How to fix CLUSTERDOWN The cluster is down in Redis

# On any accessible cluster node
redis-cli -h <node-ip> -p <port> cluster info

# Check detailed slot status
redis-cli -h <node-ip> -p <port> cluster slots

# Check individual node status
redis-cli -h <node-ip> -p <port> cluster nodes

# From a node that's still accessible
redis-cli -h <node-ip> -p <port> cluster nodes | grep -E 'master|slave'

# Output shows node status (connected/disconnected)
# Example:
# 1a2b3c... 10.0.0.1:6379 master - 0 1500000000000 1 connected 0-5460
# 4d5e6f... 10.0.0.2:6379 slave 1a2b3c... 0 1500000001000 1 connected

# Via systemd (Linux)
sudo systemctl restart redis-server

# Or if using redis_6379 naming convention
sudo systemctl restart redis_6379

# Via direct command
redis-server /etc/redis/redis.conf

# Check if the node rejoins the cluster
redis-cli -h <node-ip> -p <port> cluster info

# Watch cluster recovery
watch -n 1 'redis-cli -h <node-ip> -p <port> cluster info | grep cluster_state'

# Find stuck slots (showing importing/migrating state)
redis-cli -h <node-ip> -p <port> cluster slots

# On BOTH the source and target nodes, stabilize the slot
redis-cli -h <source-node> -p <port> CLUSTER SETSLOT <slot-number> STABLE
redis-cli -h <target-node> -p <port> CLUSTER SETSLOT <slot-number> STABLE

# Example: Stabilize slot 5000
redis-cli -h 10.0.0.1 -p 6379 CLUSTER SETSLOT 5000 STABLE
redis-cli -h 10.0.0.2 -p 6379 CLUSTER SETSLOT 5000 STABLE

# Verify the cluster recovers
redis-cli -h <node-ip> -p <port> cluster info

# On any accessible node
redis-cli -h <node-ip> -p <port> CONFIG SET cluster-require-full-coverage no

# Verify the change
redis-cli -h <node-ip> -p <port> CONFIG GET cluster-require-full-coverage

# The cluster should now serve requests for available slots
redis-cli -h <node-ip> -p <port> cluster info

# Use redis-cli --cluster fix command (Redis 5.0+)
redis-cli --cluster fix <node-ip>:<port>

# For older Redis versions, use redis-trib.rb
./redis-trib.rb fix <node-ip>:<port>

# Check the results
redis-cli -h <node-ip> -p <port> cluster info

# On any cluster node, temporarily adjust timeouts
redis-cli -h <node-ip> -p <port> CONFIG SET cluster-node-timeout 15000

# Also check and adjust Lua script timeout (default 5000ms)
redis-cli -h <node-ip> -p <port> CONFIG SET lua-time-limit 10000

# Verify changes
redis-cli -h <node-ip> -p <port> CONFIG GET cluster-node-timeout
redis-cli -h <node-ip> -p <port> CONFIG GET lua-time-limit

# Real-time cluster status monitoring
while true; do
  echo "=== Cluster Status at $(date) ==="
  redis-cli -h <node-ip> -p <port> cluster info | grep cluster_state
  redis-cli -h <node-ip> -p <port> cluster info | grep cluster_slots
  redis-cli -h <node-ip> -p <port> cluster nodes | grep -E 'master|slave' | awk '{print $1, $2, $3, $4}'
  sleep 10
done

# Or use redis-cli's built-in monitor
redis-cli -h <node-ip> -p <port> --cluster check <node-ip>:<port>

# Check Redis logs for errors
tail -f /var/log/redis/redis-server.log

# Monitor system resources on affected nodes
watch -n 1 'free -h && df -h && ps aux | grep redis'

# Check for out-of-memory conditions
redis-cli -h <node-ip> -p <port> info memory

# Look for replication lag (if applicable)
redis-cli -h <node-ip> -p <port> info replication