opensource/coder
3
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-09-24 15:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add high availability for multiple replicas (#4555)

Browse Source 
* feat: HA tailnet coordinator

* fixup! feat: HA tailnet coordinator

* fixup! feat: HA tailnet coordinator

* remove printlns

* close all connections on coordinator

* impelement high availability feature

* fixup! impelement high availability feature

* fixup! impelement high availability feature

* fixup! impelement high availability feature

* fixup! impelement high availability feature

* Add replicas

* Add DERP meshing to arbitrary addresses

* Move packages to highavailability folder

* Move coordinator to high availability package

* Add flags for HA

* Rename to replicasync

* Denest packages for replicas

* Add test for multiple replicas

* Fix coordination test

* Add HA to the helm chart

* Rename function pointer

* Add warnings for HA

* Add the ability to block endpoints

* Add flag to disable P2P connections

* Wow, I made the tests pass

* Add replicas endpoint

* Ensure close kills replica

* Update sql

* Add database latency to high availability

* Pipe TLS to DERP mesh

* Fix DERP mesh with TLS

* Add tests for TLS

* Fix replica sync TLS

* Fix RootCA for replica meshing

* Remove ID from replicasync

* Fix getting certificates for meshing

* Remove excessive locking

* Fix linting

* Store mesh key in the database

* Fix replica key for tests

* Fix types gen

* Fix unlocking unlocked

* Fix race in tests

* Update enterprise/derpmesh/derpmesh.go

Co-authored-by: Colin Adler <colin1adler@gmail.com>

* Rename to syncReplicas

* Reuse http client

* Delete old replicas on a CRON

* Fix race condition in connection tests

* Fix linting

* Fix nil type

* Move pubsub to in-memory for twenty test

* Add comment for configuration tweaking

* Fix leak with transport

* Fix close leak in derpmesh

* Fix race when creating server

* Remove handler update

* Skip test on Windows

* Fix DERP mesh test

* Wrap HTTP handler replacement in mutex

* Fix error message for relay

* Fix API handler for normal tests

* Fix speedtest

* Fix replica resend

* Fix derpmesh send

* Ping async

* Increase wait time of template version jobd

* Fix race when closing replica sync

* Add name to client

* Log the derpmap being used

* Don't connect if DERP is empty

* Improve agent coordinator logging

* Fix lock in coordinator

* Fix relay addr

* Fix race when updating durations

* Fix client publish race

* Run pubsub loop in a queue

* Store agent nodes in order

* Fix coordinator locking

* Check for closed pipe

Co-authored-by: Colin Adler <colin1adler@gmail.com>
This commit is contained in:
Kyle Carberry
2022-10-17 13:43:30 +00:00
committed by GitHub
co-authored by Colin Adler
parent dc3519e973
commit 2ba4a62a0d
76 changed files with 3437 additions and 404 deletions
Download Patch File Download Diff File Expand all files Collapse all files
coderd/coderd.go
+15 -5
View File
@@ -1,6 +1,7 @@
package coderd
import (
"crypto/tls"
"crypto/x509"
"io"
"net/http"
@@ -82,7 +83,10 @@ type Options struct {
TracerProvider trace.TracerProvider
AutoImportTemplates []AutoImportTemplate
TailnetCoordinator *tailnet.Coordinator
// TLSCertificates is used to mesh DERP servers securely.
TLSCertificates []tls.Certificate
TailnetCoordinator tailnet.Coordinator
DERPServer *derp.Server
DERPMap *tailcfg.DERPMap
MetricsCacheRefreshInterval time.Duration
@@ -130,6 +134,9 @@ func New(options *Options) *API {
if options.TailnetCoordinator == nil {
options.TailnetCoordinator = tailnet.NewCoordinator()
}
if options.DERPServer == nil {
options.DERPServer = derp.NewServer(key.NewNode(), tailnet.Logger(options.Logger.Named("derp")))
}
if options.Auditor == nil {
options.Auditor = audit.NewNop()
}
@@ -168,7 +175,7 @@ func New(options *Options) *API {
api.Auditor.Store(&options.Auditor)
api.WorkspaceQuotaEnforcer.Store(&options.WorkspaceQuotaEnforcer)
api.workspaceAgentCache = wsconncache.New(api.dialWorkspaceAgentTailnet, 0)
api.derpServer = derp.NewServer(key.NewNode(), tailnet.Logger(options.Logger))
api.TailnetCoordinator.Store(&options.TailnetCoordinator)
oauthConfigs := &httpmw.OAuth2Configs{
Github: options.GithubOAuth2Config,
OIDC: options.OIDCConfig,
@@ -246,7 +253,7 @@ func New(options *Options) *API {
r.Route("/%40{user}/{workspace_and_agent}/apps/{workspaceapp}", apps)
r.Route("/@{user}/{workspace_and_agent}/apps/{workspaceapp}", apps)
r.Route("/derp", func(r chi.Router) {
r.Get("/", derphttp.Handler(api.derpServer).ServeHTTP)
r.Get("/", derphttp.Handler(api.DERPServer).ServeHTTP)
// This is used when UDP is blocked, and latency must be checked via HTTP(s).
r.Get("/latency-check", func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusOK)
@@ -550,6 +557,7 @@ type API struct {
Auditor atomic.Pointer[audit.Auditor]
WorkspaceClientCoordinateOverride atomic.Pointer[func(rw http.ResponseWriter) bool]
WorkspaceQuotaEnforcer atomic.Pointer[workspacequota.Enforcer]
TailnetCoordinator atomic.Pointer[tailnet.Coordinator]
HTTPAuth *HTTPAuthorizer
// APIHandler serves "/api/v2"
@@ -557,7 +565,6 @@ type API struct {
// RootHandler serves "/"
RootHandler chi.Router
derpServer *derp.Server
metricsCache *metricscache.Cache
siteHandler http.Handler
websocketWaitMutex sync.Mutex
@@ -572,7 +579,10 @@ func (api *API) Close() error {
api.websocketWaitMutex.Unlock()
api.metricsCache.Close()
coordinator := api.TailnetCoordinator.Load()
if coordinator != nil {
_ = (*coordinator).Close()
}
return api.workspaceAgentCache.Close()
}