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

    PfSense overhead

    Scheduled Pinned Locked Moved General pfSense Questions
    18 Posts 5 Posters 3.8k 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.
    • B Offline
      berrick
      last edited by

      Hi All,

      What sort of overhead (impact on broadband speed) should I expect to see

      I have just installed pfsense 2.01 on an old Nokia IP330. This connects to a vDSL modem connected to a 40/20 FTTC link.

      There is no fancy config in pfsense yet I see a consistent 10Mbps drop in download speed and a 6Mbps drop in up load speeds when pfsense is used.

      1 Reply Last reply Reply Quote 0
      • J Offline
        jasonlitka
        last edited by

        This is my go-to list for people reporting slowdowns:

        • Duplex mismatch between your pfSense box and the DSL/Cable modem.

        • Double NAT.

        • pfSense box is underpowered (eg. trying to run a 100/100 line on an Alix or trying to use Snort, Squid, L7 shaping, etc. without being aware of how much CPU power those need to perform well).

        Depending on what model IP330 you've got, it might well be something like a 166MHz Pentium w/ MMX (like this guy from 2006).  If so, be thankful you're getting what you're getting.

        I can break anything.

        1 Reply Last reply Reply Quote 0
        • B Offline
          berrick
          last edited by

          • No Duplex mismatch - I meant to state that but forgot

          • No double NAT - the vDSL modem is configured as a bridge, NAT, PPPoE etc to be handled by another device

          • the CPU doesn't seem to break a sweat though when testing

          1 Reply Last reply Reply Quote 0
          • D Offline
            dreamslacker
            last edited by

            If you have traffic shaping setup, that could be the problem. The wizard generated values might be limiting the bandwidth available for your downloading.

            1 Reply Last reply Reply Quote 0
            • stephenw10S Offline
              stephenw10 Netgate Administrator
              last edited by

              I wouldn't expect that CPU to have a problem at 40Mbps and you have said it doesn't appear to have excessive CPU use. How are you measuring that?
              Try running 'top SH' at the console.

              Are you running the default install or have you added packages, enabled extra services, tweaked it in any way?

              Steve

              1 Reply Last reply Reply Quote 0
              • B Offline
                berrick
                last edited by

                OK,

                Using a different router to perform the modem bit, a different hard disk and pfSense 2.1 just for good measure I have a slight improvement but still dropping about 8Mbps on the download and 5Mbps on the upload speedtest.

                I'm taking speedtests to the same sites just before and just after I insert the F/W and always see this "overhead"

                top sh shows

                • CPU: 54.9% user,  0.0% nice,  7.4% system,  0.8% interrupt, 37.0% idle - no speedtest

                • CPU:  0.0% user,  1.4% nice,  6.8% system, 91.7% interrupt,  0.0% idle - Download speedtest

                • CPU: 41.8% user,  0.0% nice,  8.8% system, 49.4% interrupt,  0.0% idle - Upload speedtest

                So would my assessment that the high interrupt values is down to the NIC's and that this is where the overhead is coming from?

                1 Reply Last reply Reply Quote 0
                • H Offline
                  heper
                  last edited by

                  what is using 55% of cpu when it's supposed to be almost idle ? this can't be right … not even on a P2

                  1 Reply Last reply Reply Quote 0
                  • B Offline
                    berrick
                    last edited by

                    @heper

                    Its not a what its several processes at the same time. That is if I'm doing this correctly.

                    I used top -S and very frequently the CPU peaks at around the 50% mark. When this happens several processes are running such as netstat, php,grep.

                    Does that answer your concerns?

                    1 Reply Last reply Reply Quote 0
                    • stephenw10S Offline
                      stephenw10 Netgate Administrator
                      last edited by

                      Do you have any sort of power saving features enabled?
                      92% interrupt load doesn't look good though. What's causing that? Try running 'vmstat -i'.

                      Steve

                      1 Reply Last reply Reply Quote 0
                      • B Offline
                        berrick
                        last edited by

                        I ran the command and below is what it returned. I dont know this command, not sure how to read the output.
                        Please be aware I was installing ntop at the smae time

                        interrupt                          total      rate
                        irq0: clk                        955353        99
                        irq4: uart0                        3272          0
                        irq5: fxp2                        148409        15
                        irq7: ppc0                            1          0
                        irq8: rtc                        1222813        127
                        irq10: fxp0                      194081        20
                        irq14: ata0                        19767          2
                        Total                            2543696        266

                        1 Reply Last reply Reply Quote 0
                        • stephenw10S Offline
                          stephenw10 Netgate Administrator
                          last edited by

                          Ok, well that looks fine the rates are all reasonable. Try re-running it when you are downloading at max speed.
                          You haven't enabled powerd I assume?

                          Steve

                          1 Reply Last reply Reply Quote 0
                          • B Offline
                            berrick
                            last edited by

                            This is a fresh vanilla install of 2.1 Just in stalling ntop then squid to get user statistics.

                            I will try another download test prior to setting up squid.

                            So would my assessment that the high interrupt values is down to the NIC's and that this is where the overhead is coming from?

                            Was my statement above correct?

                            Here is the output from vmstat -i whilst performing a download and upload test

                            interrupt                          total      rate
                            irq0: clk                        1444232        99
                            irq4: uart0                        3272          0
                            irq5: fxp2                        281746        19
                            irq7: ppc0                            1          0
                            irq8: rtc                        1848559        127
                            irq10: fxp0                      288395        19
                            irq14: ata0                        75292          5
                            Total                            3941497        272

                            interrupt                          total      rate
                            irq0: clk                        1449051        99
                            irq4: uart0                        3272          0
                            irq5: fxp2                        283602        19
                            irq7: ppc0                            1          0
                            irq8: rtc                        1854727        127
                            irq10: fxp0                      289780        19
                            irq14: ata0                        75378          5
                            Total                            3955811        272

                            interrupt                          total      rate
                            irq0: clk                        1451151        99
                            irq4: uart0                        3272          0
                            irq5: fxp2                        284229        19
                            irq7: ppc0                            1          0
                            irq8: rtc                        1857415        127
                            irq10: fxp0                      290190        19
                            irq14: ata0                        75403          5
                            Total                            3961661        272

                            interrupt                          total      rate
                            irq0: clk                        1452137        99
                            irq4: uart0                        3272          0
                            irq5: fxp2                        287504        19
                            irq7: ppc0                            1          0
                            irq8: rtc                        1858677        127
                            irq10: fxp0                      292891        20
                            irq14: ata0                        75406          5
                            Total                            3969888        273

                            interrupt                          total      rate
                            irq0: clk                        1452770        99
                            irq4: uart0                        3272          0
                            irq5: fxp2                        290780        20
                            irq7: ppc0                            1          0
                            irq8: rtc                        1859487        127
                            irq10: fxp0                      296712        20
                            irq14: ata0                        75461          5
                            Total                            3978483        273

                            interrupt                          total      rate
                            interrupt: Command not found.
                            irq5: fxp2                        281746        19
                            irq7: ppc0                            1          0
                            irq8: rtc                        1848559        127
                            irq10: fxp0                      288395        19
                            irq14: ata0                        75292          5
                            Total                            3941497        272

                            1 Reply Last reply Reply Quote 0
                            • H Offline
                              heper
                              last edited by

                              try removing ntop …. it could be the elephant in the room

                              1 Reply Last reply Reply Quote 0
                              • stephenw10S Offline
                                stephenw10 Netgate Administrator
                                last edited by

                                Presumably you are downloading between fxp0 and fxp2? The interrupt rates look low. I expected far higher given the interrupt load on the cpu.

                                Can you show the full output of 'top -SH'?

                                Steve

                                1 Reply Last reply Reply Quote 0
                                • B Offline
                                  berrick
                                  last edited by

                                  Hi,

                                  Sorry for the delay.

                                  This is the output pre Speed test

                                  During Download test, the screen refresh stops during this

                                  During Upload test

                                  I have added nTOP, Squid, Lightsquid, Sarg and Dansguardian as I needed to demostrate these features.

                                  Look forward to your comments

                                  1 Reply Last reply Reply Quote 0
                                  • stephenw10S Offline
                                    stephenw10 Netgate Administrator
                                    last edited by

                                    Those packages are going to really hit that box hard. Many people would consider them unsuitable for the Alix box with it's 500MHz CPU and 256MB ram. Those interupt figures don't look inconsistent in any way. Perhaps that's just the limit of the hardware.  :-\ It could be that I'm showing my age but I remeber the K6-2 as being quite fast. Happy hours on Doom2! The alix has a NAT/firewall limit of 85Mbps, significantly faster.
                                    It's difficult to find and benchmarks that compare the two processors. Somthing useful can be found here:
                                    http://new.haveland.com/povbench/graph.php
                                    There we can see the Geode 700LX (500MHz) score 8.19x (the speed of a Pentium 100) where as the K6-2 at 400MHz scores 3.46x. Thus if both boxes are dependent purely on processing power and the Alix tops out at 85Mbps I would expect yours to manage 36Mbps. Close to what you're seeing. That doesn't really explain the drop when uploading though.  :-\

                                    Steve

                                    1 Reply Last reply Reply Quote 0
                                    • B Offline
                                      berrick
                                      last edited by

                                      Ok, Good link.

                                      I understand what you are saying I'm guessing that its the NAT part which is the overhead. The reason for stating this is I configured the IP330 as a transparent bridge and repeated the speed tests, no overhead. Get the same figures whether I go through the IP330 or not.

                                      If I'm wrong please correct me.

                                      1 Reply Last reply Reply Quote 0
                                      • stephenw10S Offline
                                        stephenw10 Netgate Administrator
                                        last edited by

                                        Yep you will see significantly faster throughput in transparent mode. There are a lot less processing steps when you disable NAT, even less when you are bridging.

                                        However that still doesn't explain why you are seeing reduced upload speeds. You would normally see no significant reduction in throughput until you hit the limits of the hardware.

                                        Steve

                                        1 Reply Last reply Reply Quote 0
                                        • First post
                                          Last post
                                        Copyright 2025 Rubicon Communications LLC (Netgate). All rights reserved.