Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754475Ab3C0NMF (ORCPT ); Wed, 27 Mar 2013 09:12:05 -0400 Received: from mail09.linbit.com ([212.69.161.110]:44313 "EHLO mail09.linbit.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753342Ab3C0NJV (ORCPT ); Wed, 27 Mar 2013 09:09:21 -0400 From: Philipp Reisner To: linux-kernel@vger.kernel.org, Jens Axboe Cc: drbd-dev@lists.linbit.com, Philipp Reisner , Lars Ellenberg Subject: [PATCH 08/17] drbd: Fix disconnect to keep the peer disk state if connection breaks during operation Date: Wed, 27 Mar 2013 14:08:40 +0100 Message-Id: <1364389729-17559-9-git-send-email-philipp.reisner@linbit.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1364389729-17559-1-git-send-email-philipp.reisner@linbit.com> References: <1364389729-17559-1-git-send-email-philipp.reisner@linbit.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4237 Lines: 103 The issue was that if the connection broke while we did the gracefull state change to C_DISCONNECTING (C_TEARDOWN), then we returned a success code from the state engine. (SS_CW_NO_NEED) The result of that is that we missed to call the fence-peer script in such a case. Fixed that by introducing a new error code (SS_OUTDATE_WO_CONN). This one should never reach back into user space. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_nl.c | 7 +++++-- drivers/block/drbd/drbd_state.c | 14 +++++++------- drivers/block/drbd/drbd_strings.c | 1 + include/linux/drbd.h | 3 ++- 4 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 56bafdc..39e9a91 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -2198,8 +2198,11 @@ static enum drbd_state_rv conn_try_disconnect(struct drbd_tconn *tconn, bool for return SS_SUCCESS; case SS_PRIMARY_NOP: /* Our state checking code wants to see the peer outdated. */ - rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING, - pdsk, D_OUTDATED), CS_VERBOSE); + rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING, pdsk, D_OUTDATED), 0); + + if (rv == SS_OUTDATE_WO_CONN) /* lost connection before graceful disconnect succeeded */ + rv = conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_VERBOSE); + break; case SS_CW_FAILED_BY_PEER: /* The peer probably wants to see us outdated. */ diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 22e259f..90c5be2 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -642,6 +642,10 @@ is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_t && os.conn < C_WF_REPORT_PARAMS) rv = SS_NEED_CONNECTION; /* No NetworkFailure -> SyncTarget etc... */ + if (ns.conn == C_DISCONNECTING && ns.pdsk == D_OUTDATED && + os.conn < C_CONNECTED && os.pdsk > D_OUTDATED) + rv = SS_OUTDATE_WO_CONN; + return rv; } @@ -1748,13 +1752,9 @@ _conn_rq_cond(struct drbd_tconn *tconn, union drbd_state mask, union drbd_state if (test_and_clear_bit(CONN_WD_ST_CHG_FAIL, &tconn->flags)) return SS_CW_FAILED_BY_PEER; - rv = tconn->cstate != C_WF_REPORT_PARAMS ? SS_CW_NO_NEED : SS_UNKNOWN_ERROR; - - if (rv == SS_UNKNOWN_ERROR) - rv = conn_is_valid_transition(tconn, mask, val, 0); - - if (rv == SS_SUCCESS) - rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */ + rv = conn_is_valid_transition(tconn, mask, val, 0); + if (rv == SS_SUCCESS && tconn->cstate == C_WF_REPORT_PARAMS) + rv = SS_UNKNOWN_ERROR; /* continue waiting */ return rv; } diff --git a/drivers/block/drbd/drbd_strings.c b/drivers/block/drbd/drbd_strings.c index 9a664bd..58e08ff 100644 --- a/drivers/block/drbd/drbd_strings.c +++ b/drivers/block/drbd/drbd_strings.c @@ -89,6 +89,7 @@ static const char *drbd_state_sw_errors[] = { [-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated", [-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change", [-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted", + [-SS_OUTDATE_WO_CONN] = "Need a connection for a graceful disconnect/outdate peer", [-SS_O_VOL_PEER_PRI] = "Other vol primary on peer not allowed by config", }; diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 0c5a18e..3163307 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -319,7 +319,8 @@ enum drbd_state_rv { SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ SS_O_VOL_PEER_PRI = -20, - SS_AFTER_LAST_ERROR = -21, /* Keep this at bottom */ + SS_OUTDATE_WO_CONN = -21, + SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */ }; /* from drbd_strings.c */ -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/