
2023-10-25 18:25 ` Namhyung Kim
2023-10-25 18:35 ` Adrian Hunter
2023-10-24 22:23 ` [PATCH v3 13/50] libperf: Lazily allocate mmap event copy Ian Rogers
2023-10-25 2:38 ` Yang Jihong
2023-10-25 3:28 ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 14/50] perf mmap: Lazily initialize zstd streams Ian Rogers
2023-10-24 22:23 ` [PATCH v3 15/50] perf machine thread: Remove exited threads by default Ian Rogers
2023-10-24 22:23 ` [PATCH v3 16/50] tools api fs: Switch filename__read_str to use io.h Ian Rogers
2023-10-24 22:23 ` [PATCH v3 17/50] tools api fs: Avoid reading whole file for a 1 byte bool Ian Rogers
2023-10-24 22:23 ` [PATCH v3 18/50] tools lib api: Add io_dir an allocation free readdir alternative Ian Rogers
2023-10-25 18:43 ` Namhyung Kim
2023-10-25 22:15 ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 19/50] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer Ian Rogers
2023-10-25 3:44 ` Yang Jihong
2023-10-25 17:00 ` Ian Rogers
2023-10-25 19:04 ` Namhyung Kim
2023-10-25 19:00 ` Namhyung Kim
2023-10-24 22:23 ` [PATCH v3 21/50] perf pmu: Switch to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 22/50] perf bpf: Don't synthesize BPF events when disabled Ian Rogers
2023-10-24 22:23 ` [PATCH v3 23/50] perf header: Switch mem topology to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 24/50] perf events: Remove scandir in thread synthesis Ian Rogers
2023-10-24 22:23 ` [PATCH v3 25/50] perf map: Simplify map_ip/unmap_ip and make map size smaller Ian Rogers
2023-10-24 22:23 ` [PATCH v3 26/50] perf maps: Move symbol maps functions to maps.c Ian Rogers
2023-10-24 22:23 ` [PATCH v3 27/50] perf thread: Add missing RC_CHK_ACCESS Ian Rogers
2023-10-24 22:23 ` [PATCH v3 28/50] perf maps: Add maps__for_each_map to call a function on each entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 29/50] perf maps: Add remove maps function to remove a map based on callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 30/50] perf debug: Expose debug file Ian Rogers
2023-10-24 22:23 ` [PATCH v3 31/50] perf maps: Refactor maps__fixup_overlappings Ian Rogers
2023-10-24 22:23 ` [PATCH v3 32/50] perf maps: Do simple merge if given map doesn't overlap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 33/50] perf maps: Rename clone to copy from Ian Rogers
2023-10-24 22:23 ` [PATCH v3 34/50] perf maps: Add maps__load_first Ian Rogers
2023-10-24 22:23 ` [PATCH v3 35/50] perf maps: Add find next entry to give entry after the given map Ian Rogers
2023-10-24 22:23 ` [PATCH v3 36/50] perf maps: Reduce scope of map_rb_node and maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 37/50] perf maps: Fix up overlaps during fixup_end Ian Rogers
2023-10-24 22:23 ` [PATCH v3 38/50] perf maps: Switch from rbtree to lazily sorted array for addresses Ian Rogers
2023-10-24 22:23 ` [PATCH v3 39/50] perf maps: Get map before returning in maps__find Ian Rogers
2023-10-24 22:23 ` [PATCH v3 40/50] perf maps: Get map before returning in maps__find_by_name Ian Rogers
2023-10-24 22:23 ` [PATCH v3 41/50] perf maps: Get map before returning in maps__find_next_entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 42/50] perf maps: Hide maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 43/50] perf maps: Locking tidy up of nr_maps Ian Rogers
2023-10-24 22:23 ` [PATCH v3 44/50] perf dso: Reorder variables to save space in struct dso Ian Rogers
2023-10-24 22:23 ` [PATCH v3 45/50] perf report: Sort child tasks by tid Ian Rogers
2023-10-24 22:23 ` [PATCH v3 46/50] perf trace: Ignore thread hashing in summary Ian Rogers
2023-10-24 22:23 ` [PATCH v3 47/50] perf machine: Move fprintf to for_each loop and a callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 48/50] perf threads: Move threads to its own files Ian Rogers
2023-10-24 22:23 ` [PATCH v3 49/50] perf threads: Switch from rbtree to hashmap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 50/50] perf threads: Reduce table size from 256 to 8 Ian Rogers
2023-10-26 17:11 ` (subset) [PATCH v3 00/50] Improvements to memory use Namhyung Kim
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=20231024222353.3024098-10-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=anshuman.khandual@arm.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=changbin.du@huawei.com \
--cc=german.gomez@arm.com \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=kjain@linux.ibm.com \
--cc=kprateek.nayak@amd.com \
--cc=leo.yan@linaro.org \
--cc=liam.howlett@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=liuwenyu7@huawei.com \
--cc=mark.rutland@arm.com \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=ojeda@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=sandipan.das@amd.com \
--cc=seanjc@google.com \
--cc=siyanteng@loongson.cn \
--cc=song@kernel.org \
--cc=terrelln@fb.com \
--cc=yangjihong1@huawei.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