open-consul/agent/structs/federation_state.go

147 lines
3.7 KiB
Go
Raw Normal View History

// Copyright (c) HashiCorp, Inc.
// SPDX-License-Identifier: MPL-2.0
wan federation via mesh gateways (#6884) This is like a Möbius strip of code due to the fact that low-level components (serf/memberlist) are connected to high-level components (the catalog and mesh-gateways) in a twisty maze of references which make it hard to dive into. With that in mind here's a high level summary of what you'll find in the patch: There are several distinct chunks of code that are affected: * new flags and config options for the server * retry join WAN is slightly different * retry join code is shared to discover primary mesh gateways from secondary datacenters * because retry join logic runs in the *agent* and the results of that operation for primary mesh gateways are needed in the *server* there are some methods like `RefreshPrimaryGatewayFallbackAddresses` that must occur at multiple layers of abstraction just to pass the data down to the right layer. * new cache type `FederationStateListMeshGatewaysName` for use in `proxycfg/xds` layers * the function signature for RPC dialing picked up a new required field (the node name of the destination) * several new RPCs for manipulating a FederationState object: `FederationState:{Apply,Get,List,ListMeshGateways}` * 3 read-only internal APIs for debugging use to invoke those RPCs from curl * raft and fsm changes to persist these FederationStates * replication for FederationStates as they are canonically stored in the Primary and replicated to the Secondaries. * a special derivative of anti-entropy that runs in secondaries to snapshot their local mesh gateway `CheckServiceNodes` and sync them into their upstream FederationState in the primary (this works in conjunction with the replication to distribute addresses for all mesh gateways in all DCs to all other DCs) * a "gateway locator" convenience object to make use of this data to choose the addresses of gateways to use for any given RPC or gossip operation to a remote DC. This gets data from the "retry join" logic in the agent and also directly calls into the FSM. * RPC (`:8300`) on the server sniffs the first byte of a new connection to determine if it's actually doing native TLS. If so it checks the ALPN header for protocol determination (just like how the existing system uses the type-byte marker). * 2 new kinds of protocols are exclusively decoded via this native TLS mechanism: one for ferrying "packet" operations (udp-like) from the gossip layer and one for "stream" operations (tcp-like). The packet operations re-use sockets (using length-prefixing) to cut down on TLS re-negotiation overhead. * the server instances specially wrap the `memberlist.NetTransport` when running with gateway federation enabled (in a `wanfed.Transport`). The general gist is that if it tries to dial a node in the SAME datacenter (deduced by looking at the suffix of the node name) there is no change. If dialing a DIFFERENT datacenter it is wrapped up in a TLS+ALPN blob and sent through some mesh gateways to eventually end up in a server's :8300 port. * a new flag when launching a mesh gateway via `consul connect envoy` to indicate that the servers are to be exposed. This sets a special service meta when registering the gateway into the catalog. * `proxycfg/xds` notice this metadata blob to activate additional watches for the FederationState objects as well as the location of all of the consul servers in that datacenter. * `xds:` if the extra metadata is in place additional clusters are defined in a DC to bulk sink all traffic to another DC's gateways. For the current datacenter we listen on a wildcard name (`server.<dc>.consul`) that load balances all servers as well as one mini-cluster per node (`<node>.server.<dc>.consul`) * the `consul tls cert create` command got a new flag (`-node`) to help create an additional SAN in certs that can be used with this flavor of federation.
2020-03-09 20:59:02 +00:00
package structs
import (
"sort"
"time"
)
// FederationStateOp is the operation for a request related to federation states.
type FederationStateOp string
const (
FederationStateUpsert FederationStateOp = "upsert"
FederationStateDelete FederationStateOp = "delete"
)
// FederationStateRequest is used to upsert and delete federation states.
type FederationStateRequest struct {
// Datacenter is the target for this request.
Datacenter string
// Op is the type of operation being requested.
Op FederationStateOp
// State is the federation state to upsert or in the case of a delete
// only the State.Datacenter field should be set.
State *FederationState
// WriteRequest is a common struct containing ACL tokens and other
// write-related common elements for requests.
WriteRequest
}
// RequestDatacenter returns the datacenter for a given request.
func (c *FederationStateRequest) RequestDatacenter() string {
return c.Datacenter
}
// FederationStates is a list of federation states.
type FederationStates []*FederationState
// Sort sorts federation states by their datacenter.
func (listings FederationStates) Sort() {
sort.Slice(listings, func(i, j int) bool {
return listings[i].Datacenter < listings[j].Datacenter
})
}
// FederationState defines some WAN federation related state that should be
// cross-shared between all datacenters joined on the WAN. One record exists
// per datacenter.
type FederationState struct {
// Datacenter is the name of the datacenter.
Datacenter string
// MeshGateways is a snapshot of the catalog state for all mesh gateways in
// this datacenter.
MeshGateways CheckServiceNodes `json:",omitempty"`
// UpdatedAt keeps track of when this record was modified.
UpdatedAt time.Time
// PrimaryModifyIndex is the ModifyIndex of the original data as it exists
// in the primary datacenter.
PrimaryModifyIndex uint64
// RaftIndex is local raft data.
RaftIndex
}
// IsSame is used to compare two federation states for the purposes of
// anti-entropy.
func (c *FederationState) IsSame(other *FederationState) bool {
if c.Datacenter != other.Datacenter {
return false
}
// We don't include the UpdatedAt field in this comparison because that is
// only updated when we re-persist.
if len(c.MeshGateways) != len(other.MeshGateways) {
return false
}
// NOTE: we don't bother to sort these since the order is going to be
// already defined by how the catalog returns results which should be
// stable enough.
for i := 0; i < len(c.MeshGateways); i++ {
a := c.MeshGateways[i]
b := other.MeshGateways[i]
if !a.Node.IsSame(b.Node) {
return false
}
if !a.Service.IsSame(b.Service) {
return false
}
if len(a.Checks) != len(b.Checks) {
return false
}
for j := 0; j < len(a.Checks); j++ {
ca := a.Checks[j]
cb := b.Checks[j]
if !ca.IsSame(cb) {
return false
}
}
}
return true
}
// FederationStateQuery is used to query federation states.
type FederationStateQuery struct {
// Datacenter is the target this request is intended for.
Datacenter string
// TargetDatacenter is the name of a datacenter to fetch the federation state for.
TargetDatacenter string
// Options for queries
QueryOptions
}
// RequestDatacenter returns the datacenter for a given request.
func (c *FederationStateQuery) RequestDatacenter() string {
return c.TargetDatacenter
}
// FederationStateResponse is the response to a FederationStateQuery request.
type FederationStateResponse struct {
State *FederationState
QueryMeta
}
// IndexedFederationStates represents the list of all federation states.
type IndexedFederationStates struct {
States FederationStates
QueryMeta
}