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>
This commit is contained in:
@@ -0,0 +1,68 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Check if Scrutiny has failure_rate fields we should be using
|
||||
"""
|
||||
|
||||
import os
|
||||
from influxdb_client import InfluxDBClient
|
||||
from dotenv import load_dotenv
|
||||
|
||||
load_dotenv()
|
||||
|
||||
def check_scrutiny_failure_rates():
|
||||
"""Check Scrutiny's own failure rate calculations."""
|
||||
url = os.getenv('INFLUXDB_URL')
|
||||
token = os.getenv('INFLUXDB_TOKEN')
|
||||
org = os.getenv('INFLUXDB_ORG', 'scrutiny')
|
||||
bucket = os.getenv('INFLUXDB_BUCKET', 'metrics')
|
||||
|
||||
client = InfluxDBClient(url=url, token=token, org=org)
|
||||
query_api = client.query_api()
|
||||
|
||||
# Get failure_rate fields
|
||||
query = f'''
|
||||
from(bucket: "{bucket}")
|
||||
|> range(start: -1h)
|
||||
|> filter(fn: (r) => r._measurement == "smart")
|
||||
|> filter(fn: (r) => r._field =~ /failure_rate/)
|
||||
|> last()
|
||||
'''
|
||||
|
||||
print("=" * 80)
|
||||
print("Scrutiny's Failure Rate Calculations")
|
||||
print("=" * 80)
|
||||
|
||||
result = query_api.query(query)
|
||||
|
||||
devices = {}
|
||||
for table in result:
|
||||
for record in table.records:
|
||||
wwn = record.values.get('device_wwn')
|
||||
field = record.get_field()
|
||||
value = record.get_value()
|
||||
|
||||
if wwn not in devices:
|
||||
devices[wwn] = {}
|
||||
|
||||
# Extract attribute ID
|
||||
parts = field.split('.')
|
||||
if len(parts) >= 2:
|
||||
attr_id = parts[1]
|
||||
devices[wwn][attr_id] = value
|
||||
|
||||
# Show per device
|
||||
for wwn, attrs in sorted(devices.items()):
|
||||
print(f"\nDevice {wwn}:")
|
||||
max_rate = 0
|
||||
for attr_id, rate in sorted(attrs.items(), key=lambda x: int(x[0])):
|
||||
if rate and rate > 0:
|
||||
print(f" Attr {attr_id:3s}: {rate:.4f}")
|
||||
max_rate = max(max_rate, rate)
|
||||
|
||||
if max_rate > 0:
|
||||
print(f" MAX: {max_rate:.4f} ({max_rate*100:.2f}%)")
|
||||
|
||||
client.close()
|
||||
|
||||
if __name__ == '__main__':
|
||||
check_scrutiny_failure_rates()
|
||||
Reference in New Issue
Block a user