📄 mod_disk_cache.c
字号:
/* Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with * this work for additional information regarding copyright ownership. * The ASF licenses this file to You under the Apache License, Version 2.0 * (the "License"); you may not use this file except in compliance with * the License. You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */#include "apr_file_io.h"#include "apr_strings.h"#include "mod_cache.h"#include "mod_disk_cache.h"#include "ap_provider.h"#include "util_filter.h"#include "util_script.h"#include "util_charset.h"/* * mod_disk_cache: Disk Based HTTP 1.1 Cache. * * Flow to Find the .data file: * Incoming client requests URI /foo/bar/baz * Generate <hash> off of /foo/bar/baz * Open <hash>.header * Read in <hash>.header file (may contain Format #1 or Format #2) * If format #1 (Contains a list of Vary Headers): * Use each header name (from .header) with our request values (headers_in) to * regenerate <hash> using HeaderName+HeaderValue+.../foo/bar/baz * re-read in <hash>.header (must be format #2) * read in <hash>.data * * Format #1: * apr_uint32_t format; * apr_time_t expire; * apr_array_t vary_headers (delimited by CRLF) * * Format #2: * disk_cache_info_t (first sizeof(apr_uint32_t) bytes is the format) * entity name (dobj->name) [length is in disk_cache_info_t->name_len] * r->headers_out (delimited by CRLF) * CRLF * r->headers_in (delimited by CRLF) * CRLF */module AP_MODULE_DECLARE_DATA disk_cache_module;/* Forward declarations */static int remove_entity(cache_handle_t *h);static apr_status_t store_headers(cache_handle_t *h, request_rec *r, cache_info *i);static apr_status_t store_body(cache_handle_t *h, request_rec *r, apr_bucket_brigade *b);static apr_status_t recall_headers(cache_handle_t *h, request_rec *r);static apr_status_t recall_body(cache_handle_t *h, apr_pool_t *p, apr_bucket_brigade *bb);static apr_status_t read_array(request_rec *r, apr_array_header_t* arr, apr_file_t *file);/* * Local static functions */static char *header_file(apr_pool_t *p, disk_cache_conf *conf, disk_cache_object_t *dobj, const char *name){ if (!dobj->hashfile) { dobj->hashfile = ap_cache_generate_name(p, conf->dirlevels, conf->dirlength, name); } if (dobj->prefix) { return apr_pstrcat(p, dobj->prefix, CACHE_VDIR_SUFFIX, "/", dobj->hashfile, CACHE_HEADER_SUFFIX, NULL); } else { return apr_pstrcat(p, conf->cache_root, "/", dobj->hashfile, CACHE_HEADER_SUFFIX, NULL); }}static char *data_file(apr_pool_t *p, disk_cache_conf *conf, disk_cache_object_t *dobj, const char *name){ if (!dobj->hashfile) { dobj->hashfile = ap_cache_generate_name(p, conf->dirlevels, conf->dirlength, name); } if (dobj->prefix) { return apr_pstrcat(p, dobj->prefix, CACHE_VDIR_SUFFIX, "/", dobj->hashfile, CACHE_DATA_SUFFIX, NULL); } else { return apr_pstrcat(p, conf->cache_root, "/", dobj->hashfile, CACHE_DATA_SUFFIX, NULL); }}static void mkdir_structure(disk_cache_conf *conf, const char *file, apr_pool_t *pool){ apr_status_t rv; char *p; for (p = (char*)file + conf->cache_root_len + 1;;) { p = strchr(p, '/'); if (!p) break; *p = '\0'; rv = apr_dir_make(file, APR_UREAD|APR_UWRITE|APR_UEXECUTE, pool); if (rv != APR_SUCCESS && !APR_STATUS_IS_EEXIST(rv)) { /* XXX */ } *p = '/'; ++p; }}/* htcacheclean may remove directories underneath us. * So, we'll try renaming three times at a cost of 0.002 seconds. */static apr_status_t safe_file_rename(disk_cache_conf *conf, const char *src, const char *dest, apr_pool_t *pool){ apr_status_t rv; rv = apr_file_rename(src, dest, pool); if (rv != APR_SUCCESS) { int i; for (i = 0; i < 2 && rv != APR_SUCCESS; i++) { /* 1000 micro-seconds aka 0.001 seconds. */ apr_sleep(1000); mkdir_structure(conf, dest, pool); rv = apr_file_rename(src, dest, pool); } } return rv;}static apr_status_t file_cache_el_final(disk_cache_object_t *dobj, request_rec *r){ /* move the data over */ if (dobj->tfd) { apr_status_t rv; apr_file_close(dobj->tfd); /* This assumes that the tempfile is on the same file system * as the cache_root. If not, then we need a file copy/move * rather than a rename. */ rv = apr_file_rename(dobj->tempfile, dobj->datafile, r->pool); if (rv != APR_SUCCESS) { ap_log_error(APLOG_MARK, APLOG_WARNING, rv, r->server, "disk_cache: rename tempfile to datafile failed:" " %s -> %s", dobj->tempfile, dobj->datafile); apr_file_remove(dobj->tempfile, r->pool); } dobj->tfd = NULL; } return APR_SUCCESS;}static apr_status_t file_cache_errorcleanup(disk_cache_object_t *dobj, request_rec *r){ /* Remove the header file and the body file. */ apr_file_remove(dobj->hdrsfile, r->pool); apr_file_remove(dobj->datafile, r->pool); /* If we opened the temporary data file, close and remove it. */ if (dobj->tfd) { apr_file_close(dobj->tfd); apr_file_remove(dobj->tempfile, r->pool); dobj->tfd = NULL; } return APR_SUCCESS;}/* These two functions get and put state information into the data * file for an ap_cache_el, this state information will be read * and written transparent to clients of this module */static int file_cache_recall_mydata(apr_file_t *fd, cache_info *info, disk_cache_object_t *dobj, request_rec *r){ apr_status_t rv; char *urlbuff; disk_cache_info_t disk_info; apr_size_t len; /* read the data from the cache file */ len = sizeof(disk_cache_info_t); rv = apr_file_read_full(fd, &disk_info, len, &len); if (rv != APR_SUCCESS) { return rv; } /* Store it away so we can get it later. */ dobj->disk_info = disk_info; info->status = disk_info.status; info->date = disk_info.date; info->expire = disk_info.expire; info->request_time = disk_info.request_time; info->response_time = disk_info.response_time; /* Note that we could optimize this by conditionally doing the palloc * depending upon the size. */ urlbuff = apr_palloc(r->pool, disk_info.name_len + 1); len = disk_info.name_len; rv = apr_file_read_full(fd, urlbuff, len, &len); if (rv != APR_SUCCESS) { return rv; } urlbuff[disk_info.name_len] = '\0'; /* check that we have the same URL */ /* Would strncmp be correct? */ if (strcmp(urlbuff, dobj->name) != 0) { return APR_EGENERAL; } return APR_SUCCESS;}static const char* regen_key(apr_pool_t *p, apr_table_t *headers, apr_array_header_t *varray, const char *oldkey){ struct iovec *iov; int i, k; int nvec; const char *header; const char **elts; nvec = (varray->nelts * 2) + 1; iov = apr_palloc(p, sizeof(struct iovec) * nvec); elts = (const char **) varray->elts; /* TODO: * - Handle multiple-value headers better. (sort them?) * - Handle Case in-sensitive Values better. * This isn't the end of the world, since it just lowers the cache * hit rate, but it would be nice to fix. * * The majority are case insenstive if they are values (encoding etc). * Most of rfc2616 is case insensitive on header contents. * * So the better solution may be to identify headers which should be * treated case-sensitive? * HTTP URI's (3.2.3) [host and scheme are insensitive] * HTTP method (5.1.1) * HTTP-date values (3.3.1) * 3.7 Media Types [exerpt] * The type, subtype, and parameter attribute names are case- * insensitive. Parameter values might or might not be case-sensitive, * depending on the semantics of the parameter name. * 4.20 Except [exerpt] * Comparison of expectation values is case-insensitive for unquoted * tokens (including the 100-continue token), and is case-sensitive for * quoted-string expectation-extensions. */ for(i=0, k=0; i < varray->nelts; i++) { header = apr_table_get(headers, elts[i]); if (!header) { header = ""; } iov[k].iov_base = (char*) elts[i]; iov[k].iov_len = strlen(elts[i]); k++; iov[k].iov_base = (char*) header; iov[k].iov_len = strlen(header); k++; } iov[k].iov_base = (char*) oldkey; iov[k].iov_len = strlen(oldkey); k++; return apr_pstrcatv(p, iov, k, NULL);}static int array_alphasort(const void *fn1, const void *fn2){ return strcmp(*(char**)fn1, *(char**)fn2);}static void tokens_to_array(apr_pool_t *p, const char *data, apr_array_header_t *arr){ char *token; while ((token = ap_get_list_item(p, &data)) != NULL) { *((const char **) apr_array_push(arr)) = token; } /* Sort it so that "Vary: A, B" and "Vary: B, A" are stored the same. */ qsort((void *) arr->elts, arr->nelts, sizeof(char *), array_alphasort);}/* * Hook and mod_cache callback functions */static int create_entity(cache_handle_t *h, request_rec *r, const char *key, apr_off_t len){ disk_cache_conf *conf = ap_get_module_config(r->server->module_config, &disk_cache_module); cache_object_t *obj; disk_cache_object_t *dobj; if (conf->cache_root == NULL) { return DECLINED; } /* Allocate and initialize cache_object_t and disk_cache_object_t */ h->cache_obj = obj = apr_pcalloc(r->pool, sizeof(*obj)); obj->vobj = dobj = apr_pcalloc(r->pool, sizeof(*dobj)); obj->key = apr_pstrdup(r->pool, key); dobj->name = obj->key; dobj->prefix = NULL; /* Save the cache root */ dobj->root = apr_pstrndup(r->pool, conf->cache_root, conf->cache_root_len); dobj->root_len = conf->cache_root_len; dobj->datafile = data_file(r->pool, conf, dobj, key); dobj->hdrsfile = header_file(r->pool, conf, dobj, key); dobj->tempfile = apr_pstrcat(r->pool, conf->cache_root, AP_TEMPFILE, NULL); return OK;}static int open_entity(cache_handle_t *h, request_rec *r, const char *key){ apr_uint32_t format; apr_size_t len; const char *nkey; apr_status_t rc; static int error_logged = 0; disk_cache_conf *conf = ap_get_module_config(r->server->module_config, &disk_cache_module); apr_finfo_t finfo; cache_object_t *obj; cache_info *info; disk_cache_object_t *dobj; int flags; h->cache_obj = NULL; /* Look up entity keyed to 'url' */ if (conf->cache_root == NULL) { if (!error_logged) { error_logged = 1; ap_log_error(APLOG_MARK, APLOG_ERR, 0, r->server, "disk_cache: Cannot cache files to disk without a CacheRoot specified."); } return DECLINED; } /* Create and init the cache object */ h->cache_obj = obj = apr_pcalloc(r->pool, sizeof(cache_object_t)); obj->vobj = dobj = apr_pcalloc(r->pool, sizeof(disk_cache_object_t)); info = &(obj->info); /* Open the headers file */ dobj->prefix = NULL; /* Save the cache root */ dobj->root = apr_pstrndup(r->pool, conf->cache_root, conf->cache_root_len); dobj->root_len = conf->cache_root_len; dobj->hdrsfile = header_file(r->pool, conf, dobj, key); flags = APR_READ|APR_BINARY|APR_BUFFERED; rc = apr_file_open(&dobj->hfd, dobj->hdrsfile, flags, 0, r->pool); if (rc != APR_SUCCESS) { return DECLINED; } /* read the format from the cache file */
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -