*Description*:Route matches requests based on preset rules, and loads the appropriate plugin according to the matching result, then forwarding requests to target Upstream.
|PATCH |/apisix/admin/routes/{id}|{...}|Standard PATCH. Update some attributes of the existing Route, and other attributes not involved will remain as they are; if you want to delete an attribute, set the value of the attribute Set to null to delete; especially, when the value of the attribute is an array, the attribute will be updated in full|
|PATCH |/apisix/admin/routes/{id}/{path}|{...}|SubPath PATCH, specify the attribute of Route to be updated through {path}, update the value of this attribute in full, and other attributes that are not involved will remain as they are. The difference between the two PATCH can refer to the following examples|
|uri |True |Match Rules|In addition to full matching such as `/foo/bar`、`/foo/gloo`, using different [Router](architecture-design.md#router) allows more advanced matching, see [Router](architecture-design.md#router) for more.|"/hello"|
|host |False |Match Rules|Currently requesting a domain name, such as `foo.com`; pan-domain names such as `*.foo.com` are also supported.|"foo.com"|
|hosts |False |Match Rules|The `host` in the form of a list means that multiple different hosts are allowed, and match any one of them.|{"foo.com", "*.bar.com"}|
|remote_addr|False |Match Rules|The client requests an IP address: `192.168.1.101`, `192.168.1.102`, and CIDR format support `192.168.1.0/24`. In particular, APISIX also fully supports IPv6 address matching: `::1`, `fe80::1`, `fe80::1/64`, etc.|"192.168.1.0/24"|
|remote_addrs|False |Match Rules|The `remote_addr` in the form of a list indicates that multiple different IP addresses are allowed, and match any one of them.|{"127.0.0.1", "192.0.0.0/8", "::1"}|
|methods |False |Match Rules|If empty or without this option, there are no `method` restrictions, and it can be a combination of one or more: `GET`,`POST`,`PUT`,`DELETE`,`PATCH`, `HEAD`,`OPTIONS`,`CONNECT`,`TRACE`.|{"GET", "POST"}|
|priority |False |Match Rules|If different routes contain the same `uri`, determine which route is matched first based on the attribute` priority`. Larger value means higher priority. The default value is 0.|priority = 10|
|vars |False |Match Rules |A list of one or more `{var, operator, val}` elements, like this: `{{var, operator, val}, {var, operator, val}, ...}}`. For example: `{"arg_name", "==", "json"}` means that the current request parameter `name` is `json`. The `var` here is consistent with the internal variable name of Nginx, so you can also use `request_uri`, `host`, etc. For the operator part, the currently supported operators are `==`, `~=`,`>`, `<`, and `~~`. For the `>` and `<` operators, the result is first converted to `number` and then compared. See a list of [supported operators](#available-operators) |{{"arg_name", "==", "json"}, {"arg_age", ">", 18}}|
|filter_func|False|Match Rules|User-defined filtering function. You can use it to achieve matching requirements for special scenarios. This function accepts an input parameter named `vars` by default, which you can use to get Nginx variables.|function(vars) return vars["arg_name"] == "json" end|
|service_protocol|False|Upstream protocol type|only `grpc` and `http` are supported|`http` is the default value; Must set `grpc` if using `gRPC proxy` or `gRPC transcode`|
For the same type of parameters, such as `host` and `hosts`, `remote_addr` and `remote_addrs` cannot exist at the same time, only one of them can be selected. If enabled at the same time, the API will response an error.
"methods": ["GET","POST"], # Can fill multiple methods
"host": "aa.com", # host
"hosts": ["a.com","b.com"], # A set of host. Host and hosts only need to be non-empty one.
"plugins": {}, # Bound plugin
"priority": 0, # If different routes contain the same `uri`, determine which route is matched first based on the attribute` priority`, the default value is 0.
Consider the following example: matching requests whose `request name` is equal to `json`, `age` is greater than `18`, and `address` begins with `China`:
*Description*:A `Service` is an abstraction of an API (which can also be understood as a set of Route abstractions). It usually corresponds to the upstream service abstraction. Between `Route` and `Service`, usually the relationship of N:1.
|PATCH |/apisix/admin/services/{id}|{...}|Standard PATCH. Update some attributes of the existing Service, and other attributes not involved will remain as they are; if you want to delete an attribute, set the value of the attribute Set to null to delete; especially, when the value of the attribute is an array, the attribute will be updated in full|
|PATCH |/apisix/admin/services/{id}/{path}|{...}|SubPath PATCH, specify the attribute of Service to be updated through {path}, update the value of this attribute in full, and other attributes that are not involved will remain as they are. The difference between the two PATCH can refer to the following examples|
The binding authentication and authorization plug-in is a bit special. When it needs to be used in conjunction with the consumer, it needs to provide user name, password and other information; on the other hand, when it is bound with route / service, it does not require any parameters. Because at this time, it is based on the user request data to infer which consumer the user corresponds to.
*Description*:Upstream configuration can be directly bound to the specified `Route` or it can be bound to `Service`, but the configuration in `Route` has a higher priority. The priority behavior here is very similar to `Plugin`.
|PATCH |/apisix/admin/upstreams/{id}|{...}|Standard PATCH. Update some attributes of the existing Upstream, and other attributes not involved will remain as they are; if you want to delete an attribute, set the value of the attribute Set to null to delete; especially, when the value of the attribute is an array, the attribute will be updated in full|
|PATCH |/apisix/admin/upstreams/{id}/{path}|{...}|SubPath PATCH, specify the attribute of Upstream to be updated through {path}, update the value of this attribute in full, and other attributes that are not involved will remain as they are. The difference between the two PATCH can refer to the following example|
In addition to the basic complex equalization algorithm selection, APISIX's Upstream also supports logic for upstream passive health check and retry, see the table below.
|type |required|`roundrobin` supports the weight of the load, `chash` consistency hash,`ewma` minimum latency ,pick one of them.see https://en.wikipedia.org/wiki/EWMA_chart for details|
|nodes |required if `k8s_deployment_info` not configured|Hash table, the key of the internal element is the upstream machine address list, the format is `Address + Port`, where the address part can be IP or domain name, such as `192.168.1.100:80`, `foo.com:80`, etc. Value is the weight of the node. In particular, when the weight value is `0`, it has a special meaning, which usually means that the upstream node is invalid and never wants to be selected.|
|k8s_deployment_info|required if `nodes` not configured|fields: `namespace`、`deploy_name`、`service_name`、`port`、`backend_type`, `port` is number, `backend_type` is `pod` or `service`, others is string. |
|hash_on |optional|This option is only valid if the `type` is `chash`. Supported types `vars`(Nginx variables), `header`(custom header), `cookie`, `consumer`, the default value is `vars`.|
|key |optional|This option is only valid if the `type` is `chash`. Find the corresponding node `id` according to `hash_on` and `key`. When `hash_on` is set as `vars`, `key` is the required parameter, for now, it support nginx built-in variables like `uri, server_name, server_addr, request_uri, remote_port, remote_addr, query_string, host, hostname, arg_***`, `arg_***` is arguments in the request line, [Nginx variables list](http://nginx.org/en/docs/varindex.html). When `hash_on` is set as `header`, `key` is the required parameter, and `header name` is customized. When `hash_on` is set to `cookie`, `key` is the required parameter, and `cookie name` is customized. When `hash_on` is set to `consumer`, `key` does not need to be set. In this case, the `key` adopted by the hash algorithm is the `consumer_id` authenticated. If the specified `hash_on` and `key` can not fetch values, it will be fetch `remote_addr` by default.|
|retries |optional|Pass the request to the next upstream using the underlying Nginx retry mechanism, the retry mechanism is enabled by default and set the number of retries according to the number of backend nodes. If `retries` option is explicitly set, it will override the default value. `0` means disable retry mechanism.|
|pass_host |optional|`pass` pass the client request host, `node` not pass the client request host, using the upstream node host, `rewrite` rewrite host by the configured `upstream_host`.|
|upstream_host |optional|This option is only valid if the `pass_host` is `rewrite`.|