All of lore.kernel.org
 help / color / mirror / Atom feed
From: NeilBrown <neilb@suse.de>
To: "J. Bruce Fields" <bfields@fieldses.org>
Cc: linux-nfs@vger.kernel.org
Subject: [PATCH 1/6] sunrpc/cache: allow threads to block while waiting for cache update.
Date: Thu, 12 Aug 2010 17:04:06 +1000	[thread overview]
Message-ID: <20100812070405.11459.91402.stgit@localhost.localdomain> (raw)
In-Reply-To: <20100812065722.11459.18978.stgit@localhost.localdomain>

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>
---
 include/linux/sunrpc/cache.h |    3 +++
 net/sunrpc/cache.c           |   47 +++++++++++++++++++++++++++++++++++++++++-
 net/sunrpc/svc_xprt.c        |   11 ++++++++++
 3 files changed, 60 insertions(+), 1 deletions(-)

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 7bf3e84..61f521f 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -125,6 +125,9 @@ struct cache_detail {
  */
 struct cache_req {
 	struct cache_deferred_req *(*defer)(struct cache_req *req);
+	int thread_wait;  /* How long (jiffies) we can block the
+			   * current thread to wait for updates.
+			   */
 };
 /* this must be embedded in a deferred_request that is being
  * delayed awaiting cache-fill
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 2b06410..2fdd66b 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -509,10 +509,22 @@ static LIST_HEAD(cache_defer_list);
 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 @@ static int cache_defer_req(struct cache_req *req, struct cache_head *item)
 		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 +575,31 @@ static int cache_defer_req(struct cache_req *req, struct cache_head *item)
 		cache_revisit_request(item);
 		return -EAGAIN;
 	}
+
+	if (dreq == &sleeper.handle) {
+		wait_for_completion_interruptible_timeout(
+			&sleeper.completion, req->thread_wait);
+		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);
+		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;
 }
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index cbc0849..8ff6840 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -651,6 +651,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	if (signalled() || kthread_should_stop())
 		return -EINTR;
 
+	/* Normally we will wait up to 5 seconds for any required
+	 * cache information to be provided.
+	 */
+	rqstp->rq_chandle.thread_wait = 5*HZ;
+
 	spin_lock_bh(&pool->sp_lock);
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
@@ -658,6 +663,12 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+
+		/* As there is a shortage of threads and this request
+		 * had to be queue, don't allow the thread to wait so
+		 * long for cache updates.
+		 */
+		rqstp->rq_chandle.thread_wait = 1*HZ;
 	} else {
 		/* No data pending. Go to sleep */
 		svc_thread_enqueue(pool, rqstp);



  reply	other threads:[~2010-08-12  7:05 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-08-12  7:04 [PATCH 0/6] Cache deferral improvements - try N+2 NeilBrown
2010-08-12  7:04 ` NeilBrown [this message]
2010-08-12  7:04 ` [PATCH 2/6] nfsd/idmap: drop special request deferal in favour of improved default NeilBrown
     [not found]   ` <20100812070406.11459.89468.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2010-09-21 21:08     ` J. Bruce Fields
2010-08-12  7:04 ` [PATCH 5/6] svcauth_gss: replace a trivial 'switch' with an 'if' NeilBrown
2010-08-12  7:04 ` [PATCH 4/6] nfsd: disable deferral for NFSv4 NeilBrown
     [not found]   ` <20100812070407.11459.2929.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2010-09-21 21:01     ` J. Bruce Fields
2010-08-12  7:04 ` [PATCH 3/6] sunrpc: close connection when a request is irretrievably lost NeilBrown
2010-09-21 20:53   ` J. Bruce Fields
2010-09-21 23:37     ` Neil Brown
2010-09-22  2:13       ` J. Bruce Fields
2010-08-12  7:04 ` [PATCH 6/6] sunrpc/cache: change deferred-request hash table to use hlist NeilBrown
     [not found] ` <20100812065722.11459.18978.stgit-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2010-08-12 12:03   ` [PATCH 0/6] Cache deferral improvements - try N+2 J. Bruce Fields
2010-08-17  5:15 ` [PATCH 1.5/6] Fix race in new request delay code NeilBrown
2010-08-26 21:08   ` J. Bruce Fields
2010-08-29 23:36     ` Neil Brown
2010-09-01 11:31       ` J. Bruce Fields
2010-09-21  8:35       ` Neil Brown
2010-09-22  2:15         ` J. Bruce Fields

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20100812070405.11459.91402.stgit@localhost.localdomain \
    --to=neilb@suse.de \
    --cc=bfields@fieldses.org \
    --cc=linux-nfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.