[03:41] perhaps an attempt to use it in an amplification attack [03:41] without realizing it won't participate [03:41] I can send 4GB of packets to any host and there isn't much it can do about it :P [04:20] 4gb isn't really that much these days [04:21] there are so many gigabit connected hackable hosts i suppose [04:29] I was amazed to discover 100 GbE interconnects when I was looking at Google's peering page. That definitely wasn't a thing when I worked at Cisco. I think 10GbE had just come out. [04:29] the 40 to 100 gbe shift was pretty quick [04:30] it's "reasonably affordable" to get 40 to 100 gigabit interconnects now [04:30] it's base 10 gigabit stuff that's struggling to come down [04:30] Yeah. [04:30] like if you want a 16 port 10 gigabit switch for a small company you can't really get anything cheap [04:30] Run fiber to every desk. 😂 [04:30] even 100 gigabit ethernet cards for pc are "reasonably affordable" [04:30] like $400 USD or something [04:31] Huh. [04:31] they're pci-e x16 [04:31] mellanox make one with pcie 4 [04:31] but hardly anything supports pcie 4 yet [04:31] apparently some amd boards may [04:32] https://www.ebay.com/itm/Arista-DCS-7280SE-72-F-48-Port-10GbE-100GbE-7280E-Switch-1-Year-Warranty/273398255690?hash=item3fa7ce504a:g:ltQAAOSw1dJbbIPL [04:33] Dang. [04:33] https://www.ebay.com/itm/Mellanox-MCX456A-ECAT-CX456A-ConnectX-4-VPI-EDR-IB-100GbE-Dual-Port-QSFP28-PCIe/323751423135?hash=item4b6116ac9f:m:mimSiA5cDCfvjWmI5dPNSeQ [04:34] I was mislead by the model number, totally thought that was a Cisco. [04:34] heh [04:34] arista are gaining market share rapidly [04:34] Yeah it's a name I never heard of and now keeps coming up. [04:34] so are huawei though [04:34] oh wow [04:35] https://www.ebay.com/itm/Arista-DCS-7280CR-48-F-7280R2-48x-100GbE-QSFP-8x-40GbE-QSFP-Switch-Router/401736132191?hash=item5d8956e65f:g:5woAAOSwYqVcb43U [04:35] surely it means 48 10gbe [04:35] Wow. [04:35] nope the data sheet says the same [04:36] i think google are actually using 100gbe to their servers? [04:36] but they're running their own switches i think [04:36] well someone probably makes them for them [04:36] but they spec what they want [04:37] i kind of wish infiniband was more popular [04:38] hmm this web site says 25gigabit is going to take off [04:38] Yeah I was pumped about that. [04:38] HUh. [04:38] i haven't seen anything that does 25 gigabit yet [04:38] there's also rdma over converged ethernet [04:38] but i don't think that's really taking off either [04:40] hmm this site says 400gbe should become big this y ear [04:40] oh no hangon it says shipments will start in december this year [04:40] damn this arista switch has 16gb of ram [04:41] and 24gb of packet buffer memory [04:41] si i suppose the packet buffer memory isn't included in the 16gb [04:41] oh it is 60x100gbe [04:42] i wonder when people will habitually have more than gigabit internet to the desktop [06:48] *** r0ni has joined #arpnetworks [08:37] *** hive-mind has quit IRC (Ping timeout: 244 seconds) [08:45] *** hive-mind has joined #arpnetworks [08:56] *** ziyourenxiang has quit IRC (Ping timeout: 276 seconds) [12:53] I have a friend who's going to work at arista in a couple months [12:53] apparently they're really pushing the cutting edge right now [12:57] nice [17:04] *** ziyourenxiang has joined #arpnetworks [18:36] *** nathani has quit IRC (Quit: WeeChat 1.4) [19:06] @seen nathani [19:06] mnathani, I last saw nathani 30 min 13 sec ago quitting: Quit: WeeChat 1.4. [21:43] Huh... zeit tripped the "'eth0' total download 4.8 GB matches limit [download rate > 3 GB in last 1 hour]" alert at about the same time as yesterday... [21:44] No discernible spike in traffic traffic, not that it alerted anyways. But enough to trip the alert. [21:45] (Normal hourly rx traffic is 150MB, so 3GB is quite the anomaly.) [21:46] Not seeing anything out of the ordinary right now though. Drat. [23:04] mercutio: Are y'all moving ARP Metal right now? I thought I had until next week (and I was mid-OpenBSD-upgrade!) [23:05] ...or apparently less time? Re-read the email, it says it was supposed to have been done last weekend. [23:13] uptime 5 minutes, yep... Seems like it. [23:14] Not cools, knocking me offline outside your prescribed maintenance window, guys! [23:19] what mtl host? [23:19] there's no reason that i know of that your server should have gone down [23:19] seeing connectivity problems here [23:20] on arp metal [23:20] ipv6? ipv4? [23:20] packet loss or unable to reach? [23:20] s/minutes/hours [23:20] uptime 5 hours, yep... Seems like it. [23:20] http://paste.debian.net/1079242/ [23:20] mercutio: stl21 [23:20] trace to 8.8.8.8 [23:20] lots of problems the past few weeks [23:21] I might need to move stuff to ec2 temporarily or something [23:21] hmm i can trace 8.8.8.8 fine [23:22] I cannot, from 174.136.111.132 [23:22] hmm i'm in taht same /24 where i'm testing from [23:23] I'm 95% sure this isn't a problem with my system [23:23] ho hmm [23:23] yeh i can trace from arp to there but not from home [23:23] checking [23:23] My stl21 machine is very unhappy about life - at a mininum its networking is funar. Not sure what yet, still working through logs to see what happened 5 hours ago, why it mysteriously shutdown [23:24] note that I *can* reach some internet destinations [23:24] (systemd didn't even start!) [23:24] hence how I can ssh into this in the first place [23:24] there was a second round of migrations earlier today but there were hardly any machines in that [23:24] but it's broken cloudfront and something else v important [23:24] it was around 8 hours ago though [23:24] and customers involved were emailed [23:25] i don't think your one was ni that list [23:25] afaict this seems to have started roughly 2 hours ago [23:25] yeah taht's odd [23:25] mercutio: turns out it was, but Garry's emails went to my wrong folder [23:25] oh [23:26] gotta run for a couple minutes but I'll be back [23:26] (still broken of course) [23:26] fuck fuck fuck [23:26] did monitoring not alert you? [23:26] mercutio: I'm not sure what's up with that monitoring [23:29] this is odd [23:29] i'm only seeing your other subnet with arp entries acf [23:29] is your other subnet working fine? [23:31] acf_: let me know if you see any difference now [23:35] mercutio: yeah, my 174.136.x.x subnet is routed via the other one [23:35] so it would make sense for there to be no arp entries for that [23:35] yeah i clicked after taht [23:35] oh ok looks like it might be back? [23:35] sweet [23:36] yeah afaict it's good now [23:36] it would have been affecting traffic from one router in but not the other [23:36] that's why some stuff worked and some didn't [23:36] and only that /27 [23:36] ahhh interesting [23:36] We don't have OSPF redistributing static routes [23:37] and we have very, very few customers with static routes [23:37] So we didn't see this at first [23:38] once we have all customers moved to the new switch, this issue will not appear again [23:38] we're almost done [23:39] This happened a couple hours ago because I started announcing our IP blocks out a 2nd BGP session, for redundancy, and traffic going into that router then didn't know how to get to your /27 [23:39] So I've just removed those announcements for now [23:40] ahh I see [23:40] yeah as soon as mercutio mentioned it only affected my /27 I thought it had something to do with the static route haha