diff --git a/.github/workflows/v2-integration.yml b/.github/workflows/v2-integration.yml index d903c4a1a..f875933bb 100644 --- a/.github/workflows/v2-integration.yml +++ b/.github/workflows/v2-integration.yml @@ -76,15 +76,12 @@ jobs: env: # #816/#818 added 8 executing OpcUaClient tests; raise to 448 once a hosted run confirms them (blocked on #860) # (scripts/ci/README.md §"Fixture-backed integration"). - MIN_EXECUTED: "440" + MIN_EXECUTED: "448" run: bash scripts/ci/assert-not-all-skipped.sh artifacts/trx/*.trx - name: fixture logs on failure if: failure() continue-on-error: true - run: | - for c in otopcua-ci-mssql otopcua-ci-pg otopcua-ci-questdb otopcua-ci-opcplc otopcua-ci-opcplc-nat; do - echo "=== $c ==="; docker logs --tail 40 "$c" 2>&1 || true - done + run: bash scripts/ci/integration-fixtures.sh logs - name: stop fixtures if: always() continue-on-error: true diff --git a/infra/README.md b/infra/README.md index 6787b19ad..0315de8be 100644 --- a/infra/README.md +++ b/infra/README.md @@ -297,11 +297,11 @@ Things that are not obvious (#606): step also prints an individual-skip diagnostic (`Results/UnitTestResult` records with outcome `NotExecuted`); it does not affect the floor. Raise the floor as the suite grows. -### CI legs beyond `unit-tests` (#757; unverified on a hosted runner until first run) +### CI legs beyond `unit-tests` (#757; `v2-integration` hosted-verified 2026-11-11, run 1225) `v2-integration.yml` runs the fixture-backed Sql / Historian (SQL Server, QuestDB) / OpcUaClient integration projects against throwaway containers the job starts itself (`scripts/ci/integration-fixtures.sh`; not the -shared 10.100.0.35 host), floor `MIN_EXECUTED=440`; that includes a port-NAT opc-plc (`otopcua-ci-opcplc-nat`, +shared 10.100.0.35 host), floor `MIN_EXECUTED=448` (first hosted pass: run 1225, 2026-11-11, 525 executed); that includes a port-NAT opc-plc (`otopcua-ci-opcplc-nat`, host port 50110, exported as `OPCUA_NAT_ENDPOINT`) for the NAT browse tests (#813). `v2-e2e.yml` is manual/weekly and skips cleanly unless 10.100.0.35 is reachable from the runner; it sets `OPCUA_NAT_ENDPOINT=opc.tcp://10.100.0.35:50010` (the shared NAT stack, not a probe-required port — its tests skip if it is down). Each has its own concurrency group; see diff --git a/scripts/ci/README.md b/scripts/ci/README.md index 752a2b1f4..89e31a449 100644 --- a/scripts/ci/README.md +++ b/scripts/ci/README.md @@ -68,7 +68,7 @@ Neither touches `v2-ci.yml`; each has its own concurrency group (`lmxopcua-v2-in - **`v2-integration.yml`** (push to `master`, path-filtered PRs, manual; `timeout-minutes: 60`). `integration-fixtures.sh up` starts throwaway SQL Server 2022, PostgreSQL 17 (seeded from `seed-pg.sql`), QuestDB and opc-plc — plus a port-NAT opc-plc (`otopcua-ci-opcplc-nat`, host 50110 → 50000, private `.invalid` - advertised host, `OPCUA_NAT_ENDPOINT`, #813) — (`otopcua-ci-*`, non-default host ports), exports the env vars the fixtures read, and + advertised host, `OPCUA_NAT_ENDPOINT`, #813) — (`otopcua-ci-*-`, non-default host ports; a port already taken on the shared runner host is retried one higher and the chosen ports are exported), exports the env vars the fixtures read, and `down` removes them. It uses plain `docker run`, not `services:` (act_runner support is undocumented and Postgres needs a seed step); the only runner requirement is a docker daemon. **QuestDB is a throwaway container by decision (#841), not the shared `/opt/otopcua-questdb` fixture (#822):** CI stays @@ -79,7 +79,7 @@ Neither touches `v2-ci.yml`; each has its own concurrency group (`lmxopcua-v2-in one, and fails `up` if that line is missing. Upgrade QuestDB by bumping the compose file (and the docker-dev overlay); `CI_QDB_IMAGE` overrides the image for a one-off trial. Both run QuestDB's defaults (incl. `cairo.ttl.use.wall.clock=true`, which the historian relies on). Runs the Sql, Historian.SqlServer, - Historian.QuestDb, OpcUaClient and OpcUaClient.Browser `*.IntegrationTests` with `MIN_EXECUTED=440`. + Historian.QuestDb, OpcUaClient and OpcUaClient.Browser `*.IntegrationTests` with `MIN_EXECUTED=448`. Local run: 468 executed / 8 skipped (Oracle x2, the blackhole `docker pause` gate, one QuestDB stress test, 4 others), about 4.5 min of test time, QuestDB the longest (~3.3 min). Not covered (no pullable image or needs credentials): Modbus/S7/AB/FOCAS/TwinCAT sims, Mqtt, MTConnect, Oracle, Host real-infra mode. @@ -89,9 +89,9 @@ Neither touches `v2-ci.yml`; each has its own concurrency group (`lmxopcua-v2-in `OPCUA_NAT_SERVER_CERT`). Locally (2026-11-11, same CI filter) the two OpcUaClient projects went 13 → 21 executed with 0 skipped (`Driver.OpcUaClient` 9, `Driver.OpcUaClient.Browser` 12), and the NAT class passed 7/7 against a CI-style throwaway `docker run` of the NAT container plus the `docker exec` certificate hand-off. - Once a hosted run's TRX shows `Driver.OpcUaClient.trx` executed=9 and `Driver.OpcUaClient.Browser.trx` executed=12, - raise `MIN_EXECUTED` in `v2-integration.yml` **440 → 448** (and `v2-e2e.yml` 35 → 39). Hosted runs have not yet - reached the test step (fixture start times out on the first network probe, #860), so this is still open (#818). + **Hosted-confirmed 2026-11-11 (run 1225):** `Driver.OpcUaClient.trx` executed=9, `Driver.OpcUaClient.Browser.trx` + executed=12, 525 executed in all, so `MIN_EXECUTED` in `v2-integration.yml` is now **448** (#818). The `v2-e2e.yml` + 35 → 39 raise still waits for a hosted e2e run. If the NAT three show as skipped there, the certificate hand-off (`docker exec … /app/pki/own/certs/*.der`) did not work on the runner — fix that, do not lower the bump. - **`v2-e2e.yml`** (manual + weekly cron only; `timeout-minutes: 90`). `probe-e2e-fixtures.sh` TCP-probes diff --git a/scripts/ci/integration-fixtures.sh b/scripts/ci/integration-fixtures.sh index 41ff32bf8..e0db6683e 100755 --- a/scripts/ci/integration-fixtures.sh +++ b/scripts/ci/integration-fixtures.sh @@ -6,6 +6,7 @@ # otopcua-ci-*, wait until each is usable, and print the env exports the # *.IntegrationTests fixtures read (also appended to $GITHUB_ENV when set). # down remove those containers (idempotent; touches nothing else). +# logs print the tail of each fixture container's log (the workflow's on-failure step). # # Deliberately NOT the shared 10.100.0.35 host: CI must not depend on that box, and these # containers are created and destroyed inside the job. Host ports are non-default so a @@ -27,7 +28,15 @@ OPC_NAT_PORT="${CI_OPC_NAT_PORT:-50110}" # Throwaway-container-only credentials (never used against anything else). SA_PASSWORD="${CI_SA_PASSWORD:-Ci_throwaway_Pw1}" PG_PASSWORD="${CI_PG_PASSWORD:-Ci_throwaway_pg1}" -NAMES=(otopcua-ci-mssql otopcua-ci-pg otopcua-ci-questdb otopcua-ci-opcplc otopcua-ci-opcplc-nat) +# Per-run container names: the runner's docker daemon is shared, so fixed names let a concurrent run's `down` remove +# this run's containers. GITHUB_RUN_ID is set in every step of a run, so `up`, `logs` and `down` agree. +SUFFIX="${CI_FIXTURE_SUFFIX-${GITHUB_RUN_ID:+-$GITHUB_RUN_ID}}" +C_MSSQL="otopcua-ci-mssql$SUFFIX" +C_PG="otopcua-ci-pg$SUFFIX" +C_QDB="otopcua-ci-questdb$SUFFIX" +C_OPC="otopcua-ci-opcplc$SUFFIX" +C_NAT="otopcua-ci-opcplc-nat$SUFFIX" +NAMES=("$C_MSSQL" "$C_PG" "$C_QDB" "$C_OPC" "$C_NAT") ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)" # #841: CI keeps its OWN throwaway QuestDB (hermetic — never the shared /opt/otopcua-questdb fixture), but runs the # SAME image the shared fixture's compose file pins, read from that file so the two cannot drift. CI_QDB_IMAGE @@ -72,6 +81,35 @@ fixture_host() { down() { docker rm -f "${NAMES[@]}" >/dev/null 2>&1 || true; } +logs() { for c in "${NAMES[@]}"; do echo "=== $c ==="; docker logs --tail 40 "$c" 2>&1 || true; done; } + +# start_on_free_port +# The runner's docker host is shared, so a default host port can already be taken (#860 follow-up: run 1224 failed +# "Bind for :::19000 failed: port is already allocated"). On that error, retry with every port bumped by one; the +# chosen values are written back to the named variables, which the waits and the exports read afterwards. +start_on_free_port() { + local name="$1" vars="$2"; shift 2 + local -a names; IFS=, read -r -a names <<< "$vars" + local -a ports=(); local v; for v in "${names[@]}"; do ports+=("${!v}"); done + local attempt out i + for ((attempt = 0; attempt < 20; attempt++)); do + local -a args=("$@") + for i in "${!ports[@]}"; do args=("${args[@]//@P${i}@/${ports[$i]}}"); done + if out="$(docker run -d --name "$name" "${args[@]}" 2>&1)"; then + for i in "${!names[@]}"; do printf -v "${names[$i]}" '%s' "${ports[$i]}"; done + return 0 + fi + docker rm -f "$name" >/dev/null 2>&1 || true + if [[ "$out" == *"port is already allocated"* || "$out" == *"address already in use"* ]]; then + echo "host port(s) ${ports[*]} busy for $name; retrying one higher" >&2 + for i in "${!ports[@]}"; do ports[$i]=$((ports[$i] + 1)); done + continue + fi + echo "$out" >&2; return 1 + done + echo "no free host port for $name after 20 attempts" >&2; return 1 +} + wait_for() { # local what="$1" t="$2"; shift 2 local end=$((SECONDS + t)) @@ -86,31 +124,31 @@ up() { command -v docker >/dev/null || { echo "docker not available" >&2; exit 1; } local qdb_image; qdb_image="$(questdb_image)" down - docker run -d --name otopcua-ci-mssql -e ACCEPT_EULA=Y -e MSSQL_PID=Developer \ - -e "MSSQL_SA_PASSWORD=$SA_PASSWORD" -p "$SQL_PORT:1433" \ - mcr.microsoft.com/mssql/server:2022-latest >/dev/null - docker run -d --name otopcua-ci-pg -e "POSTGRES_PASSWORD=$PG_PASSWORD" -e POSTGRES_DB=sqlpollfixture \ - -p "$PG_PORT:5432" postgres:17-alpine >/dev/null - docker run -d --name otopcua-ci-questdb -p "$QDB_PORT:8812" -p "$QDB_HTTP_PORT:9000" \ - "$qdb_image" >/dev/null - docker run -d --name otopcua-ci-opcplc -p "$OPC_PORT:$OPC_PORT" \ - mcr.microsoft.com/iotedge/opc-plc:2.14.10 --pn="$OPC_PORT" --ut --aa --alm >/dev/null + start_on_free_port "$C_MSSQL" SQL_PORT -e ACCEPT_EULA=Y -e MSSQL_PID=Developer \ + -e "MSSQL_SA_PASSWORD=$SA_PASSWORD" -p "@P0@:1433" mcr.microsoft.com/mssql/server:2022-latest + start_on_free_port "$C_PG" PG_PORT -e "POSTGRES_PASSWORD=$PG_PASSWORD" -e POSTGRES_DB=sqlpollfixture \ + -p "@P0@:5432" postgres:17-alpine + start_on_free_port "$C_QDB" QDB_PORT,QDB_HTTP_PORT -p "@P0@:8812" -p "@P1@:9000" "$qdb_image" + # opc-plc advertises the port it listens on, so it must be the SAME inside and out (--pn follows the host port). + start_on_free_port "$C_OPC" OPC_PORT -p "@P0@:@P0@" \ + mcr.microsoft.com/iotedge/opc-plc:2.14.10 --pn="@P0@" --ut --aa --alm # Mirrors tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.OpcUaClient.IntegrationTests/Docker/nat/docker-compose.yml. - docker run -d --name otopcua-ci-opcplc-nat --hostname otopcua-ci-opcplc-nat-private -p "$OPC_NAT_PORT:50000" \ - mcr.microsoft.com/iotedge/opc-plc:2.14.10 --pn=50000 --ph=otopcua-ci-opcplc-nat-private.invalid --ut --aa >/dev/null + start_on_free_port "$C_NAT" OPC_NAT_PORT --hostname otopcua-ci-opcplc-nat-private -p "@P0@:50000" \ + mcr.microsoft.com/iotedge/opc-plc:2.14.10 --pn=50000 --ph=otopcua-ci-opcplc-nat-private.invalid --ut --aa + echo "fixture ports: sql=$SQL_PORT pg=$PG_PORT questdb=$QDB_PORT/$QDB_HTTP_PORT opc=$OPC_PORT opc-nat=$OPC_NAT_PORT (containers *$SUFFIX)" - wait_for "postgres" 120 docker exec otopcua-ci-pg pg_isready -U postgres -d sqlpollfixture + wait_for "postgres" 120 docker exec "$C_PG" pg_isready -U postgres -d sqlpollfixture # pg_isready can answer during initdb's temp server; require a real query on the final server. - wait_for "postgres query" 60 docker exec -e "PGPASSWORD=$PG_PASSWORD" otopcua-ci-pg \ + wait_for "postgres query" 60 docker exec -e "PGPASSWORD=$PG_PASSWORD" "$C_PG" \ psql -h 127.0.0.1 -U postgres -d sqlpollfixture -c 'select 1' - docker exec -i -e "PGPASSWORD=$PG_PASSWORD" otopcua-ci-pg \ + docker exec -i -e "PGPASSWORD=$PG_PASSWORD" "$C_PG" \ psql -v ON_ERROR_STOP=1 -v "app_password=$PG_PASSWORD" -h 127.0.0.1 -U postgres -d sqlpollfixture \ < "$ROOT/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Sql.IntegrationTests/Docker/postgres/seed-pg.sql" >/dev/null echo "seeded: postgres" echo "fixture host: $(fixture_host) (in container: $([ -f /.dockerenv ] && echo yes || echo no))" local sqlcmd=/opt/mssql-tools18/bin/sqlcmd - wait_for "sql server" 300 docker exec otopcua-ci-mssql "$sqlcmd" -C -S localhost -U sa -P "$SA_PASSWORD" -Q 'SELECT 1' + wait_for "sql server" 300 docker exec "$C_MSSQL" "$sqlcmd" -C -S localhost -U sa -P "$SA_PASSWORD" -Q 'SELECT 1' wait_for "questdb" 120 curl -fsS "http://$(fixture_host):$QDB_HTTP_PORT/exec?query=select%201" wait_for "opc-plc" 120 bash -c "exec 3<>/dev/tcp/$(fixture_host)/$OPC_PORT" wait_for "opc-plc (NAT)" 120 bash -c "exec 3<>/dev/tcp/$(fixture_host)/$OPC_NAT_PORT" @@ -121,7 +159,7 @@ up() { local nat_cert="${RUNNER_TEMP:-${TMPDIR:-/tmp}}/otopcua-ci-fixtures/opc-plc-nat-server.der" mkdir -p "$(dirname "$nat_cert")" wait_for "opc-plc (NAT) certificate" 60 bash -c \ - "docker exec otopcua-ci-opcplc-nat bash -c 'cat /app/pki/own/certs/*.der' > '$nat_cert' && [ -s '$nat_cert' ]" + "docker exec '$C_NAT' bash -c 'cat /app/pki/own/certs/*.der' > '$nat_cert' && [ -s '$nat_cert' ]" local h; h="$(fixture_host)" local -a exports=( @@ -145,5 +183,6 @@ up() { case "${1:-}" in up) up ;; down) down ;; - *) echo "usage: $0 up|down" >&2; exit 2 ;; + logs) logs ;; + *) echo "usage: $0 up|down|logs" >&2; exit 2 ;; esac