Regression analysis with Mackerel

mackerel_metric.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.DEBUG)

MACKEREL_APIKEY = os.environ.get("MACKEREL_APIKEY")
BASEURL="https://mackerel.io"
HOSTNAME="testserver"
epoch_time = int(time.time())
duration = 60 * 60 * 24

def fetch_hosts():
    headers = {'X-Api-Key': MACKEREL_APIKEY}
    payload = {'name': HOSTNAME}
    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):
    # {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.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 process_targets(dat):
    for hostname in dat.keys():
        logger.info('fetching %s', hostname)
        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 = fetch_metrics(dat[hostname]['id'], metric_name, epoch_time, epoch_time - duration)
            if len(metrics) == 0:
                logger.info("skip the fs: %s" % (metric_name))
                continue

            import_df(metrics)

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