Files
WesandClaude Sonnet 4.5 27afedb32e Complete rewrite: SnapRAID SMART logger with BackBlaze algorithm
Fetches SMART data from Scrutiny's InfluxDB and calculates failure
probabilities using the exact BackBlaze tables from SnapRAID source.

Key features:
- Calculates both v12 (with attr 193) and v13 (without attr 193) algorithms
- v12 matches SnapRAID pre-v13.0 (includes Load Cycle Count)
- v13 matches modern SnapRAID v13.0+ (excludes Load Cycle Count)
- Stores both values for trending and comparison
- Correctly applies bit masks (16-bit for 187/188, 32-bit for others)
- Annualizes monthly rates and applies Poisson distribution
- Logs to PostgreSQL with device metadata

Solved the mystery: SnapRAID v12 uses attribute 193 which was removed
in v13.0. Load cycle count has massive impact on failure predictions
for some drives (80% vs 4% difference).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-07 06:55:39 -05:00

107 lines
3.7 KiB
SQL

-- PostgreSQL schema for SMART data logging (Version 2)
-- Now includes a devices metadata table
-- Device metadata table (populated manually)
CREATE TABLE IF NOT EXISTS devices (
device_wwn VARCHAR(50) PRIMARY KEY, -- e.g., '0x5000c500744487c5'
device_path VARCHAR(255) NOT NULL, -- e.g., '/dev/sda'
serial_number VARCHAR(255) NOT NULL,
model VARCHAR(255),
manufacturer VARCHAR(100),
capacity_bytes BIGINT,
size_tb DECIMAL(10, 2),
disk_role VARCHAR(50), -- e.g., 'd1', 'd2', 'parity', '2-parity', or '-' for unused
notes TEXT,
created_at TIMESTAMPTZ DEFAULT NOW(),
updated_at TIMESTAMPTZ DEFAULT NOW()
);
-- Main table for SMART metrics snapshots
CREATE TABLE IF NOT EXISTS smart_metrics (
id BIGSERIAL PRIMARY KEY,
timestamp TIMESTAMPTZ NOT NULL DEFAULT NOW(),
device_wwn VARCHAR(50) NOT NULL, -- Foreign key to devices table
-- Basic metrics (from SnapRAID smart output)
temperature_celsius INTEGER,
power_on_days INTEGER,
error_count INTEGER,
-- Calculated failure probability
failure_probability_pct DECIMAL(5, 2), -- 0.00 to 100.00
-- Raw SMART attributes (key-value pairs as JSONB)
smart_attributes JSONB,
-- Foreign key constraint
CONSTRAINT fk_device FOREIGN KEY (device_wwn) REFERENCES devices(device_wwn),
-- Unique constraint
CONSTRAINT unique_device_timestamp UNIQUE (device_wwn, timestamp)
);
-- Indexes for efficient querying
CREATE INDEX IF NOT EXISTS idx_smart_metrics_device_wwn ON smart_metrics(device_wwn);
CREATE INDEX IF NOT EXISTS idx_smart_metrics_timestamp ON smart_metrics(timestamp DESC);
CREATE INDEX IF NOT EXISTS idx_smart_attributes_gin ON smart_metrics USING gin (smart_attributes);
CREATE INDEX IF NOT EXISTS idx_devices_serial ON devices(serial_number);
CREATE INDEX IF NOT EXISTS idx_devices_path ON devices(device_path);
-- View for latest metrics per device with metadata
CREATE OR REPLACE VIEW smart_latest AS
SELECT DISTINCT ON (d.device_wwn)
d.device_wwn,
d.device_path,
d.serial_number,
d.model,
d.manufacturer,
d.size_tb,
d.disk_role,
sm.timestamp,
sm.temperature_celsius,
sm.power_on_days,
sm.error_count,
sm.failure_probability_pct,
sm.smart_attributes
FROM devices d
LEFT JOIN smart_metrics sm ON d.device_wwn = sm.device_wwn
ORDER BY d.device_wwn, sm.timestamp DESC NULLS LAST;
-- View for high-risk devices (failure probability > 50%)
CREATE OR REPLACE VIEW smart_high_risk AS
SELECT *
FROM smart_latest
WHERE failure_probability_pct > 50.0
ORDER BY failure_probability_pct DESC;
-- View for summary (like snapraid smart output)
CREATE OR REPLACE VIEW smart_summary AS
SELECT
device_path,
serial_number,
temperature_celsius as temp_c,
power_on_days,
error_count,
failure_probability_pct as fp_pct,
size_tb,
disk_role,
model,
timestamp as last_updated
FROM smart_latest
ORDER BY
CASE disk_role
WHEN 'parity' THEN 1
WHEN '2-parity' THEN 2
ELSE 3
END,
device_path;
-- Comments
COMMENT ON TABLE devices IS 'Device metadata (WWN, serial, model, etc.) - manually populated';
COMMENT ON TABLE smart_metrics IS 'Historical SMART metrics collected from Scrutiny InfluxDB';
COMMENT ON COLUMN smart_metrics.failure_probability_pct IS 'BackBlaze-based 1-year failure probability (0-100%)';
COMMENT ON COLUMN smart_metrics.smart_attributes IS 'Raw SMART attributes as JSON (attribute_id -> value)';
COMMENT ON VIEW smart_latest IS 'Latest SMART metrics for each device with metadata';
COMMENT ON VIEW smart_high_risk IS 'Devices with >50% annual failure probability';
COMMENT ON VIEW smart_summary IS 'Summary view matching snapraid smart output format';