• Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Search
  • Register
  • Login
Netgate Discussion Forum
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Search
  • Register
  • Login

PC Engines apu2 experiences

Scheduled Pinned Locked Moved Hardware
711 Posts 73 Posters 774.1k Views
Loading More Posts
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • K
    kevindd992002
    last edited by Nov 29, 2016, 12:44 PM

    I don't think I am. Clearly, unchecking the boxes = ENABLES these features. checking the boxes=DISABLES these features. It's very easy to distinguish between the two.

    j4k3 said in his post: "I had to uncheck Disable hardware large receive offload, and Disable hardware TCP segmentation offload". Which means that enabling (very different from "checking") them improves performance.

    So then I asked: "But why is the NIC performance hampered with these settings disabled anyway?". Or in other words: "why is the NIC performance hampered with the boxes CHECKED anyway?"

    Does that make sense? Again, disable=checked and enabled=unchecked. Please check the terminologies that I used in my posts.

    1 Reply Last reply Reply Quote 0
    • ?
      Guest
      last edited by Nov 29, 2016, 1:44 PM

      Does that mean these two should be unchecked to get the full potential of the NIC's of the APU2C4?

      Here under this link you will be able to read what is really needed for getting 1 GBit/s at the
      WAN interface, there is told something likes, Server grade hardware and ~2,0GHz CPU speed.
      And as I see it right the APU1D4 and APU2C4 are only sorted with something around ~1,1GHz
      or 1,2GHz CPU power, that's it in short. Please read under under CPU selection

      Any disadvantages of keeping them unchecked (enabled)?

      Tunings and pimps can be done on each machine for sure to high up the
      throughput but in that case, you should be followed to that guidance
      from above at first.

      1 Reply Last reply Reply Quote 0
      • C
        cwagz
        last edited by Dec 1, 2016, 6:34 PM

        @cwagz:

        I am looking for some opinions on downsizing my current pfSense system with an APU2C4.

        Currently I have:
        Supermicro A1SRI-2558
        8GB Ram
        120GB SSD
        Akasa Fanless Enclosure

        There are 6 people in my house and 30 or so devices.  I am the only person that ever uses OpenVPN and it is usually from a mobile device on LTE so OpenVPN performance is probably not a huge deal.  I run Squid and Squidguard to proxy the internet for my kids.  Our internet connection is FiOS 150/150 Mbps.

        It seems like I could build an apu2c4 and sell my current hardware.  I would probably have money left over and a smaller, slightly cooler running device for pfSense.

        Do you guys see any potential performance issues or reasons why this is a bad idea?

        I went ahead and built the apu2c4 and am very happy with the outcome.  The performance seems to be the same for our usage.  Also, the overall footprint and heat output into my small network cabinet is improved.

        Netgate 6100 MAX

        1 Reply Last reply Reply Quote 0
        • H
          HackedComputer
          last edited by Dec 12, 2016, 3:39 PM

          Hey,

          I recently took delivery of an APU2C4. It is certainly a decent performer for the size of it!

          I am wondering, has anyone got the AES-NI to work with the OpenVPN? The reason I ask is that I don't appear to see any acceleration happening with AES-128-CBC / AES-256-CBC. The rough maximum I have achieved is 30Mbps.

          I have tried enabling the AES-NI within Advanced Options, and then enabling the cryptodev within OpenVPN. As well as disabling AES-NI and leaving Cryptodev enabled vice-versa.

          However, I see no changes whatsoever.

          I am on the latest PFSense 2.3.x release

          Kindest Regards
          HC

          1 Reply Last reply Reply Quote 0
          • ?
            Guest
            last edited by Dec 17, 2016, 8:10 PM Dec 13, 2016, 4:17 AM

            I am wondering, has anyone got the AES-NI to work with the OpenVPN? The reason I ask is that I don't appear to see any acceleration happening with AES-128-CBC / AES-256-CBC. The rough maximum I have achieved is 30Mbps.

            From what total line speed you archived the 30Mbps? And how strong was the other VPN Peer end?

            I have tried enabling the AES-NI within Advanced Options, and then enabling the cryptodev within OpenVPN. As well as disabling AES-NI and leaving Cryptodev enabled vice-versa.

            At the moment only IPsec is really benefitting from the AES-NI, so you might be having
            perhaps more luck if the OpenVPN version 2.4 is out there.

            1 Reply Last reply Reply Quote 0
            • H
              HackedComputer
              last edited by Dec 14, 2016, 11:05 PM

              From what total line speed you archived the 30Mbps? And how strong was the other VPN pear end?

              Connecting from a 317Mbps line, the other end is serviced by a 10Gbit (SFP) line @ Rackspace

              At the moment only IPsec is really benefitting from the AES-NI, so you might be having
              perhaps more luck if the OpenVPN version 2.4 is out there.

              I'll hold out, I'm not too fussed - I didn't expect a lot. But I expected a tad better as my old equipment was a dual core 800Mhz MiPS. I had tried the "fix" here:

              http://1101entrails.blogspot.co.uk/2016/05/getting-aes-ni-to-work-using-pfsense-on.html

              1 Reply Last reply Reply Quote 0
              • V
                VAMike
                last edited by Dec 15, 2016, 12:58 AM

                @HackedComputer:

                At the moment only IPsec is really benefitting from the AES-NI, so you might be having
                perhaps more luck if the OpenVPN version 2.4 is out there.

                I'll hold out, I'm not too fussed - I didn't expect a lot. But I expected a tad better as my old equipment was a dual core 800Mhz MiPS. I had tried the "fix" here:

                http://1101entrails.blogspot.co.uk/2016/05/getting-aes-ni-to-work-using-pfsense-on.html

                That page is mostly correct–openvpn does use aes-ni, having pfsense try to load any cryptographic stuff will slow things down, and you should be getting significantly more than 30Mbps. Make sure you're connecting with aes on the client side and turn off all the hardware crypto settings in pfsense.

                1 Reply Last reply Reply Quote 0
                • H
                  HackedComputer
                  last edited by Dec 15, 2016, 6:04 PM Dec 15, 2016, 6:00 PM

                  Just an update:

                  So, changing the cryptographic options within pfSense didn't yield any differences. Perhaps, by 5Mbps.

                  However, I looked more into the OpenVPN configuration and appended the following to the client configuration:

                  sndbuf 393216;
                  rcvbuf 393216

                  and thus, this was achieved:

                  1 Reply Last reply Reply Quote 0
                  • F
                    FreeMinded
                    last edited by Dec 27, 2016, 3:14 PM

                    Here some "facts" from tests with APU2C4 and the latest pfSense (2.3.2_1)

                    WAN Speed on a clean Gigabit Link: ~640 MBits/s
                    OpenVPN Speed: ~50 MBits/s (AES-128-CBC with SHA256)

                    By enabling "Hardware Checksum Offloading" (by unchecking the setting) and "Hardware TCP Segmentation Offloading" (by unchecking the setting) I was able to get a 20-30 MBits/s improvement. Better, but still way off real Gigabit Speed.

                    Same for the OpenVPN throughput

                    • Activating the AES-NI support doesn't currently do anything (should hopefully improve with OpenVPN Version 2.4+)

                    • Activating BSD Crypto engine reduces (!) the throughput by ~5MBits/s

                    • setting sndbuf 393216; rcvbuf 393216 in the client config as suggest above didn't do anything neither. But this might be due to the server side still using an older OpenVPN version (2.3.2) where there are low defaults. The OpenVPN log shows Socket Buffers: R=[42080->393216] S=[57344->393216]

                    Looking forward to other reports and suggestions!

                    1 Reply Last reply Reply Quote 0
                    • V
                      VAMike
                      last edited by Dec 28, 2016, 6:08 PM

                      @FreeMinded:

                      Activating the AES-NI support doesn't currently do anything (should hopefully improve with OpenVPN Version 2.4+)
                      Activating BSD Crypto engine reduces (!) the throughput by ~5MBits/s

                      AES-NI is always on in current openvpn. Activating cryptodev overrides the built-in AES-NI support and does generally make openvpn slower. This is not specific to the APU2. If AES-NI were actually off (this can be done by setting an environment variable to tell openssl to ignore AES-NI support when running openvpn from the command line) you'd get a substantial reduction in throughput (more like 30% than 5%; the actual difference in crypto rates is much greater but openvpn has other bottlenecks).

                      1 Reply Last reply Reply Quote 0
                      • A
                        Af0x
                        last edited by Feb 5, 2017, 10:33 PM

                        hi guys, has anyone managed to use the full capacity of your storage. I installed by this guide: http://pcengines.ch/howto.htm#OS_installation

                        Problem is that it only uses a part of my storage capacity. Can anyone tell me how to install on all available storage capacity?

                        1 Reply Last reply Reply Quote 0
                        • D
                          doktornotor Banned
                          last edited by Feb 5, 2017, 10:41 PM

                          @Af0x:

                          hi guys, has anyone managed to use the full capacity of your storage.

                          Stop using nanobsd.

                          1 Reply Last reply Reply Quote 0
                          • A
                            Af0x
                            last edited by Feb 10, 2017, 5:56 AM

                            @doktornotor:

                            Stop using nanobsd.

                            ok, thank you. I did that and want to know which kernel is suitable for the apu2? I think it is the embedded one, but am not sure.

                            1 Reply Last reply Reply Quote 0
                            • D
                              doktornotor Banned
                              last edited by Feb 10, 2017, 8:52 AM

                              Cannot recall ever selecting something there.  Get the memstick-serial image and leave it at default. :)

                              1 Reply Last reply Reply Quote 0
                              • ?
                                Guest
                                last edited by Feb 10, 2017, 12:05 PM

                                Can anyone tell me how to install on all available storage capacity?

                                Where you want to install pfSense? In a mSATA, USB drive or a real HDD/SSD?
                                If you take an usb drive and put on it the MEMSTICK-Serial-AM64 image and the you install from there onto a…....
                                That is a fresh and full install and might be the best bet for you.

                                1 Reply Last reply Reply Quote 0
                                • A
                                  Af0x
                                  last edited by Feb 10, 2017, 3:29 PM

                                  hi, thanks you guys. I already downloaded and installed on my mSATA. During Installation you get the choice like on the picture:
                                  https://doc.pfsense.org/images/1/11/Installer_05_select_console.png

                                  I chose embedded but I read that it has reduced possibilities talking about packages.

                                  1 Reply Last reply Reply Quote 0
                                  • H
                                    hda
                                    last edited by Feb 10, 2017, 3:55 PM

                                    @Af0x:

                                    …mSATA...

                                    APU2 & mSata ? >>> 64-bit Full Install.

                                    1 Reply Last reply Reply Quote 0
                                    • O
                                      Ofloo
                                      last edited by Apr 7, 2017, 11:18 AM Apr 7, 2017, 10:36 AM

                                      apu1d4: throughput was arround 700mbit/s ~ 900mbit/s, when i first bought it pfsense did 500mbit/s later on that changed
                                      apu3a4: throughput is 250mbit/s ~ 300mbit/s

                                      What i do notice is that apu1d4 uses realtek(re) drivers and the apu3 uses intel(igb)
                                      for the igb driver: TSO LRO .. checksum offload turned on or off makes no difference

                                      strange thing is when I run iperf through vlan but not hosted on the router but on a server on a different subnet which is routed though the router i get

                                      –----------------------------------------------------------
                                      [  3] local 192.168.1.100 port 44774 connected with 172.18.1.11 port 5001
                                      [ ID] Interval      Transfer    Bandwidth
                                      [  3]  0.0-10.0 sec  715 MBytes  600 Mbits/sec

                                      when i turn on tso lro checksum offload, cpu rather then hiadapt to maximum

                                      ------------------------------------------------------------
                                      Client connecting to loki, TCP port 5001
                                      TCP window size: 85.0 KByte (default)
                                      ------------------------------------------------------------
                                      [  3] local 192.168.1.100 port 45468 connected with 172.18.1.11 port 5001
                                      [ ID] Interval       Transfer     Bandwidth
                                      [  3]  0.0-10.0 sec   757 MBytes   635 Mbits/sec
                                      
                                      ------------------------------------------------------------
                                      Client connecting to loki, TCP port 5001
                                      TCP window size: 85.0 KByte (default)
                                      ------------------------------------------------------------
                                      [  3] local 192.168.1.100 port 45462 connected with 172.18.1.11 port 5001
                                      [ ID] Interval       Transfer     Bandwidth
                                      [  3]  0.0-10.0 sec   742 MBytes   622 Mbits/sec
                                      
                                      1 Reply Last reply Reply Quote 0
                                      • ?
                                        Guest
                                        last edited by Apr 8, 2017, 7:46 AM

                                        apu1d4: throughput was arround 700mbit/s ~ 900mbit/s, when i first bought it pfsense did 500mbit/s later on that changed

                                        Without PowerD (hi adaptive) it was more around ~450 - 550 MBit/s but with "turned on" PowerD it Comes nearly to that numbers
                                        like you are naming here, ~650 MBit/s - 750 MBit/s and yes for sure that can be different from OS to OS! From FreeBSD to Linux
                                        as the base system, such as IPFire or ZeroShell are based on due to the better driver support.

                                        apu3a4: throughput is 250mbit/s ~ 300mbit/s

                                        The APU1D4 and APU2C4 are regular boards that was produced for the whole public, but likes in the past too, there
                                        are options, that you might be calling for a customized board based on the number of boards you must then buy.
                                        Let us say 150 - 1000 as a minimum and in former times this boards where then only for you or that customer and
                                        not available for the rest of us or the whole public customers, this was changing now, and so rests of such a special
                                        version or customized board will now also available to the public by sale. But please accept that this APU3 boards are
                                        optimized for LTE usage, also the LAN ports as I am right informed and this might be then driving such a throughput
                                        test in a total other direction! If you are using 3G and/or LTE modems inside  this will be then perhaps once more
                                        again differing from what you see now or get out now!

                                        What i do notice is that apu1d4 uses realtek(re) drivers and the apu3 uses intel(igb)
                                        for the igb driver: TSO LRO .. checksum offload turned on or off makes no difference

                                        That might be shinning as the changing point for sure and first of all, but there are also two other things
                                        that will be interesting now. The PowerD is bursting the APU1 cpu (T40E dual core) much more then the
                                        APU2 cpu (GX-412TC quad core) that is taking not really a benefit well from activating this PowerD option
                                        and then the igb(4) driver is now also multi cpu threading but even not the PPPoE part!

                                        I don´t know if that "optimized option" will be able to change or something else, but perhaps this might be
                                        then pushing that number somehow in the high, if there will be an option to change them. Perhaps in the BIOS!?

                                        1 Reply Last reply Reply Quote 0
                                        • VeldkornetV
                                          Veldkornet
                                          last edited by May 5, 2017, 7:08 AM

                                          Has anyone  updated to the latest BIOS?

                                          I noticed in pfSense that the system is now just seen as "pfSense" where as it was "PC Engines APU2"
                                          See screenshots.

                                          Not that the name really matters to me, was just wondering others had the same.

                                          Before.png
                                          Before.png_thumb
                                          After.png
                                          After.png_thumb

                                          1 Reply Last reply Reply Quote 0
                                          • First post
                                            Last post
                                          Copyright 2025 Rubicon Communications LLC (Netgate). All rights reserved.
                                            This community forum collects and processes your personal information.
                                            consent.not_received