mirror of https://github.com/hashicorp/consul
07b49f8887
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. |
||
|---|---|---|
| .. | ||
| nspace | ||
| type | ||
| acl.js | ||
| coordinate.js | ||
| dc.js | ||
| discovery-chain.js | ||
| intention.js | ||
| kv.js | ||
| node.js | ||
| nspace.js | ||
| oidc-provider.js | ||
| policy.js | ||
| proxy.js | ||
| role.js | ||
| service.js | ||
| session.js | ||
| token.js | ||