laboratori-cloud/labs/lab-03-compute/tests/02-healthcheck-test.sh

#!/bin/bash
# Test 02: Healthcheck Configuration
# Verifies that docker-compose.yml services have healthchecks configured
# Usage: bash labs/lab-03-compute/tests/02-healthcheck-test.sh

set -euo pipefail

# Color definitions
RED='\033[0;31m'
GREEN='\033[0;32m'
BLUE='\033[0;34m'
YELLOW='\033[1;33m'
BOLD='\033[1m'
NC='\033[0m'

# Get script directory
TEST_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
LAB_DIR="$(cd "$TEST_DIR/.." && pwd)"

# Counter helpers
pass_count=0
fail_count=0

inc_pass() { ((pass_count++)) || true; }
inc_fail() { ((fail_count++)) || true; }

# Helper functions
print_header() {
    echo -e "${BLUE}╔═══════════════════════════════════════════════════════════════╗${NC}"
    echo -e "${BLUE}║${NC} ${BOLD}$1${NC}"
    echo -e "${BLUE}╚═══════════════════════════════════════════════════════════════╝${NC}"
}

print_test() {
    echo -e "\n${BLUE}[TEST]${NC} $1"
}

print_pass() {
    echo -e "  ${GREEN}[✓]${NC} $1"
    inc_pass
}

print_fail() {
    echo -e "  ${RED}[✗]${NC} $1"
    inc_fail
}

print_info() {
    echo -e "  ${BLUE}[i]${NC} $1"
}

# Main verification
print_header "Lab 03 Healthcheck Verification"

cd "$LAB_DIR"

# Test 1: docker-compose.yml exists
print_test "Verifying docker-compose.yml exists"
if [[ -f "docker-compose.yml" ]]; then
    print_pass "docker-compose.yml found"
else
    print_fail "docker-compose.yml not found"
    exit 1
fi

# Test 2: docker-compose.yml is valid
print_test "Validating docker-compose.yml syntax"
if docker compose config &> /dev/null; then
    print_pass "docker-compose.yml has valid syntax"
else
    print_fail "docker-compose.yml has syntax errors"
    exit 1
fi

# Test 3: Services are defined
print_test "Verifying services are defined"
SERVICES=$(docker compose config --services 2>/dev/null)
SERVICE_COUNT=$(echo "$SERVICES" | wc -l)
if [[ $SERVICE_COUNT -gt 0 ]]; then
    print_pass "Found $SERVICE_COUNT services"
else
    print_fail "No services defined"
    exit 1
fi

# Test 4: Healthcheck configuration check
print_test "Checking healthcheck configuration"
MISSING_HEALTHCHECK=0

for service in $SERVICES; do
    # Check for healthcheck section
    has_healthcheck=$(docker compose config 2>/dev/null | grep -A 50 "^$service:" | grep -c "healthcheck:" || echo "0")

    if [[ $has_healthcheck -eq 0 ]]; then
        print_fail "  $service: Missing healthcheck section"
        ((MISSING_HEALTHCHECK++)) || true
    else
        # Verify healthcheck has test command
        has_test=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 5 "healthcheck:" | grep -c "test:" || echo "0")

        if [[ $has_test -eq 0 ]]; then
            print_fail "  $service: Missing healthcheck test command"
            ((MISSING_HEALTHCHECK++)) || true
        else
            # Extract test command for reporting
            test_cmd=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 5 "healthcheck:" | grep "test:" | head -1 | sed 's/.*test: //' | tr -d '"')
            print_pass "  $service: healthcheck configured"
            print_info "    test: $test_cmd"
        fi
    fi
done

if [[ $MISSING_HEALTHCHECK -eq 0 ]]; then
    print_pass "All services have healthchecks configured"
else
    print_fail "$MISSING_HEALTHCHECK services missing healthchecks"
fi

# Test 5: Healthcheck parameters verification
print_test "Verifying healthcheck parameters"
PARAMS_OK=0

for service in $SERVICES; do
    has_healthcheck=$(docker compose config 2>/dev/null | grep -A 50 "^$service:" | grep -c "healthcheck:" || echo "0")

    if [[ $has_healthcheck -gt 0 ]]; then
        # Check for interval
        has_interval=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep -c "interval:" || echo "0")
        # Check for timeout
        has_timeout=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep -c "timeout:" || echo "0")
        # Check for retries
        has_retries=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep -c "retries:" || echo "0")

        interval=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "interval:" | sed 's/.*interval: //' | tr -d " '"" || echo "N/A")
        timeout=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "timeout:" | sed 's/.*timeout: //' | tr -d " '"" || echo "N/A")
        retries=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "retries:" | sed 's/.*retries: //' | tr -d " '"" || echo "N/A")

        if [[ $has_interval -gt 0 && $has_timeout -gt 0 && $has_retries -gt 0 ]]; then
            print_pass "  $service: interval=$interval, timeout=$timeout, retries=$retries"
            ((PARAMS_OK++)) || true
        else
            print_info "  $service: interval=$interval, timeout=$timeout, retries=$retries"
            # Check for start_period (optional)
            has_start_period=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep -c "start_period:" || echo "0")
            if [[ $has_start_period -gt 0 ]]; then
                start_period=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "start_period:" | sed 's/.*start_period: //' | tr -d " '"" || echo "")
                print_info "    start_period=$start_period"
            fi
        fi
    fi
done

if [[ $PARAMS_OK -gt 0 ]]; then
    print_pass "$PARAMS_OK services have complete healthcheck parameters"
else
    print_fail "No services with complete healthcheck parameters"
fi

# Test 6: Healthcheck command types
print_test "Analyzing healthcheck command types"
HTTP_COUNT=0
CMD_SHELL_COUNT=0
CMD_COUNT=0
CUSTOM_COUNT=0

for service in $SERVICES; do
    has_healthcheck=$(docker compose config 2>/dev/null | grep -A 50 "^$service:" | grep -c "healthcheck:" || echo "0")

    if [[ $has_healthcheck -gt 0 ]]; then
        # Get test command
        test_section=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" || echo "")

        if echo "$test_section" | grep -q "CMD-SHELL"; then
            print_info "  $service: CMD-SHELL healthcheck"
            ((CMD_SHELL_COUNT++)) || true
        elif echo "$test_section" | grep -q "CMD"; then
            print_info "  $service: CMD healthcheck"
            ((CMD_COUNT++)) || true
        else
            print_info "  $service: Custom healthcheck format"
            ((CUSTOM_COUNT++)) || true
        fi

        # Check if HTTP-based
        if echo "$test_section" | grep -qiE "(wget|curl|http)"; then
            ((HTTP_COUNT++)) || true
        fi
    fi
done

print_info "Healthcheck types: CMD-SHELL ($CMD_SHELL_COUNT), CMD ($CMD_COUNT), Custom ($CUSTOM_COUNT)"
if [[ $HTTP_COUNT -gt 0 ]]; then
    print_pass "$HTTP_COUNT services use HTTP-based healthchecks"
fi

# Test 7: ELB Health Check Parallel verification
print_test "Verifying ELB Health Check parallelism"
ELB_PARALLEL=0

for service in $SERVICES; do
    has_healthcheck=$(docker compose config 2>/dev/null | grep -A 50 "^$service:" | grep -c "healthcheck:" || echo "0")

    if [[ $has_healthcheck -gt 0 ]]; then
        interval=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "interval:" | sed 's/.*interval: //' | tr -d " '"" || echo "")
        timeout=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "timeout:" | sed 's/.*timeout: //' | tr -d " '"" || echo "")
        retries=$(docker compose config 2>/dev/null | grep -A 60 "^$service:" | grep -A 10 "healthcheck:" | grep "retries:" | sed 's/.*retries: //' | tr -d " '"" || echo "")

        # Map to ELB defaults
        if [[ "$interval" == "30s" || "$interval" =~ ^30 ]]; then
            elb_interval="default (30s)"
            ((ELB_PARALLEL++)) || true
        else
            elb_interval="custom ($interval)"
        fi

        if [[ "$timeout" == "5s" || "$timeout" =~ ^5 ]]; then
            elb_timeout="default (5s)"
            ((ELB_PARALLEL++)) || true
        else
            elb_timeout="custom ($timeout)"
        fi

        if [[ "$retries" == "3" || "$retries" =~ ^3 ]]; then
            elb_retries="default (3)"
            ((ELB_PARALLEL++)) || true
        else
            elb_retries="custom ($retries)"
        fi

        print_info "  $service: ELB parallel (interval: $elb_interval, timeout: $elb_timeout, retries: $elb_retries)"
    fi
done

if [[ $ELB_PARALLEL -gt 0 ]]; then
    print_pass "ELB Health Check parallelism verified"
fi

# Summary
print_header "Healthcheck Verification Summary"

echo -e "Tests run: $((pass_count + fail_count))"
echo -e "${GREEN}Passed: $pass_count${NC}"
if [[ $fail_count -gt 0 ]]; then
    echo -e "${RED}Failed: $fail_count${NC}"
fi

if [[ $fail_count -eq 0 ]]; then
    echo -e "\n${GREEN}${BOLD}✓ ALL HEALTHCHECK CHECKS PASSED${NC}"
    echo -e "\nHealthcheck configuration verified!"
    exit 0
else
    echo -e "\n${RED}Some healthcheck checks failed${NC}"
    echo -e "Please ensure all services have healthchecks configured."
    exit 1
fi