BOSH Monit Health Checks

bosh_health_checks.sh

Monit Process Healthcheck for all vm’s in the foundation:
for i in `bosh --tty deployments --json | jq -r '.Tables[].Rows[] | .name'`; do echo -e "\033[1;32mDeployment Name: \033[0m" $i; DEPLOYMENT=$i; bosh --tty -d $DEPLOYMENT  instances --ps --json | jq '.Tables[].Rows[] | select(.process != "")' | jq -s -r 'group_by(.process_state)[] | .[0].process_state + ": " + (length | tostring)'; echo;  bosh --tty -d $DEPLOYMENT instances --ps --json | jq -r '.Tables[].Rows[] | select((.process_state != "running") and .process_state != "") | "\(.instance) \(.process) \(.process_state)"'; echo ;done

Memory health check for all vm’s in the foundation:
for i in `bosh --tty deployments --json | jq -r '.Tables[].Rows[] | .name'`; do echo -e "\033[1;32mDeployment Name: \033[0m" $i; DEPLOYMENT=$i; bosh --tty -d $DEPLOYMENT  instances --vitals --json | jq -r '.Tables[].Rows[] | select(.memory_usage != "") | select((.memory_usage | split("%") | .[0] | tonumber) >= 70) | "Instance: " + .instance + ", Memory: " + .memory_usage' | column -t; echo ;done

Ephemeral disk health check:
for i in `bosh --tty deployments --json | jq -r '.Tables[].Rows[] | .name'`; do echo -e "\033[1;32mDeployment Name: \033[0m" $i; DEPLOYMENT=$i; bosh --tty -d $DEPLOYMENT  instances --vitals --json | jq -r '.Tables[].Rows[] | select(.ephemeral_disk_usage != "") | select((.ephemeral_disk_usage | split("%") | .[0] | tonumber) >= 70) | "Instance: " + .instance + ", Ephemeral Disk Usage: " + .ephemeral_disk_usage' | column -t; echo ;done

Persistent disk health check:
for i in `bosh --tty deployments --json | jq -r '.Tables[].Rows[] | .name'`; do echo -e "\033[1;32mDeployment Name: \033[0m" $i; DEPLOYMENT=$i; bosh --tty -d $DEPLOYMENT  instances --vitals --json | jq -r '.Tables[].Rows[] | select(.persistent_disk_usage != "") | select((.persistent_disk_usage | split("%") | .[0] | tonumber) >= 70) | "Instance: " + .instance + ", Persistent Disk Usage: " + .persistent_disk_usage' | column -t; echo ;done