mirror of
https://github.com/we-promise/sure.git
synced 2026-07-19 08:15:21 +00:00
Merge branch 'main' into Transfer-charges
This commit is contained in:
maverick
8
.github/workflows/preview-deploy.yml
vendored
8
.github/workflows/preview-deploy.yml
vendored
@@ -361,7 +361,13 @@ jobs:
|
||||
last_error=""
|
||||
mkdir -p "$diagnostics_dir"
|
||||
|
||||
for attempt in $(seq 1 40); do
|
||||
# ~100 polls x ~3.5s = up to ~6 min. The preview must cold-start the
|
||||
# container (≈1.3 GB image pull + sandbox init) and generate the full
|
||||
# demo dataset before previewReady flips. A real Cloudflare standard-1
|
||||
# run measured previewReady at ~195s (rails ~46s, demo data ~149s) —
|
||||
# the old 40-poll (~140s) budget would have failed a working preview.
|
||||
# Keep generous headroom; the loop still breaks early on ready/failed.
|
||||
for attempt in $(seq 1 100); do
|
||||
if curl -fsS --connect-timeout 5 --max-time 15 "$PREVIEW_URL/_container_status" -o "$diagnostics_file"; then
|
||||
if jq -e . "$diagnostics_file" >/dev/null 2>&1; then
|
||||
jq -c --argjson attempt "$attempt" --arg at "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
|
||||
|
||||
@@ -48,13 +48,41 @@ RUN groupadd --system --gid 1000 rails && \
|
||||
echo "rails ALL=(ALL) NOPASSWD: /usr/bin/pg_ctlcluster, /usr/bin/redis-server" > /etc/sudoers.d/rails && \
|
||||
chmod 0440 /etc/sudoers.d/rails
|
||||
|
||||
# Configure PostgreSQL to allow local connections
|
||||
RUN PG_HBA=$(find /etc/postgresql -name pg_hba.conf 2>/dev/null | head -1) && \
|
||||
if [ -n "$PG_HBA" ]; then \
|
||||
echo "local all all trust" > "$PG_HBA" && \
|
||||
echo "host all all 127.0.0.1/32 trust" >> "$PG_HBA" && \
|
||||
echo "host all all ::1/128 trust" >> "$PG_HBA"; \
|
||||
fi
|
||||
# Configure PostgreSQL to allow local connections. Target the highest-version
|
||||
# cluster's pg_hba.conf -- the same one the entrypoint starts (ls
|
||||
# /etc/postgresql | sort -V | tail -1) -- so the trust rules always land on the
|
||||
# cluster that actually runs, even if multiple majors are present.
|
||||
RUN PG_VERSION="$(ls /etc/postgresql 2>/dev/null | sort -V | tail -1)" && \
|
||||
PG_HBA="/etc/postgresql/${PG_VERSION}/main/pg_hba.conf" && \
|
||||
if [ -z "$PG_VERSION" ] || [ ! -f "$PG_HBA" ]; then \
|
||||
echo "ERROR: pg_hba.conf not found for cluster '${PG_VERSION:-none}'; cannot configure local trust" >&2; \
|
||||
exit 1; \
|
||||
fi && \
|
||||
echo "local all all trust" > "$PG_HBA" && \
|
||||
echo "host all all 127.0.0.1/32 trust" >> "$PG_HBA" && \
|
||||
echo "host all all ::1/128 trust" >> "$PG_HBA"
|
||||
|
||||
# Use file-backed dynamic shared memory instead of POSIX /dev/shm.
|
||||
# Cloudflare Containers provide only a tiny /dev/shm, and PostgreSQL's default
|
||||
# dynamic_shared_memory_type = posix FATALs on startup there with
|
||||
# "could not resize shared memory segment ... No space left on device", which
|
||||
# kills the container before it can serve a port. mmap keeps DSM in the data
|
||||
# directory ($PGDATA/pg_dynshmem), removing the /dev/shm dependency. Local
|
||||
# Docker hides this because its default /dev/shm is 64MB.
|
||||
#
|
||||
# Select the highest-version cluster's config -- the same one the entrypoint
|
||||
# starts (ls /etc/postgresql | sort -V | tail -1) -- so the override always
|
||||
# lands on the cluster that actually runs, even if multiple majors are present.
|
||||
RUN PG_VERSION="$(ls /etc/postgresql 2>/dev/null | sort -V | tail -1)" && \
|
||||
PG_CONF="/etc/postgresql/${PG_VERSION}/main/postgresql.conf" && \
|
||||
if [ -z "$PG_VERSION" ] || [ ! -f "$PG_CONF" ]; then \
|
||||
echo "ERROR: postgresql.conf not found for cluster '${PG_VERSION:-none}'; cannot disable /dev/shm DSM dependency" >&2; \
|
||||
exit 1; \
|
||||
fi && \
|
||||
sed -i 's/^[[:space:]]*dynamic_shared_memory_type[[:space:]]*=/# &/' "$PG_CONF" && \
|
||||
printf '\n# Preview: avoid /dev/shm dependency (small in Cloudflare Containers)\ndynamic_shared_memory_type = mmap\n' >> "$PG_CONF" && \
|
||||
grep -qx 'dynamic_shared_memory_type = mmap' "$PG_CONF" && \
|
||||
echo "Configured dynamic_shared_memory_type=mmap in $PG_CONF"
|
||||
|
||||
# Create database directory with correct permissions
|
||||
RUN mkdir -p /var/run/postgresql && \
|
||||
@@ -72,19 +100,26 @@ set -e
|
||||
|
||||
cd /rails
|
||||
|
||||
emit_status() {
|
||||
# Diagnostics posts are best-effort and must NEVER stall boot: the worker's
|
||||
# Durable Object can be unresponsive while it waits for this container's port,
|
||||
# so an unbounded curl here deadlocks startup against the port check.
|
||||
emit_status_sync() {
|
||||
if [ -n "$PREVIEW_ORIGIN" ] && [ -n "$PREVIEW_DIAGNOSTICS_NONCE" ]; then
|
||||
local stage="$1"
|
||||
local detail="$2"
|
||||
local payload
|
||||
payload=$(STAGE="$stage" DETAIL="$detail" ruby -rjson -e 'print JSON.generate({stage: ENV.fetch("STAGE"), detail: ENV.fetch("DETAIL", "")})' 2>/dev/null) || return 0
|
||||
curl -fsS -X POST "$PREVIEW_ORIGIN/_container_event" \
|
||||
curl -fsS --connect-timeout 2 --max-time 5 -X POST "$PREVIEW_ORIGIN/_container_event" \
|
||||
-H 'content-type: application/json' \
|
||||
-H "x-preview-diagnostics-nonce: $PREVIEW_DIAGNOSTICS_NONCE" \
|
||||
--data "$payload" >/dev/null || true
|
||||
fi
|
||||
}
|
||||
|
||||
emit_status() {
|
||||
emit_status_sync "$1" "$2" &
|
||||
}
|
||||
|
||||
summarize_log_tail() {
|
||||
local file="$1"
|
||||
local label="$2"
|
||||
@@ -104,7 +139,12 @@ summarize_log_tail() {
|
||||
fail_preview() {
|
||||
local detail="$1"
|
||||
trap - ERR
|
||||
emit_status failed "$detail"
|
||||
# Always log to stderr too: the HTTP diagnostics channel can be unreachable
|
||||
# while the worker's Durable Object is still waiting for this container's
|
||||
# port, but stderr is captured by Cloudflare container observability, so the
|
||||
# real reason survives even when the event POST does not.
|
||||
echo "PREVIEW FAILED: ${detail}" >&2
|
||||
emit_status_sync failed "$detail"
|
||||
exit 1
|
||||
}
|
||||
|
||||
@@ -126,9 +166,60 @@ postgres_cluster_snapshot() {
|
||||
printf '%s' "$snapshot"
|
||||
}
|
||||
|
||||
trap 'emit_status failed "preview-entrypoint failed on line ${LINENO}"' ERR
|
||||
trap 'emit_status_sync failed "preview-entrypoint failed on line ${LINENO}"' ERR
|
||||
emit_status boot "preview-entrypoint started"
|
||||
|
||||
# Bind :3000 immediately with a tiny placeholder responder. Cloudflare's
|
||||
# container supervisor only waits ~20s for the port, while the full stack
|
||||
# (redis, postgres, migrations) needs 60s+ on a basic instance. The
|
||||
# placeholder answers 503 with a meta-refresh; the worker still gates
|
||||
# previewReady on the real Rails /up probe and sample data, so readiness
|
||||
# semantics are unchanged. It is replaced by the real server below.
|
||||
ruby -rsocket -e '
|
||||
server = TCPServer.new("0.0.0.0", 3000)
|
||||
body = "<!doctype html><html><head><meta http-equiv=\"refresh\" content=\"3\"><title>Sure preview warming</title></head><body>Sure preview is booting (database setup in progress). This page refreshes automatically.</body></html>"
|
||||
loop do
|
||||
client = begin
|
||||
server.accept
|
||||
rescue StandardError
|
||||
next
|
||||
end
|
||||
begin
|
||||
# Never read from the client: the response is static, and a blocking read
|
||||
# would let one silent connection (e.g. a bare TCP port probe) wedge this
|
||||
# single-threaded loop and starve every later probe.
|
||||
client.write("HTTP/1.1 503 Service Unavailable\r\nContent-Type: text/html; charset=utf-8\r\nContent-Length: #{body.bytesize}\r\nRetry-After: 3\r\nConnection: close\r\n\r\n#{body}")
|
||||
rescue StandardError
|
||||
ensure
|
||||
begin
|
||||
client.close
|
||||
rescue StandardError
|
||||
end
|
||||
end
|
||||
end
|
||||
' >/tmp/port-placeholder.log 2>&1 &
|
||||
PLACEHOLDER_PID=$!
|
||||
|
||||
# Confirm the placeholder actually bound :3000 before reporting it. A plain
|
||||
# TCP connect is used because the placeholder intentionally answers 503.
|
||||
PLACEHOLDER_BOUND=0
|
||||
for i in {1..10}; do
|
||||
if (exec 3<>/dev/tcp/127.0.0.1/3000) 2>/dev/null; then
|
||||
PLACEHOLDER_BOUND=1
|
||||
break
|
||||
fi
|
||||
if ! kill -0 "$PLACEHOLDER_PID" 2>/dev/null; then
|
||||
break
|
||||
fi
|
||||
sleep 0.2
|
||||
done
|
||||
if [ "$PLACEHOLDER_BOUND" -eq 1 ]; then
|
||||
emit_status port-placeholder "bound :3000 placeholder responder (pid ${PLACEHOLDER_PID})"
|
||||
else
|
||||
echo "Warning: :3000 placeholder did not come up; continuing boot" >&2
|
||||
emit_status port-placeholder-missing "placeholder responder failed to bind :3000: $(summarize_log_tail /tmp/port-placeholder.log port-placeholder)"
|
||||
fi
|
||||
|
||||
REDIS_READY=0
|
||||
POSTGRES_READY=0
|
||||
|
||||
@@ -230,6 +321,11 @@ else
|
||||
emit_status demo-data-deferred "deferring demo data creation until after rails boot"
|
||||
fi
|
||||
|
||||
# Release :3000 for the real server. The brief listener gap is handled by the
|
||||
# worker, which catches containerFetch errors and serves its wait page.
|
||||
kill "$PLACEHOLDER_PID" 2>/dev/null || true
|
||||
wait "$PLACEHOLDER_PID" 2>/dev/null || true
|
||||
|
||||
# Execute the main command with an internal readiness probe
|
||||
echo "Starting Rails server..."
|
||||
emit_status rails-start "starting rails server"
|
||||
|
||||
@@ -487,7 +487,7 @@ assert(!configure_image_run.include?('const updated = original.replace(/image =
|
||||
assert_run_includes(create_deployment, "github.rest.repos.createDeployment", "ref: headSha", "preview-pr-${prNumber}")
|
||||
assert_run_includes(deploy, 'cd "$RUNNER_TEMP/sure-preview-worker"', "deploy_once()", "./node_modules/.bin/wrangler deploy --config wrangler.toml", '--var "PR_NUMBER:${PR_NUMBER}"', 'tee "$deploy_log" | ./deploy/redact_preview_log.sh', "deploy_status=${PIPESTATUS[0]}", "associated with a different durable object namespace", 'if ! ./node_modules/.bin/wrangler delete --name "sure-preview-${PR_NUMBER}" --force', "Preview Worker delete failed", "retrying once")
|
||||
assert_run_includes(warm_preview, "$PREVIEW_URL/_container_status", "--connect-timeout 5", "--max-time 15")
|
||||
assert_run_includes(collect_diagnostics, "$PREVIEW_URL/_container_status", "--connect-timeout 5", "--max-time 15", "seq 1 40", "preview-diagnostics", "preview-diagnostics.json", "latest-metrics.json", "metrics-polls.log", "summary.md", '! jq -e . "$diagnostics_file"', 'raw_snippet="$(head -c 2048 "$diagnostics_file")"', 'latest_metrics_snapshot="$(head -c 2048 "$latest_metrics_file")"', "rawSnippet", "latestMetrics", "jq -e '.previewReady == true or .previewFailed == true'", "jq -e '.previewFailed == true'", "Preview diagnostics from _container_status reported previewFailed=true", "jq -e '.previewReady == true'", "Preview diagnostics from _container_status did not reach previewReady=true", ".timings.previewReadyAt != null and .timings.secondsToPreviewReady != null", "Preview diagnostics are missing readiness timing fields", "exit 1")
|
||||
assert_run_includes(collect_diagnostics, "$PREVIEW_URL/_container_status", "--connect-timeout 5", "--max-time 15", "seq 1 100", "preview-diagnostics", "preview-diagnostics.json", "latest-metrics.json", "metrics-polls.log", "summary.md", '! jq -e . "$diagnostics_file"', 'raw_snippet="$(head -c 2048 "$diagnostics_file")"', 'latest_metrics_snapshot="$(head -c 2048 "$latest_metrics_file")"', "rawSnippet", "latestMetrics", "jq -e '.previewReady == true or .previewFailed == true'", "jq -e '.previewFailed == true'", "Preview diagnostics from _container_status reported previewFailed=true", "jq -e '.previewReady == true'", "Preview diagnostics from _container_status did not reach previewReady=true", ".timings.previewReadyAt != null and .timings.secondsToPreviewReady != null", "Preview diagnostics are missing readiness timing fields", "exit 1")
|
||||
assert_run_includes(collect_failure_diagnostics, "preview-failure-diagnostics", "preview-request.json", "preview-image-manifest.json", "wrangler-source.toml", "wrangler-push.toml", "wrangler-final.toml", "wrangler.toml", "wrangler-containers-push.log", "wrangler-deploy.log", "redaction_helper=", 'sanitize_copy "$RUNNER_TEMP/sure-preview-worker/wrangler.source.toml"', 'sanitize_copy "$RUNNER_TEMP/wrangler-push.toml"', 'sanitize_copy "$RUNNER_TEMP/wrangler-final.toml"', "wrangler-deploy.clean.log", "resolutionSource")
|
||||
assert_run_includes(prepare_cleanup_metadata, "preview-cleanup-metadata", "redact_preview_log.sh", "$RUNNER_TEMP/sure-preview-worker/wrangler.toml", "$metadata_dir/wrangler.toml")
|
||||
assert_run_includes(update_deployment_status, "github.rest.repos.createDeploymentStatus", "process.env.DEPLOY_RESULT === 'success'", "deployment_id: Number(process.env.DEPLOYMENT_ID)")
|
||||
|
||||
@@ -17,7 +17,14 @@ enabled = true
|
||||
[[containers]]
|
||||
class_name = "RailsContainer"
|
||||
image = "../../Dockerfile.preview"
|
||||
instance_type = "basic"
|
||||
# standard-1 (1/2 vCPU, 4 GiB RAM, 8 GB disk), not basic (1/4 vCPU, 1 GiB,
|
||||
# 4 GB): this single container runs postgres + redis + puma AND generates the
|
||||
# full demo dataset (Demo::Generator: ~12 years of transactions). That
|
||||
# generation peaks just over 1 GiB, so basic OOM-kills it (exit 137) mid-boot
|
||||
# and the preview never reaches demo-data-ready. Verified on a real Cloudflare
|
||||
# standard-1 deploy: rails ready ~46s, demo data ~149s, previewReady ~195s,
|
||||
# peak well under 4 GiB, no OOM.
|
||||
instance_type = "standard-1"
|
||||
max_instances = 1
|
||||
|
||||
# Durable Object binding for the container
|
||||
|
||||
Reference in New Issue
Block a user