lkml.org 
[lkml]   [2014]   [Apr]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 3/3] perf tools: Replace dso data cache with mapped data
Date
Removing dso data cache processing and mapping
whole dso object instead when requested.

Got about 13% speed up in dso__data_read_offset function
for report command processing dwarf unwind stacks.

Output from report over 1.5 GB data with DWARF unwind stacks:
(TODO fix perf diff)

13.63% perf.old perf.old [.] dso__data_read_offset

0.32% perf perf [.] dso__data_read_offset

And overall speedup:

Performance counter stats for './perf.old report -i perf-test.data --stdio':

113,076,591,004 cycles:u # 2.675 GHz
163,353,590,494 instructions:u # 1.44 insns per cycle
42269.774797 task-clock (msec) # 1.000 CPUs utilized

42.267550053 seconds time elapsed

Performance counter stats for './perf report -i perf-test.data --stdio':

92,953,167,072 cycles:u # 2.534 GHz
132,967,448,023 instructions:u # 1.43 insns per cycle
36683.242639 task-clock (msec) # 1.000 CPUs utilized

36.682799394 seconds time elapsed

Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Jean Pihet <jean.pihet@linaro.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/tests/dso-data.c | 7 ++
tools/perf/util/dso.c | 185 +++++++++++---------------------------------
tools/perf/util/dso.h | 13 +---
3 files changed, 54 insertions(+), 151 deletions(-)

diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 9cc81a3..024c15f 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -40,6 +40,13 @@ static char *test_file(int size)
return templ;
}

+/*
+ * The data access is now pure memory map of the file,
+ * so we dont need DSO__DATA_CACHE_SIZE anymore.
+ * Anyway keeping it for the sake of this test to
+ * ensure dso__data_read_offset interface works.
+ */
+#define DSO__DATA_CACHE_SIZE 4096
#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)

struct test_data_offset {
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 0dca5d6..f274c85 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,5 @@
+#include <sys/mman.h>
+
#include "symbol.h"
#include "dso.h"
#include "machine.h"
@@ -161,6 +163,14 @@ static int open_dso(struct dso *dso, struct machine *machine)

static void dso__data_close(struct dso *dso)
{
+ if (dso->data_mmap) {
+ size_t size = PERF_ALIGN(dso->data_size, page_size);
+
+ if (munmap(dso->data_mmap, size))
+ pr_err("dso mmap failed, munmap: %s\n",
+ strerror(errno));
+ }
+
if (dso->data_fd >= 0)
close(dso->data_fd);
}
@@ -191,164 +201,61 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
return -EINVAL;
}

-static void
-dso_cache__free(struct rb_root *root)
-{
- struct rb_node *next = rb_first(root);
-
- while (next) {
- struct dso_cache *cache;
-
- cache = rb_entry(next, struct dso_cache, rb_node);
- next = rb_next(&cache->rb_node);
- rb_erase(&cache->rb_node, root);
- free(cache);
- }
-}
-
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static int dso__data_mmap(struct dso *dso, struct machine *machine, char **ptr)
{
- struct rb_node * const *p = &root->rb_node;
- const struct rb_node *parent = NULL;
- struct dso_cache *cache;
-
- while (*p != NULL) {
- u64 end;
-
- parent = *p;
- cache = rb_entry(parent, struct dso_cache, rb_node);
- end = cache->offset + DSO__DATA_CACHE_SIZE;
-
- if (offset < cache->offset)
- p = &(*p)->rb_left;
- else if (offset >= end)
- p = &(*p)->rb_right;
- else
- return cache;
- }
- return NULL;
-}
-
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
-{
- struct rb_node **p = &root->rb_node;
- struct rb_node *parent = NULL;
- struct dso_cache *cache;
- u64 offset = new->offset;
-
- while (*p != NULL) {
- u64 end;
-
- parent = *p;
- cache = rb_entry(parent, struct dso_cache, rb_node);
- end = cache->offset + DSO__DATA_CACHE_SIZE;
-
- if (offset < cache->offset)
- p = &(*p)->rb_left;
- else if (offset >= end)
- p = &(*p)->rb_right;
- }
-
- rb_link_node(&new->rb_node, parent, p);
- rb_insert_color(&new->rb_node, root);
-}
-
-static ssize_t
-dso_cache__memcpy(struct dso_cache *cache, u64 offset,
- u8 *data, u64 size)
-{
- u64 cache_offset = offset - cache->offset;
- u64 cache_size = min(cache->size - cache_offset, size);
-
- memcpy(data, cache->data + cache_offset, cache_size);
- return cache_size;
-}
-
-static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
-{
- struct dso_cache *cache;
- ssize_t ret;
+ struct stat st;
int fd;
+ char *m;
+
+ if (dso->data_mmap)
+ goto out;

fd = dso__data_fd(dso, machine);
if (fd < 0)
- return -1;
-
- do {
- u64 cache_offset;
-
- ret = -ENOMEM;
-
- cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
- if (!cache)
- break;
-
- cache_offset = offset & DSO__DATA_CACHE_MASK;
- ret = -EINVAL;
-
- if (-1 == lseek(fd, cache_offset, SEEK_SET))
- break;
+ return fd;

- ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
- if (ret <= 0)
- break;
-
- cache->offset = cache_offset;
- cache->size = ret;
- dso_cache__insert(&dso->cache, cache);
-
- ret = dso_cache__memcpy(cache, offset, data, size);
-
- } while (0);
+ if (fstat(fd, &st)) {
+ pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+ return -1;
+ }

- if (ret <= 0)
- free(cache);
+ dso->data_size = st.st_size;

- return ret;
-}
+ m = mmap(0, PERF_ALIGN(dso->data_size, page_size),
+ PROT_READ, MAP_SHARED, fd, 0);
+ if (m == MAP_FAILED) {
+ pr_err("dso mmap failed, mmap: %s\n", strerror(errno));
+ return -1;
+ }

-static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
-{
- struct dso_cache *cache;
+ dso->data_mmap = m;

- cache = dso_cache__find(&dso->cache, offset);
- if (cache)
- return dso_cache__memcpy(cache, offset, data, size);
- else
- return dso_cache__read(dso, machine, offset, data, size);
+out:
+ *ptr = dso->data_mmap;
+ return 0;
}

ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
- ssize_t r = 0;
- u8 *p = data;
+ ssize_t rsize = size;
+ char *m;

- do {
- ssize_t ret;
-
- ret = dso_cache_read(dso, machine, offset, p, size);
- if (ret < 0)
- return ret;
-
- /* Reached EOF, return what we have. */
- if (!ret)
- break;
+ if (dso__data_mmap(dso, machine, &m))
+ return -1;

- BUG_ON(ret > size);
+ if (offset > dso->data_size)
+ return -1;

- r += ret;
- p += ret;
- offset += ret;
- size -= ret;
+ /* unlikely, but anyway.. check overflow ;-) */
+ if (offset + size < offset)
+ return -1;

- } while (size);
+ if (offset + size > dso->data_size)
+ rsize = dso->data_size - offset;

- return r;
+ memcpy(data, m + offset, rsize);
+ return rsize;
}

ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
@@ -478,7 +385,6 @@ struct dso *dso__new(const char *name)
dso__set_short_name(dso, dso->name, false);
for (i = 0; i < MAP__NR_TYPES; ++i)
dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
- dso->cache = RB_ROOT;
dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->loaded = 0;
@@ -513,7 +419,6 @@ void dso__delete(struct dso *dso)
}

dso__data_close(dso);
- dso_cache__free(&dso->cache);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
free(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 6e48cdc..fe4e4aa 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -62,21 +62,10 @@ enum dso_swap_type {
____r; \
})

-#define DSO__DATA_CACHE_SIZE 4096
-#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
-
-struct dso_cache {
- struct rb_node rb_node;
- u64 offset;
- u64 size;
- char data[0];
-};
-
struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
- struct rb_root cache;
void *a2l;
char *symsrc_filename;
unsigned int a2l_fails;
@@ -100,6 +89,8 @@ struct dso {
u16 long_name_len;
u16 short_name_len;
int data_fd;
+ size_t data_size;
+ char *data_mmap;
char name[0];
};

--
1.8.3.1


\
 
 \ /
  Last update: 2014-04-17 20:01    [W:0.191 / U:0.184 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site