From 8ae44c778d8cb5bb3a2fed2c2f9d5ac8ae39df02 Mon Sep 17 00:00:00 2001 From: wang di Date: Thu, 27 Oct 2016 18:11:51 -0400 Subject: [PATCH] staging: lustre: ptlrpc: replay bulk request Even though the server might already got the bulk replay request, but bulk transfer timeout, let's replay the bulk request, i.e. treat such replay as same as no replied replay request (See ptlrpc_replay_interpret()). Signed-off-by: wang di Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6924 Reviewed-on: http://review.whamcloud.com/15793 Reviewed-by: Alex Zhuravlev Reviewed-by: Niu Yawei Reviewed-by: Oleg Drokin Signed-off-by: James Simmons Signed-off-by: Greg Kroah-Hartman --- drivers/staging/lustre/lustre/ptlrpc/client.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/staging/lustre/lustre/ptlrpc/client.c b/drivers/staging/lustre/lustre/ptlrpc/client.c index e4fbdd0d0720..bda925ed5294 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/client.c +++ b/drivers/staging/lustre/lustre/ptlrpc/client.c @@ -2762,8 +2762,15 @@ static int ptlrpc_replay_interpret(const struct lu_env *env, atomic_dec(&imp->imp_replay_inflight); - if (!ptlrpc_client_replied(req)) { - CERROR("request replay timed out, restarting recovery\n"); + /* + * Note: if it is bulk replay (MDS-MDS replay), then even if + * server got the request, but bulk transfer timeout, let's + * replay the bulk req again + */ + if (!ptlrpc_client_replied(req) || + (req->rq_bulk && + lustre_msg_get_status(req->rq_repmsg) == -ETIMEDOUT)) { + DEBUG_REQ(D_ERROR, req, "request replay timed out.\n"); rc = -ETIMEDOUT; goto out; } -- 2.39.5