Re: Gateway server experiencing degraded performance
On Sun, May 15, 2022 at 7:52 AM Andrew K Adams wrote: > > Hi, I’ve noticed a problem with my NetBSD server that I really could > use some help with. The server is acting as my home router (gateway) > in ‘pass-through’ mode with Comcast Xfinity as the service provider. > The only functions/services enabled on the server are: ip-forwarding, > dhcp-client, and NTP. And on the internal-facing lan: NAT, DHCP, and > SSH. The internal network supports 5+ wired hosts & 10+ wireless > devices. I currently have the 1Gig option with Comcast and when > things are operating as expected, I see from an internal (wired) host > 750mbs of throughput according to Comcast’s Xfinity speed test > website. The problem is that performance doesn’t last. In anywhere > from 3 weeks to 24 hours, my network performance (again, using the > same wired host measured by Xfinity’s speed test) will drop to ~20mbs. > And the change is clearly observable in all networking applications, > e.g., Netflix. I’m querying here, though, because the fix I’ve found > is to reboot the server. Upon reboot, I immediately go back to > 750mbs. Hence, I’d like to figure out how to troubleshoot what on my > server is (eventually) degrading my network performance. > > The server is relatively new; I built it using an ASUS Mini ITX with > two onboard GigE ethernet ports. Here’s some relevant dmesg output: > > [ 1.00] NetBSD 9.1 (GENERIC) #0: Sun Oct 18 19:24:30 UTC 2020 > [ 1.00] > mkre...@mkrepro.netbsd.org:/usr/src/sys/arch/i386/compile/GENERIC > [ 1.00] total memory = 3457 MB > [ 1.00] avail memory = 3380 MB > > [ 1.025286] wm0 at pci0 dev 25 function 0: I217 LM Ethernet > Connection (rev. 0x05) > [ 1.025286] wm0: interrupting at msi2 vec 0 > [ 1.025286] wm0: PCI-Express bus > [ 1.025286] wm0: 2048 words FLASH, version 0.13.4 > [ 1.025286] wm0: 0x6a4480 > > [ 1.025286] re0 at pci3 dev 0 function 0: RealTek 8168/8111 PCIe > Gigabit Ethernet (rev. 0x0c) > [ 1.025286] re0: interrupting at msix4 vec 0 > [ 1.025286] re0: using 256 tx descriptors > > > And from ifconfig (note, I’ve removed my IP & MAC address from the output): > > iquitos# ifconfig -a > wm0: flags=0x8843 mtu 1500 > capabilities=7ff80 > capabilities=7ff80 > capabilities=7ff80 > enabled=0 > ec_capabilities=17 > ec_enabled=2 > media: Ethernet autoselect (1000baseT > full-duplex,flowcontrol,rxpause,txpause) > status: active > inet X.X.X.X/20 broadcast 255.255.255.255 flags 0x0 > Inet6 X%wm0/64 flags 0x0 scopeid 0x1 > re0: flags=0x8843 mtu 1500 > capabilities=3f80 > capabilities=3f80 > enabled=0 > ec_capabilities=3 > ec_enabled=0 > media: Ethernet autoselect (1000baseT full-duplex) > status: active > inet 10.19.34.1/24 broadcast 10.19.34.255 flags 0x0 > inet6 fe80::728b:cdff:febc:831b%re0/64 flags 0x0 scopeid 0x2 > lo0: flags=0x8049 mtu 33176 > inet 127.0.0.1/8 flags 0x0 > inet6 ::1/128 flags 0x20 > inet6 fe80::1%lo0/64 flags 0x0 scopeid 0x3 > > > I’m not sure what other information would be useful, just let me know, > and thank you in advance for help you can give me! Just a question, not a requirement, but have you looked at Wireshark traces comparing good performance vs. bad performance? It's just another way to find possibly find a problem. I'm sure someone else will have better ideas. Andy
Gateway server experiencing degraded performance
Hi, I’ve noticed a problem with my NetBSD server that I really could use some help with. The server is acting as my home router (gateway) in ‘pass-through’ mode with Comcast Xfinity as the service provider. The only functions/services enabled on the server are: ip-forwarding, dhcp-client, and NTP. And on the internal-facing lan: NAT, DHCP, and SSH. The internal network supports 5+ wired hosts & 10+ wireless devices. I currently have the 1Gig option with Comcast and when things are operating as expected, I see from an internal (wired) host 750mbs of throughput according to Comcast’s Xfinity speed test website. The problem is that performance doesn’t last. In anywhere from 3 weeks to 24 hours, my network performance (again, using the same wired host measured by Xfinity’s speed test) will drop to ~20mbs. And the change is clearly observable in all networking applications, e.g., Netflix. I’m querying here, though, because the fix I’ve found is to reboot the server. Upon reboot, I immediately go back to 750mbs. Hence, I’d like to figure out how to troubleshoot what on my server is (eventually) degrading my network performance. The server is relatively new; I built it using an ASUS Mini ITX with two onboard GigE ethernet ports. Here’s some relevant dmesg output: [ 1.00] NetBSD 9.1 (GENERIC) #0: Sun Oct 18 19:24:30 UTC 2020 [ 1.00] mkre...@mkrepro.netbsd.org:/usr/src/sys/arch/i386/compile/GENERIC [ 1.00] total memory = 3457 MB [ 1.00] avail memory = 3380 MB [ 1.025286] wm0 at pci0 dev 25 function 0: I217 LM Ethernet Connection (rev. 0x05) [ 1.025286] wm0: interrupting at msi2 vec 0 [ 1.025286] wm0: PCI-Express bus [ 1.025286] wm0: 2048 words FLASH, version 0.13.4 [ 1.025286] wm0: 0x6a4480 [ 1.025286] re0 at pci3 dev 0 function 0: RealTek 8168/8111 PCIe Gigabit Ethernet (rev. 0x0c) [ 1.025286] re0: interrupting at msix4 vec 0 [ 1.025286] re0: using 256 tx descriptors And from ifconfig (note, I’ve removed my IP & MAC address from the output): iquitos# ifconfig -a wm0: flags=0x8843 mtu 1500 capabilities=7ff80 capabilities=7ff80 capabilities=7ff80 enabled=0 ec_capabilities=17 ec_enabled=2 media: Ethernet autoselect (1000baseT full-duplex,flowcontrol,rxpause,txpause) status: active inet X.X.X.X/20 broadcast 255.255.255.255 flags 0x0 Inet6 X%wm0/64 flags 0x0 scopeid 0x1 re0: flags=0x8843 mtu 1500 capabilities=3f80 capabilities=3f80 enabled=0 ec_capabilities=3 ec_enabled=0 media: Ethernet autoselect (1000baseT full-duplex) status: active inet 10.19.34.1/24 broadcast 10.19.34.255 flags 0x0 inet6 fe80::728b:cdff:febc:831b%re0/64 flags 0x0 scopeid 0x2 lo0: flags=0x8049 mtu 33176 inet 127.0.0.1/8 flags 0x0 inet6 ::1/128 flags 0x20 inet6 fe80::1%lo0/64 flags 0x0 scopeid 0x3 I’m not sure what other information would be useful, just let me know, and thank you in advance for help you can give me! Andrew -- Andrew K. Adams, MCS, MIS CISO, NSF Cybersecurity Center of Excellence / trustedci.org PISO, Security Manager, Pittsburgh Supercomputing Center / psc.edu Carnegie Mellon University akad...@psc.edu / +1 412-268-5142