switched from rds to i5 ec2 for nvme disk read/write speeds

infra/db-setup.sh

@@ -0,0 +1,157 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# EveryTab Postgres Setup — for dedicated i3 database instance
+# Run on the i3.large EC2 instance (475GB local NVMe).
+# Configures Postgres to use the NVMe for data storage.
+# Optimized for write-heavy bulk loads — fsync disabled, large buffers.
+# Data is ephemeral — back up with pg_dump before terminating the instance.
+
+echo "=== EveryTab Postgres Setup (i3 NVMe) ==="
+
+# --- Format and mount the NVMe drive ---
+echo "--- Setting up NVMe storage ---"
+NVME_DEV="/dev/nvme1n1"
+NVME_MOUNT="/data"
+
+if [ ! -d "$NVME_MOUNT" ]; then
+    # Find the NVMe instance store (not the root EBS)
+    # i3.large has one 475GB NVMe at /dev/nvme1n1 or similar
+    if [ ! -b "$NVME_DEV" ]; then
+        # Try finding it
+        NVME_DEV=$(lsblk -dpno NAME,SIZE | grep -v "$(lsblk -dpno NAME /)" | head -1 | awk '{print $1}')
+        if [ -z "$NVME_DEV" ]; then
+            echo "ERROR: Could not find NVMe instance store device"
+            echo "Run 'lsblk' and set NVME_DEV manually"
+            exit 1
+        fi
+    fi
+    echo "Using NVMe device: $NVME_DEV"
+    sudo mkfs.xfs -f "$NVME_DEV"
+    sudo mkdir -p "$NVME_MOUNT"
+    sudo mount "$NVME_DEV" "$NVME_MOUNT"
+    sudo chown ec2-user:ec2-user "$NVME_MOUNT"
+    echo "Mounted $NVME_DEV at $NVME_MOUNT"
+else
+    echo "NVMe already mounted at $NVME_MOUNT"
+fi
+
+# --- Install Postgres ---
+echo "--- Installing PostgreSQL 16 ---"
+if ! command -v pg_isready &>/dev/null; then
+    sudo dnf install -y postgresql16-server
+fi
+
+# --- Init database on NVMe ---
+echo "--- Initializing database on NVMe ---"
+PG_DATA="$NVME_MOUNT/pgdata"
+if [ ! -d "$PG_DATA" ]; then
+    sudo mkdir -p "$PG_DATA"
+    sudo chown postgres:postgres "$PG_DATA"
+    sudo -u postgres /usr/bin/initdb -D "$PG_DATA"
+fi
+
+# --- Configure for pipeline workload ---
+echo "--- Configuring for bulk load performance ---"
+PRIVATE_IP=$(hostname -I | awk '{print $1}')
+
+sudo tee "$PG_DATA/postgresql.conf" > /dev/null <<EOF
+# Connection — listen on private IP for compute instance
+listen_addresses = 'localhost,$PRIVATE_IP'
+port = 5432
+max_connections = 100
+
+# Memory — i3.large has 15.25GB RAM, Postgres gets most of it
+shared_buffers = 8GB
+work_mem = 512MB
+maintenance_work_mem = 2GB
+effective_cache_size = 12GB
+
+# Write performance — data is reproducible, maximize speed over durability
+fsync = off
+synchronous_commit = off
+full_page_writes = off
+
+# WAL — minimal logging since no replication needed
+wal_level = minimal
+max_wal_senders = 0
+max_wal_size = 8GB
+checkpoint_timeout = 30min
+checkpoint_completion_target = 0.9
+
+# Autovacuum
+autovacuum = on
+autovacuum_naptime = 60s
+EOF
+
+# Allow connections from VPC (10.0.0.0/8 and 172.16.0.0/12 cover most VPC CIDRs)
+sudo tee "$PG_DATA/pg_hba.conf" > /dev/null <<'EOF'
+# Local connections
+local   all   all                 trust
+host    all   all   127.0.0.1/32  trust
+host    all   all   ::1/128       trust
+# VPC connections (from compute instance)
+host    all   all   10.0.0.0/8    trust
+host    all   all   172.16.0.0/12 trust
+EOF
+
+# --- Start with custom data directory ---
+echo "--- Starting PostgreSQL ---"
+sudo tee /etc/systemd/system/postgresql-everytab.service > /dev/null <<EOF
+[Unit]
+Description=PostgreSQL for EveryTab (NVMe)
+After=network.target
+
+[Service]
+Type=forking
+User=postgres
+ExecStart=/usr/bin/pg_ctl start -D $PG_DATA -l $PG_DATA/pg.log
+ExecStop=/usr/bin/pg_ctl stop -D $PG_DATA
+ExecReload=/usr/bin/pg_ctl reload -D $PG_DATA
+
+[Install]
+WantedBy=multi-user.target
+EOF
+
+sudo systemctl daemon-reload
+sudo systemctl enable postgresql-everytab
+sudo systemctl restart postgresql-everytab
+
+# --- Create database ---
+echo "--- Creating everytab database ---"
+sudo -u postgres psql -p 5432 -c "CREATE USER everytab;" 2>/dev/null || true
+sudo -u postgres psql -p 5432 -c "CREATE DATABASE everytab OWNER everytab;" 2>/dev/null || true
+
+# --- Apply schema ---
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+SCHEMA="$SCRIPT_DIR/../pipeline/01_cc_index/schema.sql"
+if [ -f "$SCHEMA" ]; then
+    echo "--- Applying schema ---"
+    psql -U everytab -h localhost -d everytab -f "$SCHEMA"
+else
+    echo "Warning: schema.sql not found at $SCHEMA"
+    echo "Copy it over and run: psql -U everytab -h localhost -d everytab -f schema.sql"
+fi
+
+# --- Validate ---
+echo ""
+echo "=== Validation ==="
+pg_isready -h localhost
+psql -U everytab -h localhost -d everytab -c "SELECT 'Postgres OK';" -t -A
+echo "NVMe disk usage:"
+df -h "$NVME_MOUNT"
+
+echo ""
+echo "=== Setup Complete ==="
+echo ""
+echo "Private IP: $PRIVATE_IP"
+echo ""
+echo "Connection string (from compute instance):"
+echo "  export DATABASE_URL='postgres://everytab@${PRIVATE_IP}:5432/everytab'"
+echo ""
+echo "Connection string (local):"
+echo "  export DATABASE_URL='postgres://everytab@localhost:5432/everytab'"
+echo ""
+echo "IMPORTANT: Ensure the compute instance's security group allows"
+echo "outbound traffic to this instance on port 5432, and this instance's"
+echo "security group allows inbound on 5432 from the compute instance."