From df76de44198761874141bf21a6f57ebc88fdade2 Mon Sep 17 00:00:00 2001
From: Tim Gross <tgross@hashicorp.com>
Date: Fri, 11 Feb 2022 14:21:47 -0500
Subject: [PATCH] csi: plugin instance manager should retry creating gRPC
 client

---
 client/pluginmanager/csimanager/instance.go | 24 +++++++++++++--------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/client/pluginmanager/csimanager/instance.go b/client/pluginmanager/csimanager/instance.go
index 062b73972783..f76d4a703a34 100644
--- a/client/pluginmanager/csimanager/instance.go
+++ b/client/pluginmanager/csimanager/instance.go
@@ -10,6 +10,7 @@ import (
 )
 
 const managerFingerprintInterval = 30 * time.Second
+const managerFingerprintRetryInterval = 5 * time.Second
 
 // instanceManager is used to manage the fingerprinting and supervision of a
 // single CSI Plugin.
@@ -73,15 +74,6 @@ func newInstanceManager(logger hclog.Logger, eventer TriggerNodeEvent, updater U
 }
 
 func (i *instanceManager) run() {
-	c, err := csi.NewClient(i.info.ConnectionInfo.SocketPath, i.logger)
-	if err != nil {
-		i.logger.Error("failed to setup instance manager client", "error", err)
-		close(i.shutdownCh)
-		return
-	}
-	i.client = c
-	i.fp.client = c
-
 	go i.setupVolumeManager()
 	go i.runLoop()
 }
@@ -96,6 +88,9 @@ func (i *instanceManager) setupVolumeManager() {
 	case <-i.shutdownCtx.Done():
 		return
 	case <-i.fp.hadFirstSuccessfulFingerprintCh:
+		// the runLoop goroutine populates i.client but we never get
+		// the first fingerprint until after it's been populated, so
+		// this is safe
 		i.volumeManager = newVolumeManager(i.logger, i.eventer, i.client, i.mountPoint, i.containerMountPoint, i.fp.requiresStaging)
 		i.logger.Debug("volume manager setup complete")
 		close(i.volumeManagerSetupCh)
@@ -142,6 +137,17 @@ func (i *instanceManager) runLoop() {
 			return
 
 		case <-timer.C:
+			if i.client == nil {
+				c, err := csi.NewClient(i.info.ConnectionInfo.SocketPath, i.logger)
+				if err != nil {
+					i.logger.Debug("failed to setup instance manager client", "error", err)
+					timer.Reset(managerFingerprintRetryInterval)
+					continue
+				}
+				i.client = c
+				i.fp.client = c
+			}
+
 			ctx, cancelFn := i.requestCtxWithTimeout(managerFingerprintInterval)
 			info := i.fp.fingerprint(ctx)
 			cancelFn()