Patchwork Reduce memory usage for storing LTO decl resolutions

login
register
mail settings
Submitter Andi Kleen
Date Sept. 4, 2012, 4:43 p.m.
Message ID <1346776997-8726-1-git-send-email-andi@firstfloor.org>
Download mbox | patch
Permalink /patch/181626/
State New
Headers show

Comments

Andi Kleen - Sept. 4, 2012, 4:43 p.m.
From: Andi Kleen <ak@linux.intel.com>

With a LTO build of a large project (>11k subfiles incrementially linked)
storing the LTO resolutions took over 0.5GB memory:

lto/lto.c:1087 (lto_resolution_read)                      0: 0.0%  540398500           15903: 0.0%

The reason is that the declaration indexes are quite sparse, but every subfile
got a full continuous vector for them. Since there are so many of them the
many vectors add up.

This patch instead stores the resolutions initially in a compact (index, resolution)
format. This is only expanded into a sparse vector for fast lookup when
the subfile is actually read, but then immediately freed. This means only one
vector is allocated at a time.

This brings the overhead for this down to less than 3MB for the test case:

lto/lto.c:1087 (lto_resolution_read)                      0: 0.0%    2821456           42186: 0.0%

Passed bootstrap and test suite on x86_64-linux.

Ok for 4.8 and possibly for 4.7?

-Andi

2012-09-04  Andi Kleen  <ak@linux.intel.com>

	* gcc/lto-streamer.h (res_pair): Add.
	(lto_file_decl_data): Replace resolutions with respairs.
	Add max_index.
	* gcc/lto/lto.c (lto_resolution_read): Remove max_index.  Add rp.
	Initialize respairs.
	(lto_file_finalize): Set up resolutions vector lazily from respairs.
---
 gcc/lto-streamer.h |   15 ++++++++++++++-
 gcc/lto/lto.c      |   31 ++++++++++++++++++++++---------
 2 files changed, 36 insertions(+), 10 deletions(-)
Steven Bosscher - Sept. 4, 2012, 10:49 p.m.
On Tue, Sep 4, 2012 at 6:43 PM, Andi Kleen <andi@firstfloor.org> wrote:
> +/* Compact representation of a index <-> resolution pair. Unpacked to an
> +   vector later. */
> +struct res_pair
> +{
> +  ld_plugin_symbol_resolution_t res;
> +  unsigned index;
> +};
> +typedef struct res_pair res_pair;
> +
> +DEF_VEC_P(res_pair);
> +DEF_VEC_ALLOC_P(res_pair, heap);

Did you mean to use DEF_VEC_O here?
(Not sure it matters after the vec rewrite for c++)

Ciao!
Steven
Richard Guenther - Sept. 5, 2012, 9:48 a.m.
On Wed, Sep 5, 2012 at 12:49 AM, Steven Bosscher <stevenb.gcc@gmail.com> wrote:
> On Tue, Sep 4, 2012 at 6:43 PM, Andi Kleen <andi@firstfloor.org> wrote:
>> +/* Compact representation of a index <-> resolution pair. Unpacked to an
>> +   vector later. */
>> +struct res_pair
>> +{
>> +  ld_plugin_symbol_resolution_t res;
>> +  unsigned index;
>> +};
>> +typedef struct res_pair res_pair;
>> +
>> +DEF_VEC_P(res_pair);
>> +DEF_VEC_ALLOC_P(res_pair, heap);
>
> Did you mean to use DEF_VEC_O here?
> (Not sure it matters after the vec rewrite for c++)

Should be indeed _O.  Ok with that change (double-check it still works
with the recent VEC C++ changes).  Ok to backport, check again if it works
properly though!

Thanks,
Richard.

> Ciao!
> Steven
Diego Novillo - Sept. 5, 2012, 11:18 a.m.
On 2012-09-04 18:49 , Steven Bosscher wrote:

> Did you mean to use DEF_VEC_O here?
> (Not sure it matters after the vec rewrite for c++)

It doesn't anymore.  But it will matter for backports.


Diego.

Patch

diff --git a/gcc/lto-streamer.h b/gcc/lto-streamer.h
index bed408a..19a35cb 100644
--- a/gcc/lto-streamer.h
+++ b/gcc/lto-streamer.h
@@ -513,6 +513,18 @@  typedef struct lto_out_decl_state *lto_out_decl_state_ptr;
 DEF_VEC_P(lto_out_decl_state_ptr);
 DEF_VEC_ALLOC_P(lto_out_decl_state_ptr, heap);
 
+/* Compact representation of a index <-> resolution pair. Unpacked to an 
+   vector later. */
+struct res_pair 
+{
+  ld_plugin_symbol_resolution_t res;
+  unsigned index;
+};
+typedef struct res_pair res_pair;
+
+DEF_VEC_P(res_pair);
+DEF_VEC_ALLOC_P(res_pair, heap);
+
 /* One of these is allocated for each object file that being compiled
    by lto.  This structure contains the tables that are needed by the
    serialized functions and ipa passes to connect themselves to the
@@ -548,7 +560,8 @@  struct GTY(()) lto_file_decl_data
   unsigned HOST_WIDE_INT id;
 
   /* Symbol resolutions for this file */
-  VEC(ld_plugin_symbol_resolution_t,heap) * GTY((skip)) resolutions;
+  VEC(res_pair, heap) * GTY((skip)) respairs;
+  unsigned max_index;
 
   struct gcov_ctr_summary GTY((skip)) profile_info;
 };
diff --git a/gcc/lto/lto.c b/gcc/lto/lto.c
index bd91c39..5da5412 100644
--- a/gcc/lto/lto.c
+++ b/gcc/lto/lto.c
@@ -1012,7 +1012,6 @@  lto_resolution_read (splay_tree file_ids, FILE *resolution, lto_file *file)
   unsigned int num_symbols;
   unsigned int i;
   struct lto_file_decl_data *file_data;
-  unsigned max_index = 0;
   splay_tree_node nd = NULL; 
 
   if (!resolution)
@@ -1054,13 +1053,12 @@  lto_resolution_read (splay_tree file_ids, FILE *resolution, lto_file *file)
       unsigned int j;
       unsigned int lto_resolution_str_len =
 	sizeof (lto_resolution_str) / sizeof (char *);
+      res_pair rp;
 
       t = fscanf (resolution, "%u " HOST_WIDE_INT_PRINT_HEX_PURE " %26s %*[^\n]\n", 
 		  &index, &id, r_str);
       if (t != 3)
         internal_error ("invalid line in the resolution file");
-      if (index > max_index)
-	max_index = index;
 
       for (j = 0; j < lto_resolution_str_len; j++)
 	{
@@ -1082,11 +1080,13 @@  lto_resolution_read (splay_tree file_ids, FILE *resolution, lto_file *file)
 	}
 
       file_data = (struct lto_file_decl_data *)nd->value;
-      VEC_safe_grow_cleared (ld_plugin_symbol_resolution_t, heap, 
-			     file_data->resolutions,
-			     max_index + 1);
-      VEC_replace (ld_plugin_symbol_resolution_t, 
-		   file_data->resolutions, index, r);
+      /* The indexes are very sparse. To save memory save them in a compact
+         format that is only unpacked later when the subfile is processed. */
+      rp.res = r;
+      rp.index = index;
+      VEC_safe_push (res_pair, heap, file_data->respairs, rp);
+      if (file_data->max_index < index)
+        file_data->max_index = index;
     }
 }
 
@@ -1166,6 +1166,18 @@  lto_file_finalize (struct lto_file_decl_data *file_data, lto_file *file)
 {
   const char *data;
   size_t len;
+  VEC(ld_plugin_symbol_resolution_t,heap) *resolutions = NULL;
+  int i;
+  res_pair *rp;
+
+  /* Create vector for fast access of resolution. We do this lazily
+     to save memory. */ 
+  VEC_safe_grow_cleared (ld_plugin_symbol_resolution_t, heap, 
+                            resolutions,
+                            file_data->max_index + 1);
+  for (i = 0; VEC_iterate (res_pair, file_data->respairs, i, rp); i++)
+    VEC_replace (ld_plugin_symbol_resolution_t, resolutions, rp->index, rp->res);
+  VEC_free (res_pair, heap, file_data->respairs);
 
   file_data->renaming_hash_table = lto_create_renaming_table ();
   file_data->file_name = file->filename;
@@ -1175,7 +1187,8 @@  lto_file_finalize (struct lto_file_decl_data *file_data, lto_file *file)
       internal_error ("cannot read LTO decls from %s", file_data->file_name);
       return;
     }
-  lto_read_decls (file_data, data, file_data->resolutions);
+  /* Frees resolutions */
+  lto_read_decls (file_data, data, resolutions);
   lto_free_section_data (file_data, LTO_section_decls, NULL, data, len);
 }