Apache では静的ファイルの ETAG をどうやって生成しているのか確認してみたくなったので調査。
FileETag Directive は次のように説明されている
The FileETag directive allows you to choose which of these — if any — should be used. The recognized keywords are:
INode The file's i-node number will be included in the calculation MTime The date and time the file was last modified will be included Size The number of bytes in the file will be included All All available fields will be used. This is equivalent to: FileETag INode MTime Size
“All” の場合、次のようになる。
$ HEAD http://localhost/
200 OK
Connection: close
Date: Tue, 06 Jul 2010 04:22:52 GMT
Accept-Ranges: bytes
ETag: "16a386-2d-460ce601ebfc0"
Server: Apache/2.2.9 (Ubuntu) PHP/5.2.6-2ubuntu4.6 with Suhosin-Patch
Vary: Accept-Encoding
Content-Length: 45
Content-Type: text/html
Last-Modified: Mon, 19 Jan 2009 04:29:59 GMT
Client-Date: Tue, 06 Aug 2010 04:22:52 GMT
Client-Peer: 127.0.0.1:80
Client-Response-Num: 1
—
計算は次の箇所で行われている(Apache のバージョンは 2.2.15)
httpd-2.2.15/modules/http/http_etag.c
55 #define ETAG_WEAK "W/"
56 #define CHARS_PER_UINT64 (sizeof(apr_uint64_t) * 2)
57 /*
58 * Construct an entity tag (ETag) from resource information. If it's a real
59 * file, build in some of the file characteristics. If the modification time
60 * is newer than (request-time minus 1 second), mark the ETag as weak - it
61 * could be modified again in as short an interval. We rationalize the
62 * modification time we're given to keep it from being in the future.
63 */
64 AP_DECLARE(char *) ap_make_etag(request_rec *r, int force_weak)
65 {
...
91 /*
92 * Make an ETag header out of various pieces of information. We use
93 * the last-modified date and, if we have a real file, the
94 * length and inode number - note that this doesn't have to match
95 * the content-length (i.e. includes), it just has to be unique
96 * for the file.
97 *
98 * If the request was made within a second of the last-modified date,
99 * we send a weak tag instead of a strong one, since it could
100 * be modified again later in the second, and the validation
101 * would be incorrect.
102 */
103 if ((r->request_time - r->mtime > (1 * APR_USEC_PER_SEC)) &&
104 !force_weak) {
105 weak = NULL;
106 weak_len = 0;
107 }
108 else {
109 weak = ETAG_WEAK;
110 weak_len = sizeof(ETAG_WEAK);
111 }
112
113 if (r->finfo.filetype != 0) {
114 /*
115 * ETag gets set to [W/]"inode-size-mtime", modulo any
116 * FileETag keywords.
117 */
118 etag = apr_palloc(r->pool, weak_len + sizeof("\"--\"") +
119 3 * CHARS_PER_UINT64 + 1);
120 next = etag;
121 if (weak) {
122 while (*weak) {
123 *next++ = *weak++;
124 }
125 }
126 *next++ = '"';
127 bits_added = 0;
128 if (etag_bits & ETAG_INODE) {
129 next = etag_uint64_to_hex(next, r->finfo.inode); // Python:hex(statinfo.st_ino)
130 bits_added |= ETAG_INODE;
131 }
132 if (etag_bits & ETAG_SIZE) {
133 if (bits_added != 0) {
134 *next++ = '-';
135 }
136 next = etag_uint64_to_hex(next, r->finfo.size); // hex(statinfo.st_size)
137 bits_added |= ETAG_SIZE;
138 }
139 if (etag_bits & ETAG_MTIME) {
140 if (bits_added != 0) {
141 *next++ = '-';
142 }
143 next = etag_uint64_to_hex(next, r->mtime); // int(statinfo.st_mtime * 1000000))
144 }
145 *next++ = '"';
146 *next = '';
147 }
148 else {
149 /*
150 * Not a file document, so just use the mtime: [W/]"mtime"
151 */
...
164 }
165
166 return etag;
なお request_rec->mtime は次の箇所で定義されている
httpd-2.2.15/include/httpd.h
773 /**
774 * @brief A structure that represents the current request
775 */
776 struct request_rec {
...
861 /** Last modified time of the requested resource */
862 apr_time_t mtime;
さらに apr_time_t は次の箇所で typedef されている
httpd-2.2.15/srclib/apr/include/apr_time.h 45 /** number of microseconds since 00:00:00 january 1, 1970 UTC */ 46 typedef apr_int64_t apr_time_t;
—
結局 Python だと次のようになる
>>> import os
>>> statinfo = os.stat('/var/www/index.html')
>>> statinfo.st_ino
1483654L
>>> hex(_)
'0x16a386L'
>>> statinfo.st_size
45L
>>> hex(_)
'0x2dL'
>>> statinfo.st_mtime
1232339399.0
>>> hex(int(_ * 1000000))
'0x460ce601ebfc0L'
上記をまとめると
>>> print '%x-%x-%x' % (statinfo.st_ino,
... statinfo.st_size,
... int(statinfo.st_mtime * 1000000))
16a386-2d-460ce601ebfc0
これは、最初の ETAG の値「ETag: “16a386-2d-460ce601ebfc0″」と一致している。
Siguniang's Blog 