| SRE { |
| n1: circle label:"Start" |
| n2: rectangle label:"Define experiment hypothesis" |
| n3: rectangle label:"Select blast radius" |
| n4: rectangle label:"Review experiment results" |
| n5: rectangle label:"Document learnings" |
| n6: circle label:"End" |
| n1.handle(right) -> n2.handle(left) |
| n2.handle(right) -> n3.handle(left) |
| n3.handle(bottom) -> ChaosMonkey.n7.handle(top) [label="Configure"] |
| n4.handle(right) -> n5.handle(left) |
| n5.handle(right) -> n6.handle(left) |
| } |
| ChaosMonkey { |
| n7: rectangle label:"Schedule experiment window" |
| n8: diamond label:"Steady state verified?" |
| n9: rectangle label:"Inject failure" |
| n10: rectangle label:"Abort experiment" |
| n11: diamond label:"Failure type?" |
| n12: rectangle label:"Kill random instance" |
| n13: rectangle label:"Inject network latency" |
| n14: rectangle label:"Exhaust CPU resources" |
| n7.handle(right) -> n8.handle(left) |
| n8.handle(right) -> n9.handle(left) [label="Yes"] |
| n8.handle(bottom) -> n10.handle(top) [label="No"] |
| n9.handle(right) -> n11.handle(left) |
| n10.handle(top) -> SRE.n4.handle(bottom) [label="Aborted"] |
| n11.handle(right) -> n12.handle(left) [label="Instance"] |
| n11.handle(bottom) -> n13.handle(top) [label="Network"] |
| n11.handle(left) -> n14.handle(top) [label="Resource"] |
| n12.handle(bottom) -> Observability.n15.handle(top) [label="Monitor"] |
| n13.handle(bottom) -> Observability.n15.handle(top) [label="Monitor"] |
| n14.handle(bottom) -> Observability.n15.handle(top) [label="Monitor"] |
| } |
| Observability { |
| n15: rectangle label:"Monitor system metrics" |
| n16: rectangle label:"Track error rates" |
| n17: diamond label:"System recovered?" |
| n18: rectangle label:"Record recovery time" |
| n19: rectangle label:"Trigger rollback" |
| n20: rectangle label:"Generate experiment report" |
| n15.handle(right) -> n16.handle(left) |
| n16.handle(right) -> n17.handle(left) |
| n17.handle(right) -> n18.handle(left) [label="Yes"] |
| n17.handle(bottom) -> n19.handle(top) [label="No"] |
| n18.handle(right) -> n20.handle(left) |
| n19.handle(right) -> n20.handle(top) |
| n20.handle(top) -> SRE.n4.handle(bottom) [label="Results ready"] |
| } |
