import resource-agents-4.1.1-97.el8

SOURCES/bz1972743-podman-fix-container-creation-race.patch

@@ -0,0 +1,74 @@
+From 7850aea1600389beb16c7aad40bba1b76ae694c4 Mon Sep 17 00:00:00 2001
+From: Damien Ciabrini <dciabrin@redhat.com>
+Date: Tue, 15 Jun 2021 20:03:20 +0200
+Subject: [PATCH] podman: workaround race during container creation
+
+podman and OCI runtime have a race that sometimes causes
+a container to fail to be created and run [1] if the
+cgroup to be used is not available yet. When that happens,
+try to recreate it until it succeeds or the start
+timeout is reached.
+
+[1] https://bugzilla.redhat.com/show_bug.cgi?id=1972209
+---
+ heartbeat/podman | 32 ++++++++++++++++++++++++++++++--
+ 1 file changed, 30 insertions(+), 2 deletions(-)
+
+diff --git a/heartbeat/podman b/heartbeat/podman
+index 5b707f3f5..034dfff76 100755
+--- a/heartbeat/podman
++++ b/heartbeat/podman
+@@ -358,8 +358,18 @@ run_new_container()
+ 	local rc
+ 	
+ 	ocf_log info "running container $CONTAINER for the first time"
+-	ocf_run podman run $opts $image $cmd
++	out=$(podman run $opts $image $cmd 2>&1)
+ 	rc=$?
++
++	if [ -n "$out" ]; then
++		out="$(echo "$out" | tr -s ' \t\r\n' ' ')"
++		if [ $rc -eq 0 ]; then
++			ocf_log info "$out"
++		else
++			ocf_log err "$out"
++		fi
++	fi
++
+ 	if [ $rc -eq 125 ]; then
+ 		# If an internal podman error occurred, it might be because
+ 		# the internal storage layer still references an old container
+@@ -370,6 +380,24 @@ run_new_container()
+ 		ocf_run podman rm --storage $CONTAINER
+ 		ocf_run podman run $opts $image $cmd
+ 		rc=$?
++	elif [ $rc -eq 127 ]; then
++		# rhbz#1972209: podman 3.0.x seems to be hit by a race
++		# where the cgroup is not yet set up properly when the OCI
++		# runtime configures the container. If that happens, recreate
++		# the container as long as we get the same error code or
++		# until start timeout preempts us.
++		while [ $rc -eq 127 ] && (echo "$out" | grep -q "cgroup.*scope not found") ; do
++			ocf_log warn "Internal podman error while assigning cgroup. Retrying."
++			# Arbitrary sleep to prevent consuming all CPU while looping
++			sleep 1
++			podman rm -f "$CONTAINER"
++			out=$(podman run $opts $image $cmd 2>&1)
++			rc=$?
++		done
++		# Log the created container ID if it succeeded
++		if  [ $rc -eq 0 ]; then
++			ocf_log info "$out"
++		fi
+ 	fi
+ 	
+ 	return $rc
+@@ -422,7 +450,7 @@ podman_start()
+ 	fi
+ 
+ 	if [ $rc -ne 0 ]; then
+-		ocf_exit_reason "podman failed to launch container"
++		ocf_exit_reason "podman failed to launch container (rc: $rc)"
+ 		return $OCF_ERR_GENERIC
+ 	fi
+ 

SPECS/resource-agents.spec

@@ -70,7 +70,7 @@
 Name:		resource-agents
 Summary:	Open Source HA Reusable Cluster Resource Scripts
 Version:	4.1.1
-Release:	96%{?rcver:%{rcver}}%{?numcomm:.%{numcomm}}%{?alphatag:.%{alphatag}}%{?dirty:.%{dirty}}%{?dist}
+Release:	97%{?rcver:%{rcver}}%{?numcomm:.%{numcomm}}%{?alphatag:.%{alphatag}}%{?dirty:.%{dirty}}%{?dist}
 License:	GPLv2+ and LGPLv2+
 URL:		https://github.com/ClusterLabs/resource-agents
 %if 0%{?fedora} || 0%{?centos_version} || 0%{?rhel}
@@ -281,6 +281,7 @@ Patch189:	bz1872754-pgsqlms-new-ra.patch
 Patch190:	bz1957765-gcp-vpc-move-vip-retry.patch
 Patch191:	bz1969968-lvmlockd-remove-with_cmirrord.patch
 Patch192:	bz1972035-LVM-activate-fix-drop-in.patch
+Patch193:	bz1972743-podman-fix-container-creation-race.patch
 
 # bundle patches
 Patch1000:	7-gcp-bundled.patch
@@ -646,6 +647,7 @@ exit 1
 %patch190 -p1
 %patch191 -p1
 %patch192 -p1
+%patch193 -p1
 
 chmod 755 heartbeat/nova-compute-wait
 chmod 755 heartbeat/NovaEvacuate
@@ -1227,6 +1229,11 @@ ccs_update_schema > /dev/null 2>&1 ||:
 %{_usr}/lib/ocf/lib/heartbeat/OCF_*.pm
 
 %changelog
+* Thu Jun 17 2021 Oyvind Albrigtsen <oalbrigt@redhat.com> - 4.1.1-97
+- podman: fix possible race during container creation
+
+  Resolves: rhbz#1972743
+
 * Tue Jun 15 2021 Oyvind Albrigtsen <oalbrigt@redhat.com> - 4.1.1-96
 - LVM-activate: fix drop-in check to avoid re-creating drop-in