1 files changed, 93 insertions, 0 deletions
diff --git a/health/health.d/riakkv.conf b/health/health.d/riakkv.conf
new file mode 100644
index 0000000..261fd48
--- /dev/null
+++ b/health/health.d/riakkv.conf
@@ -0,0 +1,93 @@
+
+# Warn if a list keys operation is running.
+ template: riakkv_list_keys_active
+       on: riak.core.fsm_active
+    class: Utilization
+     type: Database
+component: Riak KV
+     calc: $list_fsm_active
+    units: state machines
+    every: 10s
+     warn: $list_fsm_active > 0
+     info: number of currently running list keys finite state machines
+       to: dba
+
+
+## Timing healthchecks
+# KV GET
+ template: riakkv_1h_kv_get_mean_latency
+       on: riak.kv.latency.get
+    class: Latency
+     type: Database
+component: Riak KV
+     calc: $node_get_fsm_time_mean
+   lookup: average -1h unaligned of time
+    every: 30s
+    units: ms
+     info: average time between reception of client GET request and \
+           subsequent response to client over the last hour
+
+ template: riakkv_kv_get_slow
+       on: riak.kv.latency.get
+    class: Latency
+     type: Database
+component: Riak KV
+     calc: $mean
+   lookup: average -3m unaligned of time
+    units: ms
+    every: 10s
+     warn: ($this > ($riakkv_1h_kv_get_mean_latency * 2) )
+     crit: ($this > ($riakkv_1h_kv_get_mean_latency * 3) )
+     info: average time between reception of client GET request and \
+           subsequent response to the client over the last 3 minutes, \
+           compared to the average over the last hour
+    delay: down 5m multiplier 1.5 max 1h
+       to: dba
+
+# KV PUT
+ template: riakkv_1h_kv_put_mean_latency
+       on: riak.kv.latency.put
+    class: Latency
+     type: Database
+component: Riak KV
+     calc: $node_put_fsm_time_mean
+   lookup: average -1h unaligned of time
+    every: 30s
+    units: ms
+     info: average time between reception of client PUT request and \
+           subsequent response to the client over the last hour
+
+ template: riakkv_kv_put_slow
+       on: riak.kv.latency.put
+    class: Latency
+     type: Database
+component: Riak KV
+     calc: $mean
+   lookup: average -3m unaligned of time
+    units: ms
+    every: 10s
+     warn: ($this > ($riakkv_1h_kv_put_mean_latency * 2) )
+     crit: ($this > ($riakkv_1h_kv_put_mean_latency * 3) )
+     info: average time between reception of client PUT request and \
+           subsequent response to the client over the last 3 minutes, \
+           compared to the average over the last hour
+    delay: down 5m multiplier 1.5 max 1h
+       to: dba
+
+
+## VM healthchecks
+
+# Default Erlang VM process limit: 262144
+# On systems observed, this is < 2000, but may grow depending on load.
+ template: riakkv_vm_high_process_count
+       on: riak.vm
+    class: Utilization
+     type: Database
+component: Riak KV
+     calc: $sys_process_count
+    units: processes
+    every: 10s
+     warn: $this > 10000
+     crit: $this > 100000
+     info: number of processes running in the Erlang VM
+       to: dba