[PATCH] exponential backoff for blocked LOCK call polling

* [PATCH] exponential backoff for blocked LOCK call polling
@ 2004-10-26 10:22 Greg Banks
  2004-11-08 17:27 ` Ara.T.Howard
  0 siblings, 1 reply; 5+ messages in thread
From: Greg Banks @ 2004-10-26 10:22 UTC (permalink / raw)
  To: Trond Myklebust; +Cc: Linux NFS Mailing List

[-- Attachment #1: Type: text/plain, Size: 261 bytes --]

G'day,

The attached patch makes the NLM client do exponential backoff
for the polling used to handle the case that the server has not
sent a GRANTED callback.

Greg.
-- 
Greg Banks, R&D Software Engineer, SGI Australian Software Group.
I don't speak for SGI.


[-- Attachment #2: gnb-nlm-block-backoff --]
[-- Type: text/plain, Size: 3369 bytes --]

Implement exponential backoff for the NLM client LOCK call polling
when the server doesn't send the client a GRANTED callback.

Signed-off-by: Greg Banks <gnb@melbourne.sgi.com>

Index: linux/fs/lockd/clntlock.c
===================================================================

--- linux.orig/fs/lockd/clntlock.c	Thu Oct 21 17:18:37 2004
+++ linux/fs/lockd/clntlock.c	Thu Oct 21 17:25:03 2004
@@ -45,7 +45,8 @@ static struct nlm_wait *	nlm_blocked;
  * Block on a lock
  */
 int
-nlmclnt_block(struct nlm_host *host, struct file_lock *fl, u32 *statp)
+nlmclnt_block(struct nlm_host *host, struct file_lock *fl, u32 *statp,
+	      int delay)
 {
 	struct nlm_wait	block, **head;
 	int		err;
@@ -64,12 +65,8 @@ nlmclnt_block(struct nlm_host *host, str
 	/* Go to sleep waiting for GRANT callback. Some servers seem
 	 * to lose callbacks, however, so we're going to poll from
 	 * time to time just to make sure.
-	 *
-	 * For now, the retry frequency is pretty high; normally 
-	 * a 1 minute timeout would do. See the comment before
-	 * nlmclnt_lock for an explanation.
 	 */
-	sleep_on_timeout(&block.b_wait, 30*HZ);
+	sleep_on_timeout(&block.b_wait, delay);
 
 	for (head = &nlm_blocked; *head; head = &(*head)->b_next) {
 		if (*head == &block) {
Index: linux/fs/lockd/clntproc.c
===================================================================
--- linux.orig/fs/lockd/clntproc.c	Mon Oct  4 14:35:14 2004
+++ linux/fs/lockd/clntproc.c	Thu Oct 21 17:26:43 2004
@@ -534,12 +534,16 @@ static void nlmclnt_locks_init_private(s
  * This is one of the lovely things about standards in the NFS area:
  * they're so soft and squishy you can't really blame HP for doing this.
  */
+#define NLM_LOCK_RETRY_DELAY_MIN	(110*HZ/100)
+#define NLM_LOCK_RETRY_DELAY_MAX	(64*NLM_LOCK_RETRY_DELAY_MIN)
+
 static int
 nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 {
 	struct nlm_host	*host = req->a_host;
 	struct nlm_res	*resp = &req->a_res;
 	int		status;
+	int		delay = NLM_LOCK_RETRY_DELAY_MIN;
 
 	if (!host->h_monitored && nsm_monitor(host) < 0) {
 		printk(KERN_NOTICE "lockd: failed to monitor %s\n",
@@ -552,7 +556,13 @@ nlmclnt_lock(struct nlm_rqst *req, struc
 		if ((status = nlmclnt_call(req, NLMPROC_LOCK)) >= 0) {
 			if (resp->status != NLM_LCK_BLOCKED)
 				break;
-			status = nlmclnt_block(host, fl, &resp->status);
+			status = nlmclnt_block(host, fl, &resp->status, delay);
+			/* 
+			 * Use an exponential backoff strategy for best
+			 * compromise between response time and efficiency
+			 */
+			if (delay < NLM_LOCK_RETRY_DELAY_MAX)
+				delay <<= 1;
 		}
 		if (status < 0)
 			goto out;
Index: linux/include/linux/lockd/lockd.h
===================================================================
--- linux.orig/include/linux/lockd/lockd.h	Thu Oct 21 17:08:30 2004
+++ linux/include/linux/lockd/lockd.h	Thu Oct 21 17:23:43 2004
@@ -145,7 +145,7 @@ extern unsigned long		nlmsvc_timeout;
 struct nlm_rqst * nlmclnt_alloc_call(void);
 int		  nlmclnt_call(struct nlm_rqst *, u32);
 int		  nlmclnt_async_call(struct nlm_rqst *, u32, rpc_action);
-int		  nlmclnt_block(struct nlm_host *, struct file_lock *, u32 *);
+int		  nlmclnt_block(struct nlm_host *, struct file_lock *, u32 *, int);
 int		  nlmclnt_cancel(struct nlm_host *, struct file_lock *);
 u32		  nlmclnt_grant(struct nlm_lock *);
 void		  nlmclnt_recovery(struct nlm_host *, u32);

^ permalink raw reply	[flat|nested] 5+ messages in thread