forked from mtusi2026/mtusi2026lab6
Source: immutable lab5 snapshot f88e9ba43cdfd7eb6a5a7ae5feb4247b4e820071; forward the allowed diff from 64d5c67. Carry SQLAlchemy, Alembic, reliability fixes, versioned jobs, infrastructure and student tests without changing protected coursework files. Validation: make check, validate, lint; 515 student tests passed with one Linux-only skip; public smoke with telemetry enabled and repeat migration passed. Stop the owned stack and retain volumes. Preserve the existing OTel work in progress; grade implementation remains a separate phase.
107 lines
4.4 KiB
Bash
107 lines
4.4 KiB
Bash
# Copy to .env for your LOCAL synthetic test environment; never commit .env.
|
|
# These are logical interface suggestions; map actual framework names in REPORT.md.
|
|
APP_HOST=0.0.0.0
|
|
APP_PORT=8080
|
|
APP_ENV=lab
|
|
SESSION_TTL_SECONDS=3600
|
|
# Choose credentials locally. File paths contain no secret values.
|
|
DATABASE_URL_FILE=/run/secrets/database_url
|
|
# Optional on 3, required use on 4 in lab2; Redis OR Valkey:
|
|
SESSION_STORE=postgres
|
|
CACHE_URL_FILE=/run/secrets/cache_url
|
|
API_REPLICAS=2
|
|
IDEMPOTENCY_TTL_SECONDS=86400
|
|
S3_ENDPOINT=http://s3:9000
|
|
S3_REGION=us-east-1
|
|
S3_BUCKET=messenger-attachments
|
|
S3_ACCESS_KEY_ID_FILE=/run/secrets/s3_access_key_id
|
|
S3_SECRET_ACCESS_KEY_FILE=/run/secrets/s3_secret_access_key
|
|
MAX_UPLOAD_BYTES=10485760
|
|
MAX_IMAGE_PIXELS=40000000
|
|
BROKER_URL_FILE=/run/secrets/broker_url
|
|
WORKER_CONCURRENCY=2
|
|
JOB_MAX_ATTEMPTS=5
|
|
JOB_TIMEOUT_SECONDS=60
|
|
STAGING_RETENTION_SECONDS=86400
|
|
OTEL_SERVICE_NAME=messenger-api
|
|
# Worker must set a distinct service.name.
|
|
OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4318
|
|
OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
|
|
OTEL_RESOURCE_ATTRIBUTES=deployment.environment.name=lab
|
|
# Solution-specific: published LB ports, replica limits, workers and pool per replica,
|
|
# LB queue per replica, drain window before closing the listener on SIGTERM, PostgreSQL
|
|
# limits, load generator limits (profile bench), cursor key file. API_PORT/SHORTTTL_PORT of lab2 are gone:
|
|
# only the load balancer is published.
|
|
LB_HTTP_PORT=18086
|
|
LB_STATS_PORT=26085
|
|
API_CPUS=1
|
|
API_MEMORY=512m
|
|
WEB_CONCURRENCY=2
|
|
DB_POOL_MAX_SIZE=8
|
|
API_SERVER_MAXCONN=64
|
|
DRAIN_SECONDS=2
|
|
PG_MAX_CONNECTIONS=200
|
|
PG_CPUS=2
|
|
PG_MEMORY=1g
|
|
K6_CPUS=2
|
|
K6_MEMORY=512m
|
|
CURSOR_SECRET_FILE=/run/secrets/cursor_secret
|
|
# Solution-specific for lab4: S3 client timeouts (connect + read, two attempts stay below
|
|
# REQUEST_TIMEOUT_SECONDS=8), parallel image checks per worker, RustFS memory limit.
|
|
S3_CONNECT_TIMEOUT_SECONDS=1
|
|
S3_READ_TIMEOUT_SECONDS=2
|
|
IMAGE_CHECK_CONCURRENCY=2
|
|
S3_MEMORY=512m
|
|
# Solution-specific for lab4 grade 4: upload bodies buffered at once per worker, grace period
|
|
# before an abandoned pending upload is swept, sweep interval and rows per sweep pass.
|
|
UPLOAD_CONCURRENCY=3
|
|
UPLOAD_GRACE_SECONDS=900
|
|
UPLOAD_SWEEP_INTERVAL_SECONDS=30
|
|
UPLOAD_SWEEP_BATCH=100
|
|
# Fixed glibc mmap threshold for the API: buffers above 128 KiB are returned to the system on free.
|
|
MALLOC_MMAP_THRESHOLD_=131072
|
|
# Solution-specific for lab5: RabbitMQ management UI on 127.0.0.1, backoff base of a transient
|
|
# retry (doubles per attempt up to 60 s), relay poll and sweep intervals, worker limits and the
|
|
# PostgreSQL pool of relay and worker. FAULT_POINT is set only by infra/compose.faults.yaml.
|
|
BROKER_MANAGEMENT_PORT=26086
|
|
JOB_BACKOFF_BASE_SECONDS=2
|
|
OUTBOX_POLL_SECONDS=1
|
|
SWEEP_INTERVAL_SECONDS=5
|
|
WORKER_CPUS=2
|
|
WORKER_MEMORY=1g
|
|
PIPELINE_DB_POOL_MAX_SIZE=4
|
|
# Solution-specific for lab5 grade 4: render time per job (the render process is killed after it),
|
|
# address space of one render process (WORKER_MEMORY >= WORKER_CONCURRENCY * RENDER_MEMORY_MB plus
|
|
# ~120 MiB of the worker itself), jobs per render process before it is replaced.
|
|
RENDER_TIMEOUT_SECONDS=30
|
|
RENDER_MEMORY_MB=448
|
|
RENDER_TASKS_PER_CHILD=100
|
|
# Solution-specific for lab6: host ports of Prometheus, Loki, Tempo and Grafana (127.0.0.1 only),
|
|
# Prometheus retention, OTLP export timeout in seconds, metric export interval in ms, SDK queue
|
|
# sizes, the bounded flush on shutdown; OTEL_SDK_DISABLED=true turns the SDK and instrumentations off.
|
|
# relay and worker get OTEL_SERVICE_NAME messenger-relay and messenger-worker in compose.yaml.
|
|
PROMETHEUS_PORT=26090
|
|
LOKI_PORT=26310
|
|
TEMPO_PORT=26320
|
|
GRAFANA_PORT=26300
|
|
PROMETHEUS_RETENTION=7d
|
|
OTEL_SDK_DISABLED=false
|
|
OTEL_EXPORTER_OTLP_TIMEOUT=2
|
|
OTEL_METRIC_EXPORT_INTERVAL=10000
|
|
OTEL_BSP_MAX_QUEUE_SIZE=2048
|
|
OTEL_BLRP_MAX_QUEUE_SIZE=2048
|
|
TELEMETRY_SHUTDOWN_SECONDS=2
|
|
# Minimal client transfer rate, bytes/s: every body byte moved in either direction extends the
|
|
# request deadline by 1/rate, so slow but steady uploads and downloads outlive REQUEST_TIMEOUT_SECONDS.
|
|
MIN_TRANSFER_RATE_BYTES=131072
|
|
# Solution-specific for lab4 track 2: limits of the one-off reconciler (profile reconcile), its S3
|
|
# read timeout for listing pages, optional CPU pinning of the measured services (empty = no pinning)
|
|
# and the CPU limit of RustFS (make reconcile-cost raises it with its memory for the 100k point).
|
|
RECONCILE_CPUS=1
|
|
RECONCILE_MEMORY=256m
|
|
RECONCILE_S3_READ_TIMEOUT_SECONDS=10
|
|
RECONCILE_CPUSET=
|
|
S3_CPUSET=
|
|
PG_CPUSET=
|
|
S3_CPUS=1
|