Change the getaddrinfo(3) hints family from AF_INET to AF_UNSPEC to
allow resolution of IPv6 addresses as well as IPv4 addresses. The
function will return the IP address of whichever address family is
preferenced by the operating system. Most current operating systems
will preference AF_INET6 over AF_INET.

Unfortunately without attempting to establish a connection to the
remote address we can't know if the host is capable of using the
returned IP address. It might be desirable to have anetResolve
accept an additional argument specifying the AF_INET/AF_INET6 address
the caller would like to receive. Currently though it does not appear
as though the anetResolve function is ever used within Redis.

Add REDIS_CLUSTER_IPLEN macro to define the size of the clusterNode ip
character array. Additionally use this macro in inet_ntop(3) calls where
the size of the array was being defined manually.

The REDIS_CLUSTER_IPLEN is defined as INET_ADDRSTRLEN which defines the
correct size of a buffer to store an IPv4 address in. The
INET_ADDRSTRLEN macro itself is defined in the <netinet/in.h> header
file and should be portable across the majority of systems.

Add the additional ip buffer length argument to function calls of
anetTcpAccept and anetPeerToString in network.c and cluster.c

Replace inet_ntoa(3) calls with the more future proof inet_ntop(3)
function which is capable of handling additional address families.

API Change: anetTcpAccept() & anetPeerToString() additional argument
  additional argument required to specify the length of the character
  buffer the IP address is written to in order to comply with
  inet_ntop(3) function semantics.

Change anetTcpServer() function to use getaddrinfo(3) to perform
address resolution, socket creation and binding. Resolved addresses
are limited to those reachable by the AF_INET address family.

Change anetTcpGenericConnect() function to use getaddrinfo(3) to
perform address resolution, socket creation and connection. Resolved
addresses are limited to those reachable by the AF_INET family.

Extract setting SO_REUSEADDR socket option into separate function
so the same code can be more easily used by anetCreateSocket and
other functions.

Change anetResolve() function to use getaddrinfo(3) to resolve hostnames.
Resolved hostnames are limited to those reachable by the AF_INET address
family.

API Change: anetResolve requires additional argument.
  additional argument required to specify the length of the character
  buffer the IP address is written to in order to comply with
  inet_ntop(3) function semantics. inet_ntop(3) replaces inet_ntoa(3)
  as it has been designed to be compatible with more address families.

Bind() can't be called multiple times against the same socket, multiple
sockets are required to bind multiple interfaces, silly me.

This reverts commit bd234d62.

When in --pipe mode, after all the data transfer to the server is
complete, now redis-cli waits at max the specified amount of
seconds (30 by default, use 0 to wait forever) without receiving any
reply at all from the server. After this time limit the operation is
aborted with an error.

That's related to issue #681.

If the protocol read from stdin happened to contain grabage (invalid
random chars), in the previous implementation it was possible to end
with something like:

dksfjdksjflskfjl*2\r\n$4\r\nECHO....

That is invalid as the *2 should start into a new line. Now we prefix
the ECHO with a CRLF that has no effects on the server but prevents this
issues most of the times.

Of course if the offending wrong sequence is something like:

$3248772349\r\n

No one is going to save us as Redis will wait for data in the context of
a big argument, so this fix does not cover all the cases.

This partially fixes issue #681.

It causes catastrophic performance for certain inputs.

Relevant NetBSD commit:

http://cvsweb.netbsd.org/bsdweb.cgi/src/lib/libc/stdlib/qsort.c?rev=1.20&content-type=text/x-cvsweb-markup&only_with_tag=MAIN

This fixes issue #968.

This fixes issue #1094.

The function is used to test that the specified string looks like just
as the basename of a path, without any absolute or relative path.

Clients using SYNC to replicate are older implementations, such as
redis-cli --slave, and are not designed to acknowledge the master with
REPLCONF ACK commands, so we don't have any feedback and should not
disconnect them on timeout.

It should be called just one time at startup and not every time the Lua
scripting engine is re-initialized, otherwise memory is leaked.

This commit uses the Replication Script Cache in order to avoid
translating EVALSHA into EVAL whenever possible for both the AOF and
slaves.

This code is only responsible to take an LRU-evicted fixed length cache
of SHA1 that we are sure all the slaves received.

In this commit only the implementation is provided, but the Redis core
does not use it to actually send EVALSHA to slaves when possible.