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 44/50] perf dso: Reorder variables to save space in struct dso
Date: Tue, 24 Oct 2023 15:23:47 -0700 [thread overview]
Message-ID: <20231024222353.3024098-45-irogers@google.com> (raw)
In-Reply-To: <20231024222353.3024098-1-irogers@google.com>
Save 40 bytes and move from 8 to 7 cache lines. Make variable dwfl
dependent on being a powerpc build. Squeeze bits of int/enum types
when appropriate. Remove holes/padding by reordering variables.
Before:
```
struct dso {
struct mutex lock; /* 0 40 */
struct list_head node; /* 40 16 */
struct rb_node rb_node __attribute__((__aligned__(8))); /* 56 24 */
/* --- cacheline 1 boundary (64 bytes) was 16 bytes ago --- */
struct rb_root * root; /* 80 8 */
struct rb_root_cached symbols; /* 88 16 */
struct symbol * * symbol_names; /* 104 8 */
size_t symbol_names_len; /* 112 8 */
struct rb_root_cached inlined_nodes; /* 120 16 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
struct rb_root_cached srclines; /* 136 16 */
struct {
u64 addr; /* 152 8 */
struct symbol * symbol; /* 160 8 */
} last_find_result; /* 152 16 */
void * a2l; /* 168 8 */
char * symsrc_filename; /* 176 8 */
unsigned int a2l_fails; /* 184 4 */
enum dso_space_type kernel; /* 188 4 */
/* --- cacheline 3 boundary (192 bytes) --- */
_Bool is_kmod; /* 192 1 */
/* XXX 3 bytes hole, try to pack */
enum dso_swap_type needs_swap; /* 196 4 */
enum dso_binary_type symtab_type; /* 200 4 */
enum dso_binary_type binary_type; /* 204 4 */
enum dso_load_errno load_errno; /* 208 4 */
u8 adjust_symbols:1; /* 212: 0 1 */
u8 has_build_id:1; /* 212: 1 1 */
u8 header_build_id:1; /* 212: 2 1 */
u8 has_srcline:1; /* 212: 3 1 */
u8 hit:1; /* 212: 4 1 */
u8 annotate_warned:1; /* 212: 5 1 */
u8 auxtrace_warned:1; /* 212: 6 1 */
u8 short_name_allocated:1; /* 212: 7 1 */
u8 long_name_allocated:1; /* 213: 0 1 */
u8 is_64_bit:1; /* 213: 1 1 */
/* XXX 6 bits hole, try to pack */
_Bool sorted_by_name; /* 214 1 */
_Bool loaded; /* 215 1 */
u8 rel; /* 216 1 */
/* XXX 7 bytes hole, try to pack */
struct build_id bid; /* 224 32 */
/* --- cacheline 4 boundary (256 bytes) --- */
u64 text_offset; /* 256 8 */
u64 text_end; /* 264 8 */
const char * short_name; /* 272 8 */
const char * long_name; /* 280 8 */
u16 long_name_len; /* 288 2 */
u16 short_name_len; /* 290 2 */
/* XXX 4 bytes hole, try to pack */
void * dwfl; /* 296 8 */
struct auxtrace_cache * auxtrace_cache; /* 304 8 */
int comp; /* 312 4 */
/* XXX 4 bytes hole, try to pack */
/* --- cacheline 5 boundary (320 bytes) --- */
struct {
struct rb_root cache; /* 320 8 */
int fd; /* 328 4 */
int status; /* 332 4 */
u32 status_seen; /* 336 4 */
/* XXX 4 bytes hole, try to pack */
u64 file_size; /* 344 8 */
struct list_head open_entry; /* 352 16 */
u64 elf_base_addr; /* 368 8 */
u64 debug_frame_offset; /* 376 8 */
/* --- cacheline 6 boundary (384 bytes) --- */
u64 eh_frame_hdr_addr; /* 384 8 */
u64 eh_frame_hdr_offset; /* 392 8 */
} data; /* 320 80 */
struct {
u32 id; /* 400 4 */
u32 sub_id; /* 404 4 */
struct perf_env * env; /* 408 8 */
} bpf_prog; /* 400 16 */
union {
void * priv; /* 416 8 */
u64 db_id; /* 416 8 */
}; /* 416 8 */
struct nsinfo * nsinfo; /* 424 8 */
struct dso_id id; /* 432 24 */
/* --- cacheline 7 boundary (448 bytes) was 8 bytes ago --- */
refcount_t refcnt; /* 456 4 */
char name[]; /* 460 0 */
/* size: 464, cachelines: 8, members: 49 */
/* sum members: 440, holes: 4, sum holes: 18 */
/* sum bitfield members: 10 bits, bit holes: 1, sum bit holes: 6 bits */
/* padding: 4 */
/* forced alignments: 1 */
/* last cacheline: 16 bytes */
} __attribute__((__aligned__(8)));
```
After:
```
struct dso {
struct mutex lock; /* 0 40 */
struct list_head node; /* 40 16 */
struct rb_node rb_node __attribute__((__aligned__(8))); /* 56 24 */
/* --- cacheline 1 boundary (64 bytes) was 16 bytes ago --- */
struct rb_root * root; /* 80 8 */
struct rb_root_cached symbols; /* 88 16 */
struct symbol * * symbol_names; /* 104 8 */
size_t symbol_names_len; /* 112 8 */
struct rb_root_cached inlined_nodes; /* 120 16 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
struct rb_root_cached srclines; /* 136 16 */
struct {
u64 addr; /* 152 8 */
struct symbol * symbol; /* 160 8 */
} last_find_result; /* 152 16 */
struct build_id bid; /* 168 32 */
/* --- cacheline 3 boundary (192 bytes) was 8 bytes ago --- */
u64 text_offset; /* 200 8 */
u64 text_end; /* 208 8 */
const char * short_name; /* 216 8 */
const char * long_name; /* 224 8 */
void * a2l; /* 232 8 */
char * symsrc_filename; /* 240 8 */
struct nsinfo * nsinfo; /* 248 8 */
/* --- cacheline 4 boundary (256 bytes) --- */
struct auxtrace_cache * auxtrace_cache; /* 256 8 */
union {
void * priv; /* 264 8 */
u64 db_id; /* 264 8 */
}; /* 264 8 */
struct {
struct perf_env * env; /* 272 8 */
u32 id; /* 280 4 */
u32 sub_id; /* 284 4 */
} bpf_prog; /* 272 16 */
struct {
struct rb_root cache; /* 288 8 */
struct list_head open_entry; /* 296 16 */
u64 file_size; /* 312 8 */
/* --- cacheline 5 boundary (320 bytes) --- */
u64 elf_base_addr; /* 320 8 */
u64 debug_frame_offset; /* 328 8 */
u64 eh_frame_hdr_addr; /* 336 8 */
u64 eh_frame_hdr_offset; /* 344 8 */
int fd; /* 352 4 */
int status; /* 356 4 */
u32 status_seen; /* 360 4 */
} data; /* 288 80 */
/* XXX last struct has 4 bytes of padding */
struct dso_id id; /* 368 24 */
/* --- cacheline 6 boundary (384 bytes) was 8 bytes ago --- */
unsigned int a2l_fails; /* 392 4 */
int comp; /* 396 4 */
refcount_t refcnt; /* 400 4 */
enum dso_load_errno load_errno; /* 404 4 */
u16 long_name_len; /* 408 2 */
u16 short_name_len; /* 410 2 */
enum dso_binary_type symtab_type:8; /* 412: 0 4 */
enum dso_binary_type binary_type:8; /* 412: 8 4 */
enum dso_space_type kernel:2; /* 412:16 4 */
enum dso_swap_type needs_swap:2; /* 412:18 4 */
/* Bitfield combined with next fields */
_Bool is_kmod:1; /* 414: 4 1 */
u8 adjust_symbols:1; /* 414: 5 1 */
u8 has_build_id:1; /* 414: 6 1 */
u8 header_build_id:1; /* 414: 7 1 */
u8 has_srcline:1; /* 415: 0 1 */
u8 hit:1; /* 415: 1 1 */
u8 annotate_warned:1; /* 415: 2 1 */
u8 auxtrace_warned:1; /* 415: 3 1 */
u8 short_name_allocated:1; /* 415: 4 1 */
u8 long_name_allocated:1; /* 415: 5 1 */
u8 is_64_bit:1; /* 415: 6 1 */
/* XXX 1 bit hole, try to pack */
_Bool sorted_by_name; /* 416 1 */
_Bool loaded; /* 417 1 */
u8 rel; /* 418 1 */
char name[]; /* 419 0 */
/* size: 424, cachelines: 7, members: 48 */
/* sum members: 415 */
/* sum bitfield members: 31 bits, bit holes: 1, sum bit holes: 1 bits */
/* padding: 5 */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 40 bytes */
} __attribute__((__aligned__(8)));
```
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/dso.h | 84 +++++++++++++++++++++----------------------
1 file changed, 42 insertions(+), 42 deletions(-)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 3759de8c2267..8bdc17d78b02 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -158,66 +158,66 @@ struct dso {
u64 addr;
struct symbol *symbol;
} last_find_result;
- void *a2l;
- char *symsrc_filename;
- unsigned int a2l_fails;
- enum dso_space_type kernel;
- bool is_kmod;
- enum dso_swap_type needs_swap;
- enum dso_binary_type symtab_type;
- enum dso_binary_type binary_type;
- enum dso_load_errno load_errno;
- u8 adjust_symbols:1;
- u8 has_build_id:1;
- u8 header_build_id:1;
- u8 has_srcline:1;
- u8 hit:1;
- u8 annotate_warned:1;
- u8 auxtrace_warned:1;
- u8 short_name_allocated:1;
- u8 long_name_allocated:1;
- u8 is_64_bit:1;
- bool sorted_by_name;
- bool loaded;
- u8 rel;
struct build_id bid;
u64 text_offset;
u64 text_end;
const char *short_name;
const char *long_name;
- u16 long_name_len;
- u16 short_name_len;
+ void *a2l;
+ char *symsrc_filename;
+#if defined(__powerpc__)
void *dwfl; /* DWARF debug info */
+#endif
+ struct nsinfo *nsinfo;
struct auxtrace_cache *auxtrace_cache;
- int comp;
-
+ union { /* Tool specific area */
+ void *priv;
+ u64 db_id;
+ };
+ /* bpf prog information */
+ struct {
+ struct perf_env *env;
+ u32 id;
+ u32 sub_id;
+ } bpf_prog;
/* dso data file */
struct {
struct rb_root cache;
- int fd;
- int status;
- u32 status_seen;
- u64 file_size;
struct list_head open_entry;
+ u64 file_size;
u64 elf_base_addr;
u64 debug_frame_offset;
u64 eh_frame_hdr_addr;
u64 eh_frame_hdr_offset;
+ int fd;
+ int status;
+ u32 status_seen;
} data;
- /* bpf prog information */
- struct {
- u32 id;
- u32 sub_id;
- struct perf_env *env;
- } bpf_prog;
-
- union { /* Tool specific area */
- void *priv;
- u64 db_id;
- };
- struct nsinfo *nsinfo;
struct dso_id id;
+ unsigned int a2l_fails;
+ int comp;
refcount_t refcnt;
+ enum dso_load_errno load_errno;
+ u16 long_name_len;
+ u16 short_name_len;
+ enum dso_binary_type symtab_type:8;
+ enum dso_binary_type binary_type:8;
+ enum dso_space_type kernel:2;
+ enum dso_swap_type needs_swap:2;
+ bool is_kmod:1;
+ u8 adjust_symbols:1;
+ u8 has_build_id:1;
+ u8 header_build_id:1;
+ u8 has_srcline:1;
+ u8 hit:1;
+ u8 annotate_warned:1;
+ u8 auxtrace_warned:1;
+ u8 short_name_allocated:1;
+ u8 long_name_allocated:1;
+ u8 is_64_bit:1;
+ bool sorted_by_name;
+ bool loaded;
+ u8 rel;
char name[];
};
--
2.42.0.758.gaed0368e0e-goog
next prev parent reply other threads:[~2023-10-24 22:28 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 ` [PATCH v3 09/50] perf callchain: Make brtype_stat in callchain_list optional Ian Rogers
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 ` Ian Rogers [this message]
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=20231024222353.3024098-45-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.