monitor_filter_non_reporting_nodes.py

gistfile1.py

#!/usr/bin/env python2

import argparse
import os
import shutil
from datetime import datetime, timedelta

RRD_PATH='/var/lib/collectd/rrd/'

parser = argparse.ArgumentParser()
parser.add_argument("-d", "--delete", help="delete entries", action="store_true")
args = parser.parse_args()

def get_last_mtime_recursively(root):
    files = []
    for dirname, dirnames, filenames in os.walk(root):
        for filename in filenames:
            path = os.path.join(dirname, filename)
            mtime = datetime.fromtimestamp(os.stat(path).st_mtime)
            files.append(mtime)

    return max(files)

# iterate over all nodes
nodes = {}
for entry in os.listdir(RRD_PATH):
    path = os.path.join(RRD_PATH, entry)
    nodes[entry] = get_last_mtime_recursively(path)

# filter all nodes which have not reported since 30 days
delta = datetime.today() - timedelta(days=30)
filtered = dict(((k,v) for (k,v) in nodes.items() if v < delta))

# Output
print("Outdated entries: %d of %d - first entry is last modification date" % \
        (len(filtered), len(nodes)))
for name,mtime in  sorted(filtered.items(), key=lambda x: x[1]):
    line = "%s - %s" % (mtime.strftime('%d.%m.%Y'), name)
    if args.delete:
	path = os.path.join(RRD_PATH, name)
        shutil.rmtree(os.path.join(RRD_PATH, name))
        print("\t* %s...\tdeleted" % path)
    else:
        print("\t* %s - %s" % (mtime.strftime('%d.%m.%Y'), name))

See http://pastebin.com/SHf6FCZV for example output.