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 <hjemli@gmail.com>

1 files changed, 37 insertions, 129 deletions

diff --git a/cgit.c b/cgit.c
index 38b0ba5..4dc8eec 100644
--- a/cgit.c
+++ b/cgit.c
@@ -47,2 +47,4 @@ void config_cb(const char *name, const char *value)
                 ctx.cfg.enable_log_linecount = atoi(value);
+        else if (!strcmp(name, "cache-size"))
+                ctx.cfg.cache_size = atoi(value);
         else if (!strcmp(name, "cache-root"))
@@ -145,2 +147,4 @@ static void prepare_context(struct cgit_context *ctx)
         ctx->cfg.agefile = "info/web/last-modified";
+        ctx->cfg.nocache = 0;
+        ctx->cfg.cache_size = 0;
         ctx->cfg.cache_dynamic_ttl = 5;
@@ -165,43 +169,4 @@ static void prepare_context(struct cgit_context *ctx)
         ctx->page.filename = NULL;
-}
-
-static int cgit_prepare_cache(struct cacheitem *item)
-{
-        if (!ctx.repo && ctx.qry.repo) {
-                ctx.page.title = fmt("%s - %s", ctx.cfg.root_title,
-                                      "Bad request");
-                cgit_print_http_headers(&ctx);
-                cgit_print_docstart(&ctx);
-                cgit_print_pageheader(&ctx);
-                cgit_print_error(fmt("Unknown repo: %s", ctx.qry.repo));
-                cgit_print_docend();
-                return 0;
-        }
-
-        if (!ctx.repo) {
-                item->name = xstrdup(fmt("%s/index.%s.html",
-                                         ctx.cfg.cache_root,
-                                         cache_safe_filename(ctx.qry.raw)));
-                item->ttl = ctx.cfg.cache_root_ttl;
-                return 1;
-        }
-
-        if (!ctx.qry.page) {
-                item->name = xstrdup(fmt("%s/%s/index.%s.html", ctx.cfg.cache_root,
-                                         cache_safe_filename(ctx.repo->url),
-                                         cache_safe_filename(ctx.qry.raw)));
-                item->ttl = ctx.cfg.cache_repo_ttl;
-        } else {
-                item->name = xstrdup(fmt("%s/%s/%s/%s.html", ctx.cfg.cache_root,
-                                         cache_safe_filename(ctx.repo->url),
-                                         ctx.qry.page,
-                                         cache_safe_filename(ctx.qry.raw)));
-                if (ctx.qry.has_symref)
-                        item->ttl = ctx.cfg.cache_dynamic_ttl;
-                else if (ctx.qry.has_sha1)
-                        item->ttl = ctx.cfg.cache_static_ttl;
-                else
-                        item->ttl = ctx.cfg.cache_repo_ttl;
-        }
-        return 1;
+        ctx->page.modified = time(NULL);
+        ctx->page.expires = ctx->page.modified;
 }
@@ -290,4 +255,5 @@ static int prepare_repo_cmd(struct cgit_context *ctx)
 
-static void process_request(struct cgit_context *ctx)
+static void process_request(void *cbdata)
 {
+        struct cgit_context *ctx = cbdata;
         struct cgit_cmd *cmd;
@@ -321,78 +287,2 @@ static void process_request(struct cgit_context *ctx)
 
-static long ttl_seconds(long ttl)
-{
-        if (ttl<0)
-                return 60 * 60 * 24 * 365;
-        else
-                return ttl * 60;
-}
-
-static void cgit_fill_cache(struct cacheitem *item, int use_cache)
-{
-        int stdout2;
-
-        if (use_cache) {
-                stdout2 = chk_positive(dup(STDOUT_FILENO),
-                                       "Preserving STDOUT");
-                chk_zero(close(STDOUT_FILENO), "Closing STDOUT");
-                chk_positive(dup2(item->fd, STDOUT_FILENO), "Dup2(cachefile)");
-        }
-
-        ctx.page.modified = time(NULL);
-        ctx.page.expires = ctx.page.modified + ttl_seconds(item->ttl);
-        process_request(&ctx);
-
-        if (use_cache) {
-                chk_zero(close(STDOUT_FILENO), "Close redirected STDOUT");
-                chk_positive(dup2(stdout2, STDOUT_FILENO),
-                             "Restoring original STDOUT");
-                chk_zero(close(stdout2), "Closing temporary STDOUT");
-        }
-}
-
-static void cgit_check_cache(struct cacheitem *item)
-{
-        int i = 0;
-
- top:
-        if (++i > ctx.cfg.max_lock_attempts) {
-                die("cgit_refresh_cache: unable to lock %s: %s",
-                    item->name, strerror(errno));
-        }
-        if (!cache_exist(item)) {
-                if (!cache_lock(item)) {
-                        sleep(1);
-                        goto top;
-                }
-                if (!cache_exist(item)) {
-                        cgit_fill_cache(item, 1);
-                        cache_unlock(item);
-                } else {
-                        cache_cancel_lock(item);
-                }
-        } else if (cache_expired(item) && cache_lock(item)) {
-                if (cache_expired(item)) {
-                        cgit_fill_cache(item, 1);
-                        cache_unlock(item);
-                } else {
-                        cache_cancel_lock(item);
-                }
-        }
-}
-
-static void cgit_print_cache(struct cacheitem *item)
-{
-        static char buf[4096];
-        ssize_t i;
-
-        int fd = open(item->name, O_RDONLY);
-        if (fd<0)
-                die("Unable to open cached file %s", item->name);
-
-        while((i=read(fd, buf, sizeof(buf))) > 0)
-                write(STDOUT_FILENO, buf, i);
-
-        close(fd);
-}
-
 static void cgit_parse_args(int argc, const char **argv)
@@ -431,9 +321,25 @@ static void cgit_parse_args(int argc, const char **argv)
 
+static int calc_ttl()
+{
+        if (!ctx.repo)
+                return ctx.cfg.cache_root_ttl;
+
+        if (!ctx.qry.page)
+                return ctx.cfg.cache_repo_ttl;
+
+        if (ctx.qry.has_symref)
+                return ctx.cfg.cache_dynamic_ttl;
+
+        if (ctx.qry.has_sha1)
+                return ctx.cfg.cache_static_ttl;
+
+        return ctx.cfg.cache_repo_ttl;
+}
+
 int main(int argc, const char **argv)
 {
-        struct cacheitem item;
         const char *cgit_config_env = getenv("CGIT_CONFIG");
+        int err, ttl;
 
         prepare_context(&ctx);
-        item.st.st_mtime = time(NULL);
         cgit_repolist.length = 0;
@@ -451,11 +357,13 @@ int main(int argc, const char **argv)
         http_parse_querystring(ctx.qry.raw, querystring_cb);
-        if (!cgit_prepare_cache(&item))
-                return 0;
-        if (ctx.cfg.nocache) {
-                cgit_fill_cache(&item, 0);
-        } else {
-                cgit_check_cache(&item);
-                cgit_print_cache(&item);
-        }
-        return 0;
+
+        ttl = calc_ttl();
+        ctx.page.expires += ttl*60;
+        if (ctx.cfg.nocache)
+                ctx.cfg.cache_size = 0;
+        err = cache_process(ctx.cfg.cache_size, ctx.cfg.cache_root,
+                            ctx.qry.raw, ttl, process_request, &ctx);
+        if (err)
+                cache_log("[cgit] error %d - %s\n",
+                          err, strerror(err));
+        return err;
 }