Troubleshooting Kubernetes Networking with Tigera Calico

Tigera Calico Troubleshooting and diagnostics

#!/bin/bash

if [[ "$1" != "diags" ]]
then
    echo "Unsupported command: $1"
    exit 1
fi
shift 1

SINCE=0s  # Only return logs newer than relative duration such as 5s, 2m, or 3h. Defaults to all logs.

# Parse optional flag(s):
#   --since=relative_duration (e.g. 10s, 5m)

while (( "$#" )); do
  case "$1" in
    --since=*)
      str=$1
      SINCE="${str#*=}"    # grab everything after '='
      shift 1

      if [[ ! $SINCE =~ ^[0-9]+[smh]$ ]]; then
          echo "invalid relative duration, try 10s, 5m, or 1h"
          exit 1
      fi
      ;;
    -*|--*=) # unsupported flags
      echo "Error: Unsupported flag $1" >&2
      exit 1
      ;;
    *) # unsupported argument
      echo "Error: Unsupported argument $1" >&2
      exit 1
      ;;
  esac
done

# Check pre-requisites, like a functioning kubectl.
if [ "$(which kubectl)" == "" ]; then echo "Unable to locate kubectl in PATH"; fi
kubectl get ns 2>&1>/dev/null || if [[ $? != 0 ]]; then echo "kubectl does not appear to be functioning"; exit 1; fi

# Make a tmp dir.
set -e
mtmp=$(mktemp -d)
mkdir ${mtmp}/calico-diagnostics
tmp=${mtmp}/calico-diagnostics
set +e


echo "==== Begin collecting diagnostics. ===="

# Get some basic cluster state.
echo "Collecting basic cluster state..."
kubectl get ns > ${tmp}/namespaces.txt
kubectl get all -n calico-system -o wide > ${tmp}/calico-system.txt
kubectl get all -n tigera-operator -o wide > ${tmp}/tigera-operator.txt

mkdir ${tmp}/operator.tigera.io
kubectl get installations -o yaml > ${tmp}/operator.tigera.io/installations.yaml
kubectl get apiservers -o yaml > ${tmp}/operator.tigera.io/apiservers.yaml
kubectl get compliances -o yaml > ${tmp}/operator.tigera.io/compliances.yaml
kubectl get intrusiondetections -o yaml > ${tmp}/operator.tigera.io/intrusiondetections.yaml
kubectl get managers -o yaml > ${tmp}/operator.tigera.io/managers.yaml
kubectl get logcollectors -o yaml > ${tmp}/operator.tigera.io/logcollectors.yaml
kubectl get logstorages -o yaml > ${tmp}/operator.tigera.io/logstorages.yaml
kubectl get managementclusterconnections -o yaml > ${tmp}/operator.tigera.io/managementclusterconnections.yaml

# Get tigera status.
echo "Collecting TigeraStatus details..."
kubectl get tigerastatus > ${tmp}/tigerastatus.txt
kubectl get tigerastatus -o yaml > ${tmp}/tigerastatus-yaml.txt

# Get nodes.
echo "Collecting Node details..."
kubectl get nodes -o wide > ${tmp}/nodes.txt
kubectl get nodes -o yaml > ${tmp}/nodes-yaml.txt

# Get IPAM information.
echo "Collecting IPAM diagnostics..."
mkdir -p ${tmp}/ipam
kubectl get ipamblocks -o yaml > ${tmp}/ipam/ipamblocks.txt
kubectl get blockaffinities -o yaml > ${tmp}/ipam/blockaffinities.txt
kubectl get ipamhandles -o yaml > ${tmp}/ipam/ipamhandles.txt

# Get operator logs. 
echo "Collecting tigera-operator logs..."
kubectl logs --since=$SINCE -n tigera-operator -l k8s-app=tigera-operator > ${tmp}/tigera-operator.logs

# Get typha logs.
echo "Collecting calico/typha logs..."
mkdir -p ${tmp}/typhas
for typha in $(kubectl get pods -n calico-system -l k8s-app=calico-typha -o go-template --template="{{range .items}}{{.metadata.name}} {{end}}"); do
	kubectl logs --since=$SINCE -n calico-system $typha > ${tmp}/typhas/${typha}.log
done

# Get per-node logs and network information.
mkdir -p ${tmp}/nodes
for node in $(kubectl get pods -n calico-system -l k8s-app=calico-node -o go-template --template="{{range .items}}{{.metadata.name}} {{end}}"); do
	echo "Collecting logs for node: $node"
	mkdir -p ${tmp}/nodes/${node}
	kubectl logs --since=$SINCE -n calico-system $node > ${tmp}/nodes/${node}/${node}.log
	kubectl exec -n calico-system -t $node -- iptables-save -c > ${tmp}/nodes/${node}/iptables-save.txt
	kubectl exec -n calico-system -t $node -- ip route > ${tmp}/nodes/${node}/iproute.txt
done

# Tar it all up for easy sharing.
echo ""
echo "==== Producing a diagnostics bundle. ===="
rm -f calico-diagnostics.tar.gz
tar cfz ${mtmp}/calico-diagnostics.tar.gz -C ${mtmp} calico-diagnostics
echo ""
echo "Diagnostic bundle produced at ${mtmp}/calico-diagnostics.tar.gz"

	#!/bin/bash

	if [[ "$1" != "diags" ]]
	then
	echo "Unsupported command: $1"
	exit 1
	fi
	shift 1

	SINCE=0s # Only return logs newer than relative duration such as 5s, 2m, or 3h. Defaults to all logs.

	# Parse optional flag(s):
	# --since=relative_duration (e.g. 10s, 5m)

	while (( "$#" )); do
	case "$1" in
	--since=*)
	str=$1
	SINCE="${str#*=}" # grab everything after '='
	shift 1

	if [[ ! $SINCE =~ ^[0-9]+[smh]$ ]]; then
	echo "invalid relative duration, try 10s, 5m, or 1h"
	exit 1
	fi
	;;
	-\|--=) # unsupported flags
	echo "Error: Unsupported flag $1" >&2
	exit 1
	;;
	*) # unsupported argument
	echo "Error: Unsupported argument $1" >&2
	exit 1
	;;
	esac
	done

	# Check pre-requisites, like a functioning kubectl.
	if [ "$(which kubectl)" == "" ]; then echo "Unable to locate kubectl in PATH"; fi
	kubectl get ns 2>&1>/dev/null \|\| if [[ $? != 0 ]]; then echo "kubectl does not appear to be functioning"; exit 1; fi

	# Make a tmp dir.
	set -e
	mtmp=$(mktemp -d)
	mkdir ${mtmp}/calico-diagnostics
	tmp=${mtmp}/calico-diagnostics
	set +e


	echo "==== Begin collecting diagnostics. ===="

	# Get some basic cluster state.
	echo "Collecting basic cluster state..."
	kubectl get ns > ${tmp}/namespaces.txt
	kubectl get all -n calico-system -o wide > ${tmp}/calico-system.txt
	kubectl get all -n tigera-operator -o wide > ${tmp}/tigera-operator.txt

	mkdir ${tmp}/operator.tigera.io
	kubectl get installations -o yaml > ${tmp}/operator.tigera.io/installations.yaml
	kubectl get apiservers -o yaml > ${tmp}/operator.tigera.io/apiservers.yaml
	kubectl get compliances -o yaml > ${tmp}/operator.tigera.io/compliances.yaml
	kubectl get intrusiondetections -o yaml > ${tmp}/operator.tigera.io/intrusiondetections.yaml
	kubectl get managers -o yaml > ${tmp}/operator.tigera.io/managers.yaml
	kubectl get logcollectors -o yaml > ${tmp}/operator.tigera.io/logcollectors.yaml
	kubectl get logstorages -o yaml > ${tmp}/operator.tigera.io/logstorages.yaml
	kubectl get managementclusterconnections -o yaml > ${tmp}/operator.tigera.io/managementclusterconnections.yaml

	# Get tigera status.
	echo "Collecting TigeraStatus details..."
	kubectl get tigerastatus > ${tmp}/tigerastatus.txt
	kubectl get tigerastatus -o yaml > ${tmp}/tigerastatus-yaml.txt

	# Get nodes.
	echo "Collecting Node details..."
	kubectl get nodes -o wide > ${tmp}/nodes.txt
	kubectl get nodes -o yaml > ${tmp}/nodes-yaml.txt

	# Get IPAM information.
	echo "Collecting IPAM diagnostics..."
	mkdir -p ${tmp}/ipam
	kubectl get ipamblocks -o yaml > ${tmp}/ipam/ipamblocks.txt
	kubectl get blockaffinities -o yaml > ${tmp}/ipam/blockaffinities.txt
	kubectl get ipamhandles -o yaml > ${tmp}/ipam/ipamhandles.txt

	# Get operator logs.
	echo "Collecting tigera-operator logs..."
	kubectl logs --since=$SINCE -n tigera-operator -l k8s-app=tigera-operator > ${tmp}/tigera-operator.logs

	# Get typha logs.
	echo "Collecting calico/typha logs..."
	mkdir -p ${tmp}/typhas
	for typha in $(kubectl get pods -n calico-system -l k8s-app=calico-typha -o go-template --template="{{range .items}}{{.metadata.name}} {{end}}"); do
	kubectl logs --since=$SINCE -n calico-system $typha > ${tmp}/typhas/${typha}.log
	done

	# Get per-node logs and network information.
	mkdir -p ${tmp}/nodes
	for node in $(kubectl get pods -n calico-system -l k8s-app=calico-node -o go-template --template="{{range .items}}{{.metadata.name}} {{end}}"); do
	echo "Collecting logs for node: $node"
	mkdir -p ${tmp}/nodes/${node}
	kubectl logs --since=$SINCE -n calico-system $node > ${tmp}/nodes/${node}/${node}.log
	kubectl exec -n calico-system -t $node -- iptables-save -c > ${tmp}/nodes/${node}/iptables-save.txt
	kubectl exec -n calico-system -t $node -- ip route > ${tmp}/nodes/${node}/iproute.txt
	done

	# Tar it all up for easy sharing.
	echo ""
	echo "==== Producing a diagnostics bundle. ===="
	rm -f calico-diagnostics.tar.gz
	tar cfz ${mtmp}/calico-diagnostics.tar.gz -C ${mtmp} calico-diagnostics
	echo ""
	echo "Diagnostic bundle produced at ${mtmp}/calico-diagnostics.tar.gz"

view raw README.sh hosted with

by GitHub

Rajesh Kumar

I’m a DevOps/SRE/DevSecOps/Cloud Expert passionate about sharing knowledge and experiences. I am working at Cotocus. I blog tech insights at DevOps School, travel stories at Holiday Landmark, stock market tips at Stocks Mantra, health and fitness guidance at My Medic Plus, product reviews at I reviewed , and SEO strategies at Wizbrand.

Please find my social handles as below;

Rajesh Kumar Personal Website
Rajesh Kumar at YOUTUBE
Rajesh Kumar at INSTAGRAM
Rajesh Kumar at X
Rajesh Kumar at FACEBOOK
Rajesh Kumar at LINKEDIN
Rajesh Kumar at PINTEREST
Rajesh Kumar at QUORA
Rajesh Kumar at WIZBRAND