问题背景
在 Debian 12 上使用 kubeadm 搭建 Kubernetes v1.28.15 集群时，工作节点（k8s-node1）一直处于 NotReady 状态，而控制平面节点（k8s-master）正常工作。
故障排查思路
第一层：检查节点和 Pod 基础状态
kubectl get nodes
# k8s-node1 NotReady
kubectl get pods -n kube-system
# kube-proxy-hf9m5 ContainerCreating
# coredns 都处于 Pending 状态
排查方向：
工作节点是否成功加入集群？
系统 Pod 为什么没有运行？
结论： 节点已加入，但网络插件未就绪导致 Pod 无法调度。
第二层：分析节点 NotReady 原因
执行命令：
kubectl describe node k8s-node1 | grep -A 5 "Conditions"
kubectl get pods --all-namespaces | grep flannel
发现：
节点 Conditions 显示正常（内存、磁盘、PID 均无压力）
Flannel Pod 在 node1 上状态为 Init:0/2 或 Init:1/2（卡在初始化）
Master 节点上的 Flannel Pod 正常 Running
结论： 问题出在工作节点的网络插件初始化上。
第三层：检查容器运行时状态
执行命令（在 node1 上）：
systemctl status containerd
ls -la /var/run/containerd/containerd.sock
发现： containerd 运行正常，socket 文件存在。
继续排查：
crictl info
# NetworkReady: false
# lastCNILoadStatus: "no network config found in /etc/cni/net.d"
结论： CNI 配置目录为空，Flannel 无法写入配置文件。
第四层：检查 CNI 配置目录
执行命令：
ls -la /etc/cni/net.d/
# 只有 .kubernetes-cni-keep 空文件，没有 .conf 或 .conflist 文件
核心问题定位：
Flannel Pod 的 init 容器 install-cni-plugin 应该负责创建 CNI 配置
但该容器异常退出，导致配置未能写入
验证：
crictl ps -a | grep flannel
# install-cni-plugin 容器状态为 Exited
结论： Flannel 的 init 容器无法完成 CNI 配置安装。
解决方案汇总
方案一：手动创建 CNI 配置（最终生效方案）
在 k8s-node1 上执行：
# 1. 手动创建 Flannel CNI 配置文件
cat > /etc/cni/net.d/10-flannel.conflist << 'EOF'
{
"name": "cbr0",
"cniVersion": "0.3.1",
"plugins": [
{
"type": "flannel",
"delegate": {
"hairpinMode": true,
"isDefaultGateway": true
}
},
{
"type": "portmap",
"capabilities": {
"portMappings": true
}
}
]
}
EOF
# 2. 重启 kubelet
systemctl restart kubelet
方案二：配置镜像加速（解决拉取问题）
由于工作节点无法直接访问 registry.k8s.io，需要配置 containerd 使用国内镜像
cat > /etc/containerd/config.toml << 'EOF'
disabled_plugins = []
imports = []
oom_score = 0
plugin_dir = ""
required_plugins = []
root = "/var/lib/containerd"
state = "/run/containerd"
temp = ""
version = 2
[cgroup]
path = ""
[debug]
address = ""
format = ""
gid = 0
level = ""
uid = 0
[grpc]
address = "/run/containerd/containerd.sock"
gid = 0
max_recv_message_size = 16777216
max_send_message_size = 16777216
tcp_address = ""
tcp_tls_ca = ""
tcp_tls_cert = ""
tcp_tls_key = ""
uid = 0
[metrics]
address = ""
grpc_histogram = false
[plugins]
[plugins."io.containerd.gc.v1.scheduler"]
deletion_threshold = 0
mutation_threshold = 100
pause_threshold = 0.02
schedule_delay = "0s"
startup_delay = "100ms"
[plugins."io.containerd.grpc.v1.cri"]
device_ownership_from_security_context = false
disable_apparmor = false
disable_cgroup = false
disable_hugetlb_controller = true
disable_proc_mount = false
disable_tcp_service = true
enable_selinux = false
enable_tls_streaming = false
enable_unprivileged_icmp = false
enable_unprivileged_ports = false
ignore_image_defined_volumes = false
max_concurrent_downloads = 3
max_container_log_line_size = 16384
netns_mounts_under_state_dir = false
restrict_oom_score_adj = false
sandbox_image = "registry.aliyuncs.com/google_containers/pause:3.9"
selinux_category_range = 1024
stats_collect_period = 10
stream_idle_timeout = "4h0m0s"
stream_server_address = "127.0.0.1"
stream_server_port = "0"
systemd_cgroup = false
tolerate_missing_hugetlb_controller = true
unset_seccomp_profile = ""
[plugins."io.containerd.grpc.v1.cri".cni]
bin_dir = "/opt/cni/bin"
conf_dir = "/etc/cni/net.d"
conf_template = ""
ip_pref = ""
max_conf_num = 1
[plugins."io.containerd.grpc.v1.cri".containerd]
default_runtime_name = "runc"
disable_snapshot_annotations = true
discard_unpacked_layers = false
ignore_rdt_not_enabled_errors = false
no_pivot = false
snapshotter = "overlayfs"
[plugins."io.containerd.grpc.v1.cri".containerd.default_runtime]
base_runtime_spec = ""
cni_conf_dir = ""
cni_max_conf_num = 0
container_annotations = []
pod_annotations = []
privileged_without_host_devices = false
runtime_engine = ""
runtime_path = ""
runtime_root = ""
runtime_type = ""
[plugins."io.containerd.grpc.v1.cri".containerd.default_runtime.options]
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes]
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
base_runtime_spec = ""
cni_conf_dir = ""
cni_max_conf_num = 0
container_annotations = []
pod_annotations = []
privileged_without_host_devices = false
runtime_engine = ""
runtime_path = ""
runtime_root = ""
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
BinaryName = ""
CriuImagePath = ""
CriuPath = ""
CriuWorkPath = ""
IoGid = 0
IoUid = 0
NoNewKeyring = false
NoPivotRoot = false
Root = ""
ShimCgroup = ""
SystemdCgroup = true
[plugins."io.containerd.grpc.v1.cri".containerd.untrusted_workload_runtime]
base_runtime_spec = ""
cni_conf_dir = ""
cni_max_conf_num = 0
container_annotations = []
pod_annotations = []
privileged_without_host_devices = false
runtime_engine = ""
runtime_path = ""
runtime_root = ""
runtime_type = ""
[plugins."io.containerd.grpc.v1.cri".containerd.untrusted_workload_runtime.options]
[plugins."io.containerd.grpc.v1.cri".image_decryption]
key_model = "node"
[plugins."io.containerd.grpc.v1.cri".registry]
config_path = ""
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
endpoint = ["https://docker.m.daocloud.io", "https://hub-mirror.c.163.com"]
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."registry.k8s.io"]
endpoint = ["https://registry.aliyuncs.com/google_containers"]
[plugins."io.containerd.grpc.v1.cri".registry.auths]
[plugins."io.containerd.grpc.v1.cri".registry.configs]
[plugins."io.containerd.grpc.v1.cri".registry.headers]
[plugins."io.containerd.grpc.v1.cri".x509_key_pair_streaming]
tls_cert_file = ""
tls_key_file = ""
[plugins."io.containerd.internal.v1.opt"]
path = "/opt/containerd"
[plugins."io.containerd.internal.v1.restart"]
interval = "10s"
[plugins."io.containerd.metadata.v1.bolt"]
content_sharing_policy = "shared"
[plugins."io.containerd.monitor.v1.cgroups"]
no_prometheus = false
[plugins."io.containerd.runtime.v1.linux"]
no_shim = false
runtime = "runc"
runtime_root = ""
shim = "containerd-shim"
shim_debug = false
[plugins."io.containerd.runtime.v2.task"]
platforms = ["linux/amd64"]
sched_core = false
[plugins."io.containerd.service.v1.diff-service"]
default = ["walking"]
[plugins."io.containerd.service.v1.tasks-service"]
rdt_config_file = ""
[plugins."io.containerd.snapshotter.v1.aufs"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.btrfs"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.devmapper"]
async_remove = false
base_image_size = ""
discard_blocks = false
fs_options = ""
fs_type = ""
pool_name = ""
root_path = ""
[plugins."io.containerd.snapshotter.v1.native"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.overlayfs"]
root_path = ""
upperdir_label = false
[plugins."io.containerd.snapshotter.v1.zfs"]
root_path = ""
[proxy_plugins]
[stream_processors]
[stream_processors."io.containerd.ocicrypt.decoder.v1.tar"]
accepts = ["application/vnd.oci.image.layer.v1.tar+encrypted"]
args = ["--decryption-keys-path", "/etc/containerd/ocicrypt/keys"]
env = ["OCICRYPT_KEYPROVIDER_CONFIG=/etc/containerd/ocicrypt/ocicrypt_keyprovider.conf"]
path = "ctd-decoder"
returns = "application/vnd.oci.image.layer.v1.tar"
[stream_processors."io.containerd.ocicrypt.decoder.v1.tar.gzip"]
accepts = ["application/vnd.oci.image.layer.v1.tar+gzip+encrypted"]
args = ["--decryption-keys-path", "/etc/containerd/ocicrypt/keys"]
env = ["OCICRYPT_KEYPROVIDER_CONFIG=/etc/containerd/ocicrypt/ocicrypt_keyprovider.conf"]
path = "ctd-decoder"
returns = "application/vnd.oci.image.layer.v1.tar+gzip"
[timeouts]
"io.containerd.timeout.bolt.open" = "0s"
"io.containerd.timeout.shim.cleanup" = "5s"
"io.containerd.timeout.shim.load" = "5s"
"io.containerd.timeout.shim.shutdown" = "3s"
"io.containerd.timeout.task.state" = "2s"
[ttrpc]
address = ""
gid = 0
uid = 0
EOF
systemctl restart containerd
方案三：重置节点并重新加入
当配置混乱时，完全重置是最干净的方案：
在 master 上：
kubectl delete node k8s-node1
kubeadm token create --print-join-command
在 node1 上：
kubeadm reset -f #完全清除
rm -rf /etc/cni/net.d/*
rm -rf /var/lib/kubelet/*
systemctl restart containerd
# 执行 master 输出的 join 命令
kubeadm join <master-ip>:6443 --token <token> --discovery-token-ca-cert-hash sha256:<hash>
验证步骤
1.检查节点状态
kubectl get nodes
# 预期：两个节点都是 Ready
2. 检查 Flannel Pod
kubectl get pods -n kube-flannel
# 预期：两个 Pod 都是 Running
3. 检查系统 Pod
kubectl get pods -n kube-system
# 预期：所有 Pod 都是 Running
4. 测试网络连通性
kubectl run test-nginx --image=nginx --restart=Never
kubectl get pods -o wide
# 预期：Pod 能获得 IP 并正常运行
kubectl delete pod test-nginx
经验总结
关键排查命令速查
# 节点状态
kubectl get nodes -w
# Pod 状态（含所有命名空间）
kubectl get pods --all-namespaces
# 节点详细信息
kubectl describe node <node-name>
# Pod 日志
kubectl logs -n <namespace> <pod-name>
# 容器运行时状态
crictl info
crictl ps -a
# CNI 配置
ls -la /etc/cni/net.d/
# containerd 日志
journalctl -u containerd -n 50
.jpg)