jepsen: testing

script/jepsen.garage/README.md

@@ -97,10 +97,10 @@ Command: `lein run test --nodes-file nodes.vagrant --time-limit 60 --rate 100  -
 
 Results:
 
-- For now, no failures with clock-scramble nemesis + partition nemesis -> TODO long test run
+- No failures with clock-scramble nemesis + db nemesis + partition nemesis (`--scenario cdp`) (0 failures in 10 runs).
 
-- **Fails with layout reconfiguration nemesis** (`--scenario r`).
-  Example of a failed run: `garage set2/20231025T115033.553+0200` (2 failures in 2 runs).
+- **Fails with just layout reconfiguration nemesis** (`--scenario r`).
+  Example of a failed run: `garage set2/20231025T141940.198+0200` (10 failures in 10 runs).
   TODO: investigate.
   This is the failure mode we are looking for and trying to fix for NLnet task 3.
 

script/jepsen.garage/src/jepsen/garage.clj

@@ -28,6 +28,7 @@
    "r"  grgNemesis/scenario-r
    "pr"  grgNemesis/scenario-pr
    "cpr"  grgNemesis/scenario-cpr
+   "cdp"  grgNemesis/scenario-cdp
    "dpr"  grgNemesis/scenario-dpr})
 
 (def patches

script/jepsen.garage/src/jepsen/garage/nemesis.clj

@@ -124,6 +124,14 @@
      (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})
      (reconfiguration-package {:interval 1})]))
 
+(defn scenario-cdp
+  "Clock modifying + db + partition scenario"
+  [opts]
+  (combined/compose-packages
+    [(combined/clock-package {:db (:db opts), :interval 1, :faults #{:clock}})
+     (combined/db-package {:db (:db opts), :interval 1, :faults #{:db :pause :kill}})
+     (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})]))
+
 (defn scenario-dpr
   "Db + partition + cluster reconfiguration scenario"
   [opts]
@@ -131,3 +139,4 @@
     [(combined/db-package {:db (:db opts), :interval 1, :faults #{:db :pause :kill}})
      (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})
      (reconfiguration-package {:interval 1})]))
+