From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001

From: Benjamin Marzinski <bmarzins@redhat.com>

Date: Tue, 29 Mar 2022 22:22:10 -0500

Subject: [PATCH] multipathd: Don't keep starting TUR threads, if they always

 hang.

If tur thead hangs, multipathd was simply creating a new thread, and

assuming that the old thread would get cleaned up eventually. I have

seen a case recently where there were 26000 multipathd threads on a

system, all stuck trying to send TUR commands to path devices. The root

cause of the issue was a scsi kernel issue, but it shows that the way

multipathd currently deals with stuck threads could use some refinement.

Now, when one tur thread hangs, multipathd will act as it did before.

If a second one in a row hangs, multipathd will instead wait for it to

complete before starting another thread. Once the thread completes, the

count is reset.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>

Reviewed-by: Martin Wilck 

---

 libmultipath/checkers/tur.c | 23 +++++++++++++++++++++--

 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/libmultipath/checkers/tur.c b/libmultipath/checkers/tur.c

index a4b4a213..d82f7dbc 100644

--- a/libmultipath/checkers/tur.c

+++ b/libmultipath/checkers/tur.c

@@ -27,6 +27,7 @@

 #define TUR_CMD_LEN 6

 #define HEAVY_CHECK_COUNT       10

+#define MAX_NR_TIMEOUTS 1

 enum {

 	MSG_TUR_RUNNING = CHECKER_FIRST_MSGID,

@@ -55,6 +56,7 @@ struct tur_checker_context {

 	int holders; /* uatomic access only */

 	int msgid;

 	struct checker_context ctx;

+	unsigned int nr_timeouts;

 };

 int libcheck_init (struct checker * c)

@@ -359,8 +361,23 @@ int libcheck_check(struct checker * c)

 		}

 	} else {

 		if (uatomic_read(&ct->holders) > 1) {

+			/* The thread has been cancelled but hasn't quit. */

+			if (ct->nr_timeouts == MAX_NR_TIMEOUTS) {

+				condlog(2, "%d:%d : waiting for stalled tur thread to finish",

+					major(ct->devt), minor(ct->devt));

+				ct->nr_timeouts++;

+			}

 			/*

-			 * The thread has been cancelled but hasn't quit.

+			 * Don't start new threads until the last once has

+			 * finished.

+			 */

+			if (ct->nr_timeouts > MAX_NR_TIMEOUTS) {

+				c->msgid = MSG_TUR_TIMEOUT;

+				return PATH_TIMEOUT;

+			}

+			ct->nr_timeouts++;

+			/*

+			 * Start a new thread while the old one is stalled.

 			 * We have to prevent it from interfering with the new

 			 * thread. We create a new context and leave the old

 			 * one with the stale thread, hoping it will clean up

@@ -376,13 +393,15 @@ int libcheck_check(struct checker * c)

 			 */

 			if (libcheck_init(c) != 0)

 				return PATH_UNCHECKED;

+			((struct tur_checker_context *)c->context)->nr_timeouts = ct->nr_timeouts;

 			if (!uatomic_sub_return(&ct->holders, 1))

 				/* It did terminate, eventually */

 				cleanup_context(ct);

 			ct = c->context;

-		}

+		} else

+			ct->nr_timeouts = 0;

 		/* Start new TUR checker */

 		pthread_mutex_lock(&ct->lock);

 		tur_status = ct->state = PATH_PENDING;