PfSense hardware for home router - OpenVPN performance

IggyB

ci323 nano u

Stats for you guys

hw.model: Intel(R) Celeron(R) CPU N3150 @ 1.60GHz
(cryptodev) BSD cryptodev engine
(rsax) RSAX engine support
(rdrand) Intel RDRAND engine
(dynamic) Dynamic engine loading support

openssl speed aes-128-cbc aes-192-cbc aes-256-cbc
OpenSSL 1.0.1s-freebsd 1 Mar 2016
built on: date not available
options:bn(64,64) rc4(16x,int) des(idx,cisc,16,int) aes(partial) idea(int) blowfish(idx)
compiler: clang
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes
aes-128 cbc 27446.63k 31065.88k 32203.01k 79808.59k 80497.95k
aes-192 cbc 23419.20k 25885.49k 26810.11k 66946.05k 67553.96k
aes-256 cbc 20250.74k 22164.16k 22912.07k 57832.11k 58552.27k

openssl speed -engine cryptodev -multi 4 aes-128-cbc aes-192-cbc aes-256-cbc
OpenSSL 1.0.1s-freebsd 1 Mar 2016
built on: date not available
options:bn(64,64) rc4(16x,int) des(idx,cisc,16,int) aes(partial) idea(int) blowfish(idx)
compiler: clang
aes-128 cbc 104805.14k 118668.96k 128936.14k 318822.11k 321327.26k
aes-192 cbc 93729.09k 103600.58k 107154.76k 267119.27k 271302.66k
aes-256 cbc 80937.83k 88656.43k 91726.42k 226115.54k 230708.57k

openssl speed -multi 4 bf-cbc
OpenSSL 1.0.1s-freebsd 1 Mar 2016
built on: date not available
options:bn(64,64) rc4(16x,int) des(idx,cisc,16,int) aes(partial) idea(int) blowfish(idx)
compiler: clang
blowfish cbc 164957.33k 185746.01k 191440.98k 193272.15k 193628.57k

openssl speed bf-cbc
OpenSSL 1.0.1s-freebsd 1 Mar 2016
built on: date not available
options:bn(64,64) rc4(16x,int) des(idx,cisc,16,int) aes(partial) idea(int) blowfish(idx)
compiler: clang
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes
blowfish cbc 41251.69k 46459.56k 47838.06k 48378.47k 48452.95k

spon901

The measurement above using command:
time openvpn –test-crypto --secret /tmp/secret --verb 0 --tun-mtu 20000 --cipher aes-256-cbc

seem to be total innacurate.

I made following tests. I connect a i5 laptop and a RK3288 based linux box to a vlan switch. The RK3288 is used as a vlan router. On Laptop I runned a speed test through this router. and I obtain 300M/150M which is what provider offer.
Running the above test command I got :
For RK3288 27 sec which mean 118.5Mbps
For I5 Laptop 6 sec which mean 533 Mbps.

So I expect a throughput of around 120Mbps . However insialling openwrt on both RK3288 box and I5 laptop, performing same test I have only 32Mbps/43Mbps. Why so big difference comparative with theoeretical speed of 120Mbps

VAMike

@Pippin:

Very much doubt these calculations or any….., to much variables to make a good estimate that will reflect reality.
Cipher, digest, hash, compression, mtu, buffersizes, network, latency, etc. all play a role.
And also the type of data that goes through the tunnel.

Intel Celeron N3150 4x1.6GHz -TDP 6W -CPU Mark 1642 -Single Thread 456
3200/27,5 = 116 Mbps OpenVPN performance (estimate)

As argument, with N3150 (Gigabyte N3150N-D3V), I can tell you that in a client to client Iperf test, I was getting 160 Mbit/s throughput, I used:
No crypto hardware selected (meaning AES-NI will be used automatically if it`s supported, N3150 does)
no compression
DH 2048
AES-256-CBC
SHA512
prng SHA512 32 #(prng_hash = 'RSA-SHA512'/prng_nonce_secret_len = 32)
cipher TLSv1/SSLv3 DHE-RSA-AES256-GCM-SHA384/2048 bit RSA

As you can see, with these somewhat "heavier" settings it is higher then the calculated 116 Mbit/s.

Furthermore, keep in mind that this was client to client, meaning there is an extra round of crypto happening at server…..

I'd guess that the original benchmark was done with aesni.ko loaded, hence the low crypto performance. Without aesni.ko I benchmark just about exactly 160Mbps on that hardware…

VAMike

@spon901:

I made following tests. I connect a i5 laptop and a RK3288 based linux box to a vlan switch. The RK3288 is used as a vlan router. On Laptop I runned a speed test through this router. and I obtain 300M/150M which is what provider offer.
Running the above test command I got :
For RK3288 27 sec which mean 118.5Mbps
For I5 Laptop 6 sec which mean 533 Mbps.

So I expect a throughput of around 120Mbps . However insialling openwrt on both RK3288 box and I5 laptop, performing same test I have only 32Mbps/43Mbps. Why so big difference comparative with theoeretical speed of 120Mbps

Do I understand correctly that you changed the OS after running the benchmark? Try running the benchmark on the OS you're using for the test.

spon901

No, was the same OS . I did not change anything. Just test directly and the immediately run same test through openvpn. The again run same test directly just to be sure. The results are :

Directly 300/150, through vpn 32/43.

Guest

@spon901:

The measurement above using command:
time openvpn –test-crypto --secret /tmp/secret --verb 0 --tun-mtu 20000 --cipher aes-256-cbc

seem to be total innacurate.

I made following tests. I connect a i5 laptop and a RK3288 based linux box to a vlan switch. The RK3288 is used as a vlan router. On Laptop I runned a speed test through this router. and I obtain 300M/150M which is what provider offer.
Running the above test command I got :
For RK3288 27 sec which mean 118.5Mbps
For I5 Laptop 6 sec which mean 533 Mbps.

So I expect a throughput of around 120Mbps . However insialling openwrt on both RK3288 box and I5 laptop, performing same test I have only 32Mbps/43Mbps. Why so big difference comparative with theoeretical speed of 120Mbps

OpenWRT is Linux based and not BSD based! This at first. But you will be also getting total
other results if you take on both sides Intel Core i5 CPUs and or i7 CPUs. And theoretical
you could do a test on the same devices for OpenSSL likes many others are doing, but
what you get then out as a result in the real life you should know, is totally another thing!

This numbers even can be and will be different pending on the;
used hardware (horse power), devices it self and topology of the network or done test.

And pease don´t forget that you will need more horse power such OpenWRT is needing,
but on the other side you get then not only a small router, you might be able to set up until
a fully UTM device if needed.

Dalsland

Here is my benchmark for

Intel J1900 Quad Core 4x2GHz
Network 4*Intel WG82583
Eglobal Fanless Mini PC

[2.3.2-RELEASE][admin@pfSense.localdomain]/root: time openvpn --test-crypto --secret /tmp/secret --verb 0 --tun-mtu 20000 --cipher aes-256-cbc
30.309u 0.023s 0:30.35 99.9%    742+177k 0+0io 0pf+0w

30s = 106 Mbps according to the calculation.

"Real world" performance:
I have a 100/100 connection

No VPN

VPN

mauroman33

@spon901:

No, was the same OS . I did not change anything. Just test directly and the immediately run same test through openvpn. The again run same test directly just to be sure. The results are :

Directly 300/150, through vpn 32/43.

Don't you have doubt that it could be related to your VPN provider?

spon901

Both i5 laptop and RK3288 box are in my location connected through a gigabit network. There is no VPN provider involved, only normal ISP that provide connection with 300Mbit/150Mbit. On laptop I have Windows 7 installed and on RK3288 Ubuntu 14.10. As I said the RK3288 act like a VLAN router and connected directly , on laptop I can successfully reach maximum speed provider offer (300/150). Now maing the same speed but through openvpn (I simulate laptop using openvpn client tried to conect to RK3288 openvpn server that connect to internet. In this case the speed was just 32/43. he issue here is not why the speed is so low. It maybe because RK3288 cannot do more (however this is also strange becasue is a capable processor having crypto hardware accelerated). The issue is why testing openvpn speed (and not openssl) gives a so big difference. And all those tests were repeated several times, just to be sure. The results were consistent. Is there any way to be sure that openvpn use hardware accelerated crypto or not. Because maybe this is the reason of so big difference.

mauroman33

Sorry mate, but I didn't understand how pfSense is involved in your test.

spon901

It is not yet. I intend to install it. ut what I wrote has nothing to do with pfsense, or to any operating system. It has to do with theoretical speed calculation cs real speed.

mauroman33

You should consider this thread is about the theoretical speed and the real speed obtained through a device running pfSense.

spon901

Ok, so on a non pFsense device there is no correlation between theoretical and real sped ?

VAMike

@spon901:

Ok, so on a non pFsense device there is no correlation between theoretical and real sped ?

The test is a heuristic, and it remains to be seen how accurate it is across a wide variety of machines. In this case I'd specifically wonder whether the abnormally large blocks used to pad the test runtime give wildly inaccurate results for off-board crypto processors. (On the RK3288, IIRC, the crypto is handled by a specific module, as in the old via padlock stuff, and those generally do much better for large blocks than small blocks because of a high fixed setup cost. On systems with onboard crypto like AES-NI for which the heuristic was initially developed, there's a much lower penalty for small blocks.) I doubt that linux vs fbsd has much to do with it.

mauroman33

@spon901:

Ok, so on a non pFsense device there is no correlation between theoretical and real sped ?

I think there is also correlation for not pfSense devices, but I don't think you could be sure to get a definitive answer on the pfSense forum.

teh g

Figured I'd show my J3455 results:

Intel Celeron J3455 4x1.5GHz -TDP 10W -CPU Mark 2134 -Single Thread 782

AES-256-CBC : 267.9 Mbps
AES-256-GCM: 282.4 Mbps

AES-128-CBC: 270.0 Mbps
AES-128-GCM: 284.9Mbps

denova

I know it's a bit of an old topic but I'm currently looking at some pfsense hardware with openvpn capabilities as well..

As I have a 1000/1000 fiber connection, I was wondering if a kaby lake celeron 3865u (1.8 GHz, dual core) would do similar or better than a j3355 for pfsense+openvpn purposes?

pfBasic

Probably pretty similar to j3355, but that's a mobile part.

chrcoluk

aes256 is just needlessly throwing away performance especially on CBC, I suggest sticking to aes128-gcm guys.

denova

@teh:

Figured I'd show my J3455 results:

Intel Celeron J3455 4x1.5GHz -TDP 10W -CPU Mark 2134 -Single Thread 782

AES-256-CBC : 267.9 Mbps
AES-256-GCM: 282.4 Mbps

AES-128-CBC: 270.0 Mbps
AES-128-GCM: 284.9Mbps

Ended up with a G4400 build myself, speed with PIA using OpenVPN and AES-128-CBC is near 500 Mbps. I never see the CPU taxed above 30% though with AES-NI enabled.

Also, the idle power consumption for the total system is about 13 watts, which is still fine for me.