X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fptlrpc%2Frecover.c;h=c526e9e5c65f7d3209cf990e7eaf06fb1684c788;hp=02f79d08e306d6f3d1a32e400527c63e76840942;hb=7d29d3167684b13a612c8c1bff860019a218115c;hpb=51f1b46dab6c2cc16f71d3f3be483f530b5e4001 diff --git a/lustre/ptlrpc/recover.c b/lustre/ptlrpc/recover.c index 02f79d0..c526e9e 100644 --- a/lustre/ptlrpc/recover.c +++ b/lustre/ptlrpc/recover.c @@ -23,7 +23,7 @@ * Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2015, Intel Corporation. + * Copyright (c) 2011, 2016, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -82,27 +82,10 @@ int ptlrpc_replay_next(struct obd_import *imp, int *inflight) imp->imp_last_transno_checked = 0; ptlrpc_free_committed(imp); last_transno = imp->imp_last_replay_transno; - spin_unlock(&imp->imp_lock); CDEBUG(D_HA, "import %p from %s committed %llu last %llu\n", - imp, obd2cli_tgt(imp->imp_obd), - imp->imp_peer_committed_transno, last_transno); - - /* Do I need to hold a lock across this iteration? We shouldn't be - * racing with any additions to the list, because we're in recovery - * and are therefore not processing additional requests to add. Calls - * to ptlrpc_free_committed might commit requests, but nothing "newer" - * than the one we're replaying (it can't be committed until it's - * replayed, and we're doing that here). l_f_e_safe protects against - * problems with the current request being committed, in the unlikely - * event of that race. So, in conclusion, I think that it's safe to - * perform this list-walk without the imp_lock held. - * - * But, the {mdc,osc}_replay_open callbacks both iterate - * request lists, and have comments saying they assume the - * imp_lock is being held by ptlrpc_replay, but it's not. it's - * just a little race... - */ + imp, obd2cli_tgt(imp->imp_obd), + imp->imp_peer_committed_transno, last_transno); /* Replay all the committed open requests on committed_list first */ if (!list_empty(&imp->imp_committed_list)) { @@ -112,9 +95,6 @@ int ptlrpc_replay_next(struct obd_import *imp, int *inflight) /* The last request on committed_list hasn't been replayed */ if (req->rq_transno > last_transno) { - /* Since the imp_committed_list is immutable before - * all of it's requests being replayed, it's safe to - * use a cursor to accelerate the search */ if (!imp->imp_resend_replay || imp->imp_replay_cursor == &imp->imp_committed_list) imp->imp_replay_cursor = @@ -129,6 +109,7 @@ int ptlrpc_replay_next(struct obd_import *imp, int *inflight) break; req = NULL; + LASSERT(!list_empty(imp->imp_replay_cursor)); imp->imp_replay_cursor = imp->imp_replay_cursor->next; } @@ -159,11 +140,13 @@ int ptlrpc_replay_next(struct obd_import *imp, int *inflight) if (req != NULL && imp->imp_resend_replay) lustre_msg_add_flags(req->rq_reqmsg, MSG_RESENT); - spin_lock(&imp->imp_lock); - /* The resend replay request may have been removed from the + /* ptlrpc_prepare_replay() may fail to add the reqeust into unreplied + * list if the request hasn't been added to replay list then. Another + * exception is that resend replay could have been removed from the * unreplied list. */ - if (req != NULL && imp->imp_resend_replay && - list_empty(&req->rq_unreplied_list)) { + if (req != NULL && list_empty(&req->rq_unreplied_list)) { + DEBUG_REQ(D_HA, req, "resend_replay: %d, last_transno: %llu\n", + imp->imp_resend_replay, last_transno); ptlrpc_add_unreplied(req); imp->imp_known_replied_xid = ptlrpc_known_replied_xid(imp); } @@ -172,8 +155,6 @@ int ptlrpc_replay_next(struct obd_import *imp, int *inflight) spin_unlock(&imp->imp_lock); if (req != NULL) { - /* The request should have been added back in unreplied list - * by ptlrpc_prepare_replay(). */ LASSERT(!list_empty(&req->rq_unreplied_list)); rc = ptlrpc_replay_req(req); @@ -222,6 +203,7 @@ int ptlrpc_resend(struct obd_import *imp) } spin_unlock(&imp->imp_lock); + OBD_FAIL_TIMEOUT(OBD_FAIL_LDLM_ENQUEUE_OLD_EXPORT, 2); RETURN(0); }