Estimate filesystem lifetime with Mackerel

mackerel_estimate_filesystem_lifetime.py

# -*- coding: utf-8 -*-

import requests
import time
import json
from StringIO import StringIO
import re
import sys
import os

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

import logging
logging.basicConfig()
logger = logging.getLogger(__name__)
logger.setLevel(level=logging.INFO)

MACKEREL_APIKEY = os.environ.get("MACKEREL_APIKEY")
BASEURL="https://mackerel.io"

epoch_time = int(time.time())
duration = 60 * 60 * 24
# duration = 60 * 60 * 24 * 7
THRESHOLD = 1

def fetch_hosts():
    headers = {'X-Api-Key': MACKEREL_APIKEY}
    payload = {}
    r = requests.get(BASEURL+"/api/v0/hosts", headers=headers, params=payload)

    hosts = json.load(StringIO(r.content))
    return hosts['hosts']

def fetch_metrics(hostid, name, time_from, time_to):

    payload = {'name': name, 'from': time_from, 'to': time_to}
    headers = {'X-Api-Key': MACKEREL_APIKEY}
    r = requests.get(BASEURL+"/api/v0/hosts/"+hostid+"/metrics", params=payload, headers=headers)

    metrics = json.load(StringIO(r.content))
    if metrics.has_key('metrics'):
        return metrics['metrics']
    else:
        return []

def import_df(metrics, size):
    # {u'metrics': [{u'value': 6.85, u'time': 1450575540}, {u'value': 7.03, u'time': 1450575600}]}
    times = []
    values = []
    for metric in metrics:
        times.append(metric['time'] - (epoch_time - duration))
        values.append(metric['value'])
    df = pd.DataFrame({'time': times, 'value': values})
    #plt.plot(times, values, 'bo')

    model = pd.ols(y=df['value'], x=df['time'], intercept=True)
    #print model
    #plt.plot(model.x['x'], model.y_fitted, 'g-')
    #plt.hlines([size, size * 0.8], times[0], times[-1], linestyles="dashed")
    #plt.show()
    return model

def prepare_targets():
    dat = {}
    hosts = fetch_hosts()
    for host in hosts:
        if not dat.has_key(host['name']):
            dat[host['name']] = {'id': host['id']}
        meta = host['meta']
        if meta.has_key('filesystem'):
            dat[host['name']]['filesystem'] = meta['filesystem'].keys()

    return dat

def human_readable_size(s):
    s = float(s)
    if s > 10**12:
        return "%.2f TB" % (s / 10**12)
    if s > 10**9:
        return "%.2f GB" % (s / 10**9)
    if s > 10**6:
        return "%.2f MB" % (s / 10**6)
    if s > 10**3:
        return "%.2f MB" % (s / 10**3)
    return "%d B" % s

def human_readable_time(s):
    r = ""
    unit = [("d", 60*60*24),("h", 60*60),("m", 60)]
    for u in unit:
        if s >= u[1]:
            i = int(s / u[1])
            r = r + "%s%s" % (i, u[0])
            s = s - i * u[1]
    return "%s%fs" % (r, s)

def process_targets(dat):
    res = []
    num = 0
    for hostname in dat.keys():
        num = num + 1
        logger.info('fetching %s (%d/%d)', hostname, num, len(dat))
        record = {'hostname': hostname, 'fs': [], 'nearest': sys.maxint}
        if not dat[hostname].has_key('filesystem'):
            continue
        for fs in dat[hostname]['filesystem']:
            (fs, count) = re.subn(r"^/dev/", "", fs)
            if count == 0:
                continue
            metric_name = "filesystem." + fs + ".used"
            metrics_size = fetch_metrics(dat[hostname]['id'], "filesystem."+ fs +".size", epoch_time, epoch_time - 60 * 10)
            if len(metrics_size) == 0:
                logger.info("skip the fs: %s" % (metric_name))
                continue

            metrics = fetch_metrics(dat[hostname]['id'], metric_name, epoch_time, epoch_time - duration)

            size = 0
            for m in metrics_size:
                size = max(size, m['value'])

            latest = 0
            for m in metrics[::-1]:
                if m['value'] > 0:
                    latest = m['value']
                    break

            model = import_df(metrics, size)
            x =  model.beta.x
            i =  model.beta.intercept
            logger.debug("metric:%s, x: %f, intercept: %f, size: %s, current: %s" % (metric_name, x, i, size, latest))
            if x > 0:
                target = size * THRESHOLD
                e = (target-i)/x
                record['fs'].append({'name': fs, 'latest': latest, 'size': size, 'x': x, 'i': i, 'fullin': e})
                record['nearest'] = min(record['nearest'], e)
                logger.debug("fs: %s, size: %s/%s, estimated %s" % (
                    fs,
                    human_readable_size(latest),
                    human_readable_size(size),
                    human_readable_time(e)))
            else:
                record['fs'].append({'name': fs, 'latest': latest, 'size': size, 'x': x, 'i': i})
                logger.debug("fs: %s, used size is reducing." % (fs))
        res.append(record)
    return res

def output_results(res):
    res = sorted(res, key=lambda x: x['nearest'])
    for host in res:
        for fs in sorted(host['fs'], key=lambda x: x['fullin'] if x.has_key('fullin') else sys.maxint):
            if fs.has_key('fullin'):
                print "%s:%s, size: %s/%s, full in %s" % (
                    host['hostname'], fs['name'],
                    human_readable_size(fs['latest']),
                    human_readable_size(fs['size']),
                    human_readable_time(fs['fullin']))
            else:
                print "%s:%s, size: %s/%s, never full" % (
                    host['hostname'], fs['name'],
                    human_readable_size(fs['latest']),
                    human_readable_size(fs['size']))

if __name__ == "__main__":
    dat = prepare_targets()
    res = process_targets(dat)
    output_results(res)