From cd5600c01e4edf312c931fbda08d0e4d87bff89f Mon Sep 17 00:00:00 2001 From: Jakob Meng Date: Wed, 13 Sep 2023 14:56:11 +0200 Subject: [PATCH] OCPBUGS-19303: Changed OKD/FCOS workaround to also support Agent-based Installer OKD/FCOS uses FCOS as its bootimage, i.e. when booting cluster nodes the first time during installation. FCOS does not provide tools such as OpenShift Client (oc) or crio.service which Agent-based Installer uses at the rendezvous host, e.g. to launch the bootstrap control plane. RHCOS and SCOS include these tools, but FCOS has to pivot the root fs [1] to okd-machine-os [2] first in order to make those tools available. Pivoting uses 'rpm-ostree rebase' but the rendezvous host is booted the first time the node boots from a FCOS Live ISO where the root fs and /sysroot are mounted read-only. Thus 'rpm-ostree rebase' fails and necessary tools will not be available, causing the setup to stall. Until rpm-ostree has implemented support for rebasing Live ISOs [3], this patch adapts the workaround for SNO installations [4] to also support Agent-based Installer. In particular, the Go conditional {{- if .BootstrapInPlace }} which is used to mark a SNO install has been replaced with a shell if-else which checks at runtime whether the system is launched from are on a Live ISO. Most code in the OpenShift ecosystem is written with RHCOS in mind and often assumes that tools like oc or crio.service are available. These assumptions can be satisfied by applying this workaround to all Live ISO boots. It will not remove functionality or overwrite configuration files in /etc and thus side effects should be minimal. The Go conditional {{- if .BootstrapInPlace }} in the release-image-\ pivot.service has been dropped completely. This service is only used in OKD only, so OCP will not be impacted at all. The 'Before=' option will not cause systemd to fail if a service does not exist. So, in case bootkube.service or kubelet.service do not exist, the option will have no effect. When bootkube.service or kubelet.service do exist, it must always be ensured that release-image-pivot.service is started first because it might reboot the system or change /usr in the Live ISO use case. So it is safe to drop the Go conditional and ask systemd to always launch release-image-pivot.service before bootkube.service and kubelet.service. [0] https://github.com/openshift/installer/blob/master/data/data/bootstrap/files/usr/local/bin/bootkube.sh.template [1] https://github.com/openshift/installer/blob/master/data/data/bootstrap/files/usr/local/bin/bootstrap-pivot.sh.template [2] https://github.com/openshift/okd-machine-os [3] https://github.com/coreos/rpm-ostree/issues/4547 [4] https://github.com/openshift/installer/pull/7445 --- .../usr/local/bin/bootstrap-pivot.sh.template | 60 +++++++++++++------ .../systemd/units/kubelet.service.template | 4 +- .../release-image-pivot.service.template | 4 -- 3 files changed, 45 insertions(+), 23 deletions(-) diff --git a/data/data/bootstrap/files/usr/local/bin/bootstrap-pivot.sh.template b/data/data/bootstrap/files/usr/local/bin/bootstrap-pivot.sh.template index 86a42bb9cc2..18d9be2be51 100644 --- a/data/data/bootstrap/files/usr/local/bin/bootstrap-pivot.sh.template +++ b/data/data/bootstrap/files/usr/local/bin/bootstrap-pivot.sh.template @@ -42,25 +42,51 @@ if [ ! -f /opt/openshift/.pivot-done ]; then record_service_stage_start "rebase-to-okd-os-image" {{if .IsFCOS -}} mnt="$(podman image mount "${MACHINE_OS_IMAGE}")" -{{- if .BootstrapInPlace }} - # SNO setup boots into Live ISO which cannot be rebased - # https://github.com/coreos/rpm-ostree/issues/4547 - mkdir /var/mnt/{upper,worker} - mount -t overlay overlay -o "lowerdir=/usr:$mnt/usr" /usr - mount -t overlay overlay -o "lowerdir=/etc:$mnt/etc,upperdir=/var/mnt/upper,workdir=/var/mnt/worker" /etc - systemctl daemon-reload - # Workaround for SELinux denials when launching crio.service from overlayfs - setenforce Permissive + # The bootstrap host during SNO installation and the rendezvous host of Agent-based Installer both boot into a Live + # ISO which cannot be rebased. Until rpm-ostree supports this live rebase [0], the following workaround will mount the + # proper OKD/FCOS Machine OS image over the existing mount at /usr and copy new config files to /etc. + # [0] https://github.com/coreos/rpm-ostree/issues/4547 + if grep -q coreos.liveiso= /proc/cmdline; then + mount -t tmpfs -o size=50% none /var/mnt/ + rsync -aHAXx "$mnt/" /var/mnt/ + mount -t overlay overlay -o lowerdir=/usr:/var/mnt/usr /usr + rsync -rlt --ignore-existing /var/mnt/etc/ /etc/ - systemctl start crio.service - # No reboot necessary because SNO setup will reboot system -{{ else }} - pushd "${mnt}/bootstrap" - # shellcheck disable=SC1091 - . ./pre-pivot.sh - popd -{{ end -}} + # Agent-based Installer will launch a ephemeral control plane at the rendezvous host which will create and publish + # Ignition configs for the other master nodes. These Ignition configs must match what the in-cluster control plane + # would generate else machine config operator will fail [0]. Because the rendezvous host is booted with a FCOS Live + # ISO without any OKD/FCOS related changes, we have to copy the manifests from OKD Machine OS manually to the + # bootstrap manifests folder of the rendezvous host. + # [0] https://access.redhat.com/solutions/4970731 + mkdir -p /var/opt/openshift/manifests + cp -av /var/mnt/manifests/*.* /var/opt/openshift/manifests/ + + # Load new systemd unit files and configuration such as crio.service after mounting the content of OKD/FCOS Machine + # OS over /usr and copying new files to /etc + systemctl daemon-reload + + # CoreDNS fails to listen to 127.0.0.53:53 when Agent-based Installer boots its the rendezvous host with a Fedora + # CoreOS bootimage because by default FCOS' systemd-resolved already listens to this port. OKD/FCOS disables + # resolved's stub listener [0] but the resolved must be restarted for this setting to take effect. + # [0] https://github.com/openshift/okd-machine-os/blob/master/overlay.d/99okd/etc/systemd/resolved.conf.d/okd-no-dns-stub.conf + systemctl restart systemd-resolved.service + + # Workaround for SELinux denials when launching crio.service from overlayfs + setenforce Permissive + + # crio.service is not part of FCOS but of OKD Machine OS. It will loaded after systemctl daemon-reload above but has + # to be started manually + systemctl start crio.service + + # No reboot necessary because setup will reboot the system automatically + else + pushd "${mnt}/bootstrap" + # shellcheck disable=SC1091 + . ./pre-pivot.sh + popd + fi + record_service_stage_success {{else if .IsSCOS -}} chmod 0644 /etc/containers/registries.conf rpm-ostree rebase --experimental "ostree-unverified-registry:${MACHINE_OS_IMAGE}" diff --git a/data/data/bootstrap/systemd/units/kubelet.service.template b/data/data/bootstrap/systemd/units/kubelet.service.template index 092d4c8e6e1..a19c998c601 100644 --- a/data/data/bootstrap/systemd/units/kubelet.service.template +++ b/data/data/bootstrap/systemd/units/kubelet.service.template @@ -1,7 +1,7 @@ [Unit] Description=Kubernetes Kubelet -Wants=rpc-statd.service crio.service release-image.service -After=crio.service release-image.service +Wants=rpc-statd.service crio.service release-image.service{{if .IsOKD}} release-image-pivot.service{{end}} +After=crio.service release-image.service{{if .IsOKD}} release-image-pivot.service{{end}} [Service] Type=notify diff --git a/data/data/bootstrap/systemd/units/release-image-pivot.service.template b/data/data/bootstrap/systemd/units/release-image-pivot.service.template index e278091cc50..fd3763f44c2 100644 --- a/data/data/bootstrap/systemd/units/release-image-pivot.service.template +++ b/data/data/bootstrap/systemd/units/release-image-pivot.service.template @@ -3,11 +3,7 @@ Description=Pivot bootstrap to the OpenShift Release Image Wants=release-image.service After=release-image.service -{{- if .BootstrapInPlace }} Before=bootkube.service kubelet.service -{{ else }} -Before=bootkube.service -{{ end -}} [Service] Type=oneshot