zfcp: auto port scan resiliency

This patch improves the Fibre Channel port scan behaviour of the zfcp lldd.
Without it the zfcp device driver may churn up the storage area network by
excessive scanning and scan bursts, particularly in big virtual server
environments, potentially resulting in interference of virtual servers and
reduced availability of storage connectivity.

The two main issues as to the zfcp device drivers automatic port scan in
virtual server environments are frequency and simultaneity.
On the one hand, there is no point in allowing lots of ports scans
in a row. It makes sense, though, to make sure that a scan is conducted
eventually if there has been any indication for potential SAN changes.
On the other hand, lots of virtual servers receiving the same indication
for a SAN change had better not attempt to conduct a scan instantly,
that is, at the same time.

Hence this patch has a two-fold approach for better port scanning:
the introduction of a rate limit to amend frequency issues, and the
introduction of a short random backoff to amend simultaneity issues.
Both approaches boil down to deferred port scans, with delays
comprising parts for both approaches.

The new port scan behaviour is summarised best by:

                                               NEW:    NEW:
                          no_auto_port_rescan  random  rate    flush
                                               backoff limit   =wait

adapter resume/thaw       yes                  yes     no      yes*
adapter online (user)     no                   yes     no      yes*
port rescan (user)        no                   no      no      yes
adapter recovery (user)   yes                  yes     yes     no
adapter recovery (other)  yes                  yes     yes     no
incoming ELS              yes                  yes     yes     no
incoming ELS lost         yes                  yes     yes     no

Implementation is straight-forward by converting an existing worker to
a delayed worker. But care is needed whenever that worker is going to be
flushed (in order to make sure work has been completed), since a flush
operation cancels the timer set up for deferred execution (see * above).

There is a small race window whenever a port scan work starts
running up to the point in time of storing the time stamp for that port
scan. The impact is negligible. Closing that gap isn't trivial, though, and
would the destroy the beauty of a simple work-to-delayed-work conversion.

Signed-off-by: Martin Peschke <mpeschke@linux.vnet.ibm.com>
Signed-off-by: Steffen Maier <maier@linux.vnet.ibm.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 49 insertions, 3 deletions

diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index ca28e1c66115..25d49f32ca63 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/utsname.h>
+#include <linux/random.h>
 #include <scsi/fc/fc_els.h>
 #include <scsi/libfc.h>
 #include "zfcp_ext.h"
@@ -31,12 +32,54 @@ module_param_named(no_auto_port_rescan, no_auto_port_rescan, bool, 0600);
 MODULE_PARM_DESC(no_auto_port_rescan,
 		 "no automatic port_rescan (default off)");
 
+static unsigned int port_scan_backoff = 500;
+module_param(port_scan_backoff, uint, 0600);
+MODULE_PARM_DESC(port_scan_backoff,
+	"upper limit of port scan random backoff in msecs (default 500)");
+
+static unsigned int port_scan_ratelimit = 60000;
+module_param(port_scan_ratelimit, uint, 0600);
+MODULE_PARM_DESC(port_scan_ratelimit,
+	"minimum interval between port scans in msecs (default 60000)");
+
+unsigned int zfcp_fc_port_scan_backoff(void)
+{
+	if (!port_scan_backoff)
+		return 0;
+	return get_random_int() % port_scan_backoff;
+}
+
+static void zfcp_fc_port_scan_time(struct zfcp_adapter *adapter)
+{
+	unsigned long interval = msecs_to_jiffies(port_scan_ratelimit);
+	unsigned long backoff = msecs_to_jiffies(zfcp_fc_port_scan_backoff());
+
+	adapter->next_port_scan = jiffies + interval + backoff;
+}
+
+static void zfcp_fc_port_scan(struct zfcp_adapter *adapter)
+{
+	unsigned long now = jiffies;
+	unsigned long next = adapter->next_port_scan;
+	unsigned long delay = 0, max;
+
+	/* delay only needed within waiting period */
+	if (time_before(now, next)) {
+		delay = next - now;
+		/* paranoia: never ever delay scans longer than specified */
+		max = msecs_to_jiffies(port_scan_ratelimit + port_scan_backoff);
+		delay = min(delay, max);
+	}
+
+	queue_delayed_work(adapter->work_queue, &adapter->scan_work, delay);
+}
+
 void zfcp_fc_conditional_port_scan(struct zfcp_adapter *adapter)
 {
 	if (no_auto_port_rescan)
 		return;
 
-	queue_work(adapter->work_queue, &adapter->scan_work);
+	zfcp_fc_port_scan(adapter);
 }
 
 void zfcp_fc_inverse_conditional_port_scan(struct zfcp_adapter *adapter)
@@ -44,7 +87,7 @@ void zfcp_fc_inverse_conditional_port_scan(struct zfcp_adapter *adapter)
 	if (!no_auto_port_rescan)
 		return;
 
-	queue_work(adapter->work_queue, &adapter->scan_work);
+	zfcp_fc_port_scan(adapter);
 }
 
 /**
@@ -680,12 +723,15 @@ static int zfcp_fc_eval_gpn_ft(struct zfcp_fc_req *fc_req,
  */
 void zfcp_fc_scan_ports(struct work_struct *work)
 {
-	struct zfcp_adapter *adapter = container_of(work, struct zfcp_adapter,
+	struct delayed_work *dw = to_delayed_work(work);
+	struct zfcp_adapter *adapter = container_of(dw, struct zfcp_adapter,
 						    scan_work);
 	int ret, i;
 	struct zfcp_fc_req *fc_req;
 	int chain, max_entries, buf_num, max_bytes;
 
+	zfcp_fc_port_scan_time(adapter);
+
 	chain = adapter->adapter_features & FSF_FEATURE_ELS_CT_CHAINED_SBALS;
 	buf_num = chain ? ZFCP_FC_GPN_FT_NUM_BUFS : 1;
 	max_entries = chain ? ZFCP_FC_GPN_FT_MAX_ENT : ZFCP_FC_GPN_FT_ENT_PAGE;