[PATCH 16/17] perf, tool: Add dso data caching

From: Jiri Olsa
Date: Sun Jul 22 2012 - 08:16:41 EST


Adding dso data caching so we don't need to open/read/close,
each time we want dso data.

The DSO data caching affects following functions:
dso__data_read_offset
dso__data_read_addr

Each DSO read tries to find the data (based on offset) inside
the cache. If it's not present it fills the cache from file,
and returns the data. If it is present, data are returned
with no file read.

Each data read is cached by reading cache page sized/aligned
amount of DSO data. The cache page size is hardcoded to 4096.
The cache is using RB tree with file offset as a sort key.

Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
---
tools/perf/util/symbol.c | 154 ++++++++++++++++++++++++++++++++++++++++------
tools/perf/util/symbol.h | 11 +++
2 files changed, 147 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ff4d603..d60490f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,6 +29,7 @@
#define NT_GNU_BUILD_ID 3
#endif

+static void dso_cache__free(struct rb_root *root);
static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
static int elf_read_build_id(Elf *elf, void *bf, size_t size);
static void dsos__add(struct list_head *head, struct dso *dso);
@@ -343,6 +344,7 @@ struct dso *dso__new(const char *name)
dso__set_short_name(dso, dso->name);
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->data_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->loaded = 0;
@@ -378,6 +380,7 @@ void dso__delete(struct dso *dso)
free((char *)dso->short_name);
if (dso->lname_alloc)
free(dso->long_name);
+ dso_cache__free(&dso->cache);
free(dso);
}

@@ -3001,22 +3004,87 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
return -EINVAL;
}

-static ssize_t dso_cache_read(struct dso *dso __used, u64 offset __used,
- u8 *data __used, ssize_t size __used)
+static void
+dso_cache__free(struct rb_root *root)
{
- return -EINVAL;
+ 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 int dso_cache_add(struct dso *dso __used, u64 offset __used,
- u8 *data __used, ssize_t size __used)
+static struct dso_cache*
+dso_cache__find(struct rb_root *root, u64 offset)
{
- return 0;
+ struct rb_node **p = &root->rb_node;
+ 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 read_dso_data(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
- ssize_t rsize = -1;
+ struct dso_cache *cache;
+ ssize_t ret;
int fd;

fd = dso__data_fd(dso, machine);
@@ -3024,28 +3092,78 @@ static ssize_t read_dso_data(struct dso *dso, struct machine *machine,
return -1;

do {
- if (-1 == lseek(fd, offset, SEEK_SET))
+ u64 cache_offset;
+
+ ret = -ENOMEM;
+
+ cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+ if (!cache)
break;

- rsize = read(fd, data, size);
- if (-1 == rsize)
+ cache_offset = offset & DSO__DATA_CACHE_MASK;
+ ret = -EINVAL;
+
+ if (-1 == lseek(fd, cache_offset, SEEK_SET))
break;

- if (dso_cache_add(dso, offset, data, size))
- pr_err("Failed to add data int dso cache.");
+ 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 (ret <= 0)
+ free(cache);
+
close(fd);
- return rsize;
+ return ret;
+}
+
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
+{
+ struct dso_cache *cache;
+
+ 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);
}

ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
- if (dso_cache_read(dso, offset, data, size))
- return read_dso_data(dso, machine, offset, data, size);
- return 0;
+ ssize_t r = 0;
+ u8 *p = data;
+
+ 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;
+
+ BUG_ON(ret > size);
+
+ r += ret;
+ p += ret;
+ offset += ret;
+ size -= ret;
+
+ } while (size);
+
+ return r;
}

ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9b9ea00..980d5f5 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -182,10 +182,21 @@ enum dso_swap_type {
DSO_SWAP__YES,
};

+#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;
enum dso_kernel_type kernel;
enum dso_swap_type needs_swap;
enum dso_binary_type symtab_type;
--
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/