dlm: retry failed SCTP sends
authorMike Christie <michaelc@cs.wisc.edu>
Fri, 14 Jun 2013 09:56:13 +0000 (04:56 -0500)
committerDavid Teigland <teigland@redhat.com>
Fri, 14 Jun 2013 18:07:11 +0000 (13:07 -0500)
commit5d6898714fe2ce485e95ac74479ed40ebd8d5748
tree83a1adc26581662bfa64d4177d2c71913822efea
parent98e1b60ecc441625c91013e88f14cbd1b3c1fa08
dlm: retry failed SCTP sends

Currently if a SCTP send fails, we lose the data we were trying
to send because the writequeue_entry is released when we do the send.
When this happens other nodes will then hang waiting for a reply.

This adds support for SCTP to retry the send operation.

I also removed the retry limit for SCTP use, because we want
to make sure we try every path during init time and for longer
failures we want to continually retry in case paths come back up
while trying other paths. We will do this until userspace tells us
to stop.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: David Teigland <teigland@redhat.com>
fs/dlm/lowcomms.c