diff options
| author | Jean-Sébastien Pédron <jean-sebastien@rabbitmq.com> | 2017-06-08 16:50:02 +0200 |
|---|---|---|
| committer | Jean-Sébastien Pédron <jean-sebastien@rabbitmq.com> | 2017-06-13 12:12:47 +0200 |
| commit | 0bd9368048704de5464605896a6c09befd173221 (patch) | |
| tree | 34c1ae5055e79566c519cd7cf78ec386c2cb7ab7 /scripts | |
| parent | 085820636c5c52c0b61900ae1597e9f2ecd740b4 (diff) | |
| download | rabbitmq-server-git-0bd9368048704de5464605896a6c09befd173221.tar.gz | |
partitions_SUITE: Try to improve partial_false_positive
The testcase simulates a small delay between the times B sees A down
and C sees A down too. Because A is effectively down for both, B's
rabbit_node_monitor shouldn't see a partial partition.
When B sees A down first, it asks C about A. In the scenario the
testcase simulates, C tries to contact A, fails and reports to B that A
is down.
However, because of the way we simulate that delay, sometimes, C still
sees A when B asks about it, because the link between A and C isn't
blocked yet. When this happens, B decides there is a partial partition.
Therefore, the testcase fails because it tests that this shouldn't
happen.
To try to be closer to a real-world situation (where A would be really
down for B and C), we suspend C's rabbit_node_monitor until we block the
link between A and C. Thus B still asks C about A, but C only processes
the request when the link is indeed down.
[#146911969]
Diffstat (limited to 'scripts')
0 files changed, 0 insertions, 0 deletions
