[Cluster-devel] cluster/cmirror-kernel/src dm-clog.c

CVSROOT:	/cvs/cluster
Module name:	cluster
Branch: 	RHEL5
Changes by:	jbrassow at sourceware.org	2008-01-23 21:22:28

Modified files:
	cmirror-kernel/src: dm-clog.c 

Log message:
	- remember CTR string so if userspace server dies and restarts, we
	can pick up where we left off.

Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/cmirror-kernel/src/dm-clog.c.diff?cvsroot=cluster&only_with_tag=RHEL5&r1=1.2.2.6&r2=1.2.2.7

--- cluster/cmirror-kernel/src/dm-clog.c	2008/01/21 20:37:03	1.2.2.6
+++ cluster/cmirror-kernel/src/dm-clog.c	2008/01/23 21:22:28	1.2.2.7
@@ -20,6 +20,9 @@
 	region_t region_count;
 	char uuid[DM_UUID_LEN];
 
+	char *ctr_str; /* Gives ability to restart if userspace dies */
+	uint32_t ctr_size;
+
 	spinlock_t flush_lock;
 	struct list_head flush_list;  /* only for clear and mark requests */
 };
@@ -36,6 +39,44 @@
 	kfree(element);
 }
 
+int cluster_do_request(struct log_c *lc, const char *uuid, int request_type,
+		       char *data, int data_size, char *rdata, int *rdata_size)
+{
+	int r;
+
+	/*
+	 * If the server isn't there, -ESRCH is returned,
+	 * and we must keep trying until the server is
+	 * restored.
+	 */
+retry:
+	r = dm_clog_consult_server(uuid, request_type, data,
+				   data_size, rdata, rdata_size);
+
+	if (r != -ESRCH)
+		return r;
+
+	DMERR(" Userspace cluster log server not found.");
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(2*HZ);
+		DMWARN("Attempting to contact cluster log server...");
+		r = dm_clog_consult_server(uuid, DM_CLOG_CTR, lc->ctr_str,
+					   lc->ctr_size, NULL, NULL);
+		if (!r)
+			break;
+	}
+	DMINFO("Reconnected to cluster log server... CTR complete");
+	r = dm_clog_consult_server(uuid, DM_CLOG_RESUME, NULL,
+				   0, NULL, NULL);
+	if (!r)
+		goto retry;
+
+	DMERR("Error trying to resume cluster log: %d", r);
+
+	return -ESRCH;
+}
+
 static int cluster_ctr(struct dirty_log *log, struct dm_target *ti,
 		       unsigned int argc, char **argv, int disk_log)
 {
@@ -96,12 +137,14 @@
 	if (r == -ESRCH)
 		DMERR(" Userspace cluster log server not found");
 
-	log->context = lc;
-
-	if (r && lc)
+	if (r) {
 		kfree(lc);
-	if (ctr_str)
 		kfree(ctr_str);
+	} else {
+		lc->ctr_str = ctr_str;
+		lc->ctr_size = str_size;
+		log->context = lc;
+	}
 
 	return r;
 }
@@ -179,7 +222,7 @@
 				   NULL, NULL);
 
 	/* FIXME: What do we do on failure? */
-
+	kfree(lc->ctr_str);
 	kfree(lc);
 
 	return;
@@ -266,9 +309,9 @@
 	struct log_c *lc = (struct log_c *)log->context;
 
 	rdata_size = sizeof(is_clean);
-	r = dm_clog_consult_server(lc->uuid, DM_CLOG_IS_CLEAN,
-				   (char *)&region, sizeof(region),
-				   (char *)&is_clean, &rdata_size);
+	r = cluster_do_request(lc, lc->uuid, DM_CLOG_IS_CLEAN,
+			       (char *)&region, sizeof(region),
+			       (char *)&is_clean, &rdata_size);
 
 	return (r) ? 0 : is_clean;
 }
@@ -296,9 +339,9 @@
 		return -EWOULDBLOCK;
 
 	rdata_size = sizeof(in_sync);
-	r = dm_clog_consult_server(lc->uuid, DM_CLOG_IN_SYNC,
-				   (char *)&region, sizeof(region),
-				   (char *)&in_sync, &rdata_size);
+	r = cluster_do_request(lc, lc->uuid, DM_CLOG_IN_SYNC,
+			       (char *)&region, sizeof(region),
+			       (char *)&in_sync, &rdata_size);
 	return (r) ? 0 : in_sync;
 }
 
@@ -343,17 +386,17 @@
 	 */
 
 	list_for_each_entry(fe, &flush_list, list) {
-		r = dm_clog_consult_server(lc->uuid, fe->type,
-					   (char *)&fe->region,
-					   sizeof(fe->region),
-					   NULL, NULL);
+		r = cluster_do_request(lc, lc->uuid, fe->type,
+				       (char *)&fe->region,
+				       sizeof(fe->region),
+				       NULL, NULL);
 		if (r)
 			goto fail;
 	}
 
 	do {
-		r = dm_clog_consult_server(lc->uuid, DM_CLOG_FLUSH,
-					   NULL, 0, NULL, NULL);
+		r = cluster_do_request(lc, lc->uuid, DM_CLOG_FLUSH,
+				       NULL, 0, NULL, NULL);
 		if (r != -EAGAIN)
 			break;
 
@@ -460,9 +503,9 @@
 	struct { int i; region_t r; } pkg;
 
 	rdata_size = sizeof(pkg);
-	r = dm_clog_consult_server(lc->uuid, DM_CLOG_GET_RESYNC_WORK,
-				   NULL, 0,
-				   (char *)&pkg, &rdata_size);
+	r = cluster_do_request(lc, lc->uuid, DM_CLOG_GET_RESYNC_WORK,
+			       NULL, 0,
+			       (char *)&pkg, &rdata_size);
 
 	*region = pkg.r;
 	return (r) ? r : pkg.i;
@@ -487,9 +530,9 @@
 	pkg.r = region;
 	pkg.i = in_sync;
 
-	r = dm_clog_consult_server(lc->uuid, DM_CLOG_SET_REGION_SYNC,
-				   (char *)&pkg, sizeof(pkg),
-				   NULL, NULL);
+	r = cluster_do_request(lc, lc->uuid, DM_CLOG_SET_REGION_SYNC,
+			       (char *)&pkg, sizeof(pkg),
+			       NULL, NULL);
 
 	/* FIXME: It would be nice to be able to report failures */
 	return;
@@ -512,9 +555,9 @@
 	struct log_c *lc = (struct log_c *)log->context;
 
 	rdata_size = sizeof(sync_count);
-	r = dm_clog_consult_server(lc->uuid, DM_CLOG_GET_SYNC_COUNT,
-				   NULL, 0,
-				   (char *)&sync_count, &rdata_size);
+	r = cluster_do_request(lc, lc->uuid, DM_CLOG_GET_SYNC_COUNT,
+			       NULL, 0,
+			       (char *)&sync_count, &rdata_size);
 
 	return (r) ? 0 : sync_count;
 }
@@ -537,18 +580,18 @@
 
 	switch(status_type) {
 	case STATUSTYPE_INFO:
-		r = dm_clog_consult_server(lc->uuid, DM_CLOG_STATUS_INFO,
-					   NULL, 0,
-					   result, &sz);
+		r = cluster_do_request(lc, lc->uuid, DM_CLOG_STATUS_INFO,
+				       NULL, 0,
+				       result, &sz);
 		/*
 		 * FIXME: If we fail to contact server, we should still
 		 * populate this with parsible results
 		 */
 		break;
 	case STATUSTYPE_TABLE:
-		r = dm_clog_consult_server(lc->uuid, DM_CLOG_STATUS_TABLE,
-					   NULL, 0,
-					   result, &sz);
+		r = cluster_do_request(lc, lc->uuid, DM_CLOG_STATUS_TABLE,
+				       NULL, 0,
+				       result, &sz);
 		break;
 	}
 	return (r) ? 0: sz;
@@ -568,9 +611,9 @@
 	struct log_c *lc = (struct log_c *)log->context;
 
 	rdata_size = sizeof(is_recovering);
-	r = dm_clog_consult_server(lc->uuid, DM_CLOG_IS_REMOTE_RECOVERING,
-				   (char *)&region, sizeof(region),
-				   (char *)&is_recovering, &rdata_size);
+	r = cluster_do_request(lc, lc->uuid, DM_CLOG_IS_REMOTE_RECOVERING,
+			       (char *)&region, sizeof(region),
+			       (char *)&is_recovering, &rdata_size);
 	return (r) ? 1 : is_recovering;
 }