Compare commits

2 Commits
325 changed files with 24993 additions and 44 deletions
+8 -20
View File
@@ -1,20 +1,8 @@
.git
.github
.env
.env.*
!.env.example
secrets
certs
volumes
data
backups
*.key
*.pem
*.p12
*.pfx
*.jks
.venv
__pycache__
node_modules
evidence
.DS_Store
*
!go.mod
!go.sum
!cmd/
!cmd/**
!internal/
!internal/**
!Dockerfile
+21
View File
@@ -0,0 +1,21 @@
name: Go correctness and per-file coverage
on: [push, pull_request]
jobs:
verify:
runs-on: ubuntu-latest
timeout-minutes: 20
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: '1.26.1'
- run: sudo apt-get update && sudo apt-get install -y jq ruby webp
- run: go vet ./...
- run: test -z "$(gofmt -l cmd internal)"
- run: LOCAL_COVERAGE=true scripts/test-local.sh
- run: docker run --rm --entrypoint /bin/promtool -v "$PWD/charts/messenger/files/observability:/rules:ro" -v "$PWD/student-tests/alerts.test.yaml:/tests.yaml:ro" prom/prometheus:v3.5.0 test rules /tests.yaml
- uses: actions/upload-artifact@v4
if: always()
with:
name: coverage
path: coverage/summary.json
+21
View File
@@ -0,0 +1,21 @@
version: "2"
run:
timeout: 3m
linters:
default: none
enable:
- errcheck
- govet
- ineffassign
- staticcheck
- unused
- revive
- gocritic
formatters:
enable:
- gofmt
- goimports
settings:
goimports:
local-prefixes:
- gitea.privcloud.tech/vlad_marlo/mtusi2026lab4
+9
View File
@@ -0,0 +1,9 @@
# Наблюдаемость мессенджера
Бизнес-архитектура lab5 сохраняется. Компонент telemetry создаётся в composition root и передаётся HTTP/worker/storage через явные границы. SDK провайдеры принадлежат Fx lifecycle. Отказ Collector не входит в readiness бизнес-API.
HTTP принимает W3C carrier, создаёт server span и записывает только шаблон маршрута, метод и класс статуса. Durable job хранит trace context. Dispatch создаёт producer span, consumer извлекает его parent, SQL и S3 операции создают дочерние spans. Retry сохраняет исходную причинную связь, но получает отдельный span попытки.
OTLP Collector принимает три сигнала и ограничивает память и очереди. Prometheus хранит метрики, Loki — структурные логи, Tempo — трассы; Grafana подключается через provisioning. Все компоненты имеют учебные имена messenger-* и находятся внутри существующего Helm release, отдельно от внешнего monitoring.
Метрики не содержат ID пользователя/чата/вложения/запроса и raw URL. Histogram boundaries заданы в секундах. Error ratio исключает health и клиентские 4xx. SLO alerts используют одновременно короткое и длинное окна; проверка краткого всплеска нужна для оценки ложных срабатываний.
+17
View File
@@ -0,0 +1,17 @@
FROM golang:1.26.1-alpine3.23 AS build
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
COPY cmd/ ./cmd/
COPY internal/ ./internal/
RUN CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" -o /out/server ./cmd/server
FROM alpine:3.23 AS runtime
RUN apk add --no-cache ca-certificates libwebp-tools
COPY --from=build /out/server /server
USER 65532:65532
ENV APP_HOST=0.0.0.0 APP_PORT=8080 GOMEMLIMIT=160MiB
EXPOSE 8080
STOPSIGNAL SIGTERM
HEALTHCHECK --interval=5s --timeout=3s --start-period=3s --retries=3 CMD ["/server", "healthcheck"]
ENTRYPOINT ["/server"]
+29
View File
@@ -28,3 +28,32 @@ test-persistence:
test-failover:
@test -n "$(ACTION_SCRIPT)" || (echo "Set ACTION_SCRIPT to your implemented executable stop-one hook"; exit 2)
$(PYTHON) tests/resilience.py --mode failover --action-script "$(ACTION_SCRIPT)" --base-url "$(BASE_URL)" $(TLS_ARGS)
.PHONY: test-student vet lint coverage chart-check
test-student:
go test -race ./...
vet:
go vet ./...
lint:
golangci-lint run ./...
coverage:
scripts/coverage.sh
chart-check:
helm lint charts/messenger
helm template lab2 charts/messenger >/dev/null
KUBE_CONTEXT ?= dev
NAMESPACE ?= highload-applications
RELEASE ?= lab2
IMAGE ?= asisti.registry.twcstorage.ru/mtusi2026lab6
TAG ?= local
.PHONY: init-secrets deploy build-push test-local
init-secrets:
KUBE_CONTEXT=$(KUBE_CONTEXT) NAMESPACE=$(NAMESPACE) scripts/init-secrets.sh
build-push:
docker buildx build --platform linux/amd64 --target runtime --tag $(IMAGE):$(TAG) --metadata-file image-build.json --push .
@echo 'Copy containerimage.digest from image-build.json into charts/messenger/values.yaml before deploy.'
deploy: chart-check
helm upgrade --install $(RELEASE) --reset-values charts/messenger --kube-context $(KUBE_CONTEXT) --namespace $(NAMESPACE) --wait --wait-for-jobs --timeout 8m
test-local:
scripts/test-local.sh
+105 -24
View File
@@ -1,37 +1,118 @@
# Отчёт — лабораторная 6
# Лабораторная 6: наблюдаемость
- Автор, группа: TODO
- Целевая оценка; выбранный трек 5, если нужен: TODO
- Commit/PR: TODO после публикации
- Использованные источники, библиотеки и помощь ИИ: TODO
Агапов, БПИ2303. Целевой уровень — 5, трек 2: SLO и обнаружение инцидентов. Оценка не выставлена. Бизнес-контракт lab5 сохранён.
## Запуск из чистого clone
## Запуск
TODO: версии runtime/образов, prerequisites, команды создания локальных secrets/.env, build, миграций, запуска, ожидания готовности, тестов и остановки. Указать необходимые действия оператора. Не вставлять секреты. Отдельно указать безопасную остановку и команду намеренного удаления учебных данных.
Нужны Go 1.26.1, Docker, Helm, kubectl, jq, openssl, Ruby и Python 3.9+ для неизменённых публичных тестов. Native worker использует cwebp; в контейнере установлен libwebp-tools. Все образы закреплены в chart по digest.
## Архитектура и решения
```sh
export GOTOOLCHAIN=go1.26.1
make check chart-check
make test-local
LOCAL_COVERAGE=true scripts/test-local.sh
# Учебный dev: секрет registry берётся из ~/.secrets/twc-registry-token.
make init-secrets
make deploy
make test BASE_URL=https://hl.agapov.space
```
TODO: схема процессов/хранилищ, источник истины, транзакционные границы, ограничения. Что перенесено из lab5, что изменено в этой работе. Соответствие переменных из .env.example реальной конфигурации.
Один Helm release `lab2`, namespace `highload-applications`, context `dev`. Ingress Traefik — https://hl.agapov.space, issuer letsencrypt-prod. Добавлены Collector, Prometheus, Loki, Tempo и Grafana; прежние API/worker/PostgreSQL/Valkey/S3/broker и PVC сохранены. Migration и S3 bootstrap выполняются идемпотентными Jobs. Registry image обновляется через `make build-push TAG=<revision>` и перенос digest в values. `--reset-values` исключает неявное использование образа предыдущей лабы.
## Доказательства критериев
[Настройки и соответствие .env.example](docs/CONFIGURATION.md). [Матрица контрактов](docs/CONTRACT-CHECK.md). Kubernetes заменяет требуемый заданием Compose/Swarm; подтверждение преподавателя на такую замену остаётся открытым вопросом. Наличие работающего dev не доказывает формальное принятие этой замены.
| Критерий README | Команда/сценарий | Наблюдаемый результат | Файл доказательства |
| --- | --- | --- | --- |
| Публичный smoke | make test | TODO | TODO |
| Остальные пункты уровня 3 | TODO | TODO | TODO |
| Все пункты уровня 4, если заявлен | TODO | TODO | TODO |
| Выбранный трек 5, если заявлен | TODO | TODO | TODO |
Grafana закрыта внутри кластера. Доступ:
TODO: добавить отдельную строку для каждого заявленного критерия. PASS без команды и наблюдения не является доказательством. Проверка инфраструктурного hook требует подтверждения, какие реальные процессы/хранилища перезапущены.
```sh
kubectl --context dev -n highload-applications port-forward svc/messenger-grafana 3000:3000
# В другом терминале: прочитать пароль только для своего локального входа.
kubectl --context dev -n highload-applications get secret messenger-grafana -o jsonpath='{.data.password}' | base64 --decode
```
## Эксперименты и отказы
Открыть http://localhost:3000, username admin. Пароль генерируется один раз; не хранить вывод в отчёте/логах. Dashboard `Messenger: API, worker and SLO` и три datasource создаются provisioning. Остановка port-forward не останавливает приложения. `helm uninstall lab2` намеренно удаляет учебные workloads всего общего release, поэтому это не обычный способ остановки одной лабы. PVC остаются; для намеренного удаления данных выбирать конкретные учебные PVC после проверки владельца. Общий namespace удалять нельзя.
TODO: гипотеза, hardware/лимиты, версии, объём данных, профиль нагрузки, concurrency/arrival rate, длительность/прогрев, повторы, успешные RPS, ошибки, p50/p95/p99, CPU/RAM. Сохранить raw summary без tokens и объяснить ограничения измерения.
## Архитектура
| Воздействие | Что ожидаем | Что наблюдали | Время восстановления / потеря данных |
| --- | --- | --- | --- |
| TODO | TODO | TODO | TODO |
API/worker → OTLP HTTP/protobuf → Collector → Prometheus (метрики), Loki (структурные логи), Tempo (трассы) → Grafana (запросы и отображение). Collector не является долговременной БД. Prometheus/Loki/Tempo сохраняют данные на PVC, retention — 24 часа; Grafana хранит настройки на своём PVC.
## Ограничения и следующие шаги
SDK trace/metric 1.38.0, log 0.14.0; Collector contrib 0.135.0, Prometheus 3.5.0, Loki 3.5.5, Tempo 2.8.2, Grafana 12.1.1. Точные версии зависимостей — go.mod; digest образов — values.yaml. Resource attributes: service.name=messenger-api/worker, service.version=lab6, service.instance.id=уникальный ID процесса, deployment.environment.name=lab. Метрики — собственные имена, единицы ниже; W3C TraceContext без baggage.
TODO: какие отказы выдерживаются и какие нет; что не реализовано; где учебное упрощение; какое улучшение подтверждено, а какое пока гипотеза.
Контекст запроса сохраняется вместе с SQL outbox; producer inject помещает дочерний контекст в Streams. Worker извлекает его для consumer span, вложенные S3/SQL spans показывают реальные операции. Retry сохраняет исходную причинную связь. SQL и параметры, ключи S3, filename, тела, пароли и токены не экспортируются. Логи содержат timestamp/severity/event/outcome и trace/span IDs; HTTP-событие также request_id. Метрики не содержат пользовательские UUID или request_id. Число service.instance.id растёт при рестартах и ограничивается retention; это не бизнес-идентификатор.
Конструкторы не проверяют доступность telemetry backend; readiness зависит от синхронных бизнес-зависимостей PostgreSQL/Valkey/S3. OTLP не участвует в успехе business commit. SDK очереди trace/log — 256 записей, batch 64, timeout 1 s, retry отключён. Метрики экспортируются раз в 5 s. Collector memory limiter 192 MiB/spike 48 MiB, batch 128/max256; exporter queues 256 batches, два consumers, retry максимум 30 s. Переполнение/отказ допускает потерю telemetry, а не бесконечное накопление. SDK/Collector shutdown ограничен lifecycle deadline.
## Сигналы и запросы
| Имя Prometheus | Значение/единица |
| --- | --- |
| messenger_http_requests_total | Количество запросов; method, route template, status_class |
| messenger_http_duration_seconds_* | Histogram длительности HTTP handler в секундах; streaming download может завершиться позже, его S3 span живёт до Close |
| messenger_jobs_total | Реальные попытки worker, job_type/outcome; duplicate без lease не считается обработкой |
| messenger_job_duration_seconds_* | Время попытки обработки, секунды |
| messenger_ready_duration_seconds_* | От durable SQL acceptance до подтверждённой публикации ready, секунды |
| messenger_queue_depth / messenger_queue_oldest_seconds | Текущие незавершённые SQL jobs / возраст старейшей; max по наблюдателям, не sum дублированных снимков |
| messenger_db_pool_used / messenger_db_pool_waiting | Соединения конкретного процесса / ожидающие acquire |
| messenger_worker_busy / messenger_worker_capacity | Занятость / одна job на процесс |
| messenger_process_cpu_seconds_total | Накопленное CPU time; rate даёт CPU cores |
| messenger_process_peak_rss_bytes | Максимальный RSS процесса, bytes; это не мгновенный RSS |
p95: `histogram_quantile(0.95, sum by (le) (rate(messenger_http_duration_seconds_bucket[1m])))`. Аналогично p50/p99; percentiles реплик не усредняются. Для RPS — `sum(rate(messenger_http_requests_total[1m]))`. Dashboard JSON содержит точные запросы и единицы всех 14 panels. [Реальные имена dev](evidence/current/dev-metric-names.json), [цели scrape](evidence/current/dev-prometheus-targets.json).
## SLO и правила
Учебное целевое окно SLO — rolling 24 h. API availability ≥99%: `1 - 5xx / все business requests`, исключены health/metrics, ошибки клиента остаются в denominator. Ready ≥95% завершённых jobs за ≤60 s от durable acceptance. Это latency SLI завершений: зависшие и terminal failed не входят в него, поэтому обязательный дополнительный alert queue lag закрывает слепую зону незавершённой работы. Эти цели выбраны для небольших учебных PNG/JPEG при доступных зависимостях, не являются подтверждённым production SLA.
Для демонстрации обнаружения используются два окна 1 m/5 m одновременно и `for=30s`. API error ratio >5% означает burn >5 относительно бюджета 1%; доля completed jobs >60 s больше25% — burn >5 относительно бюджета5%. Queue lag: oldest>60 s при depth>0, for15s. Полный день измерений не собирался; проверено поведение alerts в коротком контролируемом эксперименте. Условия и ограничения можно воспроизвести из [rules](charts/messenger/files/observability/alerts.yaml).
## Эксперимент и диагностика
29.10.2026, Apple Silicon, native API/worker + Docker Desktop. Две API, один worker, два клиента с паузой250ms; polling alerts раз5s. Нагрузка синтетическая, без Kubernetes CPU/memory limits; один проход и отдельный повтор исправленного ready alert. Гипотеза: multiwindow/for отсекают короткий всплеск, но выявляют устойчивый отказ и накопление jobs, а отказ Tempo не блокирует business API.
[Raw HTTP, события и alert snapshots](evidence/incidents/), [агрегаты](evidence/incidents/summary.json), [график](evidence/incidents/incident-timeline.png). Длительности определяются по журналу событий; точность обнаружения порядка5s плюс export/scrape задержки. Фаза HTTP назначается перед запросом, поэтому переходные запросы могут пересекать границу воздействия.
| Воздействие | Реальное наблюдение |
| --- | --- |
| PostgreSQL pause5s | 19/19 запросов фазы завершились ошибкой; API burn не firing ни во всплеске, ни в следующем91s восстановления |
| PostgreSQL pause122s | 552/552 ошибок; API burn firing через137s от начала, то есть через15s после снятия отказа. Resolved через51s после восстановления. Задержка показывает ограничение окон/export/for, а не мгновенное обнаружение |
| Worker STOP113s, 20 uploads | 734 запросов истории без ошибок; queue lag firing через87s от остановки, resolved через10s после CONT. Итоговый backlog0 |
| Tempo stop46s | 328 запросов истории,0 ошибок, p95=23.36ms; полноценный smoke с upload/message/thumbnail прошёл. Зафиксированы136 failed span deliveries, очередь после восстановления0 |
Во время основной серии пик RSS трёх процессов:30736/45600/46240KiB; CPU от0:00.09/0:00.10/0:00.10 до0:01.95/0:04.72/0:04.38. Единственный snapshot Collector:66.68MiB, CPU0.93%; это snapshot, не доказанный глобальный максимум памяти. Ограничение очередей дополнительно проверено кодом/config и тестом2000spans против недоступного OTLP. Количество failed deliveries не равнозначно точному числу безвозвратно потерянных уникальных spans.
Первый запуск выявил ошибку ready rule: selector `le="60"` не совпадал с экспортированным `60.0`. Исправление принимает обе формы. [Повтор с настоящим STOP/CONT](evidence/ready-slo/): очередь firing через86s от остановки и resolved через10s после CONT; ready burn firing через41s после CONT, resolved через66s после CONT. [Результат](evidence/ready-slo-result.txt). [promtool regression](evidence/current/alert-rule-tests.txt) дополнительно проверяет короткий/длительный error rate и canonical bucket. Первоначальная проверка полного сценария завершилась ненулевым кодом: assertion ожидал API firing до снятия отказа. Raw данные сохранены; текущий сценарий учитывает lagged detection и использует180s длительного отказа. Полный сценарий после этого изменения заново не запускался.
Runbook:
1. Открыть API errors/p95 и queue oldest/depth. Если выросли5xx, найти error trace и HTTP request_id в Loki.
2. В [DB outage trace](evidence/current/db-outage-trace.json) проверить postgres.acquire/query: около1s и error, безопасное сообщение operation failed. Это указывает на storage path, а не на decode изображения. Проверить доступность БД/pool, восстановить зависимость, наблюдать уменьшение error ratio; alert снимается с задержкой окна.
3. Если HTTP работает, но растёт queue age при нулевой занятости, проверить worker process/replicas и последние consumer logs. Возобновить worker; дождаться depth0 и resolved. После накопленной задержки ready burn некоторое время остаётся firing — это ожидаемая память окна.
4. Если Collector send_failed/queue растут, а business RPS стабилен, проверить Tempo/Loki и их PVC. Не включать их в readiness API. После восстановления проверить exporter queue0 и свежие traces; уже потерянные spans восстановить нельзя.
## Доказательства и повторение
```sh
export LOCAL_TELEMETRY_STATE=/tmp/messenger-telemetry.env
scripts/telemetry-local.sh
. "$LOCAL_TELEMETRY_STATE"
OBSERVABILITY_TESTS=true scripts/test-local.sh
RETRY_TRACE_TEST=true scripts/test-local.sh
scripts/telemetry-local.sh down
```
Скрипт down удаляет только контейнеры/данные, созданные указанным локальным state file. Не использовать state file от другого стенда. Сценарии не останавливают dev workloads. Native source snapshot — [хэши](evidence/current/source.sha256), образ — [build metadata](evidence/current/image.json). Первый длинный эксперимент выполнен до дополнительной проверки входной telemetry configuration; instrumentation/бизнес-путь не менялись. Повтор ready и проверки dev используют исправления.
| Критерий | Доказательство |
| --- | --- |
| Бизнес API, failover, persistence, очередь переживает restart | evidence/local/smoke.txt, failover.txt, persistence.txt, durable.txt; реальные действия в actions.txt |
| API→producer→consumer→S3/SQL + logs | evidence/current/correlated-trace.json, correlated-logs.json; dev-correlation.txt |
| Retry после настоящего S3 pause | retry-trace.json: первый consumer error15s, следующий успешен; retry-result.json. Assertion enum исправлен и перепроверен по сохранённому trace |
| Метрики/provisioning/live datasource | dev-dashboard.json, dev-datasources.jsonl, dev-tempo-health.txt |
| Race и каждый Go-файл≥90% | coverage-per-file.json, coverage.txt; lint.txt, static.txt |
| Burn/queue alerts и восстановление | evidence/incidents и evidence/ready-slo; alert-rule-tests.txt |
| Dev upgrade и HTTPS smoke | dev-deploy-final.txt: release lab2 revision45; dev-smoke.txt; dev-pods.txt |
Remote CI не проверялся; локальные результаты не заменяют зелёный pipeline Gitea. Нет HA telemetry backend/PostgreSQL/S3 и восстановления после потери узла/диска. Фиксированная частота sampling1 предназначена для учебной нагрузки; при большой нагрузке её следует отдельно исследовать. Рост RAM на бесконечном горизонте экспериментом не доказан; архитектурные очереди и Kubernetes memory limits конечны.
## Источники
[OTel Go](https://opentelemetry.io/docs/languages/go/instrumentation/), [Collector](https://opentelemetry.io/docs/collector/configuration/), [Loki OTLP](https://grafana.com/docs/loki/latest/send-data/otel/), обязательные контракты этого репозитория. При реализации использовалась помощь ИИ. Измерения и ограничения указаны отдельно от проектных гарантий.
+6
View File
@@ -0,0 +1,6 @@
apiVersion: v2
name: messenger
description: Учебный мессенджер с PostgreSQL и шардированным Valkey
version: 0.1.0
appVersion: lab6
type: application
@@ -0,0 +1,38 @@
groups:
- name: messenger-slo
interval: 5s
rules:
- record: messenger:api_error_ratio:1m
expr: sum(rate(messenger_http_requests_total{route!~"/health/.*|/metrics",status_class="5xx"}[1m])) / clamp_min(sum(rate(messenger_http_requests_total{route!~"/health/.*|/metrics"}[1m])), 0.001)
- record: messenger:api_error_ratio:5m
expr: sum(rate(messenger_http_requests_total{route!~"/health/.*|/metrics",status_class="5xx"}[5m])) / clamp_min(sum(rate(messenger_http_requests_total{route!~"/health/.*|/metrics"}[5m])), 0.001)
- alert: MessengerAPIBurnRate
expr: (messenger:api_error_ratio:1m > 0.05) and (messenger:api_error_ratio:5m > 0.05)
for: 30s
labels:
severity: warning
annotations:
summary: API consumes the 99% availability budget at more than 5x in both windows
runbook: REPORT.md#диагностика
- alert: MessengerReadyBurnRate
expr: ((sum(rate(messenger_ready_duration_seconds_count[1m])) - sum(rate(messenger_ready_duration_seconds_bucket{le=~"60|60.0"}[1m]))) / clamp_min(sum(rate(messenger_ready_duration_seconds_count[1m])), 0.001) > 0.25) and ((sum(rate(messenger_ready_duration_seconds_count[5m])) - sum(rate(messenger_ready_duration_seconds_bucket{le=~"60|60.0"}[5m]))) / clamp_min(sum(rate(messenger_ready_duration_seconds_count[5m])), 0.001) > 0.25)
for: 30s
labels:
severity: warning
annotations:
summary: More than 25% of completed jobs missed 60s in both windows (5x burn of 95% SLO)
runbook: REPORT.md#диагностика
- alert: MessengerQueueLag
expr: max(messenger_queue_oldest_seconds) > 60 and max(messenger_queue_depth) > 0
for: 15s
labels:
severity: warning
annotations:
summary: Accepted work has been waiting for over 60 seconds
runbook: REPORT.md#диагностика
- alert: MessengerTelemetryDrops
expr: sum(increase(otelcol_exporter_send_failed_spans_total[1m])) > 0
labels:
severity: info
annotations:
summary: Trace backend delivery is failing; inspect bounded collector queues
@@ -0,0 +1,71 @@
receivers:
otlp:
protocols:
grpc:
endpoint: 0.0.0.0:4317
http:
endpoint: 0.0.0.0:4318
processors:
memory_limiter:
check_interval: 1s
limit_mib: 192
spike_limit_mib: 48
batch:
timeout: 1s
send_batch_size: 128
send_batch_max_size: 256
exporters:
prometheus:
endpoint: 0.0.0.0:8889
resource_to_telemetry_conversion:
enabled: true
otlphttp/tempo:
endpoint: http://messenger-tempo:4318
timeout: 2s
sending_queue:
enabled: true
queue_size: 256
num_consumers: 2
retry_on_failure:
enabled: true
initial_interval: 1s
max_interval: 5s
max_elapsed_time: 30s
otlphttp/loki:
endpoint: http://messenger-loki:3100/otlp
timeout: 2s
sending_queue:
enabled: true
queue_size: 256
num_consumers: 2
retry_on_failure:
enabled: true
initial_interval: 1s
max_interval: 5s
max_elapsed_time: 30s
extensions:
health_check:
endpoint: 0.0.0.0:13133
service:
telemetry:
metrics:
readers:
- pull:
exporter:
prometheus:
host: 0.0.0.0
port: 8888
extensions: [health_check]
pipelines:
traces:
receivers: [otlp]
processors: [memory_limiter, batch]
exporters: [otlphttp/tempo]
metrics:
receivers: [otlp]
processors: [memory_limiter, batch]
exporters: [prometheus]
logs:
receivers: [otlp]
processors: [memory_limiter, batch]
exporters: [otlphttp/loki]
@@ -0,0 +1,10 @@
apiVersion: 1
providers:
- name: messenger
orgId: 1
folder: Highload applications
type: file
disableDeletion: true
editable: false
options:
path: /dashboards
@@ -0,0 +1,35 @@
apiVersion: 1
datasources:
- name: Prometheus
uid: prometheus
type: prometheus
access: proxy
url: http://messenger-prometheus:9090
isDefault: true
editable: false
- name: Loki
uid: loki
type: loki
access: proxy
url: http://messenger-loki:3100
editable: false
jsonData:
derivedFields:
- name: TraceID
matcherType: label
matcherRegex: trace_id
datasourceUid: tempo
url: '$${__value.raw}'
- name: Tempo
uid: tempo
type: tempo
access: proxy
url: http://messenger-tempo:3200
editable: false
jsonData:
tracesToLogsV2:
datasourceUid: loki
filterByTraceID: true
spanStartTimeShift: '-1m'
spanEndTimeShift: '1m'
tags: [{key: service.name, value: service_name}]
@@ -0,0 +1,41 @@
auth_enabled: false
server:
http_listen_port: 3100
common:
path_prefix: /data
replication_factor: 1
ring:
kvstore:
store: inmemory
storage:
filesystem:
chunks_directory: /data/chunks
rules_directory: /data/rules
schema_config:
configs:
- from: 2024-01-01
store: tsdb
object_store: filesystem
schema: v13
index:
prefix: index_
period: 24h
limits_config:
allow_structured_metadata: true
retention_period: 24h
ingestion_rate_mb: 2
ingestion_burst_size_mb: 4
otlp_config:
resource_attributes:
ignore_defaults: true
attributes_config:
- action: index_label
attributes: [service.name, deployment.environment.name]
- action: structured_metadata
attributes: [service.instance.id, service.version]
compactor:
working_directory: /data/compactor
retention_enabled: true
delete_request_store: filesystem
analytics:
reporting_enabled: false
@@ -0,0 +1,519 @@
{
"uid": "messenger",
"title": "Messenger: API, worker and SLO",
"schemaVersion": 41,
"version": 1,
"refresh": "5s",
"time": {
"from": "now-15m",
"to": "now"
},
"panels": [
{
"id": 1,
"title": "HTTP RPS",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 0,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum by (route) (rate(messenger_http_requests_total{route!~\"/health/.*|/metrics\"}[1m]))"
}
],
"fieldConfig": {
"defaults": {
"unit": "reqps"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 2,
"title": "API 5xx ratio",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 0,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum(rate(messenger_http_requests_total{status_class=\"5xx\",route!~\"/health/.*|/metrics\"}[1m])) / clamp_min(sum(rate(messenger_http_requests_total{route!~\"/health/.*|/metrics\"}[1m])),0.001)"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 3,
"title": "HTTP latency p50/p95/p99",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 8,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "histogram_quantile(0.5, sum by (le) (rate(messenger_http_duration_seconds_bucket{route!~\"/health/.*|/metrics\"}[1m])))"
},
{
"refId": "B",
"expr": "histogram_quantile(0.95, sum by (le) (rate(messenger_http_duration_seconds_bucket{route!~\"/health/.*|/metrics\"}[1m])))"
},
{
"refId": "C",
"expr": "histogram_quantile(0.99, sum by (le) (rate(messenger_http_duration_seconds_bucket{route!~\"/health/.*|/metrics\"}[1m])))"
}
],
"fieldConfig": {
"defaults": {
"unit": "s"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 4,
"title": "Jobs by outcome",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 8,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum by (outcome) (rate(messenger_jobs_total[1m]))"
}
],
"fieldConfig": {
"defaults": {
"unit": "ops"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 5,
"title": "Job duration p95",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 16,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "histogram_quantile(0.95, sum by (le) (rate(messenger_job_duration_seconds_bucket[1m])))"
}
],
"fieldConfig": {
"defaults": {
"unit": "s"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 6,
"title": "Time to ready p95",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 16,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "histogram_quantile(0.95, sum by (le) (rate(messenger_ready_duration_seconds_bucket[1m])))"
}
],
"fieldConfig": {
"defaults": {
"unit": "s"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 7,
"title": "Queue depth",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 24,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "max(messenger_queue_depth)"
}
],
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 8,
"title": "Oldest accepted job",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 24,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "max(messenger_queue_oldest_seconds)"
}
],
"fieldConfig": {
"defaults": {
"unit": "s"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 9,
"title": "DB pool used/waiting",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 32,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum(messenger_db_pool_used)"
},
{
"refId": "B",
"expr": "sum(messenger_db_pool_waiting)"
}
],
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 10,
"title": "Worker saturation",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 32,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum(messenger_worker_busy) / clamp_min(sum(messenger_worker_capacity),1)"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 11,
"title": "Process CPU",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 40,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum by (service_name) (rate(messenger_process_cpu_seconds_total[1m]))"
}
],
"fieldConfig": {
"defaults": {
"unit": "cores"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 12,
"title": "Process peak RSS",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 40,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "max by (service_name) (messenger_process_peak_rss_bytes)"
}
],
"fieldConfig": {
"defaults": {
"unit": "bytes"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 13,
"title": "Collector queue and failed exports",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 48,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "sum(otelcol_exporter_queue_size)"
},
{
"refId": "B",
"expr": "sum(rate(otelcol_exporter_send_failed_spans_total[1m]))"
}
],
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
},
{
"id": 14,
"title": "Active alerts",
"type": "timeseries",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 48,
"w": 12,
"h": 8
},
"targets": [
{
"refId": "A",
"expr": "ALERTS{alertstate=\"firing\"}"
}
],
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": [
]
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
}
}
}
]
}
@@ -0,0 +1,12 @@
global:
scrape_interval: 5s
evaluation_interval: 5s
rule_files:
- /config/alerts.yaml
scrape_configs:
- job_name: messenger
static_configs:
- targets: ['messenger-collector:8889']
- job_name: collector
static_configs:
- targets: ['messenger-collector:8888']
@@ -0,0 +1,24 @@
server:
http_listen_port: 3200
distributor:
receivers:
otlp:
protocols:
grpc:
endpoint: 0.0.0.0:4317
http:
endpoint: 0.0.0.0:4318
storage:
trace:
backend: local
wal:
path: /data/wal
local:
path: /data/blocks
compactor:
compaction:
block_retention: 24h
ingester:
max_block_duration: 5m
usage_report:
reporting_enabled: false
+7
View File
@@ -0,0 +1,7 @@
{{- define "messenger.shards" -}}
{{- $nodes := list -}}
{{- range $i := until (int .Values.valkey.shards) -}}
{{- $nodes = append $nodes (printf "shard%d=valkey-%d.valkey:6379" $i $i) -}}
{{- end -}}
{{- join "," $nodes -}}
{{- end -}}
+140
View File
@@ -0,0 +1,140 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: messenger-config
namespace: {{ .Release.Namespace }}
data:
APP_PORT: '8080'
{{- if .Values.observability.enabled }}
OTEL_EXPORTER_OTLP_ENDPOINT: http://messenger-collector:4318
OTEL_SAMPLE_RATIO: '1'
APP_VERSION: lab6
{{- end }}
VALKEY_COORDINATOR: shard0
VALKEY_SHARDS: {{ include "messenger.shards" . | quote }}
{{- range $key, $value := .Values.api.env }}
{{ $key }}: {{ $value | quote }}
{{- end }}
---
apiVersion: v1
kind: Service
metadata:
labels:
app: api
name: api
namespace: {{ .Release.Namespace }}
spec:
selector:
app: api
ports:
- name: http
port: 8080
targetPort: 8080
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: api
namespace: {{ .Release.Namespace }}
spec:
{{- if not .Values.autoscaling.enabled }}
replicas: {{ .Values.api.replicas }}
{{- end }}
strategy:
rollingUpdate:
maxUnavailable: 0
maxSurge: 1
selector:
matchLabels:
app: api
template:
metadata:
annotations:
checksum/config: {{ printf "%s%s" (include "messenger.shards" .) (toJson .Values.api.env) | sha256sum }}
labels:
app: api
spec:
{{- with .Values.api.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
imagePullSecrets:
- name: {{ .Values.imagePullSecret }}
terminationGracePeriodSeconds: 20
topologySpreadConstraints:
- maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
app: api
securityContext:
runAsNonRoot: true
runAsUser: 65532
seccompProfile:
type: RuntimeDefault
containers:
- name: api
image: "{{ .Values.image.repository }}@{{ .Values.image.digest }}"
imagePullPolicy: IfNotPresent
ports:
- containerPort: 8080
envFrom:
- configMapRef:
name: messenger-config
env:
- name: S3_ENDPOINT
value: s3:9000
- name: S3_BUCKET
value: {{ .Values.s3.bucket }}
- name: S3_TLS
value: "false"
- name: S3_ACCESS_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.s3.secret }}, key: access-key}
- name: S3_SECRET_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.s3.secret }}, key: secret-key}
- name: INSTANCE_ID
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: CURSOR_SIGNING_KEY
valueFrom:
secretKeyRef:
name: {{ .Values.databaseSecret }}
key: cursor-key
- name: DATABASE_URL
valueFrom:
secretKeyRef:
name: {{ .Values.databaseSecret }}
key: database-url
resources:
{{- toYaml .Values.api.resources | nindent 12 }}
lifecycle:
preStop:
sleep:
seconds: 3
startupProbe:
httpGet:
path: /health/ready
port: 8080
periodSeconds: 2
failureThreshold: 30
readinessProbe:
timeoutSeconds: {{ .Values.api.readiness.timeoutSeconds }}
failureThreshold: {{ .Values.api.readiness.failureThreshold }}
httpGet:
path: /health/ready
port: 8080
periodSeconds: 2
livenessProbe:
httpGet:
path: /health/live
port: 8080
periodSeconds: 5
securityContext:
readOnlyRootFilesystem: true
allowPrivilegeEscalation: false
capabilities:
drop: [ALL]
+7
View File
@@ -0,0 +1,7 @@
{{- $live := lookup "v1" "ConfigMap" .Release.Namespace "messenger-config" -}}
{{- if and $live (ne (index $live.data "VALKEY_SHARDS") (include "messenger.shards" .)) -}}
{{- $api := lookup "apps/v1" "Deployment" .Release.Namespace "api" -}}
{{- if or (gt (int .Values.api.replicas) 0) (and $api (gt (int $api.spec.replicas) 0)) -}}
{{- fail "Changing shards requires drained API: use make reshard SHARDS=2 or SHARDS=3" -}}
{{- end -}}
{{- end -}}
+33
View File
@@ -0,0 +1,33 @@
{{- if .Values.autoscaling.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: api
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: api
minReplicas: {{ .Values.autoscaling.minReplicas }}
maxReplicas: {{ .Values.autoscaling.maxReplicas }}
metrics:
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.cpuPercent }}
behavior:
scaleUp:
stabilizationWindowSeconds: 15
policies:
- type: Pods
value: 1
periodSeconds: 30
scaleDown:
stabilizationWindowSeconds: 120
policies:
- type: Pods
value: 1
periodSeconds: 60
{{- end }}
+23
View File
@@ -0,0 +1,23 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: messenger
annotations:
cert-manager.io/cluster-issuer: {{ .Values.ingress.clusterIssuer | quote }}
spec:
ingressClassName: {{ .Values.ingress.className }}
tls:
- hosts:
- {{ .Values.ingress.host | quote }}
secretName: messenger-tls
rules:
- host: {{ .Values.ingress.host | quote }}
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: api
port:
number: 8080
+39
View File
@@ -0,0 +1,39 @@
{{- if .Values.load.enabled }}
apiVersion: batch/v1
kind: Job
metadata:
name: load-{{ .Values.load.run }}
spec:
backoffLimit: 0
activeDeadlineSeconds: 300
ttlSecondsAfterFinished: 86400
template:
metadata:
labels:
app: load
spec:
restartPolicy: Never
containers:
- name: k6
image: grafana/k6:1.3.0
args: [run, --quiet, /scripts/{{ .Values.load.script }}]
env:
- name: BASE_URL
value: "https://{{ .Values.ingress.host }}"
- name: TARGET_INSTANCE_ID
value: {{ .Values.load.target | default "" | quote }}
- name: DURATION
value: {{ .Values.load.duration | quote }}
- name: VUS
value: {{ .Values.load.vus | quote }}
resources:
requests: {cpu: 250m, memory: 128Mi}
limits: {cpu: '2', memory: 256Mi}
volumeMounts:
- name: scripts
mountPath: /scripts
volumes:
- name: scripts
configMap:
name: load-scripts
{{- end }}
+32
View File
@@ -0,0 +1,32 @@
apiVersion: batch/v1
kind: Job
metadata:
name: migrate-{{ .Release.Revision }}
spec:
activeDeadlineSeconds: 180
backoffLimit: 3
ttlSecondsAfterFinished: 86400
template:
metadata:
labels:
app: migrate
spec:
restartPolicy: OnFailure
imagePullSecrets:
- name: {{ .Values.imagePullSecret }}
containers:
- name: migrate
image: "{{ .Values.image.repository }}@{{ .Values.image.digest }}"
args: [migrate]
envFrom:
- configMapRef:
name: messenger-config
env:
- name: DATABASE_URL
valueFrom:
secretKeyRef:
name: {{ .Values.databaseSecret }}
key: database-url
resources:
requests: {cpu: 50m, memory: 32Mi}
limits: {cpu: 500m, memory: 128Mi}
@@ -0,0 +1,19 @@
{{- if .Values.monitoring.serviceMonitor }}
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: api
labels:
app: api
spec:
namespaceSelector:
matchNames: [{{ .Release.Namespace }}]
selector:
matchLabels:
app: api
endpoints:
- port: http
path: /metrics
interval: 15s
scrapeTimeout: 3s
{{- end }}
@@ -0,0 +1,59 @@
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: private-databases
namespace: {{ .Release.Namespace }}
spec:
podSelector:
matchExpressions:
- key: app
operator: In
values: [postgres, valkey]
policyTypes: [Ingress]
ingress:
- from:
- podSelector:
matchLabels: {app: worker}
ports:
- {protocol: TCP, port: 5432}
- from:
- podSelector:
matchLabels:
app: api
ports:
- protocol: TCP
port: 5432
- protocol: TCP
port: 6379
- from:
- podSelector:
matchLabels:
app: migrate
ports:
- protocol: TCP
port: 5432
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: private-api
spec:
podSelector:
matchLabels:
app: api
policyTypes: [Ingress]
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik
ports:
- protocol: TCP
port: 8080
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: monitoring
ports:
- protocol: TCP
port: 8080
@@ -0,0 +1,124 @@
{{- if .Values.observability.enabled }}
apiVersion: v1
kind: ConfigMap
metadata:
name: messenger-observability
labels: {app: messenger-observability}
data:
{{- range $path, $_ := .Files.Glob "files/observability/*" }}
{{ base $path }}: |
{{ $.Files.Get $path | indent 4 }}
{{- end }}
{{- $components := list
(dict "name" "collector" "image" .Values.observability.collectorImage "port" 4318 "args" (list "--config=/config/collector.yaml") "memory" "256Mi" "uid" 10001)
(dict "name" "prometheus" "image" .Values.observability.prometheusImage "port" 9090 "args" (list "--config.file=/config/prometheus.yaml" "--storage.tsdb.path=/data" "--storage.tsdb.retention.time=24h" "--storage.tsdb.retention.size=1GB") "memory" "384Mi" "uid" 65534)
(dict "name" "loki" "image" .Values.observability.lokiImage "port" 3100 "args" (list "-config.file=/config/loki.yaml") "memory" "384Mi" "uid" 10001)
(dict "name" "tempo" "image" .Values.observability.tempoImage "port" 3200 "args" (list "-config.file=/config/tempo.yaml") "memory" "384Mi" "uid" 10001)
(dict "name" "grafana" "image" .Values.observability.grafanaImage "port" 3000 "args" list "memory" "256Mi" "uid" 472)
}}
{{- range $component := $components }}
---
apiVersion: v1
kind: Service
metadata:
name: messenger-{{ $component.name }}
spec:
selector: {app: 'messenger-{{ $component.name }}'}
ports:
- {name: http, port: {{ $component.port }}, targetPort: {{ $component.port }}}
{{- if eq $component.name "collector" }}
- {name: metrics, port: 8889, targetPort: 8889}
- {name: self-metrics, port: 8888, targetPort: 8888}
{{- end }}
{{- if eq $component.name "tempo" }}
- {name: otlp, port: 4318, targetPort: 4318}
{{- end }}
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: messenger-{{ $component.name }}
spec:
serviceName: messenger-{{ $component.name }}
replicas: 1
selector:
matchLabels: {app: 'messenger-{{ $component.name }}'}
template:
metadata:
labels: {app: 'messenger-{{ $component.name }}'}
annotations:
checksum/config: {{ ($.Files.Glob "files/observability/*").AsConfig | sha256sum }}
spec:
securityContext:
runAsNonRoot: true
runAsUser: {{ $component.uid }}
fsGroup: {{ $component.uid }}
containers:
- name: {{ $component.name }}
image: {{ $component.image }}
args: {{ $component.args | toJson }}
ports:
- {containerPort: {{ $component.port }}}
resources:
requests: {cpu: 50m, memory: 96Mi}
limits: {cpu: '1', memory: {{ $component.memory }}}
readinessProbe:
tcpSocket: {port: {{ $component.port }}}
{{- if eq $component.name "grafana" }}
env:
- {name: GF_PATHS_DATA, value: /data}
- {name: GF_AUTH_ANONYMOUS_ENABLED, value: 'false'}
- {name: GF_USERS_ALLOW_SIGN_UP, value: 'false'}
- {name: GF_ANALYTICS_REPORTING_ENABLED, value: 'false'}
- name: GF_SECURITY_ADMIN_USER
valueFrom:
secretKeyRef: {name: {{ $.Values.observability.secret }}, key: username}
- name: GF_SECURITY_ADMIN_PASSWORD
valueFrom:
secretKeyRef: {name: {{ $.Values.observability.secret }}, key: password}
{{- end }}
volumeMounts:
- {name: data, mountPath: /data}
- {name: config, mountPath: /config, readOnly: true}
{{- if eq $component.name "grafana" }}
- {name: config, mountPath: /etc/grafana/provisioning/datasources/datasources.yaml, subPath: datasources.yaml, readOnly: true}
- {name: config, mountPath: /etc/grafana/provisioning/dashboards/dashboards.yaml, subPath: dashboards.yaml, readOnly: true}
- {name: config, mountPath: /dashboards/messenger.json, subPath: messenger.json, readOnly: true}
{{- end }}
volumes:
- name: config
configMap: {name: messenger-observability}
volumeClaimTemplates:
- metadata: {name: data}
spec:
accessModes: [ReadWriteOnce]
{{- if $.Values.storageClass }}
storageClassName: {{ $.Values.storageClass | quote }}
{{- end }}
resources:
requests: {storage: 2Gi}
{{- end }}
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: private-observability
spec:
podSelector:
matchExpressions:
- {key: app, operator: In, values: [messenger-collector, messenger-prometheus, messenger-loki, messenger-tempo, messenger-grafana]}
policyTypes: [Ingress]
ingress:
- from:
- podSelector:
matchExpressions:
- {key: app, operator: In, values: [api, worker, messenger-collector, messenger-prometheus, messenger-loki, messenger-tempo, messenger-grafana]}
ports:
- {protocol: TCP, port: 4318}
- {protocol: TCP, port: 8888}
- {protocol: TCP, port: 8889}
- {protocol: TCP, port: 9090}
- {protocol: TCP, port: 3100}
- {protocol: TCP, port: 3200}
- {protocol: TCP, port: 3000}
{{- end }}
+66
View File
@@ -0,0 +1,66 @@
apiVersion: v1
kind: Service
metadata:
name: postgres
namespace: {{ .Release.Namespace }}
spec:
selector:
app: postgres
ports:
- port: 5432
targetPort: 5432
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: postgres
namespace: {{ .Release.Namespace }}
spec:
serviceName: postgres
replicas: 1
selector:
matchLabels:
app: postgres
template:
metadata:
labels:
app: postgres
spec:
terminationGracePeriodSeconds: 30
containers:
- name: postgres
image: {{ .Values.postgres.image | quote }}
ports:
- containerPort: 5432
env:
- name: POSTGRES_DB
value: messenger
- name: POSTGRES_USER
value: messenger
- name: POSTGRES_PASSWORD
valueFrom:
secretKeyRef:
name: {{ .Values.databaseSecret }}
key: postgres-password
- name: PGDATA
value: /var/lib/postgresql/data/pgdata
resources:
{{- toYaml .Values.postgres.resources | nindent 12 }}
readinessProbe:
exec:
command: [pg_isready, -U, messenger, -d, messenger]
initialDelaySeconds: 3
volumeMounts:
- name: data
mountPath: /var/lib/postgresql/data
volumeClaimTemplates:
- metadata:
name: data
spec:
{{- if .Values.storageClass }}
storageClassName: {{ .Values.storageClass | quote }}
{{- end }}
accessModes: [ReadWriteOnce]
resources:
requests:
storage: {{ .Values.postgres.storage }}
+97
View File
@@ -0,0 +1,97 @@
apiVersion: v1
kind: Service
metadata:
name: s3
spec:
selector: {app: s3}
ports:
- {name: s3, port: 9000, targetPort: 9000}
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: s3
spec:
serviceName: s3
replicas: 1
selector:
matchLabels: {app: s3}
template:
metadata:
labels: {app: s3}
spec:
securityContext:
runAsUser: 1000
runAsNonRoot: true
fsGroup: 1000
containers:
- name: s3
image: {{ .Values.s3.image }}
args: [server, -dir=/data, -s3, -s3.port=9000, -s3.config=/identity/identities.json, -master.volumeSizeLimitMB=100, -volume.max=32]
ports: [{containerPort: 9000}]
readinessProbe:
tcpSocket: {port: 9000}
resources:
requests: {cpu: 100m, memory: 256Mi}
limits: {cpu: '1', memory: 512Mi}
securityContext:
allowPrivilegeEscalation: false
capabilities: {drop: [ALL]}
volumeMounts:
- {name: objects, mountPath: /data}
- {name: identity, mountPath: /identity, readOnly: true}
volumes:
- name: identity
secret: {secretName: {{ .Values.s3.secret }}, items: [{key: identities.json, path: identities.json}]}
volumeClaimTemplates:
- metadata: {name: objects}
spec:
accessModes: [ReadWriteOnce]
resources:
requests: {storage: {{ .Values.s3.storage }}}
---
apiVersion: batch/v1
kind: Job
metadata:
name: s3-bootstrap-{{ .Release.Revision }}
spec:
ttlSecondsAfterFinished: 3600
backoffLimit: 4
template:
metadata:
labels: {app: s3-bootstrap}
spec:
restartPolicy: OnFailure
imagePullSecrets: [{name: {{ .Values.imagePullSecret }}}]
containers:
- name: bootstrap
image: "{{ .Values.image.repository }}@{{ .Values.image.digest }}"
args: [s3-bootstrap]
env:
- {name: S3_ENDPOINT, value: 's3:9000'}
- {name: S3_TLS, value: 'false'}
- {name: S3_BUCKET, value: {{ .Values.s3.bucket }}}
- name: S3_ACCESS_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.s3.secret }}, key: root-user}
- name: S3_SECRET_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.s3.secret }}, key: root-password}
resources:
requests: {cpu: 50m, memory: 64Mi}
limits: {cpu: 200m, memory: 128Mi}
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: private-s3
spec:
podSelector:
matchLabels: {app: s3}
policyTypes: [Ingress]
ingress:
- from:
- podSelector:
matchExpressions:
- {key: app, operator: In, values: [api, worker, s3-bootstrap, reconcile]}
ports: [{protocol: TCP, port: 9000}]
+57
View File
@@ -0,0 +1,57 @@
apiVersion: v1
kind: Service
metadata:
name: valkey
namespace: {{ .Release.Namespace }}
spec:
clusterIP: None
selector:
app: valkey
ports:
- port: 6379
targetPort: 6379
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: valkey
namespace: {{ .Release.Namespace }}
spec:
serviceName: valkey
replicas: {{ .Values.valkey.shards }}
podManagementPolicy: Parallel
selector:
matchLabels:
app: valkey
template:
metadata:
labels:
app: valkey
spec:
terminationGracePeriodSeconds: 30
containers:
- name: valkey
image: {{ .Values.valkey.image | quote }}
args: [valkey-server, --appendonly, 'yes', --appendfsync, always, --maxmemory, {{ .Values.valkey.maxmemory | quote }}, --maxmemory-policy, noeviction]
ports:
- containerPort: 6379
resources:
{{- toYaml .Values.valkey.resources | nindent 12 }}
readinessProbe:
exec:
command: [valkey-cli, ping]
initialDelaySeconds: 2
volumeMounts:
- name: data
mountPath: /data
volumeClaimTemplates:
- metadata:
name: data
spec:
{{- if .Values.storageClass }}
storageClassName: {{ .Values.storageClass | quote }}
{{- end }}
accessModes: [ReadWriteOnce]
resources:
requests:
storage: {{ .Values.valkey.storage }}
+111
View File
@@ -0,0 +1,111 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: worker
spec:
replicas: {{ .Values.worker.replicas }}
selector:
matchLabels: {app: worker}
template:
metadata:
labels: {app: worker}
spec:
imagePullSecrets:
- name: {{ .Values.imagePullSecret }}
terminationGracePeriodSeconds: 60
securityContext:
runAsNonRoot: true
runAsUser: 65532
seccompProfile: {type: RuntimeDefault}
containers:
- name: worker
image: "{{ .Values.image.repository }}@{{ .Values.image.digest }}"
args: [worker]
resources:
requests: {cpu: 250m, memory: 256Mi}
limits: {cpu: '1', memory: 1Gi}
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities: {drop: [ALL]}
envFrom:
- configMapRef: {name: messenger-config}
env:
- {name: GOMEMLIMIT, value: 768MiB}
- {name: BROKER_ADDRESS, value: 'broker:6379'}
- {name: S3_ENDPOINT, value: 's3:9000'}
- {name: S3_TLS, value: 'false'}
- name: S3_BUCKET
value: {{ .Values.s3.bucket }}
- name: DATABASE_URL
valueFrom:
secretKeyRef: {name: {{ .Values.databaseSecret }}, key: database-url}
- name: CURSOR_SIGNING_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.databaseSecret }}, key: cursor-key}
- name: S3_ACCESS_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.s3.secret }}, key: access-key}
- name: S3_SECRET_KEY
valueFrom:
secretKeyRef: {name: {{ .Values.s3.secret }}, key: secret-key}
---
apiVersion: v1
kind: Service
metadata:
name: broker
spec:
selector: {app: broker}
ports:
- {name: streams, port: 6379}
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: broker
spec:
serviceName: broker
replicas: 1
selector:
matchLabels: {app: broker}
template:
metadata:
labels: {app: broker}
spec:
containers:
- name: broker
image: {{ .Values.valkey.image }}
args: [valkey-server, --appendonly, 'yes', --appendfsync, always, --maxmemory, 128mb, --maxmemory-policy, noeviction]
resources:
requests: {cpu: 100m, memory: 160Mi}
limits: {cpu: '1', memory: 256Mi}
ports:
- {containerPort: 6379}
readinessProbe:
exec: {command: [valkey-cli, ping]}
volumeMounts:
- {name: data, mountPath: /data}
volumeClaimTemplates:
- metadata: {name: data}
spec:
accessModes: [ReadWriteOnce]
{{- if .Values.storageClass }}
storageClassName: {{ .Values.storageClass | quote }}
{{- end }}
resources:
requests: {storage: 1Gi}
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: private-broker
spec:
podSelector:
matchLabels: {app: broker}
policyTypes: [Ingress]
ingress:
- from:
- podSelector:
matchLabels: {app: worker}
ports:
- {protocol: TCP, port: 6379}
+9
View File
@@ -0,0 +1,9 @@
{
"$schema": "https://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"valkey": {"type": "object", "properties": {"shards": {"type": "integer", "minimum": 2, "maximum": 3}}},
"api": {"type": "object", "properties": {"replicas": {"type": "integer", "minimum": 0}}},
"image": {"type": "object", "properties": {"digest": {"type": "string", "pattern": "^sha256:[a-f0-9]{64}$"}}}
}
}
+76
View File
@@ -0,0 +1,76 @@
# Existing lab2 release; shared persistent stores and credentials.
image:
repository: asisti.registry.twcstorage.ru/mtusi2026lab6
digest: sha256:04a28492ad5645ed56c58d51a95214a758426adc2b0271fc184e8f204c3fa7cc
imagePullSecret: registry-pull
databaseSecret: messenger-secrets
api:
readiness:
timeoutSeconds: 2
failureThreshold: 2
replicas: 2
resources:
requests: {cpu: 250m, memory: 128Mi}
limits: {cpu: '1', memory: 768Mi}
env:
SESSION_TTL_SECONDS: '3600'
DEPENDENCY_TIMEOUT_MS: '2000'
DEPENDENCY_POOL_SIZE: '8'
REQUEST_TIMEOUT_SECONDS: '4'
SHUTDOWN_TIMEOUT_SECONDS: '5'
GOMEMLIMIT: 640MiB
MAX_CONNECTIONS: '16'
MAX_BODY_BYTES: '10485760'
postgres:
image: postgres:17.6-alpine
storage: 2Gi
resources:
requests: {cpu: 250m, memory: 256Mi}
limits: {cpu: '1', memory: 512Mi}
valkey:
image: valkey/valkey:8.1.3-alpine
shards: 3
storage: 1Gi
maxmemory: 64mb
resources:
requests: {cpu: 100m, memory: 96Mi}
limits: {cpu: 500m, memory: 128Mi}
# Пустое значение использует default StorageClass. Задать до первой установки.
storageClass: ''
autoscaling:
enabled: true
minReplicas: 2
maxReplicas: 4
cpuPercent: 60
monitoring:
serviceMonitor: false
load:
enabled: false
run: manual
script: scaling.js
duration: 30
vus: 32
ingress:
host: hl.agapov.space
className: traefik
clusterIssuer: letsencrypt-prod
s3:
image: chrislusf/seaweedfs:3.85@sha256:49312939c00c01e5ee6afbd7d728b18027821d3764c35a797a72acd4fdf3296a
secret: messenger-s3
bucket: attachments
storage: 5Gi
worker:
replicas: 1
observability:
enabled: true
collectorImage: otel/opentelemetry-collector-contrib:0.135.0@sha256:89107a3a8f4636a396927edf7025bb9614b8da2d92f4cc3f43109e8d115736e2
prometheusImage: prom/prometheus:v3.5.0@sha256:63805ebb8d2b3920190daf1cb14a60871b16fd38bed42b857a3182bc621f4996
lokiImage: grafana/loki:3.5.5@sha256:31628519045e7f28692a7ae73b4a3fd293dccb425585ed5d16ceea3b5c9592e6
tempoImage: grafana/tempo:2.8.2@sha256:0ef775495967cd5d7a6b2e146b6ea695d624803c8db8349fb8ce4164f719f9b7
grafanaImage: grafana/grafana:12.1.1@sha256:a1701c2180249361737a99a01bc770db39381640e4d631825d38ff4535efa47d
secret: messenger-grafana
+106
View File
@@ -0,0 +1,106 @@
package main
import (
"time"
"go.uber.org/fx"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/admission"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller"
fiberctrl "gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller/http/fiber"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/cursor"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/password"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service/production"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/valkey"
)
const applicationStopTimeout = 9 * time.Second
// CreateApp defines the dependency graph and Fx lifecycle for the lab2 server.
// Constructors do not open sockets; controller.RunControllerFx registers startup
// and shutdown hooks. The outer stop deadline bounds all component cleanup.
func CreateApp() fx.Option {
return fx.Options(
fx.StopTimeout(applicationStopTimeout),
fx.Supply(fx.Annotate(password.Hasher{}, fx.As(new(service.Passwords)))),
fx.Provide(
config.New,
config.NewPersistence,
config.NewObjectStore,
apiTelemetry,
observedObjects,
newMedia,
observedDatabase,
newValkey,
newAuthentication,
fx.Annotate(newMediaReadiness, fx.As(new(fiberctrl.Readiness))),
httpConfig,
loggerConfig,
newLogger,
fx.Annotate(newAdmissionLimiter, fx.As(new(admission.Distributed))),
fiberctrl.NewErrorRegistry,
fx.Annotate(databaseStore, fx.As(new(store.Interface))),
fx.Annotate(databaseAccounts, fx.As(new(service.Accounts))),
fx.Annotate(profileCache, fx.As(new(service.ProfileCache))),
fx.Annotate(newCursor, fx.As(new(service.CursorCodec))),
fx.Annotate(production.NewCached, fx.As(new(service.Service))),
fx.Annotate(observedHTTP, fx.As(new(controller.Controller))),
),
fx.WithLogger(newFxLogger),
fx.Invoke(controller.RunControllerFx, observeAPI),
)
}
// httpConfig provides the HTTP configuration section to Fx.
func httpConfig(cfg *config.Config) *config.Controller {
return cfg.HTTP
}
// loggerConfig provides the logging configuration section to Fx.
func loggerConfig(cfg *config.Config) *config.Logger {
return cfg.Logger
}
// newAdmissionLimiter translates configured bounds into separate shared policy budgets.
func newAdmissionLimiter(cfg *config.Controller, client *valkey.Client) (*valkey.Limiter, error) {
global := valkey.Budget{Rate: cfg.Admission.RequestsPerSecond, Slots: cfg.Admission.MaxInFlight}
return valkey.NewLimiter(client, valkey.Limits{
Global: global,
Groups: map[string]valkey.Budget{
"auth": {Rate: cfg.Admission.AuthRate, Slots: cfg.Admission.AuthSlots},
"read": global,
"write": global,
},
User: valkey.Budget{Rate: cfg.Admission.UserRate, Slots: cfg.Admission.UserSlots},
UserGroups: map[string]valkey.Budget{
"auth": {Rate: cfg.Admission.UserAuthRate, Slots: cfg.Admission.UserAuthSlots},
"read": {Rate: cfg.Admission.UserRate, Slots: cfg.Admission.UserSlots},
"write": {Rate: cfg.Admission.UserWriteRate, Slots: cfg.Admission.UserWriteSlots},
},
})
}
// databaseStore exposes business persistence through its consumer interface.
func databaseStore(database *postgres.Store) store.Interface {
return database
}
// databaseAccounts exposes account and session persistence through its consumer interface.
func databaseAccounts(database *postgres.Store) service.Accounts {
return database
}
// profileCache exposes immutable profiles without leaking the Valkey client.
func profileCache(client *valkey.Client) service.ProfileCache {
return client
}
// newCursor binds the shared signing secret at the composition root.
func newCursor(cfg *config.Persistence) (*cursor.Codec, error) {
return cursor.NewShared(cfg.CursorKey)
}
+108
View File
@@ -0,0 +1,108 @@
package main
import (
"context"
"net"
"os"
"testing"
"time"
"go.uber.org/fx"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
// TestDependencyGraph ensures constructor signatures and interface bindings agree.
func TestDependencyGraph(t *testing.T) {
if err := fx.ValidateApp(CreateApp(), fx.NopLogger); err != nil {
t.Fatal(err)
}
}
// TestInvalidConfigurationStopsStartup checks failure before a listener is acquired.
func TestInvalidConfigurationStopsStartup(t *testing.T) {
t.Setenv("APP_PORT", "0")
app := fx.New(CreateApp(), fx.NopLogger)
if err := app.Start(context.Background()); err == nil {
t.Fatal("invalid listener configuration accepted")
}
}
// TestCommandValidation ensures unsupported arguments cannot accidentally start a server.
func TestCommandValidation(t *testing.T) {
if err := run([]string{"unknown"}); err == nil {
t.Fatal("unknown command accepted")
}
}
// TestLoggerConfiguration checks that process logging uses its own validated section.
func TestLoggerConfiguration(t *testing.T) {
if _, err := newLogger(&config.Logger{Level: "invalid"}); err == nil {
t.Fatal("invalid logger configuration accepted")
}
}
// TestApplicationLifecycle starts the complete Fx graph and drains its real HTTP listener.
func TestApplicationLifecycle(t *testing.T) {
requirePersistence(t)
listener, err := net.Listen("tcp", "127.0.0.1:0")
if err != nil {
t.Fatal(err)
}
cfg := config.Default()
cfg.HTTP.Host = "127.0.0.1"
cfg.HTTP.Port = listener.Addr().(*net.TCPAddr).Port
cfg.Logger.Level = "error"
if err := listener.Close(); err != nil {
t.Fatal(err)
}
app := fx.New(CreateApp(), fx.Replace(cfg))
ctx, cancel := context.WithTimeout(t.Context(), 5*time.Second)
defer cancel()
if err := app.Start(ctx); err != nil {
t.Fatal(err)
}
t.Cleanup(func() {
stopCtx, stopCancel := context.WithTimeout(context.Background(), 5*time.Second)
defer stopCancel()
if err := app.Stop(stopCtx); err != nil {
t.Error(err)
}
})
if err := checkReadiness(cfg.HTTP); err != nil {
t.Fatal(err)
}
}
// TestOccupiedListenerFailsStartup ensures bind failures propagate through the Fx lifecycle.
func TestOccupiedListenerFailsStartup(t *testing.T) {
requirePersistence(t)
listener, err := net.Listen("tcp", "127.0.0.1:0")
if err != nil {
t.Fatal(err)
}
defer func() {
_ = listener.Close()
}()
cfg := config.Default()
cfg.HTTP.Host = "127.0.0.1"
cfg.HTTP.Port = listener.Addr().(*net.TCPAddr).Port
cfg.Logger.Level = "error"
app := fx.New(CreateApp(), fx.Replace(cfg), fx.NopLogger)
if err := app.Start(t.Context()); err == nil {
_ = app.Stop(t.Context())
t.Fatal("startup succeeded on an occupied listener")
}
}
// requirePersistence prevents infrastructure scenarios from silently passing on configuration failure.
func requirePersistence(t *testing.T) {
t.Helper()
if os.Getenv("DATABASE_URL") == "" || os.Getenv("VALKEY_SHARDS") == "" {
t.Skip("DATABASE_URL and VALKEY_SHARDS are required for real application lifecycle tests")
}
t.Setenv("CURSOR_SIGNING_KEY", "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=")
if err := migrate(); err != nil {
t.Fatal(err)
}
}
+57
View File
@@ -0,0 +1,57 @@
package main
import (
"context"
"fmt"
"time"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
"go.uber.org/fx"
)
// run dispatches the server command or the container healthcheck.
func run(args []string) error {
if len(args) == 1 && args[0] == "worker" {
fx.New(workerApp()).Run()
return nil
}
if len(args) == 3 && args[0] == "replay" {
return replayJob(args[1], args[2])
}
if len(args) == 1 && args[0] == "s3-bootstrap" {
return bootstrapS3()
}
if len(args) == 0 {
fx.New(CreateApp()).Run()
return nil
}
if len(args) == 1 && args[0] == "reconcile" {
return reconcile(false)
}
if len(args) == 2 && args[0] == "reconcile" && args[1] == "--apply" {
return reconcile(true)
}
if len(args) == 1 && args[0] == "migrate" {
return migrate()
}
if len(args) == 1 && args[0] == "healthcheck" {
return healthcheck()
}
return fmt.Errorf("usage: server [healthcheck|migrate]")
}
// migrate applies versioned DDL once from an operator job, independently of the API.
func migrate() error {
cfg, err := config.NewPersistence()
if err != nil {
return err
}
database, err := postgres.New(postgres.Options{URL: cfg.DatabaseURL, MaxConnections: 1, Timeout: 30 * time.Second})
if err != nil {
return err
}
defer database.Close()
return database.Start(context.Background())
}
+46
View File
@@ -0,0 +1,46 @@
package main
import (
"fmt"
"net"
"net/http"
"strconv"
"time"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
const readinessProbeTimeout = 2 * time.Second
// healthcheck loads configuration and runs the container readiness probe.
func healthcheck() error {
cfg, err := config.New()
if err != nil {
return err
}
return checkReadiness(cfg.HTTP)
}
// checkReadiness checks the local readiness endpoint within the probe timeout.
func checkReadiness(cfg *config.Controller) error {
host := cfg.Host
if host == "0.0.0.0" {
host = "127.0.0.1"
}
if host == "::" {
host = "::1"
}
address := "http://" + net.JoinHostPort(host, strconv.Itoa(cfg.Port)) + "/health/ready"
client := http.Client{Timeout: readinessProbeTimeout}
response, err := client.Get(address)
if err != nil {
return fmt.Errorf("readiness probe: %w", err)
}
defer func() {
_ = response.Body.Close()
}()
if response.StatusCode != http.StatusOK {
return fmt.Errorf("not ready: %d", response.StatusCode)
}
return nil
}
+111
View File
@@ -0,0 +1,111 @@
package main
import (
"errors"
"net"
"net/http"
"net/http/httptest"
"net/url"
"strconv"
"testing"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
// TestRun_Healthcheck verifies command routing to the readiness endpoint.
func TestRun_Healthcheck(t *testing.T) {
// Arrange.
requests := make(chan string, 1)
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
requests <- r.Method + " " + r.URL.Path
w.WriteHeader(http.StatusOK)
}))
t.Cleanup(server.Close)
address := server.Listener.Addr().(*net.TCPAddr)
t.Setenv("APP_HOST", "0.0.0.0")
t.Setenv("APP_PORT", strconv.Itoa(address.Port))
// Act.
err := run([]string{"healthcheck"})
// Assert.
if err != nil {
t.Fatal(err)
}
select {
case got := <-requests:
if got != "GET /health/ready" {
t.Fatalf("probe=%q", got)
}
default:
t.Fatal("command returned success without probing readiness")
}
}
// TestHealthcheck_InvalidConfig rejects invalid startup settings before attempting HTTP.
func TestHealthcheck_InvalidConfig(t *testing.T) {
// Arrange.
t.Setenv("APP_PORT", "invalid")
// Act.
err := healthcheck()
// Assert.
if err == nil {
t.Fatal("invalid port accepted")
}
}
// TestCheckReadiness distinguishes unhealthy responses from connection failures.
func TestCheckReadiness(t *testing.T) {
t.Run("Negative: unhealthy response", func(t *testing.T) {
// Arrange.
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusServiceUnavailable)
}))
t.Cleanup(server.Close)
address := server.Listener.Addr().(*net.TCPAddr)
cfg := config.Default().HTTP
cfg.Host = "127.0.0.1"
cfg.Port = address.Port
// Act.
err := checkReadiness(cfg)
// Assert.
if err == nil {
t.Fatalf("probe accepted %s", "Negative: unhealthy response")
}
if err.Error() != "not ready: 503" {
t.Fatalf("unexpected health failure: %v", err)
}
})
t.Run("Negative: server unavailable", func(t *testing.T) {
// Arrange.
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusServiceUnavailable)
}))
t.Cleanup(server.Close)
address := server.Listener.Addr().(*net.TCPAddr)
cfg := config.Default().HTTP
cfg.Host = "127.0.0.1"
cfg.Port = address.Port
server.Close()
// Act.
err := checkReadiness(cfg)
// Assert.
if err == nil {
t.Fatalf("probe accepted %s", "Negative: server unavailable")
}
if _, ok := errors.AsType[*url.Error](err); !ok {
t.Fatalf("connection failure was not preserved: %v", err)
}
})
}
+29
View File
@@ -0,0 +1,29 @@
package main
import (
"go.uber.org/fx/fxevent"
"go.uber.org/zap"
"go.uber.org/zap/zapcore"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
// newLogger creates a structured logger with the configured severity threshold.
func newLogger(cfg *config.Logger) (*zap.Logger, error) {
if err := cfg.Validate(); err != nil {
return nil, err
}
level, err := zapcore.ParseLevel(cfg.Level)
if err != nil {
return nil, err
}
settings := zap.NewProductionConfig()
settings.Level = zap.NewAtomicLevelAt(level)
settings.DisableStacktrace = true
return settings.Build()
}
// newFxLogger adapts the application logger for Fx lifecycle events.
func newFxLogger(log *zap.Logger) fxevent.Logger {
return &fxevent.ZapLogger{Logger: log.Named("fx")}
}
+15
View File
@@ -0,0 +1,15 @@
// Command server runs the messenger or its container readiness probe.
package main
import (
"fmt"
"os"
)
// main runs the selected command and reports failures to stderr.
func main() {
if err := run(os.Args[1:]); err != nil {
_, _ = fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
}
+39
View File
@@ -0,0 +1,39 @@
package main
import (
"go.lab260.ru/fielderr"
"go.uber.org/zap"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/admission"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
fiberctrl "gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller/http/fiber"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/media"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/valkey"
)
// newObjects binds the S3 adapter at the composition root.
func newObjects(cfg *config.ObjectStore) (*objectstore.Client, error) {
return objectstore.New(cfg)
}
// newMedia injects infrastructure through the media service's consumer interfaces.
func newMedia(database *postgres.Store, objects *objectstore.Client, chats service.Service) (*media.Service, error) {
return media.New(database, objects, chats)
}
// newHTTPController connects the independently tested transport and attachment service.
func newHTTPController(log *zap.Logger, cfg *config.Controller, svc service.Service, registry *fielderr.Registry, limiter admission.Distributed, auth service.Authentication, readiness fiberctrl.Readiness, attachments *media.Service) (*fiberctrl.Controller, error) {
ctrl, err := fiberctrl.New(log, cfg, svc, registry, limiter, auth, readiness)
if err != nil {
return nil, err
}
return ctrl.WithAttachments(attachments), nil
}
// newMediaReadiness includes private originals in the mandatory synchronous dependency path.
func newMediaReadiness(database *postgres.Store, cache *valkey.Client, objects *objectstore.Client) *dependencyReadiness {
return &dependencyReadiness{database: database, cache: cache, objects: objects}
}
+88
View File
@@ -0,0 +1,88 @@
package main
import (
"os"
"testing"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
// TestMediaHTTPConfigurationFailure rejects invalid listener settings before serving files.
func TestMediaHTTPConfigurationFailure(t *testing.T) {
if _, err := newHTTPController(nil, &config.Controller{}, nil, nil, nil, nil, nil, nil); err == nil {
t.Fatal("invalid HTTP composition accepted")
}
}
// TestReconcileConfigurationFailures checks operator commands fail closed before side effects.
func TestReconcileConfigurationFailures(t *testing.T) {
cases := []struct {
name string
key string
value string
}{
{"database missing", "DATABASE_URL", ""},
{"s3 missing", "S3_ENDPOINT", ""},
{"database malformed", "DATABASE_URL", "://invalid"},
{"s3 malformed", "S3_ENDPOINT", "http://invalid/path"},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Setenv("DATABASE_URL", "postgres://localhost/test")
t.Setenv("VALKEY_SHARDS", "shard0=localhost:6379")
t.Setenv("S3_ENDPOINT", "localhost:9000")
t.Setenv("S3_BUCKET", "attachments")
t.Setenv("S3_ACCESS_KEY", "test")
t.Setenv("S3_SECRET_KEY", "synthetic")
t.Setenv(tc.key, tc.value)
if err := run([]string{"reconcile"}); err == nil {
t.Fatal("invalid reconciliation configuration accepted")
}
})
}
}
// TestReconcileRealInventory verifies the operator command can scan both real dependencies.
func TestReconcileRealInventory(t *testing.T) {
requirePersistence(t)
if os.Getenv("S3_ENDPOINT") == "" {
t.Skip("isolated S3 required")
}
if err := run([]string{"reconcile"}); err != nil {
t.Fatal(err)
}
if err := run([]string{"reconcile", "--apply"}); err != nil {
t.Fatal(err)
}
}
// TestBootstrapConfigurationFailures rejects missing credentials and malformed endpoints.
func TestBootstrapConfigurationFailures(t *testing.T) {
t.Run("missing", func(t *testing.T) {
t.Setenv("S3_ENDPOINT", "")
if err := run([]string{"s3-bootstrap"}); err == nil {
t.Fatal("missing config accepted")
}
})
t.Run("malformed", func(t *testing.T) {
t.Setenv("S3_ENDPOINT", "http://invalid/path")
t.Setenv("S3_BUCKET", "attachments")
t.Setenv("S3_ACCESS_KEY", "test")
t.Setenv("S3_SECRET_KEY", "synthetic")
if err := run([]string{"s3-bootstrap"}); err == nil {
t.Fatal("malformed endpoint accepted")
}
})
}
// TestBootstrapExistingBucket verifies repeatable operator execution against the isolated bucket.
func TestBootstrapExistingBucket(t *testing.T) {
if os.Getenv("S3_ENDPOINT") == "" || os.Getenv("S3_ADMIN_SECRET") == "" {
t.Skip("isolated S3 operator credentials required")
}
t.Setenv("S3_ACCESS_KEY", "operator")
t.Setenv("S3_SECRET_KEY", os.Getenv("S3_ADMIN_SECRET"))
if err := run([]string{"s3-bootstrap"}); err != nil {
t.Fatal(err)
}
}
+98
View File
@@ -0,0 +1,98 @@
package main
import (
"context"
"time"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/telemetry"
"github.com/jackc/pgx/v5"
"go.uber.org/fx"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
fiberctrl "gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller/http/fiber"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service/authentication"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/valkey"
)
type dependencyReadiness struct {
database fiberctrl.Readiness
cache fiberctrl.Readiness
objects fiberctrl.Readiness
}
// Ping checks persistence and all limiter shards under a shared deadline.
func (d *dependencyReadiness) Ping(ctx context.Context) error {
if err := d.database.Ping(ctx); err != nil {
return err
}
if err := d.cache.Ping(ctx); err != nil {
return err
}
if d.objects != nil {
return d.objects.Ping(ctx)
}
return nil
}
// newDatabase creates the pool and registers its migration/start and shutdown hooks.
func newDatabase(lifecycle fx.Lifecycle, cfg *config.Persistence) (*postgres.Store, error) {
return databaseWithTracer(lifecycle, cfg, nil)
}
// observedDatabase binds the SDK tracer to the driver at composition time.
func observedDatabase(lifecycle fx.Lifecycle, cfg *config.Persistence, runtime *telemetry.Runtime) (*postgres.Store, error) {
return databaseWithTracer(lifecycle, cfg, runtime)
}
// databaseWithTracer creates and owns the optionally instrumented SQL pool.
func databaseWithTracer(lifecycle fx.Lifecycle, cfg *config.Persistence, tracer pgx.QueryTracer) (*postgres.Store, error) {
database, err := postgres.New(postgres.Options{
Tracer: tracer,
URL: cfg.DatabaseURL,
MaxConnections: int32(cfg.PoolSize),
Timeout: time.Duration(cfg.TimeoutMilliseconds) * time.Millisecond,
})
if err != nil {
return nil, err
}
lifecycle.Append(fx.Hook{
OnStart: database.CheckSchema,
OnStop: func(context.Context) error {
database.Close()
return nil
},
})
return database, nil
}
// newValkey creates bounded clients and registers connectivity and cleanup hooks.
func newValkey(lifecycle fx.Lifecycle, cfg *config.Persistence) (*valkey.Client, error) {
client, err := valkey.New(valkey.Options{
Nodes: cfg.Shards,
Coordinator: cfg.Coordinator,
PoolSize: cfg.PoolSize,
Timeout: time.Duration(cfg.TimeoutMilliseconds) * time.Millisecond,
})
if err != nil {
return nil, err
}
lifecycle.Append(fx.Hook{
OnStart: client.Ping,
OnStop: func(context.Context) error {
return client.Close()
},
})
return client, nil
}
// newAuthentication binds credentials and KDF implementations to authentication policy.
func newAuthentication(accounts service.Accounts, passwords service.Passwords, cfg *config.Persistence) (service.Authentication, error) {
return authentication.New(accounts, passwords, time.Duration(cfg.SessionTTLSeconds)*time.Second)
}
// newReadiness assembles infrastructure checks at the composition boundary.
func newReadiness(database *postgres.Store, cache *valkey.Client) *dependencyReadiness {
return &dependencyReadiness{database: database, cache: cache}
}
+66
View File
@@ -0,0 +1,66 @@
package main
import (
"testing"
"time"
"go.uber.org/fx"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
)
// TestDatabaseProviderRejectsInvalidConfiguration verifies dependency errors propagate before startup.
func TestDatabaseProviderRejectsInvalidConfiguration(t *testing.T) {
var lifecycle fx.Lifecycle
app := fx.New(fx.NopLogger, fx.Populate(&lifecycle))
if err := app.Err(); err != nil {
t.Fatal(err)
}
if _, err := newDatabase(lifecycle, &config.Persistence{}); err == nil {
t.Fatal("invalid database settings accepted")
}
}
// TestValkeyProviderRejectsInvalidConfiguration verifies the cache constructor is a real boundary.
func TestValkeyProviderRejectsInvalidConfiguration(t *testing.T) {
var lifecycle fx.Lifecycle
app := fx.New(fx.NopLogger, fx.Populate(&lifecycle))
if err := app.Err(); err != nil {
t.Fatal(err)
}
if _, err := newValkey(lifecycle, &config.Persistence{}); err == nil {
t.Fatal("invalid cache settings accepted")
}
}
// TestReadinessStopsAtUnavailableDatabase checks that mandatory persistence failure is visible.
func TestReadinessStopsAtUnavailableDatabase(t *testing.T) {
database, err := postgres.New(postgres.Options{URL: "postgres://localhost/test", MaxConnections: 1, Timeout: time.Second})
if err != nil {
t.Fatal(err)
}
database.Close()
readiness := newReadiness(database, nil)
if err := readiness.Ping(t.Context()); err == nil {
t.Fatal("closed database reported ready")
}
}
// TestMigrationCommandRejectsMissingConfiguration fails before opening a database.
func TestMigrationCommandRejectsMissingConfiguration(t *testing.T) {
t.Setenv("DATABASE_URL", "")
t.Setenv("VALKEY_SHARDS", "shard0=localhost:6379")
if err := run([]string{"migrate"}); err == nil {
t.Fatal("missing database configuration accepted")
}
}
// TestMigrationCommandRejectsMalformedDatabaseURL fails without logging credentials.
func TestMigrationCommandRejectsMalformedDatabaseURL(t *testing.T) {
t.Setenv("DATABASE_URL", "://invalid")
t.Setenv("VALKEY_SHARDS", "shard0=localhost:6379")
if err := run([]string{"migrate"}); err == nil {
t.Fatal("malformed database configuration accepted")
}
}
+43
View File
@@ -0,0 +1,43 @@
package main
import (
"context"
"os"
"time"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/media"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/pipeline"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
)
// reconcile runs a bounded dry-run scan unless the operator explicitly supplies apply.
func reconcile(apply bool) error {
cfg, err := config.NewPersistence()
if err != nil {
return err
}
s3, err := config.NewObjectStore()
if err != nil {
return err
}
database, err := postgres.New(postgres.Options{URL: cfg.DatabaseURL, MaxConnections: 1, Timeout: 5 * time.Second})
if err != nil {
return err
}
defer database.Close()
objects, err := objectstore.New(s3)
if err != nil {
return err
}
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
defer cancel()
if apply {
if _, err := pipeline.Cleanup(ctx, database, objects); err != nil {
return err
}
}
return media.RunReconciliation(ctx, database, objects, os.Stdout, apply)
}
+24
View File
@@ -0,0 +1,24 @@
package main
import (
"context"
"time"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore"
)
// bootstrapS3 creates the private bucket using separate operator credentials.
func bootstrapS3() error {
cfg, err := config.NewObjectStore()
if err != nil {
return err
}
objects, err := objectstore.New(cfg)
if err != nil {
return err
}
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
return objects.Bootstrap(ctx)
}
+93
View File
@@ -0,0 +1,93 @@
package main
import (
"context"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/admission"
fiberctrl "gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller/http/fiber"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/media"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service"
"go.lab260.ru/fielderr"
"go.uber.org/fx"
"go.uber.org/zap"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/telemetry"
)
// telemetryFor constructs one process-owned SDK runtime with bounded lifecycle shutdown.
func telemetryFor(lc fx.Lifecycle, service string) (*telemetry.Runtime, error) {
cfg, err := config.NewTelemetry(service)
if err != nil {
return nil, err
}
runtime, err := telemetry.New(context.Background(), cfg)
if err != nil {
return nil, err
}
lc.Append(fx.Hook{OnStop: runtime.Shutdown})
return runtime, nil
}
// apiTelemetry assigns the API's resource identity.
func apiTelemetry(lc fx.Lifecycle) (*telemetry.Runtime, error) {
return telemetryFor(lc, "messenger-api")
}
// workerTelemetry assigns the worker's resource identity.
func workerTelemetry(lc fx.Lifecycle) (*telemetry.Runtime, error) {
return telemetryFor(lc, "messenger-worker")
}
// observedObjects adds S3 operation spans at the infrastructure composition boundary.
func observedObjects(cfg *config.ObjectStore, runtime *telemetry.Runtime) (*objectstore.Client, error) {
client, err := newObjects(cfg)
if err != nil {
return nil, err
}
return client.WithTracer(runtime), nil
}
// observeAPI registers pool and backlog metrics outside the HTTP request path.
func observeAPI(runtime *telemetry.Runtime, database *postgres.Store) error {
return runtime.ObserveSaturation(database, false)
}
// observeWorker registers worker occupancy and database observations.
func observeWorker(runtime *telemetry.Runtime, database *postgres.Store) error {
return runtime.ObserveSaturation(database, true)
}
// observedHTTP binds the transport observer after constructing its business dependencies.
func observedHTTP(params observedHTTPParams) (*fiberctrl.Controller, error) {
ctrl, err := newHTTPController(params.Log, params.Config, params.Service, params.Errors, params.Limiter, params.Auth, params.Readiness, params.Attachments)
if err != nil {
return nil, err
}
return ctrl.WithObserver(params.Telemetry), nil
}
// observedHTTPParams declares the complete HTTP composition dependencies.
type observedHTTPParams struct {
fx.In
// Log emits process diagnostics.
Log *zap.Logger
// Config provides listener policy.
Config *config.Controller
// Service owns messaging operations.
Service service.Service
// Errors maps domain failures.
Errors *fielderr.Registry
// Limiter bounds shared admission.
Limiter admission.Distributed
// Auth resolves bearer sessions.
Auth service.Authentication
// Readiness checks mandatory dependencies.
Readiness fiberctrl.Readiness
// Attachments owns file authorization and intake.
Attachments *media.Service
// Telemetry observes safe transport metadata.
Telemetry *telemetry.Runtime
}
+29
View File
@@ -0,0 +1,29 @@
package main
import (
"testing"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
// TestTelemetryInvalidConfiguration rejects invalid sampling before lifecycle registration.
func TestTelemetryInvalidConfiguration(t *testing.T) {
t.Setenv("OTEL_SAMPLE_RATIO", "invalid")
if _, err := apiTelemetry(nil); err == nil {
t.Fatal("invalid sampling accepted")
}
}
// TestObservedObjectsInvalidEndpoint propagates S3 construction errors before instrumentation.
func TestObservedObjectsInvalidEndpoint(t *testing.T) {
if _, err := observedObjects(&config.ObjectStore{Endpoint: "http://invalid/path"}, nil); err == nil {
t.Fatal("invalid object endpoint accepted")
}
}
// TestObservedHTTPInvalidConfiguration rejects invalid listener settings before adding an observer.
func TestObservedHTTPInvalidConfiguration(t *testing.T) {
if _, err := observedHTTP(observedHTTPParams{Config: &config.Controller{}}); err == nil {
t.Fatal("invalid listener accepted")
}
}
+89
View File
@@ -0,0 +1,89 @@
package main
import (
"context"
"fmt"
"strconv"
"time"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/telemetry"
"github.com/google/uuid"
"go.uber.org/fx"
"go.uber.org/zap"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/imageprocessor"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/pipeline"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/streamqueue"
)
// workerApp composes an independently deployable worker with owned Fx lifecycle.
func workerApp() fx.Option {
return fx.Options(fx.StopTimeout(55*time.Second), fx.Provide(config.New, config.NewPersistence, config.NewObjectStore, config.NewWorker, loggerConfig, newLogger, workerTelemetry, observedDatabase, observedObjects, newQueue, imageprocessor.New, newWorker), fx.WithLogger(newFxLogger), fx.Invoke(startWorker, observeWorker))
}
// newQueue closes the queue after the worker has relinquished its processing loop.
func newQueue(lc fx.Lifecycle, cfg *config.Worker) (*streamqueue.Queue, error) {
queue, err := streamqueue.New(cfg.BrokerAddress, cfg.Consumer)
if err != nil {
return nil, err
}
lc.Append(fx.Hook{OnStop: func(context.Context) error {
return queue.Close()
}})
return queue, nil
}
// newWorker binds concrete adapters only at the composition root.
func newWorker(database *postgres.Store, queue *streamqueue.Queue, objects *objectstore.Client, processor *imageprocessor.Processor, log *zap.Logger, runtime *telemetry.Runtime) (*pipeline.Worker, error) {
worker, err := pipeline.New(database, queue, objects, processor, log)
if err != nil {
return nil, err
}
return worker.WithObserver(runtime), nil
}
// startWorker owns the background context and joins its goroutine during shutdown.
func startWorker(lc fx.Lifecycle, worker *pipeline.Worker) {
ctx, cancel := context.WithCancel(context.Background())
done := make(chan struct{})
lc.Append(fx.Hook{OnStart: func(context.Context) error {
go func() {
defer close(done)
worker.Run(ctx)
}()
return nil
}, OnStop: func(stop context.Context) error {
cancel()
select {
case <-done:
return nil
case <-stop.Done():
return stop.Err()
}
}})
}
// replayJob explicitly retries a failed version or advances a pipeline version.
func replayJob(rawID, rawVersion string) error {
id, err := uuid.Parse(rawID)
if err != nil {
return fmt.Errorf("invalid attachment ID")
}
version, err := strconv.Atoi(rawVersion)
if err != nil || version < 1 {
return fmt.Errorf("positive pipeline version required")
}
cfg, err := config.NewPersistence()
if err != nil {
return err
}
database, err := postgres.New(postgres.Options{URL: cfg.DatabaseURL, MaxConnections: 1, Timeout: 5 * time.Second})
if err != nil {
return err
}
defer database.Close()
return database.Replay(context.Background(), id, version)
}
+80
View File
@@ -0,0 +1,80 @@
package main
import (
"os"
"testing"
"time"
"github.com/google/uuid"
"go.uber.org/fx"
"gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config"
)
// TestWorkerLifecycle starts and joins the real worker without exposing an HTTP listener.
func TestWorkerLifecycle(t *testing.T) {
requirePersistence(t)
if os.Getenv("BROKER_ADDRESS") == "" || os.Getenv("S3_ENDPOINT") == "" {
t.Skip("isolated broker and S3 required")
}
app := fx.New(workerApp())
if err := app.Start(t.Context()); err != nil {
t.Fatal(err)
}
time.Sleep(30 * time.Millisecond)
if err := app.Stop(t.Context()); err != nil {
t.Fatal(err)
}
}
// TestQueueProviderRejectsMissingAddress propagates configuration failure before startup.
func TestQueueProviderRejectsMissingAddress(t *testing.T) {
var lc fx.Lifecycle
app := fx.New(fx.NopLogger, fx.Populate(&lc))
if err := app.Err(); err != nil {
t.Fatal(err)
}
if _, err := newQueue(lc, &config.Worker{}); err == nil {
t.Fatal("missing broker accepted")
}
}
// TestReplayCommandRejectsInvalidInput prevents unintended operator transitions.
func TestReplayCommandRejectsInvalidInput(t *testing.T) {
for _, tc := range []struct {
name string
id string
version string
}{{"invalid ID", "invalid", "1"}, {"invalid version", uuid.NewString(), "x"}, {"negative version", uuid.NewString(), "-1"}} {
t.Run(tc.name, func(t *testing.T) {
if err := run([]string{"replay", tc.id, tc.version}); err == nil {
t.Fatal("invalid operator input accepted")
}
})
}
}
// TestReplayCommandConfiguration checks failure before database access.
func TestReplayCommandConfiguration(t *testing.T) {
t.Run("missing", func(t *testing.T) {
t.Setenv("DATABASE_URL", "")
if err := replayJob(uuid.NewString(), "1"); err == nil {
t.Fatal("missing database accepted")
}
})
t.Run("malformed", func(t *testing.T) {
t.Setenv("DATABASE_URL", "://invalid")
t.Setenv("VALKEY_SHARDS", "shard0=localhost:6379")
if err := replayJob(uuid.NewString(), "1"); err == nil {
t.Fatal("malformed database accepted")
}
})
}
// TestReplayUnknownAttachment verifies safe operator failure against the actual schema.
func TestReplayUnknownAttachment(t *testing.T) {
requirePersistence(t)
if err := replayJob(uuid.NewString(), "1"); err == nil {
t.Fatal("unknown attachment replayed")
}
}
+27
View File
@@ -0,0 +1,27 @@
# Фактическая конфигурация
`.env.example` задания содержит логические предложения. Программа не загружает его автоматически и не читает переменные с суффиксом `_FILE`. Helm передаёт значения из Kubernetes Secrets в env; локальный test-local создаёт отдельные синтетические credentials и удаляет их после запуска.
| Настройка задания | Реальная настройка |
| --- | --- |
| DATABASE_URL_FILE | DATABASE_URL из messenger-secrets |
| SESSION_STORE | PostgreSQL, сессии не находятся только в Valkey |
| CACHE_URL_FILE | VALKEY_SHARDS: именованные host:port, consistent hashing |
| API_REPLICAS | Helm replicaCount / autoscaling minReplicas |
| APP_HOST/PORT | APP_HOST и APP_PORT |
| SESSION_TTL_SECONDS | Одноимённая переменная, по умолчанию 3600 |
| IDEMPOTENCY_TTL_SECONDS | Фиксированные контрактные 24 часа |
| S3_ENDPOINT | host:port без схемы; S3_TLS=false для приватного учебного HTTP |
| S3_ACCESS_KEY_ID_FILE / S3_SECRET_ACCESS_KEY_FILE | S3_ACCESS_KEY / S3_SECRET_KEY из messenger-s3 |
| S3_BUCKET | attachments; bootstrap отдельной административной identity |
| MAX_UPLOAD_BYTES / MAX_IMAGE_PIXELS | Именованные константы 10 MiB / 40 миллионов |
| BROKER_URL_FILE | BROKER_ADDRESS, отдельный Valkey Streams |
| WORKER_CONCURRENCY | Один обработчик в процессе; Helm worker.replicas масштабирует процессы |
| JOB_MAX_ATTEMPTS / JOB_TIMEOUT_SECONDS | Пять попыток / 45 s операции; lease 120 s |
| STAGING_RETENTION_SECONDS | Семь дней после terminal transition; orphan grace час |
| OTEL_SERVICE_NAME / RESOURCE_ATTRIBUTES | Явные SDK resource attributes messenger-api/worker, версия APP_VERSION, уникальный instance, environment=lab |
| OTEL_EXPORTER_OTLP_ENDPOINT | HTTP(S) base URL Collector; пусто отключает export |
| OTEL_EXPORTER_OTLP_PROTOCOL | Реализован OTLP HTTP/protobuf |
| Sampling | OTEL_SAMPLE_RATIO в [0,1], по умолчанию 1 |
Значения политик, не читаемые из env, нельзя менять вымышленными переменными. Фактические limits/resources/image digests находятся в chart values и Go-конфигурации. CURSOR_SIGNING_KEY берётся из Secret и сохраняется между обновлениями.
+24
View File
@@ -0,0 +1,24 @@
# Проверка обязательных контрактов
Источники: неизменённые README, COURSE, contracts/README.md, OpenAPI и observability.md. Проверка не сводится к публичному smoke. Унаследованные требования проверяются на текущем коде; результаты предыдущих репозиториев не выдаются за результаты lab6.
| Контракт | Реализация и проверка |
| --- | --- |
| Строгий JSON, UUID, Unicode, pagination, общая ошибка | strictjson, service/production, controller/http/fiber; Go regression tests и публичный smoke |
| Basic только при login, Bearer, expiry/revoke, игнорирование X-User-Id | service/authentication, postgres/sessions; session tests, smoke и persistence |
| X-Request-Id и X-Instance-Id, включая 413 | controller/http/fiber/errors.go; tests ранних transport errors |
| Две API, видимость записи, атомарная идемпотентность 24h | PostgreSQL unique key + транзакция; TestMessageRetryRace/Conflict/Expiry/Rollback, failover |
| 10 MiB / 40M pixels, MIME и filename, приватные bytes | media/validation, ограниченное чтение, objectstore; validation/ACL/private bucket tests |
| 202 только после S3 staging + durable SQL intent | QueueAttachment; fault matrix и реальный restart при остановленном worker |
| queued/processing можно прикреплять; failed запрещён; content до ready — 409 | media и PostgreSQL message transaction; attachments/pipeline tests, smoke |
| Неизменный original, JPEG fit256, alpha/EXIF, crop128, WebP fit1280 | imageprocessor tests + checksum/размеры в smoke и durable |
| At-least-once, bounded retry, fencing, replay, retention | pipeline, streamqueue, jobs/retention tests с настоящими SQL/S3 |
| OTLP API/worker, три backend, provisioning и PVC | charts/messenger; сохранённые live metric names, trace, logs, dashboard API |
| Parent chain и retry | trace-probe.sh, trace-retry.sh, OTLP tests; JSON traces в evidence/current |
| Histogram percentiles, bounded labels, queue/pool/CPU/RAM | telemetry + dashboard; histogram границы проверены по живому Prometheus |
| Multiwindow SLO, DB/worker/backend incidents | observability-incidents.sh, ready-slo.sh; raw evidence и разбор REPORT |
| Graceful lifecycle и ≥90% каждого Go-файла | coverage.sh: race tests + инструментированный настоящий процесс |
## Формальная граница
В infrastructure.json требуется Compose/Swarm. Реализован Helm/Kubernetes по принятому направлению проекта; эквивалентные роли и bootstrap доступны, но разрешение преподавателя на замену не подтверждено. Это открытое расхождение задания, а не доказанный пункт соответствия. Обязательные контракты и публичные tests не изменялись.
+10
View File
@@ -0,0 +1,10 @@
# План lab6
1. L6-01/02 — выполнено: перенос lab5, owned SDK providers, durable W3C propagation, реальная цепочка upload и retry.
2. L6-03 — выполнено: histogram/counters/saturation, три backend, provisioning14panels; проверены реальные dev имена/источники.
3. L6-04 — выполнено в заявленных границах: конечные очереди/timeouts,2000spans failure test, реальная остановка Tempo с работающим business smoke. Длительный soak не проводился.
4. L6-05/06 — выполнено: raw инциденты, API lagged firing/resolved, исправленный ready alert отдельно проверен STOP/CONT, promtool regression; REPORT сохраняет первоначальные ошибки сценария.
5. Проверки — race, per-file≥90%, lint, Helm/static, HTTPS dev smoke прошли. Общий release lab2 revision45.
6. Описание PR подготовлено в корне рабочего каталога. Публикация фиксируется отдельным Git commit; remote SHA проверяется после push.
Открытый внешний вопрос: принятие Kubernetes вместо Compose/Swarm. Remote CI и оценка преподавателя не подтверждены.
+12
View File
@@ -0,0 +1,12 @@
# Спецификация lab6
Источники: README, COURSE, contracts/README.md и contracts/observability.md. Бизнес-контракт lab5 сохраняется. Цель — уровни 3/4 и трек 5.2.
- L6-01: API/worker отправляют OTLP traces, metrics, logs в Collector; Prometheus/Loki/Tempo/Grafana разворачиваются тем же Helm release с PVC и provisioning.
- L6-02: W3C context проходит HTTP → SQL outbox → producer → broker → consumer → S3/DB. Логи содержат trace/span/request IDs, не содержат credentials, body и filename.
- L6-03: bounded labels, histogram HTTP/job/e2e в секундах, queue depth/oldest, DB used/waiting, worker busy/capacity, CPU/RAM. Dashboard с реальными именами и p50/p95/p99 из bucket aggregation.
- L6-04: bounded SDK/export queues и Collector memory limiter/batch. Отказ telemetry backend не меняет бизнес-готовность API и не приводит к неограниченному накоплению.
- L6-05: проверяемые SLO API и ready; multiwindow burn alerts и queue lag, runbook. Подтверждены firing/resolved, краткий всплеск и длительная деградация, измерено время реакции.
- L6-06: реальные инциденты остановки worker и отказа DB, связь логов/трасс; smoke с telemetry, race, coverage ≥90% каждого Go-файла, raw evidence и ограничения.
Границы: namespace highload-applications, release lab2, context dev, hl.agapov.space. Чужой monitoring не изменяется. Kubernetes substitution требует подтверждения преподавателя. Внешняя отправка уведомлений не настраивается.
+1
View File
@@ -0,0 +1 @@
SUCCESS
@@ -0,0 +1 @@
{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"up"},"value":[1793283940.497,"1"]},{"metric":{"__name__":"scrape_duration_seconds"},"value":[1793283940.497,"1"]},{"metric":{"__name__":"scrape_samples_scraped"},"value":[1793283940.497,"1"]},{"metric":{"__name__":"scrape_samples_post_metric_relabeling"},"value":[1793283940.497,"1"]},{"metric":{"__name__":"scrape_series_added"},"value":[1793283940.497,"1"]}]}}
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+5
View File
@@ -0,0 +1,5 @@
{
"trace_id": "4486ae744b284857a148568406c8ff4c",
"attachment_id": "b726dbfb-5ddc-497b-80d7-59efd8debae3",
"ready": true
}
+2
View File
@@ -0,0 +1,2 @@
curl: (22) The requested URL returned error: 404
PASS: upload and worker share trace bfeacf9a52db37463ddefff2ed23b0cb; correlated structured logs found
+113
View File
@@ -0,0 +1,113 @@
{"threshold_per_file":90,"files":[
{"file":"internal/service/production/validation.go","statements":13,"covered":13,"percent":100.00000000,"sha256":"19442e5931252a040559e34af83e8e22d47fa127677ed5dd273e0ba5bbf99ab0"},
{"file":"internal/model/http/models.go","statements":0,"covered":0,"percent":null,"sha256":"d68827b0bd3e6df4037621b6941298d3923dc348bda5bf314a34861e7c34f04e"},
{"file":"internal/service/production/members.go","statements":19,"covered":19,"percent":100.00000000,"sha256":"861263597b62be27cfbc98a5dec11fd348994cba95773405086ab39e4d18e223"},
{"file":"internal/telemetry/runtime.go","statements":32,"covered":29,"percent":90.62500000,"sha256":"7b973eadb1610369f4cc8d3dc2a4fa78d0732fb8677091c3c2db12d628868657"},
{"file":"internal/controller/http/fiber/public_errors.go","statements":15,"covered":15,"percent":100.00000000,"sha256":"c2af04ba4a1a9a1b5e6596ac5a924113bf37954b27d54037016dc1ca9ee48e77"},
{"file":"internal/store/memory/capacity.go","statements":7,"covered":7,"percent":100.00000000,"sha256":"8d8c50b868c725c0303a3cbc9578f6ea2b27d1a229700d2f80fe91f0de8622f3"},
{"file":"internal/controller/http/fiber/attachments.go","statements":28,"covered":28,"percent":100.00000000,"sha256":"7b4f03ae4414de081409ff443813e7c854a132dea9bbbce5dc9354a6bf7f989c"},
{"file":"internal/controller/http/fiber/health.go","statements":7,"covered":7,"percent":100.00000000,"sha256":"29ca7d1f1207b2fbbd272062beadcfe869d007350b8d50cc2a909b0dbe5c08d1"},
{"file":"internal/model/dto/session.go","statements":0,"covered":0,"percent":null,"sha256":"896a694b0c217240343077d4287f4a6e447338c38571abbebcb3d16a519137fb"},
{"file":"internal/service/production/service.go","statements":10,"covered":10,"percent":100.00000000,"sha256":"5f9009ad92a7e5ea5b7ed4aae7146a1805bdbb4ded66b57661dc1950a33b32e4"},
{"file":"internal/valkey/admission.go","statements":42,"covered":42,"percent":100.00000000,"sha256":"8cdb6f5e2e83341b624e9b14a52b73e17ec03b41dad620f6e3d39a3244930b4a"},
{"file":"internal/controller/http/fiber/observation.go","statements":2,"covered":2,"percent":100.00000000,"sha256":"3b36952bd2c08dfdbe04a3c1e0eeeb0b550edefee44b7816bfdb6a094787bda4"},
{"file":"internal/controller/http/fiber/error_registry.go","statements":2,"covered":2,"percent":100.00000000,"sha256":"9d5da8d98ece2706e324cb2deca915e0811b6ad98f7aaac5805ca0f3cc0a1f9a"},
{"file":"internal/service/interface.go","statements":0,"covered":0,"percent":null,"sha256":"58b49648c1b6e73971255cd9c5ae95853abd8bb44653ee2a912122c599ef23cb"},
{"file":"internal/store/memory/store.go","statements":3,"covered":3,"percent":100.00000000,"sha256":"e00a97d2b6d408bd8964fefd62f5a187a1de81c96f93637c0905a346b4beaa5b"},
{"file":"internal/config/memory.go","statements":9,"covered":9,"percent":100.00000000,"sha256":"86cdf9e90b576f4484946bfd9605333fc52077f38d3a39c5d71ddca4cdeecda0"},
{"file":"internal/service/cursor.go","statements":0,"covered":0,"percent":null,"sha256":"1815bf20f8ebfa8f8f394f8aef5e3e7954ff7652a5c4f4d6b14ace4d57b99ee2"},
{"file":"internal/store/memory/messages.go","statements":19,"covered":18,"percent":94.73684211,"sha256":"03d054b385ae51d160b6ce0441e86c2f6c4763724aa9e91228224cc88a12fdd2"},
{"file":"internal/streamqueue/queue.go","statements":33,"covered":30,"percent":90.90909091,"sha256":"0b6655c6c7d7f60758b05b3d5fc6abfea4a7de3466f7fd56d1cac0b537cc76d5"},
{"file":"internal/pipeline/types.go","statements":0,"covered":0,"percent":null,"sha256":"559c98b3fa4d4ea4aa2a07480ccdea52b37cc0dbf0910aacef7589757effaa8c"},
{"file":"internal/store/postgres/idempotency.go","statements":21,"covered":19,"percent":90.47619048,"sha256":"0f1d4b91a9deb26f276235f3a069570b3962f279aeb5a8491d6384ad2fa942ca"},
{"file":"internal/model/dto/models.go","statements":0,"covered":0,"percent":null,"sha256":"5e2536b8eba6bb92b751a7b817b6338755008857e3b53920d8da6fb67adeebdb"},
{"file":"internal/service/errors.go","statements":0,"covered":0,"percent":null,"sha256":"a1ac40c39260c9babeaf8259985de5f84abe1ce80dc8ed9f26ad1b66b1ef35af"},
{"file":"internal/config/telemetry.go","statements":13,"covered":13,"percent":100.00000000,"sha256":"a5289a9ee5c8d6b092c9719f7ccece0abbbc409ecedd187352718ec3a083bf90"},
{"file":"internal/service/cache.go","statements":0,"covered":0,"percent":null,"sha256":"d3ef483a9fcc47c0a056c0ed9e06907f51688cbd0f87c5ce1b657b2f12fc714c"},
{"file":"internal/controller/http/fiber/stream.go","statements":14,"covered":14,"percent":100.00000000,"sha256":"6bc72fdc23332e08e4dee8a5ed3f9110952208af86b529d5d4847ebcf00dd4c3"},
{"file":"internal/store/postgres/reconcile.go","statements":32,"covered":31,"percent":96.87500000,"sha256":"a770985780d475f03ca9990522f02d9bcffaa69b7701128df11e0939b55848ba"},
{"file":"cmd/server/worker.go","statements":36,"covered":34,"percent":94.44444444,"sha256":"aae78ee2a9c844684410dd6d727427d3437ec7b19f417b6e75dbafa203a86b51"},
{"file":"internal/controller/http/fiber/middleware.go","statements":53,"covered":52,"percent":98.11320755,"sha256":"18d69e4e21f9b2231d75ce9ac6dfe0243d9aa2a5ebf51932380adcd0dfec2a3a"},
{"file":"internal/objectstore/observation.go","statements":5,"covered":5,"percent":100.00000000,"sha256":"d11d878aa4b1e0e093ae39028e1cc77fbf1841036145d9ce44392b8465ebddf5"},
{"file":"internal/store/postgres/store.go","statements":58,"covered":54,"percent":93.10344828,"sha256":"ac5a64c966681f8baf5dbbc1232c9f6a2a54ad137869acfe88052e7cb943cfd5"},
{"file":"internal/config/logger.go","statements":7,"covered":7,"percent":100.00000000,"sha256":"3a69e20a00fa2ed816f344a990e9e0ef0077e1607d4207858b4b00e4ff5d1988"},
{"file":"cmd/server/logger.go","statements":10,"covered":9,"percent":90.00000000,"sha256":"d4c33ca5a93583caffd63e78bef00a2af906c477e29f1ce89495ee1737219579"},
{"file":"internal/service/auth.go","statements":0,"covered":0,"percent":null,"sha256":"f584e498d5f902f2a8eb22bb91b0dfd7a86547797995e750356415002240a50b"},
{"file":"internal/service/production/creation.go","statements":24,"covered":23,"percent":95.83333333,"sha256":"f7767482299f26cc44cb8d2c2a6fd024f5caec4a2818fbde617fe99ba687a097"},
{"file":"internal/media/service.go","statements":55,"covered":54,"percent":98.18181818,"sha256":"e0e55fcaad09af39caf5d481014de408552d28b7925de8e9492aa208938e637d"},
{"file":"internal/service/production/messages.go","statements":18,"covered":18,"percent":100.00000000,"sha256":"5ae4aae2622bad3673a5b0b4a460954a1f8ff38e337145dcfec678a401b490d4"},
{"file":"internal/controller/http/fiber/routes.go","statements":18,"covered":18,"percent":100.00000000,"sha256":"e248223517102e1eecdeba9a5e2d844c0afc14116a56e9a1d76c6afb755e63d1"},
{"file":"internal/store/postgres/jobs.go","statements":116,"covered":110,"percent":94.82758621,"sha256":"9b4445f552ad08923a59be3853fad2091ce62a4ab0f6b4875711505a4e6e5fe1"},
{"file":"internal/config/persistence.go","statements":13,"covered":13,"percent":100.00000000,"sha256":"28c61d23db4ca2ef7ed952451f465318865076d2393eaa94ff5d7bb339c4c06b"},
{"file":"internal/controller/http/fiber/error_codes.go","statements":0,"covered":0,"percent":null,"sha256":"3351a019c43d0360ee0fd68afabb5200422d065ae7bd908b1c0a5c02a0c1ad41"},
{"file":"internal/media/run_reconcile.go","statements":21,"covered":21,"percent":100.00000000,"sha256":"3255403afcb9486d33c5bb45b5afa9c3c9b85596ce97f86ac2f224011cd8a860"},
{"file":"internal/controller/http/fiber/handlers.go","statements":37,"covered":36,"percent":97.29729730,"sha256":"f514263df465c6c1e3df76590553b37f7e32330dee48add9fdfb194d9bcde28e"},
{"file":"internal/store/postgres/retention.go","statements":11,"covered":11,"percent":100.00000000,"sha256":"6ca456767aec350fe81af74deb82a04fcb8689896d11ed547d3855a01f1b57e7"},
{"file":"internal/store/postgres/chats.go","statements":26,"covered":24,"percent":92.30769231,"sha256":"1a7f671d6c781a5f3b6a03ce80e38f87e8a11e7e4cd51fca57829be9a01811ff"},
{"file":"cmd/server/media.go","statements":7,"covered":7,"percent":100.00000000,"sha256":"acc63500e1475752bc8f82472e6714d52bd30af62d82d07e44f0de3f117c22ac"},
{"file":"internal/store/memory/users.go","statements":22,"covered":21,"percent":95.45454545,"sha256":"7ef5f5000ed30aac7e9e058d33ff4a75caa4b83040a59269ae1223081cab68af"},
{"file":"internal/service/production/chats.go","statements":22,"covered":22,"percent":100.00000000,"sha256":"e917208ece7e11d442c3c3ca7e33ac303a9e50b11288f2476390d601a5d68e41"},
{"file":"internal/valkey/client.go","statements":35,"covered":34,"percent":97.14285714,"sha256":"b30fccec3b12374e76b93a2a76ffa7d9fc6a9d6a123793b8effb6b0da679a7d0"},
{"file":"internal/store/memory/ordering.go","statements":6,"covered":6,"percent":100.00000000,"sha256":"0eb10952ceb798a5e6bacfd115eeaaed9cd37e8232a56c20d2c120cf457d3c5e"},
{"file":"internal/controller/http/fiber/decode.go","statements":12,"covered":11,"percent":91.66666667,"sha256":"f5e9c3f8a8a22f51639a570e2ab2e626bde0bf29434dd6527d1da8f32f021cf0"},
{"file":"internal/controller/http/fiber/errors.go","statements":29,"covered":29,"percent":100.00000000,"sha256":"a490411aca9d3a6ddc730981cdc4e0f785172db6773db23357a05c51f7889ea3"},
{"file":"internal/controller/http/fiber/controller.go","statements":10,"covered":10,"percent":100.00000000,"sha256":"cc0fd1f1735385a5b09c836c4fbbf7da22e8343489cc9737f926bc38dcc1add9"},
{"file":"internal/observation/snapshot.go","statements":0,"covered":0,"percent":null,"sha256":"124a8a6393c3c23040b2fd7ec0dbc77b05b4a317e9b1ecddd6df366250db56a6"},
{"file":"cmd/server/telemetry.go","statements":20,"covered":19,"percent":95.00000000,"sha256":"c5c54cf34133c297c88a401f8183c8b5a269864323e24100ce0a3994e3a4f12f"},
{"file":"internal/pipeline/worker.go","statements":87,"covered":85,"percent":97.70114943,"sha256":"357355bc4420f9b4c8306967cdc468de6989ccb96d90d3a6ff5afa80f07c3259"},
{"file":"internal/service/production/access.go","statements":27,"covered":27,"percent":100.00000000,"sha256":"878415267a409244b5fa490ed09da3ed446ab5d45963f4b1c02f626fd5248614"},
{"file":"internal/valkey/cache.go","statements":17,"covered":16,"percent":94.11764706,"sha256":"6aa3f9dbf0e5f5e60a06245fefe4d5d139ab181a47ec0e2d2e88346158fd4359"},
{"file":"internal/service/production/errors.go","statements":5,"covered":5,"percent":100.00000000,"sha256":"d002ded303f0aaf8acef41f5e5846e548c52e5b4e683d7cb986be38db4227bbd"},
{"file":"internal/store/postgres/observability.go","statements":5,"covered":5,"percent":100.00000000,"sha256":"7eebf916fdc3ee58b2d19098a835405aa95cb985d2c8c7f5934e1e64d1f2b9f9"},
{"file":"internal/observation/tracer.go","statements":0,"covered":0,"percent":null,"sha256":"3642e33cdb0ae1ca5ed0a88cc0b6d0748f836d45ba0712ae1368533310aa5a7a"},
{"file":"internal/service/authentication/service.go","statements":48,"covered":47,"percent":97.91666667,"sha256":"87a752eb08988aa0b76fa3c6e37e6180508d9bf774f3d9cec0cd825162094d34"},
{"file":"internal/service/production/pagination.go","statements":21,"covered":21,"percent":100.00000000,"sha256":"2ab7be10ded3332e4bbfc0c825f5d355a68b2ef79385fc3af490ae3a11077859"},
{"file":"internal/media/orphans.go","statements":23,"covered":23,"percent":100.00000000,"sha256":"327ee894c8c9afa5bcf8236ed4c91befd66699c0ca33178e9690705764faf002"},
{"file":"internal/pipeline/cleanup.go","statements":11,"covered":11,"percent":100.00000000,"sha256":"eb4a71e1d2cbc93d539770b425305b4826b98dd7770741c6677a50c0ec43b4f8"},
{"file":"cmd/server/persistence.go","statements":24,"covered":22,"percent":91.66666667,"sha256":"8332e76c999388078bc176da84fb38535b1105e32d8d4044cf6b701188476065"},
{"file":"internal/admission/limiter.go","statements":16,"covered":16,"percent":100.00000000,"sha256":"a373c9539167a4b7c35d45334d35ffd4e9d124c1740c88c12094fededd9643b4"},
{"file":"internal/media/validation.go","statements":17,"covered":17,"percent":100.00000000,"sha256":"3662f14499e4106d3148a79a001ab92cb0d31279516ccba9a524e6bcec2a16b4"},
{"file":"cmd/server/reconcile.go","statements":19,"covered":18,"percent":94.73684211,"sha256":"42848ffa729c73773b301ab27da96633ef5fe36fd4da2ea059bb622f49a5766f"},
{"file":"internal/controller/http/fiber/lifecycle.go","statements":24,"covered":22,"percent":91.66666667,"sha256":"f39cf7a0049a2ed39d6cc1fcc66b44656d9d6120914d0e973b032e12f3d0de08"},
{"file":"internal/config/controller.go","statements":23,"covered":22,"percent":95.65217391,"sha256":"1c853c0f771e2c75958db8158797f2287e06c8d9efe8856365b7b9c71b1747b0"},
{"file":"internal/config/config.go","statements":17,"covered":17,"percent":100.00000000,"sha256":"8cb675a0bef8b1645071e4cb85b79a467620e99b375db5d8d3e16a54b4c5b5fa"},
{"file":"internal/model/dto/attachment.go","statements":0,"covered":0,"percent":null,"sha256":"801a6290037459a1f9d28669b4f3cdce5191317da8a48189027b7a507139fdc7"},
{"file":"internal/controller/http/fiber/auth.go","statements":29,"covered":29,"percent":100.00000000,"sha256":"a8fb7892f713529a9359b1c77202ef5fb9a2dd4d921ee9f1ec104da67ee1ad87"},
{"file":"internal/strictjson/decode.go","statements":47,"covered":47,"percent":100.00000000,"sha256":"d99595e1f74406c5aa617c0ec062afb7f12f116bd86776e87cc9c9a436ff7eea"},
{"file":"internal/config/objectstore.go","statements":4,"covered":4,"percent":100.00000000,"sha256":"c6283fe310747e8297850b48c0a119c1d62db4903dd2c779c6296678563df188"},
{"file":"internal/config/worker.go","statements":4,"covered":4,"percent":100.00000000,"sha256":"eb502257c4badca1e8a2d4eb17701937edcc2c45dd6d697d70abb1624f457e14"},
{"file":"internal/objectstore/list.go","statements":10,"covered":9,"percent":90.00000000,"sha256":"5eb695bb582e545a3b43ba15e7a88b6bb70bdfd43155f2169defff2ffd41fd7c"},
{"file":"cmd/server/app.go","statements":9,"covered":9,"percent":100.00000000,"sha256":"21a514acf6287bcc9c39b96e6ce22b5c58f7e0425f7cf796744f4547af11ff31"},
{"file":"cmd/server/main.go","statements":3,"covered":3,"percent":100.00000000,"sha256":"c22d8cdf4ce31fde29945e967d3f025e280a7dc4d2022329d51be972d2a0f495"},
{"file":"cmd/server/s3_bootstrap.go","statements":9,"covered":9,"percent":100.00000000,"sha256":"e8e1d54f869025360853a5a73eabb3146914d4caf6b8d4f20e1a250e79058ea7"},
{"file":"internal/config/environment.go","statements":14,"covered":14,"percent":100.00000000,"sha256":"027761b059b76898a84318ec1a8b43158d8bafd6e0b15b52efbe902b4d8c5ea3"},
{"file":"internal/telemetry/spans.go","statements":42,"covered":42,"percent":100.00000000,"sha256":"4f9ef25f02df303db401d99780888bac94ebd7601f8227be710acefd80f09987"},
{"file":"internal/store/memory/chats.go","statements":31,"covered":31,"percent":100.00000000,"sha256":"618eaf4e1c042d29abaa7df456d83a36f6b4dcc6e7a401071ec8489805dfb640"},
{"file":"internal/imageprocessor/processor.go","statements":43,"covered":39,"percent":90.69767442,"sha256":"7f1fed5f8276e19ed13e0576c633c11d213d8ad1af7e27179aea893948a795ad"},
{"file":"internal/controller/fx.go","statements":1,"covered":1,"percent":100.00000000,"sha256":"af72da25fea9811c13a50c8133e9e8b35e070c5295069c40c0ae89cdc0aff19a"},
{"file":"internal/controller/interface.go","statements":0,"covered":0,"percent":null,"sha256":"24b6b06d6fab919cd2130697b44fd0d358265184dca0ca8362e0b4fcc2ae5a68"},
{"file":"internal/media/reconcile.go","statements":38,"covered":38,"percent":100.00000000,"sha256":"90c319dc2ed9cc8193474ba84793094839d5c7a6ef19a103f4170da5558348fb"},
{"file":"internal/hashring/ring.go","statements":21,"covered":20,"percent":95.23809524,"sha256":"e205901cec2e66011ec764b70879b0eb0d28a78c4dea8913a9fb30c2d778fa8c"},
{"file":"internal/telemetry/postgres.go","statements":10,"covered":10,"percent":100.00000000,"sha256":"ddba713ce3941cef9fddd4968d63359105e4f32366a87b469268a57d0da6364a"},
{"file":"internal/pipeline/observation.go","statements":10,"covered":10,"percent":100.00000000,"sha256":"d844cf88188841f6e5ba393c48f79d393a70531eea9fedfce07da419c49bd366"},
{"file":"cmd/server/commands.go","statements":27,"covered":27,"percent":100.00000000,"sha256":"ebc7c7d4bb1a0ca63cf949ca349f4819b4e5672a3bb1d714fee90ab7ec48ceff"},
{"file":"internal/controller/http/fiber/dependencies.go","statements":0,"covered":0,"percent":null,"sha256":"6ee07f110bdb29d8d2191ab8889ba60474b33a5b225739875c8a57d8434be15d"},
{"file":"internal/service/production/pages.go","statements":17,"covered":16,"percent":94.11764706,"sha256":"a19420fa45469f36a4a624b8f8a696b81af56cbfb94f28dcc26fc5940fc0aec7"},
{"file":"internal/store/postgres/sessions.go","statements":13,"covered":13,"percent":100.00000000,"sha256":"889a63b51b29012f4ae5499d1c0577fe29f2f2959b05629f8e123715cfc1f75f"},
{"file":"internal/controller/http/fiber/configure.go","statements":7,"covered":7,"percent":100.00000000,"sha256":"be356cf26c228958d51f5bafa4305d7325e81ab01065575acbc9b2d7a6ddd4bd"},
{"file":"internal/admission/distributed.go","statements":0,"covered":0,"percent":null,"sha256":"41ef40897886c0878cbfe52f6716bdcb8433fb7eaddcfff298e1d54c55db423d"},
{"file":"internal/store/postgres/messages.go","statements":31,"covered":29,"percent":93.54838710,"sha256":"041454c30d1e1cc980567b6e11c8de0bd57cf9e0e8703d132a5172e7bc0ea901"},
{"file":"internal/cursor/codec.go","statements":36,"covered":34,"percent":94.44444444,"sha256":"678e197744fb2fc4b51715f51593b98761125bbaddbe4cb1b7032bd6b173ef04"},
{"file":"internal/store/interface.go","statements":0,"covered":0,"percent":null,"sha256":"f683306c33020d2403e91e93b0fc260ff1d3b3f1911425a7550384dfa60d9937"},
{"file":"cmd/server/healthcheck.go","statements":19,"covered":18,"percent":94.73684211,"sha256":"2308066b0bc2cb117adced1181a64d8b9998aa404d2198143000729a3b9138a1"},
{"file":"internal/controller/http/fiber/mapping.go","statements":16,"covered":16,"percent":100.00000000,"sha256":"7e67fc7c7d3076dc0927a9601871d38002d31d988c9e4c7abcac9c7a65eba327"},
{"file":"internal/password/password.go","statements":18,"covered":17,"percent":94.44444444,"sha256":"fe2df6990331573bbf0202ebc81c58263a7c16a29b713eefa0f0e852e4ee4a76"},
{"file":"internal/objectstore/client.go","statements":48,"covered":44,"percent":91.66666667,"sha256":"e2a8f39cf5ecff860bca6bceeda78779117ea122b7619621ef9a80c84eeb62cb"},
{"file":"internal/telemetry/metrics.go","statements":18,"covered":18,"percent":100.00000000,"sha256":"009d4d61832b93f1e014e1d567d9e1828efc023ec2c40204d96c5d8097c0551f"},
{"file":"internal/controller/http/fiber/headers.go","statements":0,"covered":0,"percent":null,"sha256":"d32a9a01a8b391f4d986e14947a25a0504f4363335ea1524df05e0dd8e9e61bd"},
{"file":"internal/telemetry/saturation.go","statements":28,"covered":27,"percent":96.42857143,"sha256":"4f92838ad08685b5470f9a35ec9c48a136de333ba8d2287b1384f0a35ddb1cb6"},
{"file":"internal/store/postgres/users.go","statements":21,"covered":20,"percent":95.23809524,"sha256":"15de54e4bea80c8523429e3ef5b22c49a2b36f48c9fa58c2b76bc0653a6eae23"},
{"file":"internal/controller/http/fiber/metrics.go","statements":17,"covered":17,"percent":100.00000000,"sha256":"54db82201697bdfcc65712afe61b650f8f0885fc65222dc4cc6d1c3bb07d82dd"},
{"file":"internal/service/production/users.go","statements":19,"covered":19,"percent":100.00000000,"sha256":"6e72b534a0ac2b9bfc7867826b5596da614eb1ef883b86b27fde5098bf818ca2"},
{"file":"internal/store/postgres/attachments.go","statements":21,"covered":20,"percent":95.23809524,"sha256":"5de665ff2f33918a736a97859ff9df766087e8b5deb2e01dff5d35e115a1af19"}
],"passed":true}
+139
View File
@@ -0,0 +1,139 @@
warning: GOCOVERDIR not set, no coverage data emitted
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/cmd/server 3.478s coverage: 33.3% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/admission 1.354s coverage: 0.8% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config 1.356s coverage: 4.8% of statements in ./...
gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller coverage: 0.0% of statements
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/controller/http/fiber 1.880s coverage: 31.7% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/cursor 1.386s coverage: 1.7% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/hashring 1.850s coverage: 1.0% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/imageprocessor 3.381s coverage: 1.9% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/media 1.354s coverage: 7.1% of statements in ./...
? gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/model/dto [no test files]
? gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/model/http [no test files]
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore 1.642s coverage: 3.0% of statements in ./...
? gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/observation [no test files]
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/password 2.373s coverage: 0.8% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/pipeline 1.326s coverage: 5.1% of statements in ./...
? gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service [no test files]
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service/authentication 1.338s coverage: 2.6% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/service/production 1.339s coverage: 10.5% of statements in ./...
? gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store [no test files]
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/memory 1.329s coverage: 4.4% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/store/postgres 5.321s coverage: 23.6% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/streamqueue 2.510s coverage: 1.5% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/strictjson 1.375s coverage: 2.3% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/telemetry 1.493s coverage: 6.1% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/valkey 1.393s coverage: 5.4% of statements in ./...
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/student-tests 1.618s coverage: 0.0% of statements in ./...
PASS: lab6 public API scenario; infrastructure and grading evidence remain separate.
100.00% internal/service/production/validation.go
N/A internal/model/http/models.go
100.00% internal/service/production/members.go
90.62% internal/telemetry/runtime.go
100.00% internal/controller/http/fiber/public_errors.go
100.00% internal/store/memory/capacity.go
100.00% internal/controller/http/fiber/attachments.go
100.00% internal/controller/http/fiber/health.go
N/A internal/model/dto/session.go
100.00% internal/service/production/service.go
100.00% internal/valkey/admission.go
100.00% internal/controller/http/fiber/observation.go
100.00% internal/controller/http/fiber/error_registry.go
N/A internal/service/interface.go
100.00% internal/store/memory/store.go
100.00% internal/config/memory.go
N/A internal/service/cursor.go
94.74% internal/store/memory/messages.go
90.91% internal/streamqueue/queue.go
N/A internal/pipeline/types.go
90.48% internal/store/postgres/idempotency.go
N/A internal/model/dto/models.go
N/A internal/service/errors.go
100.00% internal/config/telemetry.go
N/A internal/service/cache.go
100.00% internal/controller/http/fiber/stream.go
96.88% internal/store/postgres/reconcile.go
94.44% cmd/server/worker.go
98.11% internal/controller/http/fiber/middleware.go
100.00% internal/objectstore/observation.go
93.10% internal/store/postgres/store.go
100.00% internal/config/logger.go
90.00% cmd/server/logger.go
N/A internal/service/auth.go
95.83% internal/service/production/creation.go
98.18% internal/media/service.go
100.00% internal/service/production/messages.go
100.00% internal/controller/http/fiber/routes.go
94.83% internal/store/postgres/jobs.go
100.00% internal/config/persistence.go
N/A internal/controller/http/fiber/error_codes.go
100.00% internal/media/run_reconcile.go
97.30% internal/controller/http/fiber/handlers.go
100.00% internal/store/postgres/retention.go
92.31% internal/store/postgres/chats.go
100.00% cmd/server/media.go
95.45% internal/store/memory/users.go
100.00% internal/service/production/chats.go
97.14% internal/valkey/client.go
100.00% internal/store/memory/ordering.go
91.67% internal/controller/http/fiber/decode.go
100.00% internal/controller/http/fiber/errors.go
100.00% internal/controller/http/fiber/controller.go
N/A internal/observation/snapshot.go
95.00% cmd/server/telemetry.go
97.70% internal/pipeline/worker.go
100.00% internal/service/production/access.go
94.12% internal/valkey/cache.go
100.00% internal/service/production/errors.go
100.00% internal/store/postgres/observability.go
N/A internal/observation/tracer.go
97.92% internal/service/authentication/service.go
100.00% internal/service/production/pagination.go
100.00% internal/media/orphans.go
100.00% internal/pipeline/cleanup.go
91.67% cmd/server/persistence.go
100.00% internal/admission/limiter.go
100.00% internal/media/validation.go
94.74% cmd/server/reconcile.go
91.67% internal/controller/http/fiber/lifecycle.go
95.65% internal/config/controller.go
100.00% internal/config/config.go
N/A internal/model/dto/attachment.go
100.00% internal/controller/http/fiber/auth.go
100.00% internal/strictjson/decode.go
100.00% internal/config/objectstore.go
100.00% internal/config/worker.go
90.00% internal/objectstore/list.go
100.00% cmd/server/app.go
100.00% cmd/server/main.go
100.00% cmd/server/s3_bootstrap.go
100.00% internal/config/environment.go
100.00% internal/telemetry/spans.go
100.00% internal/store/memory/chats.go
90.70% internal/imageprocessor/processor.go
100.00% internal/controller/fx.go
N/A internal/controller/interface.go
100.00% internal/media/reconcile.go
95.24% internal/hashring/ring.go
100.00% internal/telemetry/postgres.go
100.00% internal/pipeline/observation.go
100.00% cmd/server/commands.go
N/A internal/controller/http/fiber/dependencies.go
94.12% internal/service/production/pages.go
100.00% internal/store/postgres/sessions.go
100.00% internal/controller/http/fiber/configure.go
N/A internal/admission/distributed.go
93.55% internal/store/postgres/messages.go
94.44% internal/cursor/codec.go
N/A internal/store/interface.go
94.74% cmd/server/healthcheck.go
100.00% internal/controller/http/fiber/mapping.go
94.44% internal/password/password.go
91.67% internal/objectstore/client.go
100.00% internal/telemetry/metrics.go
N/A internal/controller/http/fiber/headers.go
96.43% internal/telemetry/saturation.go
95.24% internal/store/postgres/users.go
100.00% internal/controller/http/fiber/metrics.go
100.00% internal/service/production/users.go
95.24% internal/store/postgres/attachments.go
+1
View File
@@ -0,0 +1 @@
{"batches":[{"resource":{"attributes":[{"key":"deployment.environment.name","value":{"stringValue":"lab"}},{"key":"service.instance.id","value":{"stringValue":"cd2ca7bb-0626-4ccb-bdb4-6d4b50af696e"}},{"key":"service.version","value":{"stringValue":"lab6"}},{"key":"service.name","value":{"stringValue":"messenger-api"}}]},"scopeSpans":[{"scope":{"name":"messenger"},"spans":[{"traceId":"Lo9ArJnbv1/0A4F99ifvEw==","spanId":"mue1B0sSIGc=","parentSpanId":"V49QQjAf4B0=","name":"postgres.acquire","kind":"SPAN_KIND_CLIENT","startTimeUnixNano":"1793284547292826000","endTimeUnixNano":"1793284548293359458","status":{"message":"operation failed","code":"STATUS_CODE_ERROR"}},{"traceId":"Lo9ArJnbv1/0A4F99ifvEw==","spanId":"V49QQjAf4B0=","name":"GET /api/v1","kind":"SPAN_KIND_SERVER","startTimeUnixNano":"1793284547290694000","endTimeUnixNano":"1793284548296871166","attributes":[{"key":"http.route","value":{"stringValue":"/api/v1"}},{"key":"http.request.method","value":{"stringValue":"GET"}},{"key":"http.response.status_code","value":{"intValue":"503"}}],"status":{"message":"server error","code":"STATUS_CODE_ERROR"}}]}]}]}
+1
View File
@@ -0,0 +1 @@
PASS: upload and worker share trace 4486ae744b284857a148568406c8ff4c; correlated structured logs found
+4
View File
@@ -0,0 +1,4 @@
{
"title": "Messenger: API, worker and SLO",
"panels": 14
}
+2
View File
@@ -0,0 +1,2 @@
{"uid":"prometheus","result":{"details":{"application":"Prometheus","features":{"rulerApiEnabled":false}},"message":"Successfully queried the Prometheus API.","status":"OK"}}
{"uid":"loki","result":{"message":"Data source successfully connected.","status":"OK"}}
+15
View File
@@ -0,0 +1,15 @@
helm lint charts/messenger
==> Linting charts/messenger
[INFO] Chart.yaml: icon is recommended
1 chart(s) linted, 0 chart(s) failed
helm template lab2 charts/messenger >/dev/null
helm upgrade --install lab2 --reset-values charts/messenger --kube-context dev --namespace highload-applications --wait --wait-for-jobs --timeout 8m
Release "lab2" has been upgraded. Happy Helming!
NAME: lab2
LAST DEPLOYED: Thu Oct 29 17:48:29 2026
NAMESPACE: highload-applications
STATUS: deployed
REVISION: 45
DESCRIPTION: Upgrade complete
TEST SUITE: None
+15
View File
@@ -0,0 +1,15 @@
helm lint charts/messenger
==> Linting charts/messenger
[INFO] Chart.yaml: icon is recommended
1 chart(s) linted, 0 chart(s) failed
helm template lab2 charts/messenger >/dev/null
helm upgrade --install lab2 --reset-values charts/messenger --kube-context dev --namespace highload-applications --wait --wait-for-jobs --timeout 8m
Release "lab2" has been upgraded. Happy Helming!
NAME: lab2
LAST DEPLOYED: Thu Oct 29 17:42:04 2026
NAMESPACE: highload-applications
STATUS: deployed
REVISION: 44
DESCRIPTION: Upgrade complete
TEST SUITE: None
+1
View File
@@ -0,0 +1 @@
{"status":"success","data":["messenger_db_pool_used","messenger_db_pool_waiting","messenger_http_duration_seconds_bucket","messenger_http_duration_seconds_count","messenger_http_duration_seconds_sum","messenger_http_requests_total","messenger_job_duration_seconds_bucket","messenger_job_duration_seconds_count","messenger_job_duration_seconds_sum","messenger_jobs_total","messenger_process_cpu_seconds_total","messenger_process_peak_rss_bytes","messenger_queue_depth","messenger_queue_oldest_seconds","messenger_ready_duration_seconds_bucket","messenger_ready_duration_seconds_count","messenger_ready_duration_seconds_sum","messenger_worker_busy","messenger_worker_capacity","otel_scope_info","otelcol_exporter_queue_batch_send_size_bucket","otelcol_exporter_queue_batch_send_size_count","otelcol_exporter_queue_batch_send_size_sum","otelcol_exporter_queue_capacity","otelcol_exporter_queue_size","otelcol_exporter_send_failed_log_records_total","otelcol_exporter_send_failed_metric_points_total","otelcol_exporter_send_failed_spans_total","otelcol_exporter_sent_log_records_total","otelcol_exporter_sent_metric_points_total","otelcol_exporter_sent_spans_total","otelcol_process_cpu_seconds_total","otelcol_process_memory_rss_bytes","otelcol_process_runtime_heap_alloc_bytes","otelcol_process_runtime_total_alloc_bytes_total","otelcol_process_runtime_total_sys_memory_bytes","otelcol_process_uptime_seconds_total","otelcol_processor_accepted_log_records_total","otelcol_processor_accepted_metric_points_total","otelcol_processor_accepted_spans_total","otelcol_processor_batch_batch_send_size_bucket","otelcol_processor_batch_batch_send_size_count","otelcol_processor_batch_batch_send_size_sum","otelcol_processor_batch_metadata_cardinality","otelcol_processor_batch_timeout_trigger_send_total","otelcol_processor_incoming_items_total","otelcol_processor_outgoing_items_total","otelcol_receiver_accepted_log_records_total","otelcol_receiver_accepted_metric_points_total","otelcol_receiver_accepted_spans_total","otelcol_receiver_failed_log_records_total","otelcol_receiver_failed_metric_points_total","otelcol_receiver_failed_spans_total","otelcol_receiver_refused_log_records_total","otelcol_receiver_refused_metric_points_total","otelcol_receiver_refused_spans_total","promhttp_metric_handler_errors_total","scrape_duration_seconds","scrape_samples_post_metric_relabeling","scrape_samples_scraped","scrape_series_added","target_info","up"]}
+15
View File
@@ -0,0 +1,15 @@
NAME READY RESTARTS
api-c99bb859b-hnv8w true 0
api-c99bb859b-jnfg7 true 1
broker-0 true 0
messenger-collector-0 true 0
messenger-grafana-0 true 1
messenger-loki-0 true 0
messenger-prometheus-0 true 0
messenger-tempo-0 true 0
postgres-0 true 0
s3-0 true 0
valkey-0 true 0
valkey-1 true 1
valkey-2 true 0
worker-55bb489c77-74xsw true 0
@@ -0,0 +1,12 @@
[
{
"job": "collector",
"health": "up",
"lastError": ""
},
{
"job": "messenger",
"health": "up",
"lastError": ""
}
]
+4
View File
@@ -0,0 +1,4 @@
KUBE_CONTEXT=dev NAMESPACE=highload-applications scripts/init-secrets.sh
namespace/highload-applications unchanged
secret/registry-pull unchanged
secret/messenger-grafana created
+2
View File
@@ -0,0 +1,2 @@
python3 tests/smoke.py --base-url "https://hl.agapov.space"
PASS: lab6 public API scenario; infrastructure and grading evidence remain separate.
+1
View File
@@ -0,0 +1 @@
ready
File diff suppressed because one or more lines are too long
+4
View File
@@ -0,0 +1,4 @@
{
"title": "Messenger: API, worker and SLO",
"panels": 14
}
@@ -0,0 +1,2 @@
{"uid":"prometheus","result":{"details":{"application":"Prometheus","features":{"rulerApiEnabled":false}},"message":"Successfully queried the Prometheus API.","status":"OK"}}
{"uid":"loki","result":{"message":"Data source successfully connected.","status":"OK"}}
@@ -0,0 +1 @@
+5
View File
@@ -0,0 +1,5 @@
{
"uid": "tempo",
"type": "tempo",
"url": "http://messenger-tempo:3200"
}
+78
View File
@@ -0,0 +1,78 @@
#0 building with "asisti-builder" instance using docker-container driver
#1 [internal] load build definition from Dockerfile
#1 transferring dockerfile: 640B done
#1 DONE 0.0s
#2 [internal] load metadata for docker.io/library/golang:1.26.1-alpine3.23
#2 ...
#3 [internal] load metadata for docker.io/library/alpine:3.23
#3 DONE 1.9s
#2 [internal] load metadata for docker.io/library/golang:1.26.1-alpine3.23
#2 DONE 2.0s
#4 [internal] load .dockerignore
#4 transferring context: 145B done
#4 DONE 0.0s
#5 [build 1/7] FROM docker.io/library/golang:1.26.1-alpine3.23@sha256:2389ebfa5b7f43eeafbd6be0c3700cc46690ef842ad962f6c5bd6be49ed82039
#5 resolve docker.io/library/golang:1.26.1-alpine3.23@sha256:2389ebfa5b7f43eeafbd6be0c3700cc46690ef842ad962f6c5bd6be49ed82039 done
#5 DONE 0.0s
#6 [runtime 1/3] FROM docker.io/library/alpine:3.23@sha256:ff7f0c727dd796aa36787bfcd9a64bf35a6ce72a73451b3359fde849b6703d63
#6 resolve docker.io/library/alpine:3.23@sha256:ff7f0c727dd796aa36787bfcd9a64bf35a6ce72a73451b3359fde849b6703d63 done
#6 DONE 0.0s
#7 [internal] load build context
#7 transferring context: 32.58kB 0.0s done
#7 DONE 0.0s
#8 [build 2/7] WORKDIR /src
#8 CACHED
#9 [build 3/7] COPY go.mod go.sum ./
#9 CACHED
#10 [build 4/7] RUN go mod download
#10 CACHED
#11 [build 5/7] COPY cmd/ ./cmd/
#11 DONE 0.0s
#12 [build 6/7] COPY internal/ ./internal/
#12 DONE 0.0s
#13 [build 7/7] RUN CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" -o /out/server ./cmd/server
#13 DONE 82.9s
#14 [runtime 2/3] RUN apk add --no-cache ca-certificates libwebp-tools
#14 CACHED
#15 [runtime 3/3] COPY --from=build /out/server /server
#15 DONE 0.1s
#16 exporting to image
#16 exporting layers
#16 exporting layers 0.8s done
#16 exporting manifest sha256:2a623e438729aea6730100d852a47325f3cc8eb4bb776f8928db1229efced109 done
#16 exporting config sha256:8af675a4c84386022a49c32acdf57ef883c375af4b85ef28491e7826a4a38e78 done
#16 exporting attestation manifest sha256:f0d4b2173b833f4863f1302da3d0743df949f0d96468778f5c4ae5df8fc07f05 done
#16 exporting manifest list sha256:04a28492ad5645ed56c58d51a95214a758426adc2b0271fc184e8f204c3fa7cc done
#16 pushing layers
#16 ...
#17 [auth] mtusi2026lab6:pull,push token for asisti.registry.twcstorage.ru
#17 DONE 0.0s
#16 exporting to image
#16 pushing layers 15.4s done
#16 pushing manifest for asisti.registry.twcstorage.ru/mtusi2026lab6:solution-20261029@sha256:04a28492ad5645ed56c58d51a95214a758426adc2b0271fc184e8f204c3fa7cc
#16 pushing manifest for asisti.registry.twcstorage.ru/mtusi2026lab6:solution-20261029@sha256:04a28492ad5645ed56c58d51a95214a758426adc2b0271fc184e8f204c3fa7cc 2.1s done
#16 DONE 18.3s
#18 resolving provenance for metadata file
#18 DONE 0.0s
View build details: docker-desktop://dashboard/build/asisti-builder/asisti-builder0/qgdek5lit26j8suzndebmuxl0
+20
View File
@@ -0,0 +1,20 @@
{
"buildx.build.provenance": {
"buildType": "",
"invocation": {
"configSource": {},
"parameters": {},
"environment": {
"platform": ""
}
}
},
"buildx.build.ref": "asisti-builder/asisti-builder0/qgdek5lit26j8suzndebmuxl0",
"containerimage.descriptor": {
"mediaType": "application/vnd.oci.image.index.v1+json",
"digest": "sha256:04a28492ad5645ed56c58d51a95214a758426adc2b0271fc184e8f204c3fa7cc",
"size": 855
},
"containerimage.digest": "sha256:04a28492ad5645ed56c58d51a95214a758426adc2b0271fc184e8f204c3fa7cc",
"image.name": "asisti.registry.twcstorage.ru/mtusi2026lab6:solution-20261029"
}
+1
View File
@@ -0,0 +1 @@
0 issues.
File diff suppressed because one or more lines are too long
+1
View File
@@ -0,0 +1 @@
{"status":"success","data":["ALERTS","ALERTS_FOR_STATE","messenger:api_error_ratio:1m","messenger:api_error_ratio:5m","messenger_db_pool_used","messenger_db_pool_waiting","messenger_http_duration_seconds_bucket","messenger_http_duration_seconds_count","messenger_http_duration_seconds_sum","messenger_http_requests_total","messenger_job_duration_seconds_bucket","messenger_job_duration_seconds_count","messenger_job_duration_seconds_sum","messenger_jobs_total","messenger_process_cpu_seconds_total","messenger_process_peak_rss_bytes","messenger_queue_depth","messenger_queue_oldest_seconds","messenger_ready_duration_seconds_bucket","messenger_ready_duration_seconds_count","messenger_ready_duration_seconds_sum","messenger_worker_busy","messenger_worker_capacity","otel_scope_info","otelcol_exporter_queue_batch_send_size_bucket","otelcol_exporter_queue_batch_send_size_count","otelcol_exporter_queue_batch_send_size_sum","otelcol_exporter_queue_capacity","otelcol_exporter_queue_size","otelcol_exporter_send_failed_log_records_total","otelcol_exporter_send_failed_metric_points_total","otelcol_exporter_send_failed_spans_total","otelcol_exporter_sent_log_records_total","otelcol_exporter_sent_metric_points_total","otelcol_exporter_sent_spans_total","otelcol_process_cpu_seconds_total","otelcol_process_memory_rss_bytes","otelcol_process_runtime_heap_alloc_bytes","otelcol_process_runtime_total_alloc_bytes_total","otelcol_process_runtime_total_sys_memory_bytes","otelcol_process_uptime_seconds_total","otelcol_processor_accepted_log_records_total","otelcol_processor_accepted_metric_points_total","otelcol_processor_accepted_spans_total","otelcol_processor_batch_batch_send_size_bucket","otelcol_processor_batch_batch_send_size_count","otelcol_processor_batch_batch_send_size_sum","otelcol_processor_batch_batch_size_trigger_send_total","otelcol_processor_batch_metadata_cardinality","otelcol_processor_batch_timeout_trigger_send_total","otelcol_processor_incoming_items_total","otelcol_processor_outgoing_items_total","otelcol_receiver_accepted_log_records_total","otelcol_receiver_accepted_metric_points_total","otelcol_receiver_accepted_spans_total","otelcol_receiver_failed_log_records_total","otelcol_receiver_failed_metric_points_total","otelcol_receiver_failed_spans_total","otelcol_receiver_refused_log_records_total","otelcol_receiver_refused_metric_points_total","otelcol_receiver_refused_spans_total","promhttp_metric_handler_errors_total","scrape_duration_seconds","scrape_samples_post_metric_relabeling","scrape_samples_scraped","scrape_series_added","target_info","up"]}
+1
View File
@@ -0,0 +1 @@
f7c5f8c6bf2665596f7fbac265d988feb32689081ad0aa584e3114c302f1cf3a /private/tmp/lab6-server
+2
View File
@@ -0,0 +1,2 @@
/private/tmp/lab-contract-validation/bin/python scripts/validate_openapi.py
PASS: full OpenAPI 3.1 and JSON Schema validation; application NOT tested.
+12
View File
@@ -0,0 +1,12 @@
[
{
"job": "collector",
"health": "up",
"lastError": ""
},
{
"job": "messenger",
"health": "up",
"lastError": ""
}
]
+6
View File
@@ -0,0 +1,6 @@
{
"ready_observed_before_trace_query": true,
"failed_attempt_and_retry": true,
"trace_file": "retry-trace.json",
"verification_note": "Original JSON assertion expected numeric status; Tempo returned STATUS_CODE_ERROR. Corrected assertion verified saved real trace."
}
+1
View File
@@ -0,0 +1 @@
PASS: ready polling completed; saved real trace contains failed consumer and successful retry (JSON enum assertion corrected)
File diff suppressed because one or more lines are too long
+2
View File
@@ -0,0 +1,2 @@
python3 tests/smoke.py --base-url "http://127.0.0.1:18086"
PASS: lab6 public API scenario; infrastructure and grading evidence remain separate.
+184
View File
@@ -0,0 +1,184 @@
21a514acf6287bcc9c39b96e6ce22b5c58f7e0425f7cf796744f4547af11ff31 cmd/server/app.go
fcbe015008f384eafeaf017286e53085f02d8e762e5791032fb15a4f6f5f339c cmd/server/app_test.go
ebc7c7d4bb1a0ca63cf949ca349f4819b4e5672a3bb1d714fee90ab7ec48ceff cmd/server/commands.go
2308066b0bc2cb117adced1181a64d8b9998aa404d2198143000729a3b9138a1 cmd/server/healthcheck.go
3b91d936af082e60f0160d053ea79d8821e131fceb8133ae04342f6996d578a7 cmd/server/healthcheck_test.go
d4c33ca5a93583caffd63e78bef00a2af906c477e29f1ce89495ee1737219579 cmd/server/logger.go
c22d8cdf4ce31fde29945e967d3f025e280a7dc4d2022329d51be972d2a0f495 cmd/server/main.go
acc63500e1475752bc8f82472e6714d52bd30af62d82d07e44f0de3f117c22ac cmd/server/media.go
308a01f9e933419f245de0cf22262fd11ea535fc277d9add5fabceb1150e938f cmd/server/media_test.go
8332e76c999388078bc176da84fb38535b1105e32d8d4044cf6b701188476065 cmd/server/persistence.go
426bf36d68c37566a1fc998f8f682466b594aa60a253152ce0216c8df0b135b0 cmd/server/persistence_test.go
42848ffa729c73773b301ab27da96633ef5fe36fd4da2ea059bb622f49a5766f cmd/server/reconcile.go
e8e1d54f869025360853a5a73eabb3146914d4caf6b8d4f20e1a250e79058ea7 cmd/server/s3_bootstrap.go
c5c54cf34133c297c88a401f8183c8b5a269864323e24100ce0a3994e3a4f12f cmd/server/telemetry.go
9509f8dd616ad59db6c3808caf052edb81e5234df097906dc5082be206919c38 cmd/server/telemetry_test.go
aae78ee2a9c844684410dd6d727427d3437ec7b19f417b6e75dbafa203a86b51 cmd/server/worker.go
1ee98eda5b0ea42c96ef0f11e6762c1f228da7c681e63fa2765bc2d19069e5fd cmd/server/worker_test.go
41ef40897886c0878cbfe52f6716bdcb8433fb7eaddcfff298e1d54c55db423d internal/admission/distributed.go
a373c9539167a4b7c35d45334d35ffd4e9d124c1740c88c12094fededd9643b4 internal/admission/limiter.go
d52fb501e76ddb23c645c1aaa599e32da9d01e50064c9ca97ac0e320ffc7f0c8 internal/admission/limiter_test.go
8cb675a0bef8b1645071e4cb85b79a467620e99b375db5d8d3e16a54b4c5b5fa internal/config/config.go
0181673dcc4db2557783941aa8c5b3f61bc0ca6b5196d87e69df000346c40391 internal/config/config_test.go
1c853c0f771e2c75958db8158797f2287e06c8d9efe8856365b7b9c71b1747b0 internal/config/controller.go
027761b059b76898a84318ec1a8b43158d8bafd6e0b15b52efbe902b4d8c5ea3 internal/config/environment.go
3a69e20a00fa2ed816f344a990e9e0ef0077e1607d4207858b4b00e4ff5d1988 internal/config/logger.go
86cdf9e90b576f4484946bfd9605333fc52077f38d3a39c5d71ddca4cdeecda0 internal/config/memory.go
c6283fe310747e8297850b48c0a119c1d62db4903dd2c779c6296678563df188 internal/config/objectstore.go
4e57110e53843506d1dd7336feaa603538b425a6127988590fdfc9fe3e878323 internal/config/objectstore_test.go
28c61d23db4ca2ef7ed952451f465318865076d2393eaa94ff5d7bb339c4c06b internal/config/persistence.go
7377c7fc286e04292b7c82e4e286cadf409ce833079f794a501456024e73434a internal/config/persistence_test.go
a5289a9ee5c8d6b092c9719f7ccece0abbbc409ecedd187352718ec3a083bf90 internal/config/telemetry.go
58a9af253f4de710326bb3d2310459ae40568bfaa14378423a1ca883030b28e7 internal/config/telemetry_test.go
eb502257c4badca1e8a2d4eb17701937edcc2c45dd6d697d70abb1624f457e14 internal/config/worker.go
6c68b5aa8cd0bce1f56b968555dff10f53e452f9d977bd8f21e29155b2cf8442 internal/config/worker_test.go
af72da25fea9811c13a50c8133e9e8b35e070c5295069c40c0ae89cdc0aff19a internal/controller/fx.go
7b4f03ae4414de081409ff443813e7c854a132dea9bbbce5dc9354a6bf7f989c internal/controller/http/fiber/attachments.go
ecc9a69b9f5cb2f7e9be140ff2056fddef2d2094872fd3d09c166f739a3c96db internal/controller/http/fiber/attachments_test.go
a8fb7892f713529a9359b1c77202ef5fb9a2dd4d921ee9f1ec104da67ee1ad87 internal/controller/http/fiber/auth.go
2c314670f635fd5382a2599b1415636d55c524a3440bf4354a7d7304a2e3c20d internal/controller/http/fiber/auth_test.go
efdad000a8a0773983ead41c69bd94c6f020007505761f3d8ddddfa0e4ef6af7 internal/controller/http/fiber/body_limit_test.go
9c092ba7bca191f25c3ba9c9a5d1ca844126bee740a4c0262b776e947263ac68 internal/controller/http/fiber/chats_test.go
be356cf26c228958d51f5bafa4305d7325e81ab01065575acbc9b2d7a6ddd4bd internal/controller/http/fiber/configure.go
cc0fd1f1735385a5b09c836c4fbbf7da22e8343489cc9737f926bc38dcc1add9 internal/controller/http/fiber/controller.go
ad444092926bed08371ad730d41fee060879dcdc097bd2dafed1d203437c9fad internal/controller/http/fiber/controller_test.go
f5e9c3f8a8a22f51639a570e2ab2e626bde0bf29434dd6527d1da8f32f021cf0 internal/controller/http/fiber/decode.go
6ee07f110bdb29d8d2191ab8889ba60474b33a5b225739875c8a57d8434be15d internal/controller/http/fiber/dependencies.go
3351a019c43d0360ee0fd68afabb5200422d065ae7bd908b1c0a5c02a0c1ad41 internal/controller/http/fiber/error_codes.go
9d5da8d98ece2706e324cb2deca915e0811b6ad98f7aaac5805ca0f3cc0a1f9a internal/controller/http/fiber/error_registry.go
a490411aca9d3a6ddc730981cdc4e0f785172db6773db23357a05c51f7889ea3 internal/controller/http/fiber/errors.go
7040d44ac15888b0e8498a02bddf649c1789e109201f37455bffcd41ed90783c internal/controller/http/fiber/errors_test.go
8241d83c3a9a09107cab83537a6529a14d0f39cfbeab9a8bed24af005a8ba37c internal/controller/http/fiber/fixtures_auth_test.go
f514263df465c6c1e3df76590553b37f7e32330dee48add9fdfb194d9bcde28e internal/controller/http/fiber/handlers.go
d32a9a01a8b391f4d986e14947a25a0504f4363335ea1524df05e0dd8e9e61bd internal/controller/http/fiber/headers.go
29ca7d1f1207b2fbbd272062beadcfe869d007350b8d50cc2a909b0dbe5c08d1 internal/controller/http/fiber/health.go
f39cf7a0049a2ed39d6cc1fcc66b44656d9d6120914d0e973b032e12f3d0de08 internal/controller/http/fiber/lifecycle.go
496f50e5693456574614b8a47086a550018884adb37919ce82abf8c4e7e5254d internal/controller/http/fiber/lifecycle_test.go
7e67fc7c7d3076dc0927a9601871d38002d31d988c9e4c7abcac9c7a65eba327 internal/controller/http/fiber/mapping.go
e45c78489236e58f724b1e5b9a360934851ed3587345a0242f19d14d89d3b670 internal/controller/http/fiber/messages_test.go
54db82201697bdfcc65712afe61b650f8f0885fc65222dc4cc6d1c3bb07d82dd internal/controller/http/fiber/metrics.go
fe59de68ad07ae56c061b01a7946e848b3ee41a3005a3ae9fee1843d31aba5ab internal/controller/http/fiber/metrics_labels_test.go
4b2316357f3bdcb74281fd63a11b88aaebeac89a048a152fed6ddd9069793fa9 internal/controller/http/fiber/metrics_test.go
18d69e4e21f9b2231d75ce9ac6dfe0243d9aa2a5ebf51932380adcd0dfec2a3a internal/controller/http/fiber/middleware.go
b949cb7690fa561462fa254413b48e8d88d6346d1231fa88d1249b22f394deb4 internal/controller/http/fiber/middleware_test.go
3b36952bd2c08dfdbe04a3c1e0eeeb0b550edefee44b7816bfdb6a094787bda4 internal/controller/http/fiber/observation.go
c2af04ba4a1a9a1b5e6596ac5a924113bf37954b27d54037016dc1ca9ee48e77 internal/controller/http/fiber/public_errors.go
19fd03ee526e0551bbeaa61513286b267b2b252ad3eca5c86a3a5575e4200a5a internal/controller/http/fiber/public_errors_test.go
e248223517102e1eecdeba9a5e2d844c0afc14116a56e9a1d76c6afb755e63d1 internal/controller/http/fiber/routes.go
6bc72fdc23332e08e4dee8a5ed3f9110952208af86b529d5d4847ebcf00dd4c3 internal/controller/http/fiber/stream.go
0b3fad8fc87f561573bf4ee906a48a8fb317385ecc7600bdca3cc61992fa9253 internal/controller/http/fiber/users_test.go
24b6b06d6fab919cd2130697b44fd0d358265184dca0ca8362e0b4fcc2ae5a68 internal/controller/interface.go
678e197744fb2fc4b51715f51593b98761125bbaddbe4cb1b7032bd6b173ef04 internal/cursor/codec.go
6041f376a0f69a66ebf0ecacbd20d03d5d57590ae67585613256b0713e106fdf internal/cursor/codec_test.go
e205901cec2e66011ec764b70879b0eb0d28a78c4dea8913a9fb30c2d778fa8c internal/hashring/ring.go
606cdf84342b97a63eedfb9cd37aa7c99a489eee54641d8645be930a9ce6be0d internal/hashring/ring_test.go
7f1fed5f8276e19ed13e0576c633c11d213d8ad1af7e27179aea893948a795ad internal/imageprocessor/processor.go
143fb96568f494efba46ec658e7b0a88b874938bf3f1322c090e88dabd75bd99 internal/imageprocessor/processor_test.go
327ee894c8c9afa5bcf8236ed4c91befd66699c0ca33178e9690705764faf002 internal/media/orphans.go
90c319dc2ed9cc8193474ba84793094839d5c7a6ef19a103f4170da5558348fb internal/media/reconcile.go
0713380557ed6e83e4d21d94c738a239b4bf81597e543d4ff3a5277c2ca6bf53 internal/media/reconcile_test.go
3255403afcb9486d33c5bb45b5afa9c3c9b85596ce97f86ac2f224011cd8a860 internal/media/run_reconcile.go
2c27b800f8848425efa2acbe4134d9b70b4e10728a22136f4e4046806972a1ee internal/media/run_reconcile_test.go
e0e55fcaad09af39caf5d481014de408552d28b7925de8e9492aa208938e637d internal/media/service.go
c2994186863134502a3837fa3284029b7b0a51d50d4a5fce45b708177826f459 internal/media/service_test.go
3662f14499e4106d3148a79a001ab92cb0d31279516ccba9a524e6bcec2a16b4 internal/media/validation.go
b5671dfff93be81899e729d0bef63b928ab6a1bd5a84c06117fc2ed536d654bf internal/media/validation_test.go
801a6290037459a1f9d28669b4f3cdce5191317da8a48189027b7a507139fdc7 internal/model/dto/attachment.go
5e2536b8eba6bb92b751a7b817b6338755008857e3b53920d8da6fb67adeebdb internal/model/dto/models.go
896a694b0c217240343077d4287f4a6e447338c38571abbebcb3d16a519137fb internal/model/dto/session.go
d68827b0bd3e6df4037621b6941298d3923dc348bda5bf314a34861e7c34f04e internal/model/http/models.go
e2a8f39cf5ecff860bca6bceeda78779117ea122b7619621ef9a80c84eeb62cb internal/objectstore/client.go
fc0c8d446809dc4f57bddf9699a57413f5751184a3ec38c7b9ff598aa945faa7 internal/objectstore/client_test.go
5eb695bb582e545a3b43ba15e7a88b6bb70bdfd43155f2169defff2ffd41fd7c internal/objectstore/list.go
d11d878aa4b1e0e093ae39028e1cc77fbf1841036145d9ce44392b8465ebddf5 internal/objectstore/observation.go
c3f949d4056c9c3354ffb54a4fce7d95d49c1ab65780c9798a79042987ab1e43 internal/objectstore/observation_test.go
124a8a6393c3c23040b2fd7ec0dbc77b05b4a317e9b1ecddd6df366250db56a6 internal/observation/snapshot.go
3642e33cdb0ae1ca5ed0a88cc0b6d0748f836d45ba0712ae1368533310aa5a7a internal/observation/tracer.go
fe2df6990331573bbf0202ebc81c58263a7c16a29b713eefa0f0e852e4ee4a76 internal/password/password.go
1ad8dcb7d055fcb8da56d10e1089b47fe1b9cbf848381ded1a4048f8fd41278a internal/password/password_test.go
eb4a71e1d2cbc93d539770b425305b4826b98dd7770741c6677a50c0ec43b4f8 internal/pipeline/cleanup.go
e3e65b686b8ed366b548e0515535f1a3bde1ceadd70fcff22917bb3dd06cb6c5 internal/pipeline/cleanup_test.go
d844cf88188841f6e5ba393c48f79d393a70531eea9fedfce07da419c49bd366 internal/pipeline/observation.go
a0536beb0d1dec237f907e01b6c646fbcf269dcbe4b88ec09058eb6b41e04fa6 internal/pipeline/observation_test.go
559c98b3fa4d4ea4aa2a07480ccdea52b37cc0dbf0910aacef7589757effaa8c internal/pipeline/types.go
357355bc4420f9b4c8306967cdc468de6989ccb96d90d3a6ff5afa80f07c3259 internal/pipeline/worker.go
8817f62116976afcb0fae3b12fe0849325301280db9f9f89a26b1704804e760d internal/pipeline/worker_test.go
f584e498d5f902f2a8eb22bb91b0dfd7a86547797995e750356415002240a50b internal/service/auth.go
87a752eb08988aa0b76fa3c6e37e6180508d9bf774f3d9cec0cd825162094d34 internal/service/authentication/service.go
18c050293d21f5439327b2e887c46f8be15508737cddeefa6c862d9d9781586f internal/service/authentication/service_test.go
d3ef483a9fcc47c0a056c0ed9e06907f51688cbd0f87c5ce1b657b2f12fc714c internal/service/cache.go
1815bf20f8ebfa8f8f394f8aef5e3e7954ff7652a5c4f4d6b14ace4d57b99ee2 internal/service/cursor.go
a1ac40c39260c9babeaf8259985de5f84abe1ce80dc8ed9f26ad1b66b1ef35af internal/service/errors.go
58b49648c1b6e73971255cd9c5ae95853abd8bb44653ee2a912122c599ef23cb internal/service/interface.go
878415267a409244b5fa490ed09da3ed446ab5d45963f4b1c02f626fd5248614 internal/service/production/access.go
35be54339836d885f0acc60cee572a22d15802cd88ada5e52875cce625537975 internal/service/production/cache_test.go
e917208ece7e11d442c3c3ca7e33ac303a9e50b11288f2476390d601a5d68e41 internal/service/production/chats.go
cdb0653e4b842f4e07fca041c05b037dcd5832e8641da9ce66fd98138e6b7c7e internal/service/production/chats_page_test.go
b309cd0ea7c01f994dffb4bb311472f5afb09c21b2c68f87cb7267d9d5f2da65 internal/service/production/chats_test.go
f7767482299f26cc44cb8d2c2a6fd024f5caec4a2818fbde617fe99ba687a097 internal/service/production/creation.go
d002ded303f0aaf8acef41f5e5846e548c52e5b4e683d7cb986be38db4227bbd internal/service/production/errors.go
279da30df9ceaead23d0fc961d37570330e7e80d32f8300e74cb56d51d220fad internal/service/production/fixture_test.go
861263597b62be27cfbc98a5dec11fd348994cba95773405086ab39e4d18e223 internal/service/production/members.go
5ae4aae2622bad3673a5b0b4a460954a1f8ff38e337145dcfec678a401b490d4 internal/service/production/messages.go
a8fd43ed0499db68950fdc0acef7670a0b81517fdf6ca7f5a3cc2aaeff970d6d internal/service/production/messages_page_test.go
9ad9871d7d17ffaba8f3563d6495ac3e115f4d5901c253c9db0fd66ce19aa6a0 internal/service/production/messages_test.go
a19420fa45469f36a4a624b8f8a696b81af56cbfb94f28dcc26fc5940fc0aec7 internal/service/production/pages.go
f08e44678853b768efa5b307cd93d87c5d7559a9040b588c83c8a39bada51b41 internal/service/production/pages_test.go
2ab7be10ded3332e4bbfc0c825f5d355a68b2ef79385fc3af490ae3a11077859 internal/service/production/pagination.go
d57a1e5a75ba7c3d77406ad5c316b42e7907e48f7b99785a7e75af1ea13b97d9 internal/service/production/pagination_test.go
5f9009ad92a7e5ea5b7ed4aae7146a1805bdbb4ded66b57661dc1950a33b32e4 internal/service/production/service.go
ed4900e5120a58ceb4c792057f9e6fedcc0998f94c7fe1a9de12eb81198720aa internal/service/production/service_test.go
6e72b534a0ac2b9bfc7867826b5596da614eb1ef883b86b27fde5098bf818ca2 internal/service/production/users.go
9e579bf971ca9b321c354b52761a83f4e50a1f517261b5655b4c7fc47dfe8744 internal/service/production/users_test.go
19442e5931252a040559e34af83e8e22d47fa127677ed5dd273e0ba5bbf99ab0 internal/service/production/validation.go
f683306c33020d2403e91e93b0fc260ff1d3b3f1911425a7550384dfa60d9937 internal/store/interface.go
8d8c50b868c725c0303a3cbc9578f6ea2b27d1a229700d2f80fe91f0de8622f3 internal/store/memory/capacity.go
618eaf4e1c042d29abaa7df456d83a36f6b4dcc6e7a401071ec8489805dfb640 internal/store/memory/chats.go
63ae1aab707daf6e305c847b87f920d8c39d755188e3ac1cb2aad7fdce64dff8 internal/store/memory/chats_test.go
03d054b385ae51d160b6ce0441e86c2f6c4763724aa9e91228224cc88a12fdd2 internal/store/memory/messages.go
de31d43d34d4dfa8a4aeb5f057de623e52111a01680eb3b685d43ab07cd4f175 internal/store/memory/messages_test.go
0eb10952ceb798a5e6bacfd115eeaaed9cd37e8232a56c20d2c120cf457d3c5e internal/store/memory/ordering.go
e00a97d2b6d408bd8964fefd62f5a187a1de81c96f93637c0905a346b4beaa5b internal/store/memory/store.go
7dca28303c8c2d1847e5333d48b739fa6d4d1201d9577aff32fef522014b78c7 internal/store/memory/store_test.go
7ef5f5000ed30aac7e9e058d33ff4a75caa4b83040a59269ae1223081cab68af internal/store/memory/users.go
225c05e14e0c98908edaa3d3eea413d6d347b1a2a91f1732b30d2bf02a1c6b21 internal/store/memory/users_test.go
5de665ff2f33918a736a97859ff9df766087e8b5deb2e01dff5d35e115a1af19 internal/store/postgres/attachments.go
38d0e3a31c116d098a20ad871ff4f0fb046746bd9d94a8f6b166cb7236935617 internal/store/postgres/attachments_test.go
1a7f671d6c781a5f3b6a03ce80e38f87e8a11e7e4cd51fca57829be9a01811ff internal/store/postgres/chats.go
14af394f88b01701efa0b89dd079c60793eed1811d114a880dd8e5e283de6b04 internal/store/postgres/errors_test.go
0f1d4b91a9deb26f276235f3a069570b3962f279aeb5a8491d6384ad2fa942ca internal/store/postgres/idempotency.go
a88d27065e86501d47986f048bbd34fba8f2205872df2e08ef6a04ae01f98218 internal/store/postgres/idempotency_test.go
9b4445f552ad08923a59be3853fad2091ce62a4ab0f6b4875711505a4e6e5fe1 internal/store/postgres/jobs.go
40f78e3fcd8137af0e6da0416bb587678adc789ae9a9e68f6f4a18b7bd70381b internal/store/postgres/jobs_test.go
041454c30d1e1cc980567b6e11c8de0bd57cf9e0e8703d132a5172e7bc0ea901 internal/store/postgres/messages.go
8b8bf6a255cc48cee4b3e4adc94c23cf6955ecf5dfba689bba973dfccbd1b1cb internal/store/postgres/migrations/001_initial.sql
3678bb935ed8006d4bdc3e928231cfc5e8ba29e397d6b70122675933acd2a6f4 internal/store/postgres/migrations/002_idempotency.sql
448f0287ddd1e68914edcda4b39cc90daaac952a8e19a9e938ad78d27601b590 internal/store/postgres/migrations/003_attachments.sql
8d5cdffcfadd99564821fa6f7adad8d8a2d70bfaa21b630ded6dd6d06fbf2b71 internal/store/postgres/migrations/004_pipeline.sql
1336ef711833e50342534b7186c37748fae187faccd94b8c5d06035a37925b16 internal/store/postgres/migrations/005_retention.sql
7eebf916fdc3ee58b2d19098a835405aa95cb985d2c8c7f5934e1e64d1f2b9f9 internal/store/postgres/observability.go
f7e8f54ee60cc44e12760a09c8aa7f660f69c1fd8284548b6791630c49e895f8 internal/store/postgres/observability_test.go
9f8e3e77cf1f65b17496ec65041e1546211b402e670a601db49c6bf9edfab09a internal/store/postgres/pipeline_integration_test.go
a770985780d475f03ca9990522f02d9bcffaa69b7701128df11e0939b55848ba internal/store/postgres/reconcile.go
375914d765b4ae8e1ba25767bb6e96d6de8ce29a8787055f4242971cb0b5900d internal/store/postgres/reconcile_fixture_test.go
5b300bfc628e8b8d84094b97fdebde9d021f626321323961e87801af8766f950 internal/store/postgres/research_test.go
6ca456767aec350fe81af74deb82a04fcb8689896d11ed547d3855a01f1b57e7 internal/store/postgres/retention.go
889a63b51b29012f4ae5499d1c0577fe29f2f2959b05629f8e123715cfc1f75f internal/store/postgres/sessions.go
ac5a64c966681f8baf5dbbc1232c9f6a2a54ad137869acfe88052e7cb943cfd5 internal/store/postgres/store.go
aed9f7ae7b2145f14ca4199dc98d0c3aedd454462abf2e981afce5ca2b02e74a internal/store/postgres/store_test.go
15de54e4bea80c8523429e3ef5b22c49a2b36f48c9fa58c2b76bc0653a6eae23 internal/store/postgres/users.go
0b6655c6c7d7f60758b05b3d5fc6abfea4a7de3466f7fd56d1cac0b537cc76d5 internal/streamqueue/queue.go
95bbe1f4808c3f07264d6f05a83e2cc89e187417c769095dfb13978e86f62287 internal/streamqueue/queue_test.go
d99595e1f74406c5aa617c0ec062afb7f12f116bd86776e87cc9c9a436ff7eea internal/strictjson/decode.go
ea6273526572b4bfcf681ef2659ea2c1ec74bfedeb5e9bdbd83ebfabe0647bf9 internal/strictjson/decode_test.go
3830b93225ff8056993643fd404ab990ddb752fd80fb8ece6410e834b6023f5f internal/strictjson/optional_test.go
009d4d61832b93f1e014e1d567d9e1828efc023ec2c40204d96c5d8097c0551f internal/telemetry/metrics.go
ddba713ce3941cef9fddd4968d63359105e4f32366a87b469268a57d0da6364a internal/telemetry/postgres.go
7b973eadb1610369f4cc8d3dc2a4fa78d0732fb8677091c3c2db12d628868657 internal/telemetry/runtime.go
f09654814b133000304dac635603addbc4ea6fb8dea3a3546dc7263149ab6ddb internal/telemetry/runtime_test.go
4f92838ad08685b5470f9a35ec9c48a136de333ba8d2287b1384f0a35ddb1cb6 internal/telemetry/saturation.go
4f9ef25f02df303db401d99780888bac94ebd7601f8227be710acefd80f09987 internal/telemetry/spans.go
8cdb6f5e2e83341b624e9b14a52b73e17ec03b41dad620f6e3d39a3244930b4a internal/valkey/admission.go
6aa3f9dbf0e5f5e60a06245fefe4d5d139ab181a47ec0e2d2e88346158fd4359 internal/valkey/cache.go
b30fccec3b12374e76b93a2a76ffa7d9fc6a9d6a123793b8effb6b0da679a7d0 internal/valkey/client.go
461201233ffb38201633ee6fc75d4ecd963e3ef7cf18ca6e2fa0eb88ab69e395 internal/valkey/client_test.go
+8
View File
@@ -0,0 +1,8 @@
python3 scripts/check_contract.py
PASS: offline skeleton structure, local refs and Python syntax; application NOT tested.
helm lint charts/messenger
==> Linting charts/messenger
[INFO] Chart.yaml: icon is recommended
1 chart(s) linted, 0 chart(s) failed
helm template lab2 charts/messenger >/dev/null
+78
View File
@@ -0,0 +1,78 @@
0.135.0: Pulling from otel/opentelemetry-collector-contrib
eae93a3313d3: Pulling fs layer
e431bff99ece: Pulling fs layer
df85c9d0ca2e: Pulling fs layer
eae93a3313d3: Download complete
e431bff99ece: Download complete
df85c9d0ca2e: Download complete
Digest: sha256:89107a3a8f4636a396927edf7025bb9614b8da2d92f4cc3f43109e8d115736e2
Status: Downloaded newer image for otel/opentelemetry-collector-contrib:0.135.0
docker.io/otel/opentelemetry-collector-contrib:0.135.0
v3.5.0: Pulling from prom/prometheus
Digest: sha256:63805ebb8d2b3920190daf1cb14a60871b16fd38bed42b857a3182bc621f4996
Status: Image is up to date for prom/prometheus:v3.5.0
docker.io/prom/prometheus:v3.5.0
3.5.5: Pulling from grafana/loki
56ce5a7a0a8c: Pulling fs layer
eb8f5749650b: Pulling fs layer
d557676654e5: Pulling fs layer
f04daeaed6c9: Pulling fs layer
d82bc7a76a83: Pulling fs layer
29852e282777: Pulling fs layer
2e4cf50eeb92: Pulling fs layer
b40161cd83fc: Pulling fs layer
d858cbc252ad: Pulling fs layer
e1089d61b200: Pulling fs layer
38066e8d70f6: Pulling fs layer
3f4e2c586348: Pulling fs layer
1069fc2daed1: Pulling fs layer
49e5f77b20e6: Pulling fs layer
0f8b424aa0b9: Pulling fs layer
ffeccacd1a73: Pulling fs layer
17f3dd0d85e8: Pulling fs layer
eb8f5749650b: Download complete
d858cbc252ad: Download complete
1069fc2daed1: Download complete
2e4cf50eeb92: Download complete
b40161cd83fc: Download complete
f04daeaed6c9: Download complete
3f4e2c586348: Download complete
0f8b424aa0b9: Download complete
17f3dd0d85e8: Download complete
d557676654e5: Download complete
d82bc7a76a83: Download complete
e1089d61b200: Download complete
38066e8d70f6: Download complete
49e5f77b20e6: Download complete
56ce5a7a0a8c: Download complete
ffeccacd1a73: Download complete
29852e282777: Download complete
Digest: sha256:31628519045e7f28692a7ae73b4a3fd293dccb425585ed5d16ceea3b5c9592e6
Status: Downloaded newer image for grafana/loki:3.5.5
docker.io/grafana/loki:3.5.5
2.8.2: Pulling from grafana/tempo
Digest: sha256:0ef775495967cd5d7a6b2e146b6ea695d624803c8db8349fb8ce4164f719f9b7
Status: Image is up to date for grafana/tempo:2.8.2
docker.io/grafana/tempo:2.8.2
12.1.1: Pulling from grafana/grafana
464d91115c2e: Pulling fs layer
9f1d07f40523: Pulling fs layer
7f46d17c4b0f: Pulling fs layer
476716c10da1: Pulling fs layer
6b1ef42fa3bc: Pulling fs layer
c049b4b5b81d: Pulling fs layer
ded2bfdd8adf: Pulling fs layer
3540d00d3a8d: Pulling fs layer
4f4fb700ef54: Pulling fs layer
4f4fb700ef54: Already exists
9f1d07f40523: Download complete
7f46d17c4b0f: Download complete
476716c10da1: Download complete
ded2bfdd8adf: Download complete
3540d00d3a8d: Download complete
464d91115c2e: Download complete
6b1ef42fa3bc: Download complete
c049b4b5b81d: Download complete
Digest: sha256:a1701c2180249361737a99a01bc770db39381640e4d631825d38ff4535efa47d
Status: Downloaded newer image for grafana/grafana:12.1.1
docker.io/grafana/grafana:12.1.1
+77
View File
@@ -0,0 +1,77 @@
Unable to find image 'grafana/tempo:2.8.2' locally
2.8.2: Pulling from grafana/tempo
8ab2969f3376: Pulling fs layer
2e4cf50eeb92: Pulling fs layer
7b8a369ef91e: Pulling fs layer
d557676654e5: Pulling fs layer
eb8f5749650b: Pulling fs layer
9f16f7a29f29: Pulling fs layer
e644e3619489: Pulling fs layer
4e9f20d26c87: Pulling fs layer
ffeccacd1a73: Pulling fs layer
f7a549fe62c7: Pulling fs layer
e1089d61b200: Pulling fs layer
f80d0db27f51: Pulling fs layer
f1f6c2e50dbe: Pulling fs layer
3f4e2c586348: Pulling fs layer
0f8b424aa0b9: Pulling fs layer
d858cbc252ad: Pulling fs layer
d82bc7a76a83: Pulling fs layer
1069fc2daed1: Pulling fs layer
b40161cd83fc: Pulling fs layer
eb8f5749650b: Already exists
d82bc7a76a83: Download complete
2e4cf50eeb92: Download complete
0f8b424aa0b9: Download complete
1069fc2daed1: Download complete
3f4e2c586348: Download complete
e1089d61b200: Download complete
d858cbc252ad: Download complete
b40161cd83fc: Download complete
d557676654e5: Download complete
ffeccacd1a73: Download complete
4e9f20d26c87: Download complete
f7a549fe62c7: Download complete
f80d0db27f51: Download complete
9f16f7a29f29: Download complete
e644e3619489: Download complete
7b8a369ef91e: Download complete
8ab2969f3376: Download complete
f1f6c2e50dbe: Download complete
Digest: sha256:0ef775495967cd5d7a6b2e146b6ea695d624803c8db8349fb8ce4164f719f9b7
Status: Downloaded newer image for grafana/tempo:2.8.2
Unable to find image 'grafana/loki:3.5.5' locally
3.5.5: Pulling from grafana/loki
f04daeaed6c9: Pulling fs layer
29852e282777: Pulling fs layer
17f3dd0d85e8: Pulling fs layer
38066e8d70f6: Pulling fs layer
17f3dd0d85e8: Already exists
38066e8d70f6: Already exists
f04daeaed6c9: Already exists
29852e282777: Download complete
Digest: sha256:31628519045e7f28692a7ae73b4a3fd293dccb425585ed5d16ceea3b5c9592e6
Status: Downloaded newer image for grafana/loki:3.5.5
Unable to find image 'grafana/grafana:12.1.1' locally
12.1.1: Pulling from grafana/grafana
476716c10da1: Pulling fs layer
7f46d17c4b0f: Pulling fs layer
ded2bfdd8adf: Pulling fs layer
464d91115c2e: Pulling fs layer
4f4fb700ef54: Pulling fs layer
3540d00d3a8d: Pulling fs layer
c049b4b5b81d: Pulling fs layer
6b1ef42fa3bc: Pulling fs layer
9f1d07f40523: Pulling fs layer
4f4fb700ef54: Already exists
9f1d07f40523: Download complete
476716c10da1: Download complete
ded2bfdd8adf: Download complete
7f46d17c4b0f: Download complete
3540d00d3a8d: Download complete
464d91115c2e: Download complete
6b1ef42fa3bc: Download complete
c049b4b5b81d: Download complete
Digest: sha256:a1701c2180249361737a99a01bc770db39381640e4d631825d38ff4535efa47d
Status: Downloaded newer image for grafana/grafana:12.1.1
Telemetry stack created; state: /private/tmp/lab6-observability.env
+4
View File
@@ -0,0 +1,4 @@
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/telemetry (cached)
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/pipeline 1.787s
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/objectstore 2.021s
ok gitea.privcloud.tech/vlad_marlo/mtusi2026lab6/internal/config (cached)
+1
View File
@@ -0,0 +1 @@
ready
+1
View File
@@ -0,0 +1 @@
{"traces":[{"traceID":"251b904fc2df1ae84715482aee19d976","rootServiceName":"messenger-worker","rootTraceName":"postgres.query","startTimeUnixNano":"1793283625863699000","durationMs":1},{"traceID":"41b3bf1c6d071c25fc47398e4295fbc8","rootServiceName":"messenger-worker","rootTraceName":"postgres.query","startTimeUnixNano":"1793283623836906000","durationMs":1},{"traceID":"55e55bb35edc0fb3bb0bcb8ba27d4362","rootServiceName":"messenger-worker","rootTraceName":"postgres.query","startTimeUnixNano":"1793283622818854000","durationMs":3},{"traceID":"5017ac3b7f0591dd098e6ffea9a3ec4e","rootServiceName":"messenger-worker","rootTraceName":"postgres.query","startTimeUnixNano":"1793283620792636000","durationMs":2},{"traceID":"13832d220b5e286749725102cd23307f","rootServiceName":"messenger-worker","rootTraceName":"postgres.query","startTimeUnixNano":"1793283617693074000","durationMs":3}],"metrics":{"inspectedTraces":14,"inspectedBytes":"18220","completedJobs":1,"totalJobs":1}}
+1
View File
@@ -0,0 +1 @@
+1
View File
@@ -0,0 +1 @@
Initial run exited 1: assertion required API firing during outage, but first firing occurred in db-recovery. Raw snapshots show firing and resolution. Ready selector was corrected and verified separately in evidence/ready-slo.
+134
View File
@@ -0,0 +1,134 @@
{"at":1793284209,"phase":"baseline","alerts":[]}
{"at":1793284214,"phase":"baseline","alerts":[]}
{"at":1793284219,"phase":"baseline","alerts":[]}
{"at":1793284224,"phase":"baseline","alerts":[]}
{"at":1793284229,"phase":"baseline","alerts":[]}
{"at":1793284234,"phase":"baseline","alerts":[]}
{"at":1793284239,"phase":"baseline","alerts":[]}
{"at":1793284244,"phase":"baseline","alerts":[]}
{"at":1793284250,"phase":"baseline","alerts":[]}
{"at":1793284255,"phase":"baseline","alerts":[]}
{"at":1793284260,"phase":"baseline","alerts":[]}
{"at":1793284265,"phase":"baseline","alerts":[]}
{"at":1793284270,"phase":"baseline","alerts":[]}
{"at":1793284275,"phase":"baseline","alerts":[]}
{"at":1793284280,"phase":"baseline","alerts":[]}
{"at":1793284285,"phase":"baseline","alerts":[]}
{"at":1793284290,"phase":"baseline","alerts":[]}
{"at":1793284295,"phase":"baseline","alerts":[]}
{"at":1793284300,"phase":"baseline","alerts":[]}
{"at":1793284305,"phase":"baseline","alerts":[]}
{"at":1793284310,"phase":"baseline","alerts":[]}
{"at":1793284315,"phase":"baseline","alerts":[]}
{"at":1793284320,"phase":"baseline","alerts":[]}
{"at":1793284326,"phase":"baseline","alerts":[]}
{"at":1793284331,"phase":"short-db-spike","alerts":[]}
{"at":1793284336,"phase":"spike-recovery","alerts":[]}
{"at":1793284341,"phase":"spike-recovery","alerts":[]}
{"at":1793284346,"phase":"spike-recovery","alerts":[]}
{"at":1793284351,"phase":"spike-recovery","alerts":[]}
{"at":1793284356,"phase":"spike-recovery","alerts":[]}
{"at":1793284361,"phase":"spike-recovery","alerts":[]}
{"at":1793284366,"phase":"spike-recovery","alerts":[]}
{"at":1793284371,"phase":"spike-recovery","alerts":[]}
{"at":1793284376,"phase":"spike-recovery","alerts":[]}
{"at":1793284382,"phase":"spike-recovery","alerts":[]}
{"at":1793284387,"phase":"spike-recovery","alerts":[]}
{"at":1793284392,"phase":"spike-recovery","alerts":[]}
{"at":1793284397,"phase":"spike-recovery","alerts":[]}
{"at":1793284402,"phase":"spike-recovery","alerts":[]}
{"at":1793284407,"phase":"spike-recovery","alerts":[]}
{"at":1793284412,"phase":"spike-recovery","alerts":[]}
{"at":1793284417,"phase":"spike-recovery","alerts":[]}
{"at":1793284422,"phase":"spike-recovery","alerts":[]}
{"at":1793284427,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284432,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284437,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284442,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284448,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284453,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284458,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284463,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284468,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284473,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284478,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284483,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284488,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284493,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284498,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284503,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284508,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284513,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284518,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284523,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284528,"phase":"sustained-db-outage","alerts":[]}
{"at":1793284533,"phase":"sustained-db-outage","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"pending","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1e+00"}]}
{"at":1793284539,"phase":"sustained-db-outage","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"pending","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1e+00"}]}
{"at":1793284544,"phase":"sustained-db-outage","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"pending","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1e+00"}]}
{"at":1793284549,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"pending","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1e+00"}]}
{"at":1793284554,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"pending","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1e+00"}]}
{"at":1793284559,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"pending","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1e+00"}]}
{"at":1793284564,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"5.3125e-01"}]}
{"at":1793284569,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"3.333333333333333e-01"}]}
{"at":1793284574,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"2.2033898305084748e-01"}]}
{"at":1793284579,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1.6216216216216214e-01"}]}
{"at":1793284585,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"1.1363636363636365e-01"}]}
{"at":1793284590,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"7.84313725490196e-02"}]}
{"at":1793284595,"phase":"db-recovery","alerts":[{"labels":{"alertname":"MessengerAPIBurnRate","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"API consumes the 99% availability budget at more than 5x in both windows"},"state":"firing","activeAt":"2026-10-29T14:35:31.842599208Z","value":"5.982905982905984e-02"}]}
{"at":1793284600,"phase":"db-recovery","alerts":[]}
{"at":1793284605,"phase":"db-recovery","alerts":[]}
{"at":1793284610,"phase":"db-recovery","alerts":[]}
{"at":1793284615,"phase":"db-recovery","alerts":[]}
{"at":1793284620,"phase":"db-recovery","alerts":[]}
{"at":1793284625,"phase":"db-recovery","alerts":[]}
{"at":1793284630,"phase":"db-recovery","alerts":[]}
{"at":1793284635,"phase":"db-recovery","alerts":[]}
{"at":1793284661,"phase":"worker-stopped","alerts":[]}
{"at":1793284667,"phase":"worker-stopped","alerts":[]}
{"at":1793284672,"phase":"worker-stopped","alerts":[]}
{"at":1793284677,"phase":"worker-stopped","alerts":[]}
{"at":1793284682,"phase":"worker-stopped","alerts":[]}
{"at":1793284687,"phase":"worker-stopped","alerts":[]}
{"at":1793284692,"phase":"worker-stopped","alerts":[]}
{"at":1793284697,"phase":"worker-stopped","alerts":[]}
{"at":1793284702,"phase":"worker-stopped","alerts":[]}
{"at":1793284707,"phase":"worker-stopped","alerts":[]}
{"at":1793284712,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"pending","activeAt":"2026-10-29T14:38:31.842599208Z","value":"6.3833531e+01"}]}
{"at":1793284717,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"pending","activeAt":"2026-10-29T14:38:31.842599208Z","value":"6.8832463e+01"}]}
{"at":1793284722,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"pending","activeAt":"2026-10-29T14:38:31.842599208Z","value":"7.3832915e+01"}]}
{"at":1793284727,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"7.8833019e+01"}]}
{"at":1793284732,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"8.3833952e+01"}]}
{"at":1793284737,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"8.883363e+01"}]}
{"at":1793284742,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"9.3834666e+01"}]}
{"at":1793284747,"phase":"worker-stopped","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"9.8832359e+01"}]}
{"at":1793284753,"phase":"worker-recovery","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"1.03832518e+02"}]}
{"at":1793284758,"phase":"worker-recovery","alerts":[{"labels":{"alertname":"MessengerQueueLag","severity":"warning"},"annotations":{"runbook":"REPORT.md#диагностика","summary":"Accepted work has been waiting for over 60 seconds"},"state":"firing","activeAt":"2026-10-29T14:38:31.842599208Z","value":"1.12255325e+02"}]}
{"at":1793284763,"phase":"worker-recovery","alerts":[]}
{"at":1793284768,"phase":"worker-recovery","alerts":[]}
{"at":1793284773,"phase":"worker-recovery","alerts":[]}
{"at":1793284778,"phase":"worker-recovery","alerts":[]}
{"at":1793284783,"phase":"worker-recovery","alerts":[]}
{"at":1793284788,"phase":"worker-recovery","alerts":[]}
{"at":1793284793,"phase":"worker-recovery","alerts":[]}
{"at":1793284798,"phase":"worker-recovery","alerts":[]}
{"at":1793284803,"phase":"worker-recovery","alerts":[]}
{"at":1793284808,"phase":"worker-recovery","alerts":[]}
{"at":1793284813,"phase":"worker-recovery","alerts":[]}
{"at":1793284818,"phase":"worker-recovery","alerts":[]}
{"at":1793284823,"phase":"worker-recovery","alerts":[]}
{"at":1793284828,"phase":"worker-recovery","alerts":[]}
{"at":1793284833,"phase":"worker-recovery","alerts":[]}
{"at":1793284838,"phase":"worker-recovery","alerts":[]}
{"at":1793284844,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284849,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284854,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284859,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284864,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284869,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284874,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284879,"phase":"trace-backend-outage","alerts":[]}
{"at":1793284885,"phase":"trace-backend-outage","alerts":[{"labels":{"alertname":"MessengerTelemetryDrops","severity":"info"},"annotations":{"summary":"Trace backend delivery is failing; inspect bounded collector queues"},"state":"firing","activeAt":"2026-10-29T14:41:21.842599208Z","value":"1.456090181818182e+02"}]}
{"at":1793284893,"phase":"telemetry-recovery","alerts":[{"labels":{"alertname":"MessengerTelemetryDrops","severity":"info"},"annotations":{"summary":"Trace backend delivery is failing; inspect bounded collector queues"},"state":"firing","activeAt":"2026-10-29T14:41:21.842599208Z","value":"1.456118404305611e+02"}]}
{"at":1793284898,"phase":"telemetry-recovery","alerts":[{"labels":{"alertname":"MessengerTelemetryDrops","severity":"info"},"annotations":{"summary":"Trace backend delivery is failing; inspect bounded collector queues"},"state":"firing","activeAt":"2026-10-29T14:41:21.842599208Z","value":"1.4560619613832222e+02"}]}
{"at":1793284903,"phase":"telemetry-recovery","alerts":[{"labels":{"alertname":"MessengerTelemetryDrops","severity":"info"},"annotations":{"summary":"Trace backend delivery is failing; inspect bounded collector queues"},"state":"firing","activeAt":"2026-10-29T14:41:21.842599208Z","value":"1.4560884347557317e+02"}]}
{"at":1793284908,"phase":"telemetry-recovery","alerts":[{"labels":{"alertname":"MessengerTelemetryDrops","severity":"info"},"annotations":{"summary":"Trace backend delivery is failing; inspect bounded collector queues"},"state":"firing","activeAt":"2026-10-29T14:41:21.842599208Z","value":"1.4560884347557317e+02"}]}

Some files were not shown because too many files have changed in this diff Show More