7.8 KiB
Registry
Overview
There are many services in the network on different peers, and there should be a way to find and resolve these services in runtime without prior knowledge about exact service providers. Such approach gives robustness and flexibility to our solutions in terms of discovery, redundancy and high availability.
In centralized systems, we can have centralized storage and routing, but in p2p decentralized environments, the problem becomes more challenging. Registry is our view on the solution for the problem.
Why is it important?
Scalability, redundancy and high availability are essential parts of a decentralized system, but they are not available out of the box. To enable them, information about services should be bound with peers providing them. Also, such networks are constantly changing, and those changes should be reflected and resolvable in runtime to provide uninterruptible access. So there's a need to have a decentralized protocol to update and resolve information about routing, both global and local.
What is it?
Registry is available (built-in) on every Fluence node, and it provides service advertisement and discovery. The component allows of creating relationships between unique identifiers and groups of services on various peers. So service providers can either join or disconnect during runtime and be discoverable on the network.
However, Registry is not a plain KV-storage. Instead, it is a composition of the Registry service for each network participant and the scheduled scripts maintaining replication and garbage collection.
So, if you want to discover a group of services on different peers without prior knowledge in runtime, you should register a Resource. A resource is a group of services or peers united by some common feature. Please notice that resource lifetime is ~24 hours. However, if the resource has been accessed recently, its lifetime is prolonged, and it will not be garbage-collected for the next 24 hours from the last access.
Service is represented by a combination of service_id and peer_id, it is called Record.
There is no permissions management at the moment, but in the coming updates, a resource owner will be able to provide a challenge to check against.
How to Use it in Aqua
How to import
import "@fluencelabs/registry/resources-api.aqua"
import "@fluencelabs/registry/registry-service.aqua"
func my_function(resource_id: string) -> []Record, *Error:
result, error <- resolveResource(resource_id, 2)
<- result, error
How to create Resource
createResource(label: string) -> ?ResourceId, *Error
Let's register a resource with the label sample by INIT_PEER_ID:
func my_resource() -> ?ResourceId, *Error:
id, error <- createResource("sample")
<- id, error
labelis a unique string for the peer id- creation is successful if a resource id is returned
*Erroraccumulates errors from all the affected peers
How to register a service
registerService(resource_id: ResourceId, value: string, peer_id: string service_id: ?string) -> bool, *Error
Let's register a local service greeting and pass a random string hi as a value:
func register_local_service(resource_id: string) -> ?bool, *Error:
success, error <- registerService(resource_id, "hi", INIT_PEER_ID, ?[greeting])
<- success, error
Let's register a service echo hosted on peer_id and pass a random string like sample as a value:
func register_external_service(resource_id: string, peer_id: string) -> ?bool, *Error:
success, error <- registerService(resource_id, "hi", peer_id, ?[greeting])
<- success, error
valueis a user-defined string that can be used at the discretion of the user- to update the service record, you should register it again to create a record with a newer timestamp
- service record will be automatically updated till deleted via
unregisterService
How to unregister a service
func unregisterService(resource_id: ResourceId, peer_id: PeerId) -> bool, *Error:
Let's remove a service record from a target node:
func stop_provide_external_service(resource_id: string, peer_id: string):
unregisterService(resource_id, peer_id)
- it will be removed from the target node and eventually from the network
How to resolve service records
resolveResource(resource_id: ResourceId, ack: i16) -> []Record, *Error
Let's resolve all service records for our resource_id:
func get_my_records(resource_id: string, consistency_level: i16) -> []Record, *Error:
records, error <- resolveResource(resource_id, consistency_level)
<- records, error
ackrepresents a minimal number of peers that requested for known records
How to execute a callback on Resource
executeOnResource(resource_id: ResourceId, ack: i16, call: Record -> ()) -> *Error
func call_provider(p: Record):
-- topological move to a provider via relay
on p.peer_id via p.relay_id:
-- resolve and call your service on a provider
...
Op.noop()
-- call on every provider
func call_everyone(resource_id: String, ack: i16):
executeOnResource(resource_id, ack, call_provider)
- it is a combination of
resolveResourceand aforloop through records with the callback execution - it can be useful in case of broadcasting events on providers
For more detailed example please take a look in the docs
Notes
You can redefine REPLICATION_FACTOR and CONSISTENCY_LEVEL.
Use cases
Services discovery
Discover services without prior knowledge about exact peers and service identifiers.
Service high-availability
A service provided by several peers still will be available for the client in case of disconnections and other providers' failures.
Subnetwork discovery
You can register a group of peers for a resource (without specifying any services). So you "tag" and group the nodes to create a subnetwork.
Load balancer
If you have a list of service records updated in runtime, you can create a load-balancing service based on your preferred metrics.
API
API is defined in the resources-api.aqua module. API Reference will be available in the documentation soon.