Commit Graph
3 Commits
Author SHA1 Message Date
Johnathan Corgan 9e63b42bd9 Consolidate Docker test harness infrastructure
Replace 4 near-identical per-harness Docker setups with unified shared
infrastructure. Net result: -463 lines across 55 files, faster CI
(8.5 min vs ~13.5 min), 14 scenarios (down from 21).

Unified Docker image (testing/docker/):
- Single Dockerfile (trixie-slim) with FIPS_TEST_MODE env var for
  mode dispatch: default, chaos, sidecar, tor-socks5, tor-directory
- Single entrypoint.sh with conditional logic per mode
- Replaces 5 Dockerfiles, 3 entrypoints, 4 resolv.conf copies

Shared build and libraries (testing/scripts/, testing/lib/):
- testing/scripts/build.sh: single build script with macOS zigbuild
  support, replaces 4 per-harness copies
- testing/lib/derive_keys.py: shared key derivation module, replaces
  3 copies of derive-keys.py
- testing/lib/log_analysis.py: shared log analysis extracted from
  chaos sim/logs.py, with CLI interface and rekey cutover tracking
- testing/lib/wait-converge.sh: shared convergence wait helpers
  (wait_for_links, wait_for_peers) using fipsctl JSON polling

Scenario consolidation:
- Remove 7 redundant scenarios: tcp-chain (subsumed by tcp-mesh),
  tcp-only (subsumed by tcp-mesh), chaos-10 (replaced by
  churn-mixed --nodes 10), churn-10/churn-20/churn-20-mixed
  (subsumed by parameterized churn-mixed), cost-mixed-7node
  (overlaps mixed-technology)
- Add churn-mixed scenario with --nodes flag for scale testing
- Reduce idle scenario durations: smoke-10 60s→30s,
  ethernet-only 90s→30s, cost-avoidance 120s→45s,
  depth-vs-cost 120s→45s, bottleneck-parent 120s→60s,
  mixed-technology 180s→90s

CI updates:
- ci-local.sh: unified image build, structured chaos suite entries
  with per-scenario flags, --skip-build for sidecar
- ci.yml: shared binary install + image build step, updated scenario
  matrix, chaos_flags support for parameterized scenarios
- Add tcp-mesh and congestion-stress to CI matrix
- Static ping test uses active peer convergence detection instead
  of hardcoded 5s sleep

Chaos infrastructure improvements (from discovery-rework branch):
- Pre-built Docker image instead of per-service build at scale
- --nodes flag in chaos.sh for runtime topology size override
2026-03-19 18:08:36 +00:00
Johnathan Corgan cd9289e0f3 Update test harness docs and add transport_mix support
Chaos harness enhancements:
- transport_mix config: weighted random transport assignment for random
  topologies (erdos_renyi, random_geometric) with UDP/Ethernet/TCP
- Replace LoRa with Bluetooth L2CAP in cost-based/mixed-tech scenarios
  using realistic netem values (15-40ms delay, 5-15ms jitter, 2-8% loss)
- New churn-20-mixed scenario: 20-node Erdos-Renyi with 60% UDP,
  20% Ethernet, 20% TCP, full netem/link-flap/churn/bandwidth config
- Expanded chaos README with full scenario catalog in four categories

Static harness:
- Updated README with topology table and scenario count
2026-02-27 00:52:17 +00:00
Johnathan Corgan 0d93a19e07 Implement cost-based parent selection with periodic re-evaluation
Cost-based parent selection:
- Replace depth-only parent selection with effective_depth = depth + link_cost
- link_cost computed from locally measured MMP metrics: etx * (1.0 + srtt_ms / 100.0)
- Prevents bottleneck subtrees in heterogeneous networks where a LoRa link
  at depth 1 would otherwise always beat fiber at depth 2
- Configurable hysteresis (default 0.2) prevents marginal parent switches
- Configurable hold-down timer (default 30s) suppresses re-evaluation
  after parent switch
- Mandatory switches (parent lost, root change) bypass both safeguards
- Link costs passed as HashMap parameter to keep TreeState pure

Periodic re-evaluation:
- evaluate_parent() was only called on TreeAnnounce receipt or parent loss;
  after tree stabilization, link degradation went undetected
- Added timer-based re-evaluation (reeval_interval_secs, default 60s) that
  calls evaluate_parent() from the tick handler with current MMP link costs
- Respects existing hold-down and hysteresis safeguards
- Short-circuits when disabled or <2 peers

Design documentation:
- Update 7 design docs to reflect cost-based parent selection
- Replace depth-only algorithm descriptions with effective_depth model
- Replace rejected cumulative path cost spec with local-only design rationale
- Rewrite Example 2 (heterogeneous links) for local-only cost model
- Update config docs: parent_switch_threshold replaced by parent_hysteresis,
  hold_down_secs, reeval_interval_secs

Chaos simulation enhancements:
- fips_overrides with deep merge for per-scenario FIPS config customization
- Explicit topology algorithm for deterministic test graphs
- Control socket querying via fipsctl for tree/MMP snapshot collection
- Edge existence validation in netem manager
- Per-link netem policy overrides
- 9 new chaos scenarios covering cost avoidance, depth-vs-cost tradeoffs,
  stability, mixed topologies, periodic re-evaluation, and bottleneck parent

12 new unit tests, 667 total passing, clippy clean.
2026-02-23 17:15:20 +00:00