Keep clone files and oversized responses out of the cache

The dumb transport reads files that already sit on the disk, so a pack
copied into a slot cost that disk twice and the request a second write
of every byte. A snapshot took a slot whatever its size, so a visitor
naming distinct refs and ids could fill the cache root with archives.
`cache-max-slot-size`, 64 MB unless set, now serves a larger response
from the lock file and drops it, along with any expired copy it would
have replaced.

1 file changed, 19 insertions, 1 deletion

diff --git a/source/cgit.c b/source/cgit.c
index 5806293..3e47dbe 100644
--- a/source/cgit.c
+++ b/source/cgit.c
@@ -100,6 +100,9 @@ static void prepare_context(void)
 	ctx.cfg.cache_scan_ttl = 15;
 	ctx.cfg.cache_dynamic_ttl = 5;
 	ctx.cfg.cache_static_ttl = -1;
+	// Counted in kilobytes, so sixty-four megabytes, past which a response
+	// is served but not kept.
+	ctx.cfg.cache_max_slot_size = 64 * 1024;
 	ctx.cfg.case_sensitive_sort = 1;
 	ctx.cfg.branch_sort = 0;
 	ctx.cfg.commit_sort = 0;
@@ -608,6 +611,8 @@ static void apply_config(const char *name, const char *value)
 		ctx.cfg.cache_about_ttl = atoi(value);
 	else if (!strcmp(name, "cache-snapshot-ttl"))
 		ctx.cfg.cache_snapshot_ttl = atoi(value);
+	else if (!strcmp(name, "cache-max-slot-size"))
+		ctx.cfg.cache_max_slot_size = atoi(value);
 	else if (!strcmp(name, "case-sensitive-sort"))
 		ctx.cfg.case_sensitive_sort = atoi(value);
 	else if (!strcmp(name, "about-filter"))
@@ -908,12 +913,20 @@ static int page_is_static(void)
  */
 static int calc_ttl(void)
 {
+	const struct cgit_cmd *cmd;
+
 	if (!ctx.repo)
 		return ctx.cfg.cache_index_ttl;
 
 	if (!ctx.qry.page)
 		return ctx.cfg.cache_summary_ttl;
 
+	// The dumb transport serves files that already sit on the disk, so a
+	// copy in a slot would cost that disk twice and gain nothing.
+	cmd = cgit_find_cmd(ctx.qry.page);
+	if (cmd && cmd->is_clone)
+		return 0;
+
 	if (!strcmp(ctx.qry.page, "about"))
 		return ctx.cfg.cache_about_ttl;
 
@@ -1304,6 +1317,7 @@ int cmd_main(int argc, const char **argv)
 {
 	struct strbuf cache_key = STRBUF_INIT;
 	const char *path;
+	size_t max_bytes = 0;
 	int err, ttl;
 
 	isolate_git_environment();
@@ -1357,8 +1371,12 @@ int cmd_main(int argc, const char **argv)
 	if (!ctx.env.authenticated || (ctx.env.request_method && !strcmp(ctx.env.request_method, "HEAD")))
 		ctx.cfg.cache_size = 0;
 
+	// Written in kilobytes in cgitrc, where zero and below lift the bound.
+	if (ctx.cfg.cache_max_slot_size > 0)
+		max_bytes = (size_t)ctx.cfg.cache_max_slot_size * 1024;
 	build_cache_key(&cache_key);
-	err = cache_process(ctx.cfg.cache_size, ctx.cfg.cache_root, cache_key.buf, ttl, process_request);
+	err = cache_process(ctx.cfg.cache_size, ctx.cfg.cache_root, cache_key.buf, ttl,
+		max_bytes, process_request);
 	strbuf_release(&cache_key);
 
 	cgit_cleanup_filters();