From: wang di <di.w...@intel.com> 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 <di.w...@intel.com> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6924 Reviewed-on: http://review.whamcloud.com/15793 Reviewed-by: Alex Zhuravlev <alexey.zhurav...@intel.com> Reviewed-by: Niu Yawei <yawei....@intel.com> Reviewed-by: Oleg Drokin <oleg.dro...@intel.com> Signed-off-by: James Simmons <jsimm...@infradead.org> --- drivers/staging/lustre/lustre/ptlrpc/client.c | 11 +++++++++-- 1 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/staging/lustre/lustre/ptlrpc/client.c b/drivers/staging/lustre/lustre/ptlrpc/client.c index e4fbdd0..bda925e 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; } -- 1.7.1
