From: Andrew Perepechko <andrew.perepechko@hpe.com>
Date: Mon, 27 Jul 2020 09:31:46 +0000 (+0300)
Subject: LU-13822 ptlrpc: fixes for RCU-related stalls
X-Git-Tag: 2.13.57~73
X-Git-Url: https://git.whamcloud.com/gitweb?a=commitdiff_plain;h=1bbd5b5f0ee042cf89774eadff47211a5bef7ee0;p=fs%2Flustre-release.git

LU-13822 ptlrpc: fixes for RCU-related stalls

ptlrpc_expired_set() may need to process a lot
of requests, so the processing loop needs to
schedule from time to time to avoid RCU-related
stalls.

Change-Id: I14b0aaf14ab127805699729adbb26459a2f4f07c
Signed-off-by: Andrew Perepechko <andrew.perepechko@hpe.com>
HPE-bug-id: LUS-8939
Reviewed-on: https://review.whamcloud.com/39514
Reviewed-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
---

diff --git a/lustre/ptlrpc/client.c b/lustre/ptlrpc/client.c
index 368732a..4ec69b3 100644
--- a/lustre/ptlrpc/client.c
+++ b/lustre/ptlrpc/client.c
@@ -2371,6 +2371,12 @@ void ptlrpc_expired_set(struct ptlrpc_request_set *set)
 		 * ptlrpcd thread.
 		 */
 		ptlrpc_expire_one_request(req, 1);
+		/*
+		 * Loops require that we resched once in a while to avoid
+		 * RCU stalls and a few other problems.
+		 */
+		cond_resched();
+
 	}
 }