mirror of https://git.zx2c4.com/cgit/
Add caching infrastructure
This enables internal caching of page output. Page requests are split into four groups: 1) repo listing (front page) 2) repo summary 3) repo pages w/symbolic references in query string 4) repo pages w/constant sha1's in query string Each group has a TTL specified in minutes. When a page is requested, a cached filename is stat(2)'ed and st_mtime is compared to time(2). If TTL has expired (or the file didn't exist), the cached file is regenerated. When generating a cached file, locking is used to avoid parallell processing of the request. If multiple processes tries to aquire the same lock, the ones who fail to get the lock serves the (expired) cached file. If the cached file don't exist, the process instead calls sched_yield(2) before restarting the request processing. Signed-off-by: Lars Hjemli <hjemli@gmail.com>lh/pretty-blob-view
Lars Hjemli
18 years ago
parent
856c026e22
commit
25105d7eca
@ -1,3 +1,4 @@
|
||||
# Files I don't care to see in git-status/commit
|
||||
cgit
|
||||
*.o
|
||||
*~
|
||||
|
||||
@ -0,0 +1,54 @@
|
||||
Cache algorithm
|
||||
===============
|
||||
|
||||
Cgit normally returns cached pages when invoked. If there is no cache file, or
|
||||
the cache file has expired, it is regenerated. Finally, the cache file is
|
||||
printed on stdout.
|
||||
|
||||
When it is decided that a cache file needs to be regenerated, an attempt is
|
||||
made to create a corresponding lockfile. If this fails, the process gives up
|
||||
and uses the expired cache file instead.
|
||||
|
||||
When there is no cache file for a request, an attempt is made to create a
|
||||
corresponding lockfile. If this fails, the process calls sched_yield(2) before
|
||||
restarting the request handling.
|
||||
|
||||
In pseudocode:
|
||||
|
||||
name = generate_cache_name(request);
|
||||
top:
|
||||
if (!exists(name)) {
|
||||
if (lock_cache(name)) {
|
||||
generate_cache(request, name);
|
||||
unlock_cache(name);
|
||||
} else {
|
||||
sched_yield();
|
||||
goto top;
|
||||
}
|
||||
} else if (expired(name)) {
|
||||
if (lock_cache(name)) {
|
||||
generate_cache(request, name);
|
||||
unlock_cache(name);
|
||||
}
|
||||
}
|
||||
print_file(name);
|
||||
|
||||
|
||||
The following options can be set in /etc/cgitrc to control cache behaviour:
|
||||
cache-root: root directory for cache files
|
||||
cache-root-ttl: TTL for the repo listing page
|
||||
cache-repo-ttl: TTL for any repos summary page
|
||||
cache-dynamic-ttl: TTL for pages with symbolic references (not SHA1)
|
||||
cache-static-ttl: TTL for pages with sha1 references
|
||||
|
||||
TTL is specified in minutes, -1 meaning "infinite caching".
|
||||
|
||||
|
||||
Naming of cache files
|
||||
---------------------
|
||||
Repository listing: <cachedir>/index.html
|
||||
Repository summary: <cachedir>/<repo>/index.html
|
||||
Repository subpage: <cachedir>/<repo>/<page>/<querystring>.html
|
||||
|
||||
The corresponding lock files have a ".lock" suffix.
|
||||
|
||||
@ -0,0 +1,86 @@
|
||||
#include "cgit.h"
|
||||
|
||||
const int NOLOCK = -1;
|
||||
|
||||
int cache_lookup(struct cacheitem *item)
|
||||
{
|
||||
if (!cgit_query_repo) {
|
||||
item->name = xstrdup(fmt("%s/index.html", cgit_cache_root));
|
||||
item->ttl = cgit_cache_root_ttl;
|
||||
} else if (!cgit_query_page) {
|
||||
item->name = xstrdup(fmt("%s/%s/index.html", cgit_cache_root,
|
||||
cgit_query_repo));
|
||||
item->ttl = cgit_cache_repo_ttl;
|
||||
} else {
|
||||
item->name = xstrdup(fmt("%s/%s/%s/%s.html", cgit_cache_root,
|
||||
cgit_query_repo, cgit_query_page,
|
||||
cgit_querystring));
|
||||
if (cgit_query_has_symref)
|
||||
item->ttl = cgit_cache_dynamic_ttl;
|
||||
else if (cgit_query_has_sha1)
|
||||
item->ttl = cgit_cache_static_ttl;
|
||||
else
|
||||
item->ttl = cgit_cache_repo_ttl;
|
||||
}
|
||||
if (stat(item->name, &item->st)) {
|
||||
item->st.st_mtime = 0;
|
||||
return 0;
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
|
||||
int cache_create_dirs()
|
||||
{
|
||||
char *path;
|
||||
|
||||
if (!cgit_query_repo)
|
||||
return 0;
|
||||
|
||||
path = fmt("%s/%s", cgit_cache_root, cgit_query_repo);
|
||||
if (mkdir(path, S_IRWXU) && errno!=EEXIST)
|
||||
return 0;
|
||||
|
||||
if (cgit_query_page) {
|
||||
path = fmt("%s/%s/%s", cgit_cache_root, cgit_query_repo,
|
||||
cgit_query_page);
|
||||
if (mkdir(path, S_IRWXU) && errno!=EEXIST)
|
||||
return 0;
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
|
||||
int cache_lock(struct cacheitem *item)
|
||||
{
|
||||
int ret;
|
||||
char *lockfile = fmt("%s.lock", item->name);
|
||||
|
||||
top:
|
||||
item->fd = open(lockfile, O_WRONLY | O_CREAT | O_EXCL, S_IRUSR|S_IWUSR);
|
||||
if (item->fd == NOLOCK && errno == ENOENT && cache_create_dirs())
|
||||
goto top;
|
||||
if (item->fd == NOLOCK && errno == EEXIST) {
|
||||
struct stat st;
|
||||
time_t t;
|
||||
if (stat(lockfile, &st))
|
||||
return ret;
|
||||
t = time(NULL);
|
||||
if (t-st.st_mtime > cgit_cache_max_create_time &&
|
||||
!unlink(lockfile))
|
||||
goto top;
|
||||
return 0;
|
||||
}
|
||||
return (item->fd > 0);
|
||||
}
|
||||
|
||||
int cache_unlock(struct cacheitem *item)
|
||||
{
|
||||
close(item->fd);
|
||||
return (rename(fmt("%s.lock", item->name), item->name) == 0);
|
||||
}
|
||||
|
||||
int cache_expired(struct cacheitem *item)
|
||||
{
|
||||
if (item->ttl < 0)
|
||||
return 0;
|
||||
return item->st.st_mtime + item->ttl * 60 < time(NULL);
|
||||
}
|
||||
Loading…
Reference in New Issue