From 7d81ce26c4ef8c5211e2db58b402f6b7d0a0239f Mon Sep 17 00:00:00 2001 From: Jinwoo Hong <73622457+Jinwoo-H@users.noreply.github.com> Date: Sat, 10 Oct 2026 20:03:55 -0400 Subject: [PATCH] infra(relay): staging c1 gets a 600/60 cap, and c1/c4 get rehome trust, for the step-5 e2e (#27117) * infra(relay): staging c1 gets a 600/60 cap and c1/c4 get rehome trust for the step-5 e2e The reserve and demote routes answer only on cells with rehome trust, and Terraform requires a rehome source to carry explicit connection limits. Staging only. * infra(relay): pin staging c1 to c2's cap-capable image with its new cap The legacy 2d0f6e6 image cannot report capped connection telemetry, so main holding it with a 600/60 cap would leave any c1 apply failing its heartbeats for good. --- cloud/infra/terraform/environments/staging.tfvars | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/cloud/infra/terraform/environments/staging.tfvars b/cloud/infra/terraform/environments/staging.tfvars index 1cb260e11ea..8c095bcb9ce 100644 --- a/cloud/infra/terraform/environments/staging.tfvars +++ b/cloud/infra/terraform/environments/staging.tfvars @@ -39,7 +39,11 @@ relay_gce_cells = { boot_disk_gb = 30 boot_image = "https://www.googleapis.com/compute/v1/projects/cos-cloud/global/images/cos-stable-121-18867-528-7" capacity_requests = 4000 - image = "us-central1-docker.pkg.dev/onorca-cloud-staging/orca-cloud/relay@sha256:2d0f6e6db2b0eb9d6aba188698de8330f8c30b4e76badfcf0fac3f3eb9508a87" + # c2's image: the legacy 2d0f6e6 cannot report capped telemetry, so a cap needs this one. + image = "us-central1-docker.pkg.dev/onorca-cloud-staging/orca-cloud/relay@sha256:1239830d0946dc92ded3c9edde1c0b827f584a7a2be5c177beed900056d76f69" + # Step-5 staging e2e: c1 is the second US reserve cell, so it needs a cap and rehome trust. + connection_hard_cap = 600 + connection_unobserved_bound = 60 } "staging-gce-c2" = { hostname = "c2" @@ -80,7 +84,8 @@ relay_gce_cells = { } } -relay_region_rehome_source_cell_ids = ["staging-gce-c2", "staging-gce-c3"] +# c1 and c4 hold rehome trust for the step-5 staging e2e: the reserve and demote routes need it. +relay_region_rehome_source_cell_ids = ["staging-gce-c1", "staging-gce-c2", "staging-gce-c3", "staging-gce-c4"] # Push is currently provisioned only in production. push_gateway_enabled = false