Benchmarks for Native IPsec in the 2.6 Kernel
IPsec is an addition to IP protocol that allows authentication and encryption
of IP datagrams. It is defined in detail in IETF RFCs 2401, RFC 2402,
RFC 2406 and RFC 2407 (see Resources). IPsec can be used to secure a rather wide
range of scenarios; one of its best-known usages is creating virtual
private networks (VPNs). A VPN is a secure, private tunnel between two
sub-networks using encrypted communication over the Internet.
FreeS/WAN has been the main IPsec implementation for Linux for a long
time. Unfortunately, FreeS/WAN has never been integrated into the Linux
kernel itself. Instead, the new native kernel IPsec implementation is based on the
KAME project, a part of the UNIX/BSD family.
The USAGI project used the BSD code from the KAME project as a base for integrating
IPsec into the Linux kernel. KAME's user-space tools, specifically setkey and Racoon,
have been ported to Linux by the IPsec-tools Project (see Resources).
In this article, we implement a simple scenario of setting up a
secure connection between two Linux systems, reblochon and gouda.
We explain different IPsec user-land tools and how to use them to set
up a secure connection between two systems. At the end, we present our
benchmarks and discuss them.
What You Need to Install
To use IPsec, you need a kernel that supports IPsec protocols and user-land
tools that allow key management and key exchange. These keys are
used for different cryptographic algorithms.
For Linux kernels 2.5.47 and higher, IPsec support is a part of the kernel itself.
However, this support is not enabled by default. If you have a Linux distribution such as
Suse 9.1 or Fedora Core 2, it already comes with a 2.6 kernel and IPsec is enabled by default.
If you use some other Linux distribution, for example, Fedora Core 1, you
need to install a 2.6.x version of the kernel--the higher the better.
This new kernel must be compiled with the following options enabled. Go to Device drivers ->
Networking support -> Networking options to enable:
- PF_KEY sockets
- IP: AH transformation
- IP: ESP transformation
- IP: IPComp transformation
- IPsec user configuration interface
You also must include all the cryptographic algorithms you plan to use
for your IPsec setup.
On the user-land side, the only thing you need is setkey and Racoon, which are
part of the IPsec-tools Project (see Resources). The installation of these tools is
straightforward: download the source code and proceed as usual with configure, make and
make install commands. There even might be a precompiled package for your
distribution of choice.
Setting Up a Secure Connection
You can use IPsec in two modes, transport or tunnel. Briefly, transport
mode is used to secure host-to-host communications, and tunnel mode is
used to tunnel securely site-to-site communications. In transport mode,
a special header for ESP and AH is added to the normal IP header. In
tunnel mode, the IP packet of transport mode with an ESP and AH header is
encapsulated in a normal IP packet. That way, the ESP and AH header is not
visible directly to routers that might discard a packet with unknown options.
IPsec can be configured in different ways. Here are three ways to
configure an IPsec secure connection between two hosts:
- Shared Secret Keys: Start with a shared key on two nodes. Upon
initialization of a secure connection between two nodes, this common
shared secret is used for specified encryption or authentication
algorithms. Using shared keys is the easiest way to configure but it also is
less secure, as the shared secret most probably is contained in a configuration
or script file on both machines. Also, if you do not change your keys often, it is possible that
someone could capture enough packets to be able to retrieve the key. - Pre-Shared Key: In this mode, you need to run Racoon. Its functionality
is similar to the shared secret key. The only difference is Racoon
uses the pre-shared key as a seed to negotiate a complete key and
periodically change that key. - X.509 Certificate: The most secure method to manage keys securely is to use the X.509 certificate.
This solution requires access to a trusted certification authority (CA); otherwise, you need to set up
your own CA. IPsec configuration in this case is not much more complicated, but interactions with a
trusted certificate might be a problem.
In our simple scenario, we are more interested in discussing IPsec
implementation performance rather than secure connection issues. So here we discuss
the configuration of shared and pre-shared keys only.
A Simple Scenario
The following listing is used to illustrate how to set up a secure connection between
two computers on different LANs. Below, we provide the script file of gouda
that sets a secure connection between two systems. gouda is at IP address
192.168.0.1 and reblochon is at IP address 192.168.0.2.
1: #!/usr/local/sbin/setkey -f 2: flush; 3: spdflush; 4: 5: # AH gouda to reblochon 6: add 192.168.0.1 192.168.0.2 ah 1000 7: -A hmac-md5 "1234567890123456"; 8: add 192.168.0.2 192.168.0.1 ah 2000 9: -A hmac-md5 "1234567890123456"; 10: 11: # ESP gouda to reblochon 12: add 192.168.0.1 192.168.0.2 esp 1001 13: -E 3des-cbc "123456789012345678901234" 14: -A hmac-sha1 "12345678901234567890"; 15: add 192.168.0.2 192.168.0.1 esp 2001 16: -E 3des-cbc "123456789012345678901234" 17: -A hmac-sha1 "12345678901234567890"; 18: 19: spdadd 192.168.0.1 192.168.0.2 any -P out IPsec 20: esp/transport//require 21: ah/transport//require; 22: 23: spdadd 192.168.0.2 192.168.0.1 any -P in IPsec 24: esp/transport//require 25: ah/transport//require;
For reblochon, we use the same script file with only the following differences on line 19:
19: spdadd 192.168.0.1 192.168.0.2 any -P in IPsec
and on line 23:
23: spdadd 192.168.0.2 192.168.0.1 any -P out IPsec
Note the in and out keywords are reversed.
In line 1, the setkey command is invoked. This program inserts or
deletes IPsec rules in the kernel. In lines 2 and 3, we use the setkey
command to clear all security associations (SA) and security policies (SP), because we want to begin from a clean state.
Before diving into more technical details, we need to become familiar
with two basic concepts in IPsec protocol, security association (SA)
and security policy (SP). An SA defines the security parameters, for
example, the crypto algorithm to be used, to create a secure connection
between two systems. An SP, on the other hand, is the security rule defining the security
context to be used between the two systems. For example, an SP can specify
that we need to use encryption between my desktop and a remote system on
the Internet. An SA then is the effective secure connection created
between my desktop and that system. Be aware that SAs are unidirectional.
In our scenario, we define two SPs between reblochon and gouda. An SP is
defined as:
source | destination | on which kind of traffic to apply the policy (TCP, UDP, port, any) | the direction in/out | what to do (IPsec/discard/none) | (esp/ah) / (transport/tunnel) / (IP address of both ends of the tunnel) not required in transport mode / require.
For example, these lines:
spdadd 192.168.0.1 192.168.0.2 any -P out IPsec
esp/transport//require
ah/transport//require;
declare a security policy stating that any packets coming from
192.168.0.1 and going to 192.168.0.2 should use IPsec on transport mode
with ESP and AH functionality.
Now that you defined the policy between your systems, you need to define
SAs in order to be able to achieve that policy. You need two SAs for communication,
one from gouda to reblochon and one from reblochon to gouda. The two
SAs do not need to use the same algorithm. In fact, unlike this example,
for better security you should not use the same key for both SAs.
You define a SA as
source | destination | ah/esp | SPI (Security Policy Index) any number but should be unique | algorithm and associated secret key.
For example, these lines:
add 192.168.0.1 192.168.0.2 esp 1001
-E 3des-cbc "123456789012123456789012"
-A hmac-sha1 "12345678901234567890";
define that if you want to use ESP on a packet going from gouda to
reblochon, you should use 3DES as the encryption algorithm with the quoted
text as the key and SHA1 as the authentication algorithm.
Now, you finally can run the script on both nodes. You can check the
status of different SAs established by using setkey -D. If you
want to see existing policies on your system, you can use setkey -DP. At
the end, to be sure that the traffic between two systems actually is
encrypted, you can use Ethereal to monitor the traffic between two
nodes. For example, in Figure 1, we show the traffic between two systems
exchanging messages containing the "hello world" text. As you see,
the message is encrypted between gouda and reblochon.
Figure 1: Ethereal Snapshot Showing Encrypted CommunicationsAutomatic Keying
Now, you certainly can understand why this type of configuration is less
secure. Keeping a system secure with secret keys in clear text in a
configuration file is not practical. But don't worry, the people
behind IPsec have thought about it and have come up with a protocol to
negotiate keys and set up secure connections automatically.
This functionality is implemented by Racoon. With Racoon, you do not need
to specify any SAs; you need to specify only the SP. Racoon dynamically
defines the SAs, and of course, you need to configure Racoon. The Racoon
daemon runs on UDP port 500, which means that your firewall rules should
not block this port on your system. We are not going into the details of
setting up Racoon here, but refer to the HOWTO listed in Resources for
more information.
Benchmark Results
We used Netio benchmarking software to test the new native IPsec implementation on a 2.6.7 kernel.
We used two Pentium IV 2.2GHz machines with 512MB of memory. Netio measures the throughput of a network by way of
TCP and UDP and different packet sizes. We established a secure connection
using transport mode with the encryption algorithm 3DES (key size = 192 bits)
and SHA1 for integrity checks. You can see the results in Table 1
for TCP and in Table 2 for UDP.
Table 1. Results from Netio TCP BenchmarkPacket SizeBandwidth without IPsecBandwidth with IPsec1KB10905KB5157KB2KB10832KB5222KB4KB10827KB5305 KB8KB10811KB5263KB16KB10814KB5345KB32KB10729KB5374KBTable 2. Results from Netio UDP BenchmarkPacket SizeBandwidth without IPsecBandwidth with IPsec1KB11479KB4806KB2KB11244KB4320KB4KB11698KB4985KB8KB11714KB5116KB16KB11725KB5152KB32KB11743KB5271KB
We can see that IPsec diminishes by half the throughput of a TCP or UDP
connection. Although the absolute bandwidth still is high--worst case
is 4.3MB/sec--it is enough for most applications.
Conclusion
The new native IPsec implementation has a user-friendly interface to enable users to set up
secure connections easily among different Linux systems. The
results of our tests show that even though there is need for some
improvements with regards to the stability of the implementation, the
performance of the new native IPsec implementation makes it a good candidate for use by
SOHOs as well as mid-sized enterprises.
The new Linux IPsec implementation pushes Linux farther along the path to becoming a
natural choice for many security needs of SOHOs and mid-sized companies.
Resources
IETF RFCs
Vincent Roy and Makan Pourzandi work at the Open Systems Lab at Ericcson
Canada.










This week 5 lucky Members will receive a copy of The Official Ubuntu Server Book by Benjamin Mako Hill and Linux Journal's very own Kyle Rankin. No entry necessary. Check back here early next week to find out who the lucky Online Members are.




Comments
Re: Benchmarks for Native IPsec in the 2.6 Kernel
UGH. This benchmark is .. worthless.
Next time someone does this, please test a realistic cypher. No one would use 3des on a pc platform for high speed encryption. AES would be a good choice (a good benchmark would test a couple of the options Linux provides)..
Also the packet sizes were not useful. Internet average packet size is something like 400 bytes... Additionally, it's useful to see how well the system would perform with minimum sized packets... so you know how the link will last through a DOS attack.
Anyone have links to a real test?
(btw- With freeswan + AES + compression I was saturating 100mbit ethernet with a P3 1.4gig system)
Re: Benchmarks for Native IPsec in the 2.6 Kernel
Regarding the packet size, here we should consider the packets exchanged inside a VPN connection, we don't talk about accessing Inetrnet at large with http dominated traffic. But I believe that you are right that the benchmarking with smaller than 1k packets can be very useful.
Actually, we wanted to use a well known benchmark software in order to avoid discussions about the validity of the benchmark software itself and netio people did not consider small packet sizes. I'll forward your comments on the size of the packets to netio people.
My 2 cents on DOS, if you mean a DOS attack on any end of the VPN tunnel, from my experience, Linux is pretty resitent to IP layer DOS attacks with or without IPSec. If you mean from inside the corporate to another end of the VPN, yes it comes back to what I mentioned on packet size.
Makan
Re: Benchmarks for Native IPsec in the 2.6 Kernel
you show ethereal looking at encrypted traffic, but how about unencrypted traffic before it enters the tunnel? that would be useful for debugging application and network problems that are separate from ipsec, but are carried across ipsec.
what about writing firewall rules that only allow port 80 traffic across the encrypted connection?
those are things that can't be done until the native kernel ipsec implementation includes virtual interfaces. those are things that both freeswan and openswan support in 2.4 kernels.
we've taken a step backwards as far as usefulness is concerned.
Re: Benchmarks for Native IPsec in the 2.6 Kernel
regarding firewall rules and virtual interfaces, i suggest you take a look at this document.
it is entirely possible although not as easy as with virtual interfaces.
Re: Benchmarks for Native IPsec in the 2.6 Kernel
I wonder if any of the 64-bit processors would be more efficient at the encryption algorithms?
64-bit performance
A 64-bit processor will do no better at ciphers than a 32-bit processor, given the same memory bandwidth.
Processors are sufficiently fast that essentially all latency is due to memory bandwidth, given AES. Maybe a 64-bit processor would run 3des
at the same speed as AES, but it would put out more watts doing that.
Of course, many 64-bit systems have more memory bandwidth, but not all of them.
64bit performance
As an indication, here my setup and numbers:
box1: dual 1.4Ghz Opteron, 64bit gentoo, 43% si on one processor,
cat /dev/zero | nc -l -p 4567
box2: pentium-m 2.0Gz, 32bit gentoo, 58% si
nc dualopteron 4567 > /dev/null
algo: AES, vanilla linux kernel 2.6.9
network: gigabit over two switches
speed, avg 26MB/s (megabyte per second)
Pathetic performance
First you have to compare the quote performance figures with performance of the selected cipher on the same hardware.
In any case modern computers should be able to saturate 100Mbps link with IPsec or without, and should be rather close to saturating 1Gbps link too.
Further you should also consider evaluating scalability - i.e. whether there is a slowdown if, say, a thusand tunnels are maintained simultaneousely.
Re: Pathetic performance
Do you mean that you know of any other __software only__ ipsec implementation that can achieve close to 100 Mbps? On Linux or on Windows? Can you give more details?
Regarding scalability, you're right that it will be very useful to evaluate scalability. We hope to be able to give more on that in future work.
Makan
Re: Pathetic performance
I worked with a commercial cross-platform IPsec implementation once, the throughput on the tunnel was only 10 to 30 percent worse than the throuput of the cipher itself.
Safenet Inc for one has an oem package for Linux.
Re: Benchmarks for Native IPsec in the 2.6 Kernel
3des is very slow, AES is faster and there is also an optimized assembly implementation for Pentiums in recent 2.6 kernels .
AH doesn't really serve much purpose, most people will want to just use the ESP authentication alone.
Re: Benchmarks for Native IPsec in the 2.6 Kernel
> AH doesn't really serve much purpose, most people will want to just use the ESP authentication alone.
Actually it has a purpose. If transport keys are derived from public/private key pairs (this makes a lot of sense), ESP alone will block unauthorized reading only. An attacker is still able to insert bogus packets without AH.
Re: Benchmarks for Native IPsec in the 2.6 Kernel
Except that he'd have to have the session key, right? Which will be uhhh.. difficult to achieve in practice.
Or am I missing something?
Re: Benchmarks for Native IPsec in the 2.6 Kernel
Editor, the last sentence above the conclusion needs some editing. Do you want to say that absolute bandwidth is high or that is a lower but still high enough?
Frodo
Re: Benchmarks for Native IPsec in the 2.6 Kernel
Actually, we meant that the bandwidth is still high enough to be used in most applications.
Makan
Re: Benchmarks for Native IPsec in the 2.6 Kernel
I suppose 100 Mbit cards are used within the network where the bandwidth is measured. This is a shame, because it means the bandwidth without IPSec is limited to a little more than10 Mbyte/sec.
To measure the performance hit of IPSec, it would be better to use a 1 Gbit network.
Frodo
Re: Benchmarks for Native IPsec in the 2.6 Kernel
AFAIK, IPsec is suposed to be used to create secure connections on top of an unsecure connection; usually that means internet. I can not think of any use for IPsec between two machines with a 1Gb connection between them.
Thus, IMHO, these benchmaks should have been performed on slower connections, more similar to real-world use. It would be much more informative to me knowing if IPsec slows down a connection running over ADSL.
Re: Benchmarks for Native IPsec in the 2.6 Kernel
Actually, perhaps the notation used was not clear enough. We used capital B for bytes. Therefore the measures are on Mega Bytes and not Mega _bits_ .
Regarding 1 Gbit network, that could be useful, though in my understanding the restricting factor here is not the network as the most we can achieve with IPSec is under 5000 MBytes/sec which is under 100 Mbits/sec network capacity. Am I missing something?
Makan
Missing the comparison.
Yes, the thing you're missing is in your comparison. You say that IPsec is giving about half the performance of an unencrypted connection, when the unencrypted connection seems to be limited by the network bandwidth where the encrypted one is limited by (I presume) CPU.
You'd probably want to just drop the comparison, because the useful information is how it performed, not how it performed in comparison with unencrypted over a high speed line. A friend and I transferred an ISO in 20 seconds the other day, for a rate of around 33MB/sec (probably limited by the discs on our laptops), so in that case it's more like 7x slower with encryption.
To answer the question about why would you encrypt gigabit. I can think of a few. First of all, not all public networks are low-speed. If you are hosting a security-sensitive set of systems at a third-party, ARP-poisoning the switch can allow third-parties to intercept the traffic.
Another case is how I have my home network set up. I run all my traffic to my home network over a tunnel to my firewall/gateway box, encrypted. I bridge that tunnel with the home network, so I get the same IP no matter where I go. I can access my printer and other devices at home when I'm away, printing invoices, etc... For convenience, I use that setup whether I'm at home or not, and when I'm at home and have large files to transfer I'll connect to my 100mbps wired network. With OpenVPN, I get around 7MB/sec (the firewall is a pretty old box). I could work around that with some tricks depending on whether I am at home or away, shutting down that one OpenVPN tunnel when I'm at home and just using a local address. This way is just easier.
Sean
OpenVPN
IPsec has a bad security record (being complex), see
http://www.giac.org/practical/GSEC/Charlie_Hosner_GSEC.pdf
OpenVPN works great on Linux and Windows. The tarball has .spec file
included for rpm-based systems. Use the 2.0 beta, it's quite stable.
http://openvpn.sourceforge.net/
Yes, IPsec has a security
Yes, IPsec has a security record. Well documented. Yes, it is a bit
more complex than OpenVPN. But, it also has more than one implementation. OpenVPN is the Microsoft of security protocols.
OpenVPN, being obscure, has a less well known record of security flaws.
It's also trivially is susectable to denial of service attacks.
I just want to know if there
I just want to know if there are lib functions for upper applications calling.
Post new comment