Whamcloud - gitweb
LU-11478 lnet: misleading discovery seqno. 41/36041/4
authorAmir Shehata <ashehata@whamcloud.com>
Fri, 5 Oct 2018 00:18:20 +0000 (17:18 -0700)
committerOleg Drokin <green@whamcloud.com>
Tue, 8 Oct 2019 13:25:08 +0000 (13:25 +0000)
commitda9998767a9093c088d28119179ee591f42910dc
tree10dc1e54dfee9338e3c053d42b8d09b9590c36de
parentd2bc2e4e091071986bc74177ead4bdefe99e0dd5
LU-11478 lnet: misleading discovery seqno.

There is a sequence number used when sending discovery messages. This
sequence number is intended to detect stale messages. However it
could be misleading if the peer reboots. In this case the peer's
sequence number will reset. The node will think that all information
being sent to it is stale, while in reality the peer might've
changed configuration.

There is no reliable why to know whether a peer rebooted, so we'll
always assume that the messages we're receiving are valid. So we'll
operate on first come first serve basis.

Lustre-change: https://review.whamcloud.com/33304
Lustre-commit: 42d999ed8f6113724b1ac103b832d5b74b878d55

Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I421a00e47bc93ee60fa37c648d6d9a726d9def9c
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Signed-off-by: Minh Diep <mdiep@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/36041
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
lnet/lnet/peer.c