During development a HTTP request will pause for 1 minute ONLY when an
?index is set. This gives a realistic emulation of blocking queries.
During testing we can change this latency when we are testing blocking
queries, which we do in numerous places.
A problem can arise during testing on a very slow machine.
If you are not testing blocking queries and therefore not set a latency
to test with, if the machine you are testing on is slow enough a normal
page can assert during a test, yet not tear down before a further
blocking query request is made. This blocking query then uses the default
latency which cause the page to hang for 1 minute, which in turn causes
the test to timeout.
This only seems to happen on a very slow system, but it does potentially
explain why we occasionally see the odd flakey test popping up.
* Unignore any bin files underneath the UI folder
* Add previously ignored node exec script
* Rearrange steps file so we can continue to list steps out
* Create ConsulNodeList component
* Implement ConsulNodeList and the new Search/Sort to Node List page
* Minor styling fix to align the first icons in composite row
* Fix-up and add tests for the redesigned Node List page
* Add Leader to composite row for Node List page
* Add test for node leader
* ui: Serialize proxies into the model, add Mesh* model props
Serializes the proxies associated with a service onto the Service model
itself, then adds various Mesh* properties
* ui: Uses the new Mesh* properties throughout the app
* ui: Reduce reconnection attempts on disconnection
The UI will attempt to reconnect/retry a blocking query to Consul after
a disconnection in certain circumstances.
1. On receipt of a 5xx error (used for keeping blocking queries running
through reverse proxies that have lowertimeouts than consul itself)
2. When a user switches to a different tab and back again)
3. When the connection to Consul is dropped entirely (when Consul itself
has exited)
In the last case the retry attempts where not using a 3 second interval
between attempts like the first case is.
This commit changes the last case to use the same 3 second pause as the
last case.
* ui: Switch selects to use more HTML-like approach for optgroups
* Add KV comparator
* Use new option/optgroup approach for sort/select
* Fix up tests for new order of menu items
* Add sorting to namespaces
* Add sorting to namespaces
* ui: Fix up default namespace no delete test (#8467)
Co-authored-by: John Cowen <johncowen@users.noreply.github.com>
* ui: Move more menu subcomponents deeper down into popovermenu
* ui: Simplify aria-menu component+remove auto menu close on route change
* Add ember-string-fns
* Use new PopoverMenu sub components and fix up tests
* Fix up wrong closing let
* Remove dcs from the service show page now we have it in the navigation
* Add sorting to ACLs policies with comparator
* Add acls/roles sorting test
* Add navigation test for acls/policies
* Update onchange value for sorting policies
* Add sorting to ACLs roles with comparator
* Add acls/roles sorting test
* Add navigation feature test to roles
* Update onchange value target for sorting roles
* ui: Add URLs to tabs to we can assert them
* Add dcs to the service show page, temporarily
There is an ongoing PR which removes the need to do this by adding a dcs
property to the navigation, hence temporary
* Add a step to assert on whether text _contains_ rather than exact match
* Test whether the URL of the instance tab changes when the user switches dcs using the main navigation menu
* Recompute href-to's on URL change, just like is-href
* Add sorting to ACLs tokens with tests
* Create token comparator and implement in template
* Upgrade @hashicorp/consul-api-double to 3.1.6
* Add navigation test to acls tokens
* ui: Use `X-Range` header/meta to decide whether to reconcile or not
Previously we used a `shouldReconcile` method in order to decide whether
a response should trigger a reconciliation of the frontend ember-data
'source of truth' or not. It's a lot nicer/clearer if this 'flag' can be set
alongside the HTTP request information, moreover we almost have the same
functionality in `If-Range`/`Partial Content` HTTP functionality.
Here we partly follow this HTTP semantics but use a custom `X-Range` header
instead.
* Add sorting to Intentions with tests
* Skip Intentions url back test
* Create comparator for intention and implement in template
* Add a intentions navigation feature test
Previously we used a `shouldReconcile` method in order to decide whether
a response should trigger a reconciliation of the frontend ember-data
'source of truth' or not. It's a lot nicer/clearer if this 'flag' can be set
alongside the HTTP request information, moreover we almost have the same
functionality in `If-Range`/`Partial Content` HTTP functionality.
Here we partly follow this HTTP semantics but use a custom `X-Range` header
instead.
Close#8294. Set overflow to hidden for both x and y axis. This prevents the overflow-y defaulting to auto, and creating scrollbars. Given the text overflow is set to ellipsis, this doesn't change the UI functionality.
* ui: Add new consul-nspace-list component
* ui: Use new consul-nspace-list component
* Fix up other components to use linkable list-collection action
* ui: Remove some dead CSS
* Add components for KV form, KV list and Session form
* Pass through a @label attribute for a human label + don't require error
* Ignore transition aborted errors for if you are re-transitioning
* Make old confirmation dialog more ember-like and tagless
* Make sure data-source and data-sink supports KV and sessions
* Use new components and delete all the things
* Fix up tests
* Make list component tagless
* Add component pageobject and fixup tests from that
* Add eslint warning back in
* Add uri identifiers to all data source things and make them the same
1. Add uri identitifer to data-source service
2. Make <EventSource /> and <DataSource /> as close as possible
3. Add extra `.closed` method to get a list of inactive/closed/closing
data-sources from elsewhere
* Make the connections cleanup the least worst connection when required
* Pass the uri/request id through all the things
* Better user erroring
* Make event sources close on error
* Allow <DataLoader /> data slot to be configurable
* Allow the <DataWriter /> removed state to be configurable
* Don't error if meta is undefined
* Stitch together all the repositories into the data-source/sink
* Use data.source over repositories
* Add missing <EventSource /> components
* Fix up the views/templates
* Disable all the old route based blocking query things
* We still need the repo for the mixin for the moment
* Don't default to default, default != ''
`rpc` is used to define how to make a HTTP request/response messages.
This used to be called 'request' but the term is overused and sounded
like only one leg of the message, so the naming was moved to `rpc` a
while ago, this cleans up the places where we still used the old term.
We changed our default definition list layout in
https://github.com/hashicorp/consul/pull/8117.
We replaced the default with a definition-table class but missed one
place where the old default was previously used.
This adds the definition-table class in RTT where it used to use the
default.
* Remove curly brackets and pass through attributes
* yarn upgrade and part manual deps upgrade of non-problematic things
* from-entries from ember-composable helpers receives an array
* PowerSelect destruction bug seems to be fixed upstream
* Ensure all policies have a default 0 date for ember-c-h upgrade
sorting no longer works correctly unless CreateTime has a value
* ui: Split up client/http and replace $.ajax
This splits the client/http service more in the following ways:
1. Connections are now split out into its own service
2. The transport is now split out into its own service that returns a
listener based http transport
3. Various string parsing/stringifying functions are now split out into
utils
* Remove jQuery from our production build
* Move the coverage serving to the server.js file
* Self review amends
* Add X-Requested-With header
* Move some files around, externalize some functions
* Move connection tracking to use native Set
* Ensure HTTP parsing doesn't encode headers
In the future this will change to deal with all HTTP parsing in one
place, hence the commented out METHOD_PARSING etc
* Start to fix up integration tests to use requestParams
PRs #7610 and #7962 changed the locations/URLs for the gateway docs
which results in a HTTP 404 Not Found being returned when accessing
the previous URLs.
Update URLs for gateway docs to point to new URLs.
PR #8243 adds corresponding redirects on consul.io.
* Upgrade consul-api-dobule to version 3.1.3
* Create ConsulInstaceChecks component with test
* Redesign: Service Instaces tab in for a Node
* Update Node tests to work with the ConsulServiceInstancesList
* Style fix to the copy button in the composite-row details
* Delete helper and move logic to ConsulInstanceChecks component
* Delete unused component consul-node-service-list
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.
We'd assumed that TTL check outputs shouldn't be shown as it seemed like
they never had outputs, but they can be submitted with notes, which are
then converted into the output.
This unhides the output for TTLs and treats them exactly the same as
other healthchecks.
* Update Consul Service List composite rows with Tooltips and description lists
* Update Consul Service Instance List composite rows with Tooltips and description lists
* Removed line height in reduced pill to match the description lists in the composite rows
* Add all the new data required for NodeIdentities
* Add potential NodeIdentity to the token list component
* Amend the policy-form/selector to allow node identity creation
* Fix up CSS for radio buttons and select label
* Add node-identity policy template component
* Fix up and add acceptance tests for NodeIndentities
* Make sure policy previews take node identities into account
* Only show certain policy markup if those we have those policies
* Potentially temporarily hide dt's that don't have icons yet
This mixin was a very thin mixin over the top of our listeners utility,
and we have been gradually preferring using the utility straight rather
than using the mixin. This commit removes the last places where we still
used the mixin, and also potentially the last few places where we
continued to use the old API for our listeners utility.
The WithEventSource mixin was responsible for catching EventSource
errors and cleaning up events sources then the user left a Controller.
As we are trying to avoid mixin usage, we moved this all to an
`EventSource` component, which can clean up when the component is
removed from the page, and also fires an onerror event.
Moving to a component firing an onerror event means we can also remove
all of our custom computed property work that we were using previously
to catch errors (thrown when a service etc. is removed)
* Add Health Checks and update Tooltips in Ingress Upstreams
* Update Tooltip in Proxy Info tab Upstreams
* Add Tooltips to Proxy Info tab Exposed Paths
* Add Health Checks with Tooltips to Service List page
This excludes any /components/**/pageobject.js files from our production
builds which means we can co-locate all of our component page objects
(and selectors) along with the components themselves.
* ui: Reduce discovery-chain log spam
Currently the only way that the UI can know whether connect is enabled
or not is whether we get 500 errors from certain endpoints.
One of these endpoints we already use, so aswell as recovering from a
500 error, we also remember that connect is disabled for the rest of the
page 'session' (so until the page is refreshed), and make no further
http requests to the endpoint for that specific datacenter.
This means that log spam is reduced to only 1 log per page refresh/dc
instead of 1 log per service navigation.
Longer term we'll need some way to dynamically discover whether connect
is enabled per datacenter without relying on something that will add
error logs to consul.
Found using staticcheck.
binary.Write does not accept int types without a size. The error from binary.Write was ignored, so we never saw this error. Casting the data to uint64 produces a correct hash.
Also deprecate the Default{Addr,Port} fields, and prevent them from being encoded. These fields will always be empty and are not used.
Removing these would break backwards compatibility, so they are left in place for now.
Co-authored-by: Hans Hasselberg <me@hans.io>
* ui: Add ability to sort service based on health
* ui: Move custom sorting to sort/comparator Service/Helper (like search)
This moves custom sorting to use the same pattern as custom searching.
* Remove old Controller based comparator
John Cowen
Kenia
John Cowen
duncanKr
Ondrej Sika
Blake Covarrubias
Daniel Nephin