sunrpc/cache: allow threads to block while waiting for cache update.
The current practice of waiting for cache updates by queueing the
whole request to be retried has (at least) two problems.
1/ With NFSv4, requests can be quite complex and re-trying a whole
request when a later part fails should only be a last-resort, not a
normal practice.
2/ Large requests, and in particular any 'write' request, will not be
queued by the current code and doing so would be undesirable.
In many cases only a very sort wait is needed before the cache gets
valid data.
So, providing the underlying transport permits it by setting
->thread_wait,
arrange to wait briefly for an upcall to be completed (as reflected in
the clearing of CACHE_PENDING).
If the short wait was not long enough and CACHE_PENDING is still set,
fall back on the old approach.
The 'thread_wait' value is set to 5 seconds when there are spare
threads, and 1 second when there are no spare threads.
These values are probably much higher than needed, but will ensure
some forward progress.
Note that as we only request an update for a non-valid item, and as
non-valid items are updated in place it is extremely unlikely that
cache_check will return -ETIMEDOUT. Normally cache_defer_req will
sleep for a short while and then find that the item is_valid.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 8dc1219..2c5297f 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -509,10 +509,22 @@
static struct list_head cache_defer_hash[DFR_HASHSIZE];
static int cache_defer_cnt;
+struct thread_deferred_req {
+ struct cache_deferred_req handle;
+ struct completion completion;
+};
+static void cache_restart_thread(struct cache_deferred_req *dreq, int too_many)
+{
+ struct thread_deferred_req *dr =
+ container_of(dreq, struct thread_deferred_req, handle);
+ complete(&dr->completion);
+}
+
static int cache_defer_req(struct cache_req *req, struct cache_head *item)
{
struct cache_deferred_req *dreq, *discard;
int hash = DFR_HASH(item);
+ struct thread_deferred_req sleeper;
if (cache_defer_cnt >= DFR_MAX) {
/* too much in the cache, randomly drop this one,
@@ -521,7 +533,15 @@
if (net_random()&1)
return -ENOMEM;
}
- dreq = req->defer(req);
+ if (req->thread_wait) {
+ dreq = &sleeper.handle;
+ sleeper.completion =
+ COMPLETION_INITIALIZER_ONSTACK(sleeper.completion);
+ dreq->revisit = cache_restart_thread;
+ } else
+ dreq = req->defer(req);
+
+ retry:
if (dreq == NULL)
return -ENOMEM;
@@ -555,6 +575,43 @@
cache_revisit_request(item);
return -EAGAIN;
}
+
+ if (dreq == &sleeper.handle) {
+ if (wait_for_completion_interruptible_timeout(
+ &sleeper.completion, req->thread_wait) <= 0) {
+ /* The completion wasn't completed, so we need
+ * to clean up
+ */
+ spin_lock(&cache_defer_lock);
+ if (!list_empty(&sleeper.handle.hash)) {
+ list_del_init(&sleeper.handle.recent);
+ list_del_init(&sleeper.handle.hash);
+ cache_defer_cnt--;
+ spin_unlock(&cache_defer_lock);
+ } else {
+ /* cache_revisit_request already removed
+ * this from the hash table, but hasn't
+ * called ->revisit yet. It will very soon
+ * and we need to wait for it.
+ */
+ spin_unlock(&cache_defer_lock);
+ wait_for_completion(&sleeper.completion);
+ }
+ }
+ if (test_bit(CACHE_PENDING, &item->flags)) {
+ /* item is still pending, try request
+ * deferral
+ */
+ dreq = req->defer(req);
+ goto retry;
+ }
+ /* only return success if we actually deferred the
+ * request. In this case we waited until it was
+ * answered so no deferral has happened - rather
+ * an answer already exists.
+ */
+ return -EEXIST;
+ }
return 0;
}