ovs-check-dead-ifs.in

#! /usr/bin/env @PYTHON@

import os
import re
import stat
import sys

if "--help" in sys.argv:
    sys.stdout.write("""\
ovs-check-dead-ifs: Check for packet sockets for nonexistent network devices.

One side effect of the "force-reload-kmod" command that reloads the
Open vSwitch kernel module is that all the network devices that the
Open vSwitch kernel module implemented get destroyed and then replaced
by new instances with the same names.  Unfortunately, programs that
are listening for packets on the original network devices will not
receive packets that arrive on the new instances.  This causes some
services, such as DHCP, to silently fail.  This program looks for such
problems and, if it finds any, prints information about programs that
are in such a state.  The system administrator should then take some
action to fix the problem, such as restarting these programs.
""")
    sys.exit(0)
elif len(sys.argv) > 1:
    sys.stderr.write("ovs-check-dead-ifs: no arguments or options accepted "
                     "(use --help for help)\n")
    sys.exit(1)

# Get the set of all valid ifindexes.
#
# 0 is always valid for our purposes because it means "any interface".
valid_ifindexes = set([])
for ifname in os.listdir("/sys/class/net"):
    fn = "/sys/class/net/%s/ifindex" % ifname
    try:
        valid_ifindexes.add(int(open(fn).readline()))
    except IOError:
        pass
    except ValueError:
        print "%s: unexpected format\n" % fn

# Get inodes for all packet sockets whose ifindexes don't exist.
invalid_inodes = set()
f = open("/proc/net/packet")
f.readline()                    # Skip header line.
for line in f:
    fields = line.split()
    ifindex = int(fields[4])
    if ifindex not in valid_ifindexes:
        invalid_inodes.add(int(fields[8]))
f.close()

if not invalid_inodes:
    sys.exit(0)

# Now find the processes that are using those packet sockets.
inode_re = re.compile(r'socket:\[([0-9]+)\]$')
bad_pids = set()
for pid in os.listdir("/proc"):
    try:
        pid = int(pid)
    except ValueError:
        continue

    try:
        fds = os.listdir("/proc/%d/fd" % pid)
    except OSError:
        continue

    for fd in fds:
        try:
            fd = int(fd)
        except ValueError:
            continue

        try:
            s = os.stat("/proc/%d/fd/%d" % (pid, fd))
        except OSError:
            continue

        if not stat.S_ISSOCK(s.st_mode):
            continue

        try:
            linkname = os.readlink("/proc/%d/fd/%d" % (pid, fd))
        except OSError:
            continue

        m = inode_re.match(linkname)
        if not m:
            continue

        inode = int(m.group(1))
        if inode in invalid_inodes:
            bad_pids.add(pid)

if bad_pids:
    print """
The following processes are listening for packets to arrive on network devices
that no longer exist. You may want to restart them."""
    sys.stdout.flush()
    os.execvp("ps", ["ps"] + ["%s" % pid for pid in bad_pids])