mirror of
https://github.com/status-im/consul.git
synced 2025-01-09 21:35:52 +00:00
0717f58780
In https://github.com/hashicorp/consul/pull/8065 we attempted to reduce the amount of times that the UI requests the discovery chain endpoint when connect is disabled on a datacenter. Currently we can only tell if connect is disabled on a datacenter by detecting a 500 error from a connect related endpoint. In the above PR we mistakenly returned from a catch instead of rethrowing the error, which meant that when a none 500 error was caught the discovery chain data would be removed. Whilst at first glance this doens't seem like a big problem due to the endpoint erroring, but we also receive a 0 error when we abort endpoints during blocking queries. This means that in certain cases we can remove cached data for the discovery chain and then delay reloading it via a blocking query. This PR replaces the return with a throw, which means that everything is dealt with correctly via the blocking query error detection/logic.