From 939d32fda70ea66c9db51687beb3cea6da7b0599 Mon Sep 17 00:00:00 2001 From: Lars Hjemli Date: Mon, 28 Apr 2008 11:32:42 +0200 Subject: Redesign the caching layer The original caching layer in cgit has no upper bound on the number of concurrent cache entries, so when cgit is traversed by a spider (like the googlebot), the cache might end up filling your disk. Also, if any error occurs in the cache layer, no content is returned to the client. This patch redesigns the caching layer to avoid these flaws by * giving the cache a bound number of slots * disabling the cache for the current request when errors occur The cache size limit is implemented by hashing the querystring (the cache lookup key) and generating a cache filename based on this hash modulo the cache size. In order to detect hash collisions, the full lookup key (i.e. the querystring) is stored in the cache file (separated from its associated content by ascii 0). The cache filename is the reversed 8-digit hexadecimal representation of hash(key) % cache_size which should make the filesystem lookup pretty fast (if directory content is indexed/sorted); reversing the representation avoids the problem where all keys have equal prefix. There is a new config option, cache-size, which sets the upper bound for the cache. Default value for this option is 0, which has the same effect as setting nocache=1 (hence nocache is now deprecated). Included in this patch is also a new testfile which verifies that the new option works as intended. Signed-off-by: Lars Hjemli --- cache.h | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) (limited to 'cache.h') diff --git a/cache.h b/cache.h index 4dcbea3..5f2178d 100644 --- a/cache.h +++ b/cache.h @@ -6,18 +6,27 @@ #ifndef CGIT_CACHE_H #define CGIT_CACHE_H -struct cacheitem { - char *name; - struct stat st; - int ttl; - int fd; -}; +typedef void (*cache_fill_fn)(void *cbdata); -extern char *cache_safe_filename(const char *unsafe); -extern int cache_lock(struct cacheitem *item); -extern int cache_unlock(struct cacheitem *item); -extern int cache_cancel_lock(struct cacheitem *item); -extern int cache_exist(struct cacheitem *item); -extern int cache_expired(struct cacheitem *item); + +/* Print cached content to stdout, generate the content if necessary. + * + * Parameters + * size max number of cache files + * path directory used to store cache files + * key the key used to lookup cache files + * ttl max cache time in seconds for this key + * fn content generator function for this key + * cbdata user-supplied data to the content generator function + * + * Return value + * 0 indicates success, everyting else is an error + */ +extern int cache_process(int size, const char *path, const char *key, int ttl, + cache_fill_fn fn, void *cbdata); + + +/* Print a message to stdout */ +extern void cache_log(const char *format, ...); #endif /* CGIT_CACHE_H */ -- cgit v1.2.3-70-g09d2 From 9000bbf865cb3578ba5ed3810dc44253cb46ec7f Mon Sep 17 00:00:00 2001 From: Lars Hjemli Date: Mon, 28 Apr 2008 12:10:13 +0200 Subject: Add page 'ls_cache' This new page will list all entries found in the current cache, which is useful when reviewing the new cache implementation. There are no links to the new page, but it's reachable by adding 'p=ls_cache' to any cgit url. Signed-off-by: Lars Hjemli --- cache.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ cache.h | 3 +++ cmd.c | 21 +++++++++++++++----- 3 files changed, 87 insertions(+), 5 deletions(-) (limited to 'cache.h') diff --git a/cache.c b/cache.c index e590d7b..b701e13 100644 --- a/cache.c +++ b/cache.c @@ -332,6 +332,74 @@ int cache_process(int size, const char *path, const char *key, int ttl, return process_slot(&slot); } +/* Return a strftime formatted date/time + * NB: the result from this function is to shared memory + */ +char *sprintftime(const char *format, time_t time) +{ + static char buf[64]; + struct tm *tm; + + if (!time) + return NULL; + tm = gmtime(&time); + strftime(buf, sizeof(buf)-1, format, tm); + return buf; +} + +int cache_ls(const char *path) +{ + DIR *dir; + struct dirent *ent; + int err = 0; + struct cache_slot slot; + char fullname[1024]; + char *name; + + if (!path) { + cache_log("[cgit] cache path not specified\n"); + return -1; + } + if (strlen(path) > 1024 - 10) { + cache_log("[cgit] cache path too long: %s\n", + path); + return -1; + } + dir = opendir(path); + if (!dir) { + err = errno; + cache_log("[cgit] unable to open path %s: %s (%d)\n", + path, strerror(err), err); + return err; + } + strcpy(fullname, path); + name = fullname + strlen(path); + if (*(name - 1) != '/') { + *name++ = '/'; + *name = '\0'; + } + slot.cache_name = fullname; + while((ent = readdir(dir)) != NULL) { + if (strlen(ent->d_name) != 8) + continue; + strcpy(name, ent->d_name); + if ((err = open_slot(&slot)) != 0) { + cache_log("[cgit] unable to open path %s: %s (%d)\n", + fullname, strerror(err), err); + continue; + } + printf("%s %s %10lld %s\n", + name, + sprintftime("%Y-%m-%d %H:%M:%S", + slot.cache_st.st_mtime), + slot.cache_st.st_size, + slot.buf); + close_slot(&slot); + } + closedir(dir); + return 0; +} + /* Print a message to stdout */ void cache_log(const char *format, ...) { diff --git a/cache.h b/cache.h index 5f2178d..66cc41f 100644 --- a/cache.h +++ b/cache.h @@ -26,6 +26,9 @@ extern int cache_process(int size, const char *path, const char *key, int ttl, cache_fill_fn fn, void *cbdata); +/* List info about all cache entries on stdout */ +extern int cache_ls(const char *path); + /* Print a message to stdout */ extern void cache_log(const char *format, ...); diff --git a/cmd.c b/cmd.c index e0eacbe..07f4707 100644 --- a/cmd.c +++ b/cmd.c @@ -8,6 +8,8 @@ #include "cgit.h" #include "cmd.h" +#include "cache.h" +#include "ui-shared.h" #include "ui-blob.h" #include "ui-commit.h" #include "ui-diff.h" @@ -35,17 +37,25 @@ static void diff_fn(struct cgit_context *ctx) cgit_print_diff(ctx->qry.sha1, ctx->qry.sha2, ctx->qry.path); } -static void repolist_fn(struct cgit_context *ctx) -{ - cgit_print_repolist(); -} - static void log_fn(struct cgit_context *ctx) { cgit_print_log(ctx->qry.sha1, ctx->qry.ofs, ctx->cfg.max_commit_count, ctx->qry.grep, ctx->qry.search, ctx->qry.path, 1); } +static void ls_cache_fn(struct cgit_context *ctx) +{ + ctx->page.mimetype = "text/plain"; + ctx->page.filename = "ls-cache.txt"; + cgit_print_http_headers(ctx); + cache_ls(ctx->cfg.cache_root); +} + +static void repolist_fn(struct cgit_context *ctx) +{ + cgit_print_repolist(); +} + static void patch_fn(struct cgit_context *ctx) { cgit_print_patch(ctx->qry.sha1); @@ -88,6 +98,7 @@ struct cgit_cmd *cgit_get_cmd(struct cgit_context *ctx) def_cmd(commit, 1, 1), def_cmd(diff, 1, 1), def_cmd(log, 1, 1), + def_cmd(ls_cache, 0, 0), def_cmd(patch, 1, 0), def_cmd(refs, 1, 1), def_cmd(repolist, 0, 0), -- cgit v1.2.3-70-g09d2