Re: extreme network latency
On Thu, Oct 20, 2016 at 2:22 AM, Richard Nyberg wrote: >> For better performance, you can put the if_emx_load="YES" in >> loader.conf. However, em0 will become emx0 after loading that module, >> so make sure that your rc.conf and pf.conf are also updated ;) > > It turned out hw.re.msi.enable="1" did not work so well. re0 simply That's why I didn't enable MSI on re in the first place, some chips work, some not. > stopped doing anything after a while. My current configuration uses re > and emx, both without polling. This works great since they end up > using different interrupts with emx instead of em. Heh, I see, it seems to the issue of shared interrupt. emx is actually using MSI by default, re probably is the only interrupt producer on that pin. Thanks, sephe -- Tomorrow Will Never Die
Re: extreme network latency
> For better performance, you can put the if_emx_load="YES" in > loader.conf. However, em0 will become emx0 after loading that module, > so make sure that your rc.conf and pf.conf are also updated ;) It turned out hw.re.msi.enable="1" did not work so well. re0 simply stopped doing anything after a while. My current configuration uses re and emx, both without polling. This works great since they end up using different interrupts with emx instead of em. Thanks for all your help, -Richard
Re: extreme network latency
On Wed, Oct 19, 2016 at 2:19 AM, Richard Nyberg wrote: > Hi! Yes it's quite recent hardware. > > On 18 October 2016 at 04:20, Sepherosa Ziehau wrote: >> >> Heh, I'd say avoid re :). > > I might not have made the wisest choice there. :) > >> Try put the following tunable: >> hw.re.msi.enable="1" >> to /boot/loader.conf. And reboot. > > This also worked. Using this instead of polling now. > >> Output of pciconf -lvc would really be helpful. > > Output attached. For better performance, you can put the if_emx_load="YES" in loader.conf. However, em0 will become emx0 after loading that module, so make sure that your rc.conf and pf.conf are also updated ;) Thanks, sephe -- Tomorrow Will Never Die
Re: extreme network latency
Hi! Yes it's quite recent hardware. On 18 October 2016 at 04:20, Sepherosa Ziehau wrote: > > Heh, I'd say avoid re :). I might not have made the wisest choice there. :) > Try put the following tunable: > hw.re.msi.enable="1" > to /boot/loader.conf. And reboot. This also worked. Using this instead of polling now. > Output of pciconf -lvc would really be helpful. Output attached. -Richard hostb0@pci0:0:0:0: class=0x06 card=0x86941043 chip=0x191f8086 rev=0x07 hdr=0x00 vendor = 'Intel Corporation' device = 'Skylake Host Bridge/DRAM Registers' class = bridge subclass = HOST-PCI cap 09[e0] = vendor (length 16) Intel cap 0 version 1 pcib1@pci0:0:1:0: class=0x060400 card=0x86941043 chip=0x19018086 rev=0x07 hdr=0x01 vendor = 'Intel Corporation' device = 'Skylake PCIe Controller (x16)' class = bridge subclass = PCI-PCI cap 0d[88] = PCI Bridge card=0x86941043 cap 01[80] = powerspec 3 supports D0 D3 current D0 cap 05[90] = MSI supports 1 message cap 10[a0] = PCI-Express 2 root port max data 128(256) link x1(x16) ecap 0002[100] = VC 1 max VC0 ecap 0005[140] = unknown 1 ecap 0019[d94] = unknown 1 vgapci0@pci0:0:2:0: class=0x03 card=0x86941043 chip=0x19128086 rev=0x06 hdr=0x00 vendor = 'Intel Corporation' device = 'HD Graphics 530' class = display subclass = VGA bar [10] = type Memory, range 64, base 0xf600, size 16777216, enabled bar [18] = type Prefetchable Memory, range 64, base 0xe000, size 268435456, enabled bar [20] = type I/O Port, range 32, base 0xf000, size 64, enabled cap 09[40] = vendor (length 12) Intel cap 0 version 1 cap 10[70] = PCI-Express 2 root endpoint max data 128(128) link x0(x0) cap 05[ac] = MSI supports 1 message cap 01[d0] = powerspec 2 supports D0 D3 current D0 ecap 001b[100] = unknown 1 ecap 000f[200] = unknown 1 ecap 0013[300] = unknown 1 xhci0@pci0:0:20:0: class=0x0c0330 card=0x86941043 chip=0xa12f8086 rev=0x31 hdr=0x00 vendor = 'Intel Corporation' device = 'Sunrise Point-H USB 3.0 xHCI Controller' class = serial bus subclass = USB bar [10] = type Memory, range 64, base 0xf723, size 65536, enabled cap 01[70] = powerspec 2 supports D0 D3 current D0 cap 05[80] = MSI supports 8 messages, 64 bit enabled with 1 message none0@pci0:0:22:0: class=0x078000 card=0x86941043 chip=0xa13a8086 rev=0x31 hdr=0x00 vendor = 'Intel Corporation' device = 'Sunrise Point-H CSME HECI' class = simple comms bar [10] = type Memory, range 64, base 0xf724d000, size 4096, enabled cap 01[50] = powerspec 3 supports D0 D3 current D0 cap 05[8c] = MSI supports 1 message, 64 bit ahci0@pci0:0:23:0: class=0x010601 card=0x86941043 chip=0xa1028086 rev=0x31 hdr=0x00 vendor = 'Intel Corporation' device = 'Sunrise Point-H SATA controller [AHCI mode]' class = mass storage subclass = SATA bar [10] = type Memory, range 32, base 0xf7248000, size 8192, enabled bar [14] = type Memory, range 32, base 0xf724c000, size 256, enabled bar [18] = type I/O Port, range 32, base 0xf090, size 8, enabled bar [1c] = type I/O Port, range 32, base 0xf080, size 4, enabled bar [20] = type I/O Port, range 32, base 0xf060, size 32, enabled bar [24] = type Memory, range 32, base 0xf724b000, size 2048, enabled cap 05[80] = MSI supports 1 message enabled with 1 message cap 01[70] = powerspec 3 supports D0 D3 current D0 cap 12[a8] = SATA Index-Data Pair pcib2@pci0:0:27:0: class=0x060400 card=0x86941043 chip=0xa1678086 rev=0xf1 hdr=0x01 vendor = 'Intel Corporation' device = 'Sunrise Point-H PCI Root Port' class = bridge subclass = PCI-PCI cap 10[40] = PCI-Express 2 root port max data 128(256) link x0(x4) cap 05[80] = MSI supports 1 message cap 0d[90] = PCI Bridge card=0x86941043 cap 01[a0] = powerspec 3 supports D0 D3 current D0 ecap 0001[100] = AER 1 0 fatal 0 non-fatal 0 corrected ecap 000d[140] = unknown 1 ecap 0019[220] = unknown 1 pcib3@pci0:0:28:0: class=0x060400 card=0x86941043 chip=0xa1108086 rev=0xf1 hdr=0x01 vendor = 'Intel Corporation' device = 'Sunrise Point-H PCI Express Root Port' class = bridge subclass = PCI-PCI cap 10[40] = PCI-Express 2 root port max data 128(256) link x0(x1) cap 05[80] = MSI supports 1 message cap 0d[90] = PCI Bridge card=0x86941043 cap 01[a0] = powerspec 3 supports D0 D3 current D0 pcib4@pci0:0:29:0: class=0x060400 card=0x86941043 chip=0xa1188086 rev=0xf1 hdr=0x01 vendor = 'Intel Corporation' device = 'Sunrise Point-H PCI Express Root Port' class = bridge subclass = PCI-PCI cap 10[40] = PCI-Express 2 root port max data 128(256) link x0(x1) cap 05[80] = MSI supports 1 message cap 0d[90]
Re: extreme network latency
On Tue, Oct 18, 2016 at 4:17 AM, Richard Nyberg wrote: > Yes, that was it. Many thanks! > > Should I just use polling, which works fine, or is there something one > can do about the interrupt issue? Heh, I'd say avoid re :). Try put the following tunable: hw.re.msi.enable="1" to /boot/loader.conf. And reboot. Output of pciconf -lvc would really be helpful. Thanks, sephe > > -Richard > > On 17 October 2016 at 22:05, Matthew Dillon wrote: >> That kinda sounds like an interrupt issue, in which case I suggest turning >> polling on for both interfaces. ifconfig polling ought to do it. If >> that fixes the problem, then it is definitely interrupt-related. >> >> -Matt >> >> On Mon, Oct 17, 2016 at 12:52 PM, Richard Nyberg >> wrote: >>> >>> Thanks again for your suggestions. >>> >>> Actually it's much stranger than I thought. While troubleshooting I >>> had this configuration: >>> >>> df (em0) -> switch <- desktop >>> >>> No other devices or network interfaces were connected. In this >>> configuration there was no problem at all with latency. I then plugged >>> in the cable with internet acces like below: >>> >>> internet <- (re0) df (em0) -> switch <- desktop >>> >>> In this configuration the latency problems immediately showed. The fun >>> thing is that when I unplugged the re0 interface again the em0 >>> interface stopped responding at all, until I put the cable back to >>> re0. Then em0 was back but with latency problems. >>> >>> Another data point is that while I downloaded a large file at speed >>> from the internet via df to my desktop in the above configuration and >>> pinged from the desktop to df at the same time, the latency problems >>> were gone. Until the download was finished and they started again. >>> >>> -Richard >>> >>> On 16 October 2016 at 19:14, Matthew Dillon wrote: >>> > Look for a packet loop on the interface. Use tcpdump on the interface >>> > to >>> > see if there are excess packets being generated from somewhere. There >>> > are >>> > numerous things that can blow up a LAN. The most common being that a >>> > switch >>> > port is wired to loop back into the LAN. >>> > >>> > -Matt >>> > >>> > On Sun, Oct 16, 2016 at 9:17 AM, Justin Sherrill >>> > >>> > wrote: >>> >> >>> >> On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg >>> >> >>> >> wrote: >>> >> > Thanks! >>> >> > >>> >> > Here are some more datapoints. >>> >> >>> >> I think the only constant at this point is the internal interface on >>> >> the DragonFly system. If you hook the em0 interface that's currently >>> >> internal on the DragonFly machine up to your Internet link (i.e. >>> >> reverse which interface is internal or external), does it still >>> >> perform badly? >>> >> >>> >> If it doesn't work well, then that interface is bad. I'd be >>> >> surprised, cause I've seen network ports go bad very rarely, but it's >>> >> possible. Plus, I don't have any other ideas. >>> > >>> > >> >> -- Tomorrow Will Never Die
Re: extreme network latency
Our network dev Sephe might be able to work out why the NICs are interfering with each other, but it depends how old they are. If they are old card(s) and/or it is an old motherboard, it might not be worth tracking down. Polling is a perfectly acceptable solution for older stuff. If the NICs are relatively recent, though, we would want to try to track down the problem. I think it is at least worth doing a verbose boot and posting the dmesg output from it, and also posting the output from 'pciconf -lbcv' with both NICs present. -Matt On Mon, Oct 17, 2016 at 1:17 PM, Richard Nyberg wrote: > Yes, that was it. Many thanks! > > Should I just use polling, which works fine, or is there something one > can do about the interrupt issue? > > -Richard > > On 17 October 2016 at 22:05, Matthew Dillon wrote: > > That kinda sounds like an interrupt issue, in which case I suggest > turning > > polling on for both interfaces. ifconfig polling ought to do > it. If > > that fixes the problem, then it is definitely interrupt-related. > > > > -Matt > > > > On Mon, Oct 17, 2016 at 12:52 PM, Richard Nyberg > > wrote: > >> > >> Thanks again for your suggestions. > >> > >> Actually it's much stranger than I thought. While troubleshooting I > >> had this configuration: > >> > >> df (em0) -> switch <- desktop > >> > >> No other devices or network interfaces were connected. In this > >> configuration there was no problem at all with latency. I then plugged > >> in the cable with internet acces like below: > >> > >> internet <- (re0) df (em0) -> switch <- desktop > >> > >> In this configuration the latency problems immediately showed. The fun > >> thing is that when I unplugged the re0 interface again the em0 > >> interface stopped responding at all, until I put the cable back to > >> re0. Then em0 was back but with latency problems. > >> > >> Another data point is that while I downloaded a large file at speed > >> from the internet via df to my desktop in the above configuration and > >> pinged from the desktop to df at the same time, the latency problems > >> were gone. Until the download was finished and they started again. > >> > >> -Richard > >> > >> On 16 October 2016 at 19:14, Matthew Dillon > wrote: > >> > Look for a packet loop on the interface. Use tcpdump on the interface > >> > to > >> > see if there are excess packets being generated from somewhere. There > >> > are > >> > numerous things that can blow up a LAN. The most common being that a > >> > switch > >> > port is wired to loop back into the LAN. > >> > > >> > -Matt > >> > > >> > On Sun, Oct 16, 2016 at 9:17 AM, Justin Sherrill > >> > > >> > wrote: > >> >> > >> >> On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg > >> >> > >> >> wrote: > >> >> > Thanks! > >> >> > > >> >> > Here are some more datapoints. > >> >> > >> >> I think the only constant at this point is the internal interface on > >> >> the DragonFly system. If you hook the em0 interface that's currently > >> >> internal on the DragonFly machine up to your Internet link (i.e. > >> >> reverse which interface is internal or external), does it still > >> >> perform badly? > >> >> > >> >> If it doesn't work well, then that interface is bad. I'd be > >> >> surprised, cause I've seen network ports go bad very rarely, but it's > >> >> possible. Plus, I don't have any other ideas. > >> > > >> > > > > > >
Re: extreme network latency
Yes, that was it. Many thanks! Should I just use polling, which works fine, or is there something one can do about the interrupt issue? -Richard On 17 October 2016 at 22:05, Matthew Dillon wrote: > That kinda sounds like an interrupt issue, in which case I suggest turning > polling on for both interfaces. ifconfig polling ought to do it. If > that fixes the problem, then it is definitely interrupt-related. > > -Matt > > On Mon, Oct 17, 2016 at 12:52 PM, Richard Nyberg > wrote: >> >> Thanks again for your suggestions. >> >> Actually it's much stranger than I thought. While troubleshooting I >> had this configuration: >> >> df (em0) -> switch <- desktop >> >> No other devices or network interfaces were connected. In this >> configuration there was no problem at all with latency. I then plugged >> in the cable with internet acces like below: >> >> internet <- (re0) df (em0) -> switch <- desktop >> >> In this configuration the latency problems immediately showed. The fun >> thing is that when I unplugged the re0 interface again the em0 >> interface stopped responding at all, until I put the cable back to >> re0. Then em0 was back but with latency problems. >> >> Another data point is that while I downloaded a large file at speed >> from the internet via df to my desktop in the above configuration and >> pinged from the desktop to df at the same time, the latency problems >> were gone. Until the download was finished and they started again. >> >> -Richard >> >> On 16 October 2016 at 19:14, Matthew Dillon wrote: >> > Look for a packet loop on the interface. Use tcpdump on the interface >> > to >> > see if there are excess packets being generated from somewhere. There >> > are >> > numerous things that can blow up a LAN. The most common being that a >> > switch >> > port is wired to loop back into the LAN. >> > >> > -Matt >> > >> > On Sun, Oct 16, 2016 at 9:17 AM, Justin Sherrill >> > >> > wrote: >> >> >> >> On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg >> >> >> >> wrote: >> >> > Thanks! >> >> > >> >> > Here are some more datapoints. >> >> >> >> I think the only constant at this point is the internal interface on >> >> the DragonFly system. If you hook the em0 interface that's currently >> >> internal on the DragonFly machine up to your Internet link (i.e. >> >> reverse which interface is internal or external), does it still >> >> perform badly? >> >> >> >> If it doesn't work well, then that interface is bad. I'd be >> >> surprised, cause I've seen network ports go bad very rarely, but it's >> >> possible. Plus, I don't have any other ideas. >> > >> > > >
Re: extreme network latency
That kinda sounds like an interrupt issue, in which case I suggest turning polling on for both interfaces. ifconfig polling ought to do it. If that fixes the problem, then it is definitely interrupt-related. -Matt On Mon, Oct 17, 2016 at 12:52 PM, Richard Nyberg wrote: > Thanks again for your suggestions. > > Actually it's much stranger than I thought. While troubleshooting I > had this configuration: > > df (em0) -> switch <- desktop > > No other devices or network interfaces were connected. In this > configuration there was no problem at all with latency. I then plugged > in the cable with internet acces like below: > > internet <- (re0) df (em0) -> switch <- desktop > > In this configuration the latency problems immediately showed. The fun > thing is that when I unplugged the re0 interface again the em0 > interface stopped responding at all, until I put the cable back to > re0. Then em0 was back but with latency problems. > > Another data point is that while I downloaded a large file at speed > from the internet via df to my desktop in the above configuration and > pinged from the desktop to df at the same time, the latency problems > were gone. Until the download was finished and they started again. > > -Richard > > On 16 October 2016 at 19:14, Matthew Dillon wrote: > > Look for a packet loop on the interface. Use tcpdump on the interface to > > see if there are excess packets being generated from somewhere. There > are > > numerous things that can blow up a LAN. The most common being that a > switch > > port is wired to loop back into the LAN. > > > > -Matt > > > > On Sun, Oct 16, 2016 at 9:17 AM, Justin Sherrill < > jus...@shiningsilence.com> > > wrote: > >> > >> On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg > > >> wrote: > >> > Thanks! > >> > > >> > Here are some more datapoints. > >> > >> I think the only constant at this point is the internal interface on > >> the DragonFly system. If you hook the em0 interface that's currently > >> internal on the DragonFly machine up to your Internet link (i.e. > >> reverse which interface is internal or external), does it still > >> perform badly? > >> > >> If it doesn't work well, then that interface is bad. I'd be > >> surprised, cause I've seen network ports go bad very rarely, but it's > >> possible. Plus, I don't have any other ideas. > > > > >
Re: extreme network latency
Thanks again for your suggestions. Actually it's much stranger than I thought. While troubleshooting I had this configuration: df (em0) -> switch <- desktop No other devices or network interfaces were connected. In this configuration there was no problem at all with latency. I then plugged in the cable with internet acces like below: internet <- (re0) df (em0) -> switch <- desktop In this configuration the latency problems immediately showed. The fun thing is that when I unplugged the re0 interface again the em0 interface stopped responding at all, until I put the cable back to re0. Then em0 was back but with latency problems. Another data point is that while I downloaded a large file at speed from the internet via df to my desktop in the above configuration and pinged from the desktop to df at the same time, the latency problems were gone. Until the download was finished and they started again. -Richard On 16 October 2016 at 19:14, Matthew Dillon wrote: > Look for a packet loop on the interface. Use tcpdump on the interface to > see if there are excess packets being generated from somewhere. There are > numerous things that can blow up a LAN. The most common being that a switch > port is wired to loop back into the LAN. > > -Matt > > On Sun, Oct 16, 2016 at 9:17 AM, Justin Sherrill > wrote: >> >> On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg >> wrote: >> > Thanks! >> > >> > Here are some more datapoints. >> >> I think the only constant at this point is the internal interface on >> the DragonFly system. If you hook the em0 interface that's currently >> internal on the DragonFly machine up to your Internet link (i.e. >> reverse which interface is internal or external), does it still >> perform badly? >> >> If it doesn't work well, then that interface is bad. I'd be >> surprised, cause I've seen network ports go bad very rarely, but it's >> possible. Plus, I don't have any other ideas. > >
Re: extreme network latency
Look for a packet loop on the interface. Use tcpdump on the interface to see if there are excess packets being generated from somewhere. There are numerous things that can blow up a LAN. The most common being that a switch port is wired to loop back into the LAN. -Matt On Sun, Oct 16, 2016 at 9:17 AM, Justin Sherrill wrote: > On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg > wrote: > > Thanks! > > > > Here are some more datapoints. > > I think the only constant at this point is the internal interface on > the DragonFly system. If you hook the em0 interface that's currently > internal on the DragonFly machine up to your Internet link (i.e. > reverse which interface is internal or external), does it still > perform badly? > > If it doesn't work well, then that interface is bad. I'd be > surprised, cause I've seen network ports go bad very rarely, but it's > possible. Plus, I don't have any other ideas. >
Re: extreme network latency
On Sun, Oct 16, 2016 at 11:49 AM, Richard Nyberg wrote: > Thanks! > > Here are some more datapoints. I think the only constant at this point is the internal interface on the DragonFly system. If you hook the em0 interface that's currently internal on the DragonFly machine up to your Internet link (i.e. reverse which interface is internal or external), does it still perform badly? If it doesn't work well, then that interface is bad. I'd be surprised, cause I've seen network ports go bad very rarely, but it's possible. Plus, I don't have any other ideas.
Re: extreme network latency
Thanks! Here are some more datapoints. Yeah the switch for the lan is a simple Netgear GS105. My previous df gateway was connected in the same way, also with an internal em0, Turning pf off does not help. Switching cable and port between df and the switch does not help. Pinging www.google.com on the external interface from df gives consistant < 2 ms so it's on the internal interface the problem is. Pinging from a device on wifi (access point connected to the same switch) to df also gives very high latency. Pinging from the same wifi device to my desktop gives good latency. Pinging from df to my desktop gives bad latency. On 16 October 2016 at 17:24, Justin Sherrill wrote: > This is a problem that's going to require more data. > > - If you turn pf off, does the problem go away? > - If you ping from the DragonFly machine to your desktop, do you get > the same results? > - If you ping for an extended period (ping -t), do you get more timeouts? > - Are you directly connected to the DragonFly machine? I assume it's > all going through a network switch. > - Can you swap out network cables? > - If you are using some sort of home switch, are any NAT capabilities > turned off? > > If turning pf off does not affect it, it's not pf. > If pinging DragonFly -> desktop does not do it, it's the desktop > If you get more timeouts, or if it goes away on a direct link, I'm > thinking it's something with the physical connection. > > On Sun, Oct 16, 2016 at 4:53 AM, Richard Nyberg wrote: >> Hi users! >> >> I've just changed hardware for my gateway. It's now built on the asus >> z170i pro gaming motherboard and runs df 4.6. Unfortunately it suffers >> extreme latency on my lan and I don't know how to troubleshoot this. >> Between other devices on the lan there's no problem. The gateway isn't >> loaded in the least since I haven't installed any other services other >> dhcp yet. >> >> ### Gateway lan interface config: >> >> shoebox# ifconfig em0 >> em0: flags=8843 mtu 1500 >> options=1b >> inet 10.5.2.1 netmask 0xff00 broadcast 10.5.2.255 >> inet6 fe80::2e56:dcff:fe96:5961%em0 prefixlen 64 scopeid 0x2 >> ether 2c:56:dc:96:59:61 >> media: Ethernet autoselect (1000baseT >> ) >> status: active >> >> # ## /etc/pf.conf >> >> ext_if="re0" >> int_if="em0" >> >> scrub in >> >> nat on $ext_if from !($ext_if) -> ($ext_if:0) >> >> block in >> pass out keep state >> >> pass quick on { lo0 $int_if } >> antispoof quick for { lo0 $int_if } >> >> pass on $ext_if proto { icmp } >> >> ### Pinging from my desktop: >> >> C:>ping 10.5.2.1 >> >> Pinging 10.5.2.1 with 32 bytes of data: >> Request timed out. >> Reply from 10.5.2.1: bytes=32 time=66ms TTL=64 >> Reply from 10.5.2.1: bytes=32 time=559ms TTL=64 >> Reply from 10.5.2.1: bytes=32 time=1647ms TTL=64 >> >> Ping statistics for 10.5.2.1: >> Packets: Sent = 4, Received = 3, Lost = 1 (25% loss), >> Approximate round trip times in milli-seconds: >> Minimum = 66ms, Maximum = 1647ms, Average = 757ms >> >> ### >> >> Any ideas? >> >> Best regards, >> -Richard
Re: extreme network latency
This is a problem that's going to require more data. - If you turn pf off, does the problem go away? - If you ping from the DragonFly machine to your desktop, do you get the same results? - If you ping for an extended period (ping -t), do you get more timeouts? - Are you directly connected to the DragonFly machine? I assume it's all going through a network switch. - Can you swap out network cables? - If you are using some sort of home switch, are any NAT capabilities turned off? If turning pf off does not affect it, it's not pf. If pinging DragonFly -> desktop does not do it, it's the desktop If you get more timeouts, or if it goes away on a direct link, I'm thinking it's something with the physical connection. On Sun, Oct 16, 2016 at 4:53 AM, Richard Nyberg wrote: > Hi users! > > I've just changed hardware for my gateway. It's now built on the asus > z170i pro gaming motherboard and runs df 4.6. Unfortunately it suffers > extreme latency on my lan and I don't know how to troubleshoot this. > Between other devices on the lan there's no problem. The gateway isn't > loaded in the least since I haven't installed any other services other > dhcp yet. > > ### Gateway lan interface config: > > shoebox# ifconfig em0 > em0: flags=8843 mtu 1500 > options=1b > inet 10.5.2.1 netmask 0xff00 broadcast 10.5.2.255 > inet6 fe80::2e56:dcff:fe96:5961%em0 prefixlen 64 scopeid 0x2 > ether 2c:56:dc:96:59:61 > media: Ethernet autoselect (1000baseT ) > status: active > > # ## /etc/pf.conf > > ext_if="re0" > int_if="em0" > > scrub in > > nat on $ext_if from !($ext_if) -> ($ext_if:0) > > block in > pass out keep state > > pass quick on { lo0 $int_if } > antispoof quick for { lo0 $int_if } > > pass on $ext_if proto { icmp } > > ### Pinging from my desktop: > > C:>ping 10.5.2.1 > > Pinging 10.5.2.1 with 32 bytes of data: > Request timed out. > Reply from 10.5.2.1: bytes=32 time=66ms TTL=64 > Reply from 10.5.2.1: bytes=32 time=559ms TTL=64 > Reply from 10.5.2.1: bytes=32 time=1647ms TTL=64 > > Ping statistics for 10.5.2.1: > Packets: Sent = 4, Received = 3, Lost = 1 (25% loss), > Approximate round trip times in milli-seconds: > Minimum = 66ms, Maximum = 1647ms, Average = 757ms > > ### > > Any ideas? > > Best regards, > -Richard
extreme network latency
Hi users! I've just changed hardware for my gateway. It's now built on the asus z170i pro gaming motherboard and runs df 4.6. Unfortunately it suffers extreme latency on my lan and I don't know how to troubleshoot this. Between other devices on the lan there's no problem. The gateway isn't loaded in the least since I haven't installed any other services other dhcp yet. ### Gateway lan interface config: shoebox# ifconfig em0 em0: flags=8843 mtu 1500 options=1b inet 10.5.2.1 netmask 0xff00 broadcast 10.5.2.255 inet6 fe80::2e56:dcff:fe96:5961%em0 prefixlen 64 scopeid 0x2 ether 2c:56:dc:96:59:61 media: Ethernet autoselect (1000baseT ) status: active # ## /etc/pf.conf ext_if="re0" int_if="em0" scrub in nat on $ext_if from !($ext_if) -> ($ext_if:0) block in pass out keep state pass quick on { lo0 $int_if } antispoof quick for { lo0 $int_if } pass on $ext_if proto { icmp } ### Pinging from my desktop: C:>ping 10.5.2.1 Pinging 10.5.2.1 with 32 bytes of data: Request timed out. Reply from 10.5.2.1: bytes=32 time=66ms TTL=64 Reply from 10.5.2.1: bytes=32 time=559ms TTL=64 Reply from 10.5.2.1: bytes=32 time=1647ms TTL=64 Ping statistics for 10.5.2.1: Packets: Sent = 4, Received = 3, Lost = 1 (25% loss), Approximate round trip times in milli-seconds: Minimum = 66ms, Maximum = 1647ms, Average = 757ms ### Any ideas? Best regards, -Richard