Skip to content

Commit

Permalink
Use a perfect hash map for the registry controlled domain service.
Browse files Browse the repository at this point in the history 
On my very fast machine, building the std::set in release mode on startup and blocks the UI thread for 15ms (there are > 3300 entries).  It also uses 275KB of memory, not including 50KB of data in the dll.  Using a perfect hash map, there's no startup cost.  The dll's size increases by 135KB but there's no extra memory consumption, leading to a memory reduction of 140KB.

Review URL: http://codereview.chromium.org/515001

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@35196 0039d316-1c4b-4281-b951-d872f2087c98
  • Loading branch information
jam@chromium.org committed Dec 23, 2009
1 parent f09bc4e commit 4fa642f
Show file tree
Hide file tree
Showing 11 changed files with 18,583 additions and 3,927 deletions.
18,069 changes: 14,386 additions & 3,683 deletions net/base/effective_tld_names.cc
View file

Large diffs are not rendered by default.

3,651 changes: 3,651 additions & 0 deletions net/base/effective_tld_names.gperf
View file

Large diffs are not rendered by default.

183 changes: 183 additions & 0 deletions net/base/effective_tld_names_unittest1.cc
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,183 @@
/* C++ code produced by gperf version 3.0.3 */
/* Command-line: gperf -a -L C++ -C -c -o -t -k '*' -NFindDomain -ZPerfect_Hash_Test1 -D effective_tld_names_unittest1.gperf */

#if !((' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
&& ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
&& (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
&& ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
&& ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
&& ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
&& ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
&& ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
&& ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
&& ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
&& ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
&& ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
&& ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
&& ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
&& ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
&& ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
&& ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
&& ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
&& ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
&& ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
&& ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
&& ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
&& ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126))
/* The character set is not based on ISO-646. */
#error "gperf generated tables don't work with this execution character set. Please report a bug to <bug-gnu-gperf@gnu.org>."
#endif

#line 1 "effective_tld_names_unittest1.gperf"

// Copyright (c) 2009 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that
// can be found in the LICENSE file.
// Test file used by registry_controlled_domain_unittest.
// We edit this file manually, then run
// gperf -a -L "C++" -C -G -c -o -t -k '*' -NFindDomain -ZPerfect_Hash_Test2 -Hhash_test1 -Wword_list1 -D effective_tld_names_unittest1.gperf > effective_tld_names_unittest1.cc
// to generate the perfect hashmap.
#line 10 "effective_tld_names_unittest1.gperf"
struct DomainRule {
const char *name;
int type; // 1: exception, 2: wildcard
};

#define TOTAL_KEYWORDS 8
#define MIN_WORD_LENGTH 1
#define MAX_WORD_LENGTH 11
#define MIN_HASH_VALUE 1
#define MAX_HASH_VALUE 16
/* maximum key range = 16, duplicates = 0 */

class Perfect_Hash_Test1
{
private:
static inline unsigned int hash (const char *str, unsigned int len);
public:
static const struct DomainRule *FindDomain (const char *str, unsigned int len);
};

inline unsigned int
Perfect_Hash_Test1::hash (register const char *str, register unsigned int len)
{
static const unsigned char asso_values[] =
{
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 0, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 0, 0, 0,
17, 5, 0, 17, 17, 17, 0, 17, 17, 0,
17, 0, 0, 17, 0, 17, 17, 17, 17, 17,
17, 17, 0, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
17, 17, 17, 17, 17, 17
};
register int hval = len;

switch (hval)
{
default:
hval += asso_values[(unsigned char)str[10]];
/*FALLTHROUGH*/
case 10:
hval += asso_values[(unsigned char)str[9]];
/*FALLTHROUGH*/
case 9:
hval += asso_values[(unsigned char)str[8]];
/*FALLTHROUGH*/
case 8:
hval += asso_values[(unsigned char)str[7]];
/*FALLTHROUGH*/
case 7:
hval += asso_values[(unsigned char)str[6]];
/*FALLTHROUGH*/
case 6:
hval += asso_values[(unsigned char)str[5]];
/*FALLTHROUGH*/
case 5:
hval += asso_values[(unsigned char)str[4]];
/*FALLTHROUGH*/
case 4:
hval += asso_values[(unsigned char)str[3]];
/*FALLTHROUGH*/
case 3:
hval += asso_values[(unsigned char)str[2]];
/*FALLTHROUGH*/
case 2:
hval += asso_values[(unsigned char)str[1]];
/*FALLTHROUGH*/
case 1:
hval += asso_values[(unsigned char)str[0]];
break;
}
return hval;
}

const struct DomainRule *
Perfect_Hash_Test1::FindDomain (register const char *str, register unsigned int len)
{
static const struct DomainRule wordlist[] =
{
#line 21 "effective_tld_names_unittest1.gperf"
{"c", 2},
#line 15 "effective_tld_names_unittest1.gperf"
{"jp", 0},
#line 22 "effective_tld_names_unittest1.gperf"
{"b.c", 1},
#line 16 "effective_tld_names_unittest1.gperf"
{"ac.jp", 0},
#line 17 "effective_tld_names_unittest1.gperf"
{"bar.jp", 2},
#line 18 "effective_tld_names_unittest1.gperf"
{"baz.bar.jp", 2},
#line 20 "effective_tld_names_unittest1.gperf"
{"bar.baz.com", 0},
#line 19 "effective_tld_names_unittest1.gperf"
{"pref.bar.jp", 1}
};

static const signed char lookup[] =
{
-1, 0, 1, 2, -1, 3, 4, -1, -1, -1, 5, 6, -1, -1,
-1, -1, 7
};

if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
{
register int key = hash (str, len);

if (key <= MAX_HASH_VALUE && key >= 0)
{
register int index = lookup[key];

if (index >= 0)
{
register const char *s = wordlist[index].name;

if (*str == *s && !strncmp (str + 1, s + 1, len - 1) && s[len] == '\0')
return &wordlist[index];
}
}
}
return 0;
}
#line 23 "effective_tld_names_unittest1.gperf"

23 changes: 23 additions & 0 deletions net/base/effective_tld_names_unittest1.gperf
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
%{
// Copyright (c) 2009 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that
// can be found in the LICENSE file.
// Test file used by registry_controlled_domain_unittest.
// We edit this file manually, then run
// gperf -a -L "C++" -C -c -o -t -k '*' -NFindDomain -ZPerfect_Hash_Test1 -D effective_tld_names_unittest1.gperf > effective_tld_names_unittest1.cc
// to generate the perfect hashmap.
%}
struct DomainRule {
const char *name;
int type; // 1: exception, 2: wildcard
};
%%
jp, 0
ac.jp, 0
bar.jp, 2
baz.bar.jp, 2
pref.bar.jp, 1
bar.baz.com, 0
c, 2
b.c, 1
%%
155 changes: 155 additions & 0 deletions net/base/effective_tld_names_unittest2.cc
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,155 @@
/* C++ code produced by gperf version 3.0.3 */
/* Command-line: gperf -a -L C++ -C -c -o -t -k '*' -NFindDomain -ZPerfect_Hash_Test2 -D effective_tld_names_unittest2.gperf */

#if !((' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
&& ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
&& (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
&& ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
&& ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
&& ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
&& ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
&& ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
&& ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
&& ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
&& ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
&& ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
&& ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
&& ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
&& ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
&& ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
&& ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
&& ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
&& ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
&& ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
&& ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
&& ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
&& ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126))
/* The character set is not based on ISO-646. */
#error "gperf generated tables don't work with this execution character set. Please report a bug to <bug-gnu-gperf@gnu.org>."
#endif

#line 1 "effective_tld_names_unittest2.gperf"

// Copyright (c) 2009 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that
// can be found in the LICENSE file.
// Test file used by registry_controlled_domain_unittest.
// We edit this file manually, then run
// gperf -a -L "C++" -C -c -o -t -k '*' -NFindDomain -ZPerfect_Hash_Test2 -D effective_tld_names_unittest2.gperf > effective_tld_names_unittest2.cc
// to generate the perfect hashmap.
#line 10 "effective_tld_names_unittest2.gperf"
struct DomainRule {
const char *name;
int type; // 1: exception, 2: wildcard
};

#define TOTAL_KEYWORDS 2
#define MIN_WORD_LENGTH 2
#define MAX_WORD_LENGTH 6
#define MIN_HASH_VALUE 2
#define MAX_HASH_VALUE 6
/* maximum key range = 5, duplicates = 0 */

class Perfect_Hash_Test2
{
private:
static inline unsigned int hash (const char *str, unsigned int len);
public:
static const struct DomainRule *FindDomain (const char *str, unsigned int len);
};

inline unsigned int
Perfect_Hash_Test2::hash (register const char *str, register unsigned int len)
{
static const unsigned char asso_values[] =
{
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 0, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 0, 0, 7,
7, 7, 7, 7, 7, 7, 0, 7, 7, 7,
7, 7, 0, 7, 0, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 7, 7
};
register int hval = len;

switch (hval)
{
default:
hval += asso_values[(unsigned char)str[5]];
/*FALLTHROUGH*/
case 5:
hval += asso_values[(unsigned char)str[4]];
/*FALLTHROUGH*/
case 4:
hval += asso_values[(unsigned char)str[3]];
/*FALLTHROUGH*/
case 3:
hval += asso_values[(unsigned char)str[2]];
/*FALLTHROUGH*/
case 2:
hval += asso_values[(unsigned char)str[1]];
/*FALLTHROUGH*/
case 1:
hval += asso_values[(unsigned char)str[0]];
break;
}
return hval;
}

const struct DomainRule *
Perfect_Hash_Test2::FindDomain (register const char *str, register unsigned int len)
{
static const struct DomainRule wordlist[] =
{
#line 15 "effective_tld_names_unittest2.gperf"
{"jp", 0},
#line 16 "effective_tld_names_unittest2.gperf"
{"bar.jp", 0}
};

static const signed char lookup[] =
{
-1, -1, 0, -1, -1, -1, 1
};

if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
{
register int key = hash (str, len);

if (key <= MAX_HASH_VALUE && key >= 0)
{
register int index = lookup[key];

if (index >= 0)
{
register const char *s = wordlist[index].name;

if (*str == *s && !strncmp (str + 1, s + 1, len - 1) && s[len] == '\0')
return &wordlist[index];
}
}
}
return 0;
}
#line 17 "effective_tld_names_unittest2.gperf"

17 changes: 17 additions & 0 deletions net/base/effective_tld_names_unittest2.gperf
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
%{
// Copyright (c) 2009 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that
// can be found in the LICENSE file.
// Test file used by registry_controlled_domain_unittest.
// We edit this file manually, then run
// gperf -a -L "C++" -C -c -o -t -k '*' -NFindDomain -ZPerfect_Hash_Test2 -D effective_tld_names_unittest2.gperf > effective_tld_names_unittest2.cc
// to generate the perfect hashmap.
%}
struct DomainRule {
const char *name;
int type; // 1: exception, 2: wildcard
};
%%
jp, 0
bar.jp, 0
%%
Loading

0 comments on commit 4fa642f

Please sign in to comment.