Commit Graph

  • 68a3518bf0 fix(deps): bump viperblock to the merged clusterrun-compatible dev (#669) Josh Siviour 2026-08-03 11:19:31 +10:00
  • f77a7e5976 fix(deps): bump predastore to the commit that adds clusterrun (#668) Josh Siviour 2026-08-03 11:01:23 +10:00
  • c2b80a9b93 feat: match new predastore config surface area (#591) Bryn Mailer 2026-08-03 09:59:25 +10:00
  • 5ef1954dd9 chore: record main's #613 as merged (content already on dev via #611) joshsiv-mulga 2026-08-03 09:39:53 +10:00
  • a2c451128d fix: unblock the Ubuntu 26.04 installer (qemu-kvm, sudo-rs) (#665) Josh Siviour 2026-08-03 08:57:50 +10:00
  • b9898a7e88 feat(imds): allow HttpTokens=optional per instance (#664) Josh Siviour 2026-08-03 08:56:04 +10:00
  • 6357ea70af feat: AZ-aware EKS control-plane spread and ClientRequestToken idempotency (#662) Josh Siviour 2026-08-03 07:40:54 +10:00
  • bda08e1afd fix: namespace colliding viper keys and bind viperblock flags to their own command (#661) Josh Siviour 2026-08-03 07:38:14 +10:00
  • 972f5837ea fix: bump goleak past the elided-frames stack-parse panic (#660) Josh Siviour 2026-08-03 00:49:50 +10:00
  • 3e1f9b1198 feat: segscan storage oracle for the real-predastore integration tier (#657) Josh Siviour 2026-08-03 00:40:45 +10:00
  • 8ae8d2fec4 feat: accept and surface gp3 Throughput on CreateVolume/DescribeVolumes (#658) Josh Siviour 2026-08-03 00:25:49 +10:00
  • bbf1ca7f0b fix: stop viper AutomaticEnv from shadowing predastore env vars (#659) Josh Siviour 2026-08-03 00:03:28 +10:00
  • 5de598e85a ci: trim unused E2E builds, move IMDS to the SDK, derive predastore bind in spx (#656) Josh Siviour 2026-08-02 22:32:33 +10:00
  • 8ec739d3f1 feat: close IMDS and vm_adapters trace-linking gaps (#655) Josh Siviour 2026-08-02 22:21:12 +10:00
  • 031f0a4cdd fix: preserve running guests across target restart, harden state write (#654) Josh Siviour 2026-08-02 21:28:55 +10:00
  • 22171c44ab fix: close the storage-exhaustion recovery gaps (durable terminate, per-service memory caps, local volume leak) (#653) Josh Siviour 2026-08-02 18:58:34 +10:00
  • 2011037d3d fix(vpc): close the route-table and ENI teardown leaks (#652) Josh Siviour 2026-08-02 15:16:03 +10:00
  • ae06234009 fix(spx): detect a production install from a marker a reset cannot remove (#651) Josh Siviour 2026-08-02 13:03:14 +10:00
  • 6b8e3d870e fix(logrotate): declare su so spinifex logs actually rotate (#650) Josh Siviour 2026-08-02 12:51:02 +10:00
  • dee7673e27 fix(gateway): log the three SigV4 paths that reject silently (#649) Josh Siviour 2026-08-02 12:11:40 +10:00
  • a4274f95b5 fix(systemd): keep in-use nbdkit alive across a viperblock restart (#648) Josh Siviour 2026-08-02 11:28:20 +10:00
  • 9a1fb44065 fix: CreateImage live drain + Alpine .raw sparsify (#647) Josh Siviour 2026-08-02 11:26:04 +10:00
  • 4175248386 fix: return InvalidInstanceID.NotFound for nonexistent DescribeInstances IDs (#646) Josh Siviour 2026-08-02 10:32:05 +10:00
  • 57a93fdee3 fix(nats): detect the JetStream write latch the health endpoint cannot see (#645) Josh Siviour 2026-08-02 10:29:07 +10:00
  • 34aa6d2230 fix: stop passing nbdkit S3 credentials as literal argv (#644) Josh Siviour 2026-08-02 09:07:39 +10:00
  • dad5d702e1 fix: stop lbagent heartbeats on positive LB deletion, and actually enable the JetStream watchdog (#643) Josh Siviour 2026-08-02 08:21:46 +10:00
  • a3fb4cccec fix(eks): backoff and terminal state on delete re-drive, CSI volume reclaim reporting, independent e2e subtests (#642) Josh Siviour 2026-08-02 08:21:25 +10:00
  • 9c9bb9430c test: gate image shell scripts in CI and pin the spot vCPU quota ordering (#641) Josh Siviour 2026-08-02 08:21:04 +10:00
  • 7d5ebabecc fix: explicit stop timeouts, graceful-shutdown exit code, and QEMU orphan classification (#640) Josh Siviour 2026-08-02 08:20:39 +10:00
  • 99323672bc fix: enrich REST-JSON spans with resolved AWS action (#639) Josh Siviour 2026-08-02 08:18:47 +10:00
  • 59db7d1e52 fix: stop calling RemoveSystemImage's deleted bytes "freed" (#638) Josh Siviour 2026-08-02 08:18:27 +10:00
  • 9f5f877e50 fix: batched hygiene — slog key, ui pid file, race-scaled timeouts, GPU console capture (#637) Josh Siviour 2026-08-02 08:17:18 +10:00
  • 614ab09866 fix(ec2): render empty result containers and return NotFound for missing named resources (#636) Josh Siviour 2026-08-02 08:16:47 +10:00
  • 044d7af85e fix(ui): pin router-plugin version and commit deterministic route tree (#635) Josh Siviour 2026-08-02 08:16:21 +10:00
  • 6873875248 fix(eks): tolerate the CriticalAddonsOnly taint on konnectivity-agent (#634) Josh Siviour 2026-08-02 08:16:00 +10:00
  • 6ce8b9ff18 fix: fail preflight when a gate tool is killed instead of reporting it clean (#633) Josh Siviour 2026-08-02 08:15:16 +10:00
  • d89ac24af2 fix(gateway): enforce iam:PassRole on ECS task and service role ARNs (#632) Josh Siviour 2026-08-02 08:04:12 +10:00
  • ccc726e0ba fix: close the LB name-claim orphan-reclaim race window (#631) Josh Siviour 2026-08-02 08:03:00 +10:00
  • ee0bf68d71 fix(gateway): prefer a call site's own error message over the generic lookup (#630) Josh Siviour 2026-08-02 08:02:34 +10:00
  • 135da2371e fix: scope golangci-lint cache per worktree, correct eks-node-gpu catalog description (#629) Josh Siviour 2026-08-02 08:01:45 +10:00
  • bca63a4ede fix(vm): detach non-DeleteOnTermination volumes on terminate, not just Boot ones (#628) Josh Siviour 2026-08-01 22:25:03 +10:00
  • 0628b5f20d fix(ec2): project AMIMetadata.State into DescribeImages instead of hardcoding available (#627) Josh Siviour 2026-08-01 22:24:43 +10:00
  • 82d6b2044c fix(vm): report ENOSPC to the guest instead of pausing the VM, and let the stuck-terminate backstop fire (#626) Josh Siviour 2026-08-01 21:37:43 +10:00
  • d455f3e569 fix(daemon): exit on SIGTERM instead of deadlocking on its own wait group (#625) Josh Siviour 2026-08-01 17:46:43 +10:00
  • a104f73306 test(dhcp): assert on persisted KV state, not the acquire counter (#624) Josh Siviour 2026-08-01 16:21:39 +10:00
  • d38db57912 fix(ec2): release post-launch ENIs on instance terminate (#623) Josh Siviour 2026-08-01 16:18:05 +10:00
  • 67a8b4409f chore(deps): bump viperblock for the nearfull throttle fix (#622) Josh Siviour 2026-08-01 12:16:36 +10:00
  • e4cd9ed527 chore(deps): bump viperblock for the durability batch (#621) Josh Siviour 2026-07-31 23:25:47 +10:00
  • 59b19192c4 fix(viperblockd): branch on the plugin's seal receipt, not on a deleted directory (#620) Josh Siviour 2026-07-31 23:09:36 +10:00
  • 70dda56fc3 fix(systemd): backstop viperblock stop at 30s instead of the 90s default (#619) Josh Siviour 2026-07-31 23:09:19 +10:00
  • d9fb17155f chore: fix EKS doc tomnewton-mulga 2026-07-31 17:08:49 +10:00
  • 168b8eb83e chore: RTX doc fix tomnewton-mulga 2026-07-31 16:54:57 +10:00
  • 4a87f19ca0 chore: Updated RTX-6000 doc tomnewton-mulga 2026-07-31 16:21:09 +10:00
  • 034c786916 chore(deps): bump viperblock for the nbdkit plugin stderr fix (#618) Josh Siviour 2026-07-31 14:55:51 +10:00
  • 2983160374 fix(lbagent): emit JSON logs so console attributes reach the sink as fields (#617) Josh Siviour 2026-07-31 11:28:51 +10:00
  • df6f797971 fix(otel): change log level in place so the gateway keeps shipping to the sink (#616) Josh Siviour 2026-07-31 10:45:10 +10:00
  • b6d43d8b51 feat(gateway): log the canonical request and action on signature mismatch (#615) Josh Siviour 2026-07-31 08:30:19 +10:00
  • 545ca94a8e fix(ci): report a cell that never ran a test as failed, not clean (#614) Josh Siviour 2026-07-31 00:15:19 +10:00
  • ff46314872 ci(nightly): move ubuntu cells to the 26.04 gold image (#613) Josh Siviour 2026-07-30 23:46:58 +10:00
  • 0cdf591c7c ci(nightly): move ubuntu cells to the 26.04 gold image (#611) Josh Siviour 2026-07-30 23:29:00 +10:00
  • 5fc6a137ec fix(e2e): fail TestMultinodeIPSec when a cluster that requested IPsec has none (#612) Josh Siviour 2026-07-30 23:28:42 +10:00
  • f973b306c4 fix: serialise DNS zone writes behind a per-zone lock (#610) Josh Siviour 2026-07-30 18:47:07 +10:00
  • 628fbbc0c3 fix: group-scope the OVS/OVN sockets and retire the vpcd sudoers grants (#609) Josh Siviour 2026-07-30 17:33:24 +10:00
  • e7f4ee46b0 feat: enforce rds:* authorization by principal class and resource (#607) Julian Sommer 2026-07-30 13:46:02 +10:00
  • eff11b611b fix: stop upstream DHCP leases leaking out of the external pool (#602) Josh Siviour 2026-07-30 13:29:19 +10:00
  • 3e195506d3 feat(images): mkosi system-image migration — CPU eks-node/ecs-node + GPU variants (#605) Josh Siviour 2026-07-30 12:57:43 +10:00
  • 2db1034436 feat(acm): managed certificate issuance and renewal from a tenant Private CA (#606) Josh Siviour 2026-07-30 12:52:24 +10:00
  • edf2113f54 feat: schedule RDS automated backups and sweep them past retention (#604) Julian Sommer 2026-07-30 12:34:41 +10:00
  • 2638a792c5 fix(ecs): task-definition round-trip fidelity and a task that dies while the agent is down (#603) Josh Siviour 2026-07-30 11:58:54 +10:00
  • d2eb3b11dd feat: add manual DB snapshots and restore (#601) Julian Sommer 2026-07-30 11:09:22 +10:00
  • d4d9db9e0b feat: add DB subnet groups and DB parameter groups (#600) Julian Sommer 2026-07-30 09:39:52 +10:00
  • a0659ae7d0 fix: gate ovn-controller on SB RAFT readiness and force recompute (#599) Josh Siviour 2026-07-29 16:22:30 +10:00
  • 53c0671512 feat: rds-6 failure detection — an honest health state for a DB instance Julian Sommer 2026-07-29 15:28:12 +10:00
  • 23de2ad85d feat: ModifyDBInstance and the shared VM-replace helper (#597) Julian Sommer 2026-07-29 15:07:06 +10:00
  • 7d2106bfb5 fix(test): reclaim fixture scratch dirs stranded in /tmp (#598) Josh Siviour 2026-07-29 14:57:50 +10:00
  • fc6e055ca0 feat: RDS lifecycle core — reboot, start, stop, delete, events (#596) Julian Sommer 2026-07-29 14:01:02 +10:00
  • 6eb76b439b feat: RDS tag actions, --tags on create, and the ARN parser (#595) Julian Sommer 2026-07-29 12:07:32 +10:00
  • 51ecddbf81 routeTree file tomnewton-mulga 2026-07-29 11:51:35 +10:00
  • 27aa2394b3 chore: Updated RTX-6000 RA Doc tomnewton-mulga 2026-07-29 11:38:06 +10:00
  • 2569601e3d feat: implement RDS CreateDBInstance, reconciler and endpoint DNS (#594) Julian Sommer 2026-07-29 11:32:59 +10:00
  • 32d80b473a feat: RDS v1 foundations (#592) Julian Sommer 2026-07-29 10:38:22 +10:00
  • 6cf9ee9d03 fix(dhcp): retransmit within a DORA transaction, resolve the chaddr on every path, stop masking IPAM errors (#593) Josh Siviour 2026-07-29 10:13:51 +10:00
  • 84418a218c refactor: extract the managed system-VPC builder out of EKS (#590) Julian Sommer 2026-07-29 08:59:28 +10:00
  • a1331b3785 release: update go.mod for v1.14.0 v1.14.0 tomnewton-mulga 2026-07-28 16:14:13 +10:00
  • 341f36a432 chore: bump alpine image to 3.24.1 Julian Sommer 2026-07-28 11:05:50 +10:00
  • 5800f39e42 fix(ec2): drain a snapshot's volume on the node hosting it (#589) Julian Sommer 2026-07-27 15:40:29 +10:00
  • 7e356b5b9b test: cover DescribeInstanceStatus and the SDK instance-status-ok waiter (#588) Julian Sommer 2026-07-27 13:46:16 +10:00
  • 331e46951f chore: rebuild frontend with new deps Julian Sommer 2026-07-27 12:51:36 +10:00
  • 6ba9e11461 chore: bump the npm-dependencies group (#587) dependabot[bot] 2026-07-27 12:49:48 +10:00
  • 1d1b1f6a51 chore: bump the go-dependencies group with 3 updates (#586) dependabot[bot] 2026-07-27 12:48:17 +10:00
  • 5b8f20b89f test: assert ModifyVolume resize reaches the guest block device (#585) Julian Sommer 2026-07-27 12:47:42 +10:00
  • 6389b37433 fix(gpu): Blackwell GPU support fixes for EKS/ECS image builds and VFIO (#559) tomnewton-mulga 2026-07-27 12:11:18 +10:00
  • 0708ac4816 chore: setup react-you-might-not-need-an-effect Julian Sommer 2026-07-27 11:36:16 +10:00
  • 9cec5a50c6 fix: pin isos to /latest so they stop getting pruned Julian Sommer 2026-07-27 09:33:44 +10:00
  • d96bc3c095 fix: bump grpc Julian Sommer 2026-07-27 09:15:36 +10:00
  • 04c7efde19 chore: lint config Julian Sommer 2026-07-27 09:08:53 +10:00
  • 95973eeb3c refactor: migrate spinifex off legacy nats.JetStreamContext onto nats.go/jetstream (#584) Julian Sommer 2026-07-24 16:40:57 +10:00
  • e79ca59d4b fix: configure host DNS from spx admin init/join (#582) Julian Sommer 2026-07-24 10:02:11 +10:00
  • 61319ba4a4 fix: terminate/detach volume-wedge — detach-before-delete, bounded detach, vanished-QEMU + stuck-terminate backstops (#583) Josh Siviour 2026-07-23 23:30:12 +10:00
  • 6e13a9d9f4 test: add continuous single-open churn e2e for viperblock 503/GC joshsiv-mulga 2026-07-23 14:48:50 +10:00