[01:03] *** Guest95570 has joined #arpnetworks [01:57] *** data has quit IRC (Quit: Leaving) [02:54] *** Guest95570 has quit IRC (Ping timeout: 264 seconds) [03:03] *** mnathani_ has quit IRC (Ping timeout: 250 seconds) [03:06] *** Guest95570 has joined #arpnetworks [03:12] *** mnathani_ has joined #arpnetworks [03:43] *** Guest95570 has quit IRC (Ping timeout: 256 seconds) [05:34] *** _iwc has joined #arpnetworks [05:39] <grody> it did spike at 93C [05:40] <grody> then dmesg was flooded with overheating, scaling down blah blah [05:40] <grody> then bham [05:40] <grody> seems to be holding itself together, thank goodness.. can't afford that loss just yet [06:02] <mercutio> weird [07:23] *** dj_goku has quit IRC (Read error: Connection reset by peer) [07:23] *** dj_goku_ has joined #arpnetworks [07:39] * grody must stop using bleeding edge code [07:39] <grody> last 3 builds of openwrt for my pocket router has been laden with an array of annoying bugs :( [07:56] *** brycec is now known as Big_Pimpin [07:57] *** Big_Pimpin is now known as brycec [11:28] *** neish_ has joined #arpnetworks [11:28] *** ameise has joined #arpnetworks [11:32] *** phlux has quit IRC (*.net *.split) [11:32] *** rendrag has quit IRC (*.net *.split) [11:32] *** ant has quit IRC (*.net *.split) [11:32] *** m0unds has quit IRC (*.net *.split) [11:32] *** NiTe has quit IRC (*.net *.split) [11:32] *** staticsafe has quit IRC (*.net *.split) [11:32] *** neish has quit IRC (*.net *.split) [11:32] *** daca has quit IRC (*.net *.split) [11:32] *** ameise is now known as ant [12:51] *** rendrag has joined #arpnetworks [12:54] *** phlux has joined #arpnetworks [12:54] *** m0unds has joined #arpnetworks [12:54] *** staticsafe has joined #arpnetworks [12:54] *** daca has joined #arpnetworks [13:03] *** NiTe has joined #arpnetworks [13:32] *** Guest95570 has joined #arpnetworks [14:31] <staticsafe> hrm v4 connectivity between my ARP Networks VM and my Nagios instance seems to be broken somewhere - http://paste.ee/p/1YMMA [14:35] <meingtsla> I'm hearing rumblings of Any2 connectivity issues since about 1:45pm PDT [14:36] <kellytk> I've not heard of that provider. Transit? [14:36] <meingtsla> No, peering exchange [14:37] <kellytk> That makes more sense [15:25] <mercutio> static: that looks like a networklayer issue [15:25] <mercutio> a forward problem from cs01.lax01.networklayer.com [15:29] <mercutio> unless linode hvae done something silly like have rpf issue as it's showing router-1-dal.linode.com and router-2-dal.linode.com [15:29] <mercutio> meingtsla: where did you hear that? [15:30] <mercutio> http://lg.arpnetworks.com/cgi-bin/bgplg?cmd=show+ip+bgp&req=45.33.23.57 [15:31] <mercutio> so softlayer are linode? [15:41] <staticsafe> Linode is using Softlayer's network [15:48] <mercutio> i'd ticket linode given those two traces. [15:48] <mercutio> last i knew linode don't have looking glass. [15:49] <mercutio> looks like softlayer do though [15:51] <mercutio> erk their dallas node can reach both arp in general and your vm it seems [15:51] <brycec> I don't suppose http://apps.fs.usda.gov/ArcX/rest/info?f=json loads for any one else? (vs immediate connection reset or timeout) [15:51] <mercutio> but they don't give linkable urls with their lg. (http://lg.softlayer.cmo) [15:52] <mercutio> yeh not loading for me either [15:52] <brycec> thx [15:52] <mercutio> it actually just hangs [15:52] <mercutio> rather than connection reset [15:52] <brycec> I've been getting both [15:53] <mercutio> ahh [15:53] <mercutio> maybe their load balancer is misbehaving while web servers are unreachable [15:53] <mercutio> ie it's overloading because of so many connections trying to work [15:57] <mercutio> static: lax01 can't reach arp, lax02 can. i have no idea of what ip lax01 is on and reverse dns lookup from your traceroute doesn't have forward lookup [15:57] <mercutio> bbr01 vs bbr02, not lax01 vs lax02 [15:59] <staticsafe> hm [16:00] <mercutio> found it, the ip is 206.72.210.131 [16:01] <mercutio> which is the any2ix ip address, which isn't advertised so isn't necessarily an issue [16:02] <mercutio> (because it's just used for connecting locally to other hosts, and forwarding traffic normally; they don't have an ip address just for traceroute, so it's using the facing address) [16:15] <meingtsla> mercutio: Email from CoreSite [16:15] <mercutio> meingtsla: ahh [16:16] <mercutio> i don't know who you are :) [16:16] <mercutio> but most people don't seem to know what any2ix is [16:18] <brycec> (Now I'm getting connection resets, woo) [16:19] <mercutio> yeah i wouldn't worry about how it manifests [16:19] <mercutio> it's likely to be the same core issue [16:19] <brycec> It's inconvenient is what it is :p [16:19] <mercutio> welcome to life :) [16:20] <mercutio> $136 usd is cheap for 480gb ssd [16:20] <brycec> Yes [16:20] <brycec> Yes it is... [16:20] <brycec> What form factor? [16:20] <mercutio> i'm thinking about going to 3 way raid-z with 3 of them [16:21] <mercutio> 2.5" 7mm [16:21] <mercutio> http://www.amazon.com/gp/product/B00M8ABFX6?psc=1&redirect=true&ref_=ox_sc_act_title_1&smid=ATVPDKIKX0DER [16:21] <BryceBot> Amazon: "SanDisk Ultra II 480GB SATA III 2.5-Inch 7mm Height Solid State Drive (SSD) With Read Up To 550MB/s- SDSSDHII-480G-G25" [16:21] <mercutio> it's tlc, but i have two and they seem to go better than the samsungs [16:21] <mercutio> err better than the samsung 840 evos that were in there too [16:21] <mercutio> does over a gb/sec for two of them in raid 0 for part of the disk [16:22] <mercutio> and the reset is mixed with what were samsung 840 evos [16:22] <mercutio> err 250gb samsung evo's [16:22] <mercutio> it's just some non imortant stuff that's raid0'ed [16:22] <mercutio> but i've had to secure erase etc the samsung's [16:22] <mercutio> because performance of the whole set was going down.. [16:23] <mercutio> Timing buffered disk reads: 3240 MB in 3.00 seconds = 1079.71 MB/sec [16:23] <mercutio> that's two of them [16:23] <mercutio> people are always like up to 550, up to 540... but usualyl i find samsungs are more like 510mb/sec [16:24] <mercutio> Timing buffered disk reads: 1470 MB in 3.00 seconds = 489.50 MB/sec [16:24] <mercutio> like that's a samsug ssd [16:24] <mercutio> Timing buffered disk reads: 1550 MB in 3.00 seconds = 516.50 MB/sec [16:24] <mercutio> and that's another samsung ssd [16:24] <mercutio> the first samsung was secure erased to get speed back up [16:24] <mercutio> it was going like 50mb/sec or something [16:25] <mercutio> (840 evo, the second is 850 evo) [16:39] *** dne has quit IRC (Ping timeout: 252 seconds) [16:40] *** dne has joined #arpnetworks [17:03] <m0unds> im hesitant to buy another samsung ssd ever again. had two of two fail and get replaced under warranty. [17:04] <m0unds> one stopped showing up in bios/uefi anymore and the other wigged out randomly [17:05] <m0unds> the hotel im staying at in durango co has a free cocktail hour. time for booze. [17:47] <mnathani> @weather yyz [17:47] <BryceBot> Toronto-Pearson International, Ontario: Mostly Cloudy ☠75°F (24°C), Humidity: 73%, Wind: From the Variable at 2 MPH -- For more details including the forecast and almanac, see http://www.wunderground.com/cgi-bin/findweather/getForecast?query=43.67722321,-79.63055420 or re-request this with: @weather -v yyz [17:48] <mercutio> yeh sandisk actually don't seem too bad. [17:48] <mercutio> they have worse random performance than samsung, but it's not like you're going to notice it with normal work loads. [17:48] <mercutio> i'm a bit hesitant about these cheap ssd plus ssd's with no reviews though [18:45] <grody> i have two ocz ssds and they seem fine [18:45] <grody> one is nearly two years and going strong [18:50] <grody> i dont see anywhere near those speeds though, mainly 'cause i run them on SATA 2 [19:01] <acf_> hm. I've had three Samsung SSDs for a couple of years, and they're all still fine [19:01] <acf_> very light workload though [19:02] <acf_> and no power failures [19:09] <m0unds> mercutio: yeah, i replaced my samsung drives with sandisk extreme 2s or something [19:10] <m0unds> acf_: my pc is on a ups and stuff. i guess maybe it was just a shitty batch or something [19:10] <mercutio> weird, i've only had ocz hard failure. [19:10] <mercutio> and i've got a few ssd's [19:11] <mercutio> this sandisk 480gb for $135 or something seems pretty sharp. [19:11] <m0unds> i have an intel 240 in my macbook and a corsair in the pc w the matched ones [19:11] <mercutio> wonder what amazon prime is going to bring though [19:12] <m0unds> keep dropping keystrokes. im connected to my box via lte on my phone [19:13] <mercutio> that seems strange, are you using that weird udp thing [19:13] <mercutio> or the lag is just disconcerting? [19:14] <m0unds> i think its just my keyboard [19:14] <m0unds> fleksy screws up [19:14] <mercutio> my error rate has gone down a bit from shifting back to blue from red. [19:15] <mercutio> err that's cherry mx. [19:16] <m0unds> this is on my phone [19:16] <m0unds> so touchscreen kb [19:17] <m0unds> juicessh [19:17] <m0unds> is the ssh app im usinf [19:17] <m0unds> using [19:19] <mnathani_> is there a good way to remember which argument goes first when executing a "ln -s path1 path2" command ? I frequently enter it incorrectly [19:21] <mercutio> not that i know of :) [19:22] <mercutio> i've screwed that up before too [19:23] <mercutio> maybe think think of -s as source [19:24] <mercutio> although it's not [19:24] <mercutio> so that it's ln -s source destination [19:24] <mercutio> just trying to think of something rememberable [19:24] <mercutio> although it depends how you think of source/destination [19:26] <mercutio> ie, source you could consider to be the original file, or the symlink that points to the original file [19:26] <mercutio> i cosndier it the original file, but it wouldn't be wrong to see it the other way around. [20:09] <grody> when you see 'file already exists' you know it's the wrong way :) [20:09] <grody> i almost always do it the wrong way, especially during file managemtn in the cli [20:11] <grody> got into habbit of link "this right here" "into this location here" now [20:23] <mnathani_> mercutio: thanks [20:24] <mercutio> grody: it doesn't always do that. [20:26] <grody> not always, especially when batching [20:30] <mercutio> oh, what i've hit is when it's a directory [20:31] <mercutio> so if if you do "mkdir somedir; ln -s notdir somedir" then you'll end up with a symlink of notdir to notdir in the symdir directory. [20:34] <mjp_> just remember its the opposite of whatever you think it is [20:34] <mercutio> haha [20:34] <mjp_> ln -s <real_thing> <link_that_points_to_it> [20:36] <mercutio> i'm trying to think up words that begin with s to link to "real thing" [20:36] <mercutio> static is my best one so far. [20:36] <mercutio> so static file, and dynamic link to it [20:37] <mercutio> probably better than source/destination [20:39] <mercutio> actually just thinking of it as ln -s <destination> <source> works better for me [20:39] <mercutio> it's always the little things that are complicated :) [20:41] <mnathani_> how about ln -s <existing path> <path or file to be created and linked to existing from first argument> [20:41] <mnathani_> althought I might have them in the reverse order [21:10] <mercutio> not having whoisguard on domain attracts so much spam [21:10] <mnathani_> depends how popular the domain is I guess [21:10] <mercutio> notinthe.us [21:11] <mnathani_> saying the domain in here wouldnt really help as [FBI] would log it [21:11] <mercutio> haha idk it's already getting spam [21:11] <mercutio> it's targeted spam, so i don't know how much diff it'll make [21:11] <mercutio> there's probably some list of new domain names somewhere [21:11] <mnathani_> who is the registrar? [21:11] <mercutio> namecheap [21:11] <mnathani_> enom or enom reseller [21:12] <mnathani_> ahh [21:12] <mercutio> my whoisguard domains don't get spam [21:13] <mercutio> but .us can't get whoisguard on. also strictly speaking i'm not meant to have a .us domain unless i'm in the US [21:13] <mnathani_> says so right in the domain [21:13] <mnathani_> not in the us [21:13] <mnathani_> lol [21:13] <mercutio> heh [21:13] <mercutio> it's been fine so far [21:14] <mnathani_> what do you think of softlayer as a dedicated provider? [21:14] <mercutio> well static just had issues with softlayer [21:14] <mercutio> like 7 hours ago [21:15] <mercutio> but yeah i dunno what they're like... i think they're big in dallas? [21:15] <mercutio> why not just use arp for dedicated servers? [21:15] <mnathani_> his issue was more with linode [21:16] <mnathani_> a customer of softlayer I beleive [21:16] <mercutio> yeh could just be linode [21:16] <mercutio> you have a good point there [21:16] <mercutio> because the dallas softlayer looking glass worked. [21:16] <mnathani_> I would go with ARP, except my customer is looking for a Toronto dedicated server [21:16] <mercutio> ahh [21:16] <mercutio> toronto is another kettle of fish [21:17] <mercutio> i don't really know much about the area... [21:17] <mnathani_> and I like a provider that thas decent SLA, hardware replacement guarantees etc [21:17] <mercutio> but level of service could be quite different there (for better or for worse) [21:17] <acf_> I've been looking for Canada things recently [21:17] <mercutio> doesn't even ovh have that [21:17] <acf_> ovh has one location in Quebec [21:17] <mnathani_> amanah.com [21:18] <mnathani_> those guys seem decent. Voip.ms use them [21:18] <mercutio> they were top link [21:18] <mercutio> i was put off by it saying 100tb [21:18] <mercutio> peer1 came to mind as a sensible idea [21:18] <mercutio> without too much thought [21:18] <mnathani_> softlayer only offer 500 gig on their base dedicated [21:18] <acf_> most of the providers I've seen are peer1 resellers [21:18] <acf_> or ovh resellers [21:18] <mercutio> well peer1 are old [21:19] <mercutio> s/old/established/ [21:19] <BryceBot> <mercutio> well peer1 are established [21:19] <mercutio> yeh i wouldn't go with ovh [21:19] <acf_> what I was noticing [21:19] <acf_> tracerouting places [21:19] <acf_> most routes in Canada come back through US anyway [21:20] <acf_> Vancouver -> Vancouver goes back through Seattle a lot [21:20] <mercutio> i suspect peer1 are expensive direct. [21:20] <mnathani_> 100 TB per month is like 304 mbit sustained for the whole month [21:20] <acf_> even Quebec -> Vancouver sometimes goes back through Seattle [21:20] <BryceBot> That's what she said!! [21:20] <mercutio> mnathani_: yeh, it means "oversold" [21:20] <mercutio> acf: that kind of stuff really bugs me. [21:20] <mercutio> in the US it's pretty common to take strange paths to some states. [21:20] <mercutio> like kansas is pretty basd. [21:20] <mercutio> bad [21:21] <mercutio> texas is pretty good generally. [21:21] <acf_> I was also looking at Centurylink cloud [21:21] <acf_> because they have a PoP in Vancouver [21:21] <acf_> (Savvis) [21:21] <mercutio> california it's mostly just san jose or los angeles leading to some weirdness, but it's not terrible. [21:21] <mercutio> ie it stays in state at least. [21:21] <mercutio> aren't savvis like cogent? [21:21] <acf_> Savvis always finds some way to route you around the other side of the country [21:21] <acf_> ie, if you're tracing LAX -> LAX it will send you to NY [21:22] <mnathani_> Should I be looking at purchasing a dedicated and colocating somewhere? [21:22] <mercutio> hahaha [21:22] <mercutio> he.net used to be like that [21:22] <mercutio> mnathani_: yes. [21:22] <mercutio> well maybe [21:22] *** Guest95570 has quit IRC (Ping timeout: 240 seconds) [21:22] <mercutio> s/looking/considering/ [21:22] <BryceBot> <mnathani_> Should I be considering at purchasing a dedicated and colocating somewhere? [21:22] <acf_> I think HE had some of the best routing in Canada (from my traceroutes) [21:22] <mnathani_> I always get nervous when I am the one responsible to replace equipment [21:22] <acf_> Peer1 was OK too [21:22] <mnathani_> I guess remote hands to exist [21:22] <BryceBot> That's what she said!! [21:22] <mnathani_> BryceBot: no [21:22] <BryceBot> Oh, okay... I'm sorry. 'I guess remote hands to exist' [21:22] <mercutio> yeh he.net is terrible to asia, and used to have some weird stuff in the US, but i think it's not too bad in canada [21:23] <mercutio> it's around atlanta that it was most iffy iirc [21:23] <mercutio> and weird things like sj -> ny -> fl or something [21:23] <mercutio> mnathani_: just get 3 hosts [21:23] <mercutio> and host 2 [21:24] <mercutio> then you have redundancy and a spare host if run into issues [21:24] <mercutio> l5520 type hosts are cheap on ebay [21:24] <mercutio> and good enough for non cpu demanding things [21:25] <mercutio> http://www.ebay.com/itm/HP-PROLIANT-DL320-G6-SERVER-505768-B21-XEON-SIX-CORE-X5650-2-67GHz-DVD-MULTI-/331584098520?pt=LH_DefaultDomain_0&hash=item4d33f3d0d8 [21:25] <mercutio> what about something like that? [21:26] <mercutio> there are lots of options, and shipping varies a lot... [21:26] <mercutio> but if you don't need a lot of cpu the hp g6s all have ilo built in for remote serial / video [21:26] <mnathani_> bring your own ram [21:27] <mercutio> you need ddr3 ecc [21:27] <mercutio> which is about $100 US per 16gb i think [21:27] <mercutio> with single cpu you can run 6 or 9 slots depending if you care about maxing memory speed [21:27] <mercutio> with dual cpu 12 or 18 [21:28] <mercutio> but you only really want to go dual cpu if virtualising or knowing you're running really scalable stuff [21:28] <mnathani_> something like : http://www.ebay.com/itm/16GB-4X4GB-DDR3-MEMORY-RAM-PC3-10600-ECC-REG-DIMM-/350444499824?pt=LH_DefaultDomain_0&hash=item51981eb370 [21:28] <mercutio> i'd shift to a e3 or e5 if cpu demands were high [21:28] <mercutio> yeh except if you want to mix with existing ram you have to check if it's registered or unregistered [21:28] <mercutio> if replacing all ram then it goes in sets of 3 [21:28] <mercutio> so i'd do 3x8gb.. [21:28] <mercutio> ie it's triple channel [21:30] <mercutio> http://www.ebay.com/itm/48GB-6X8GB-Hynix-HMT31GR7CFR4A-H9-2Rx4-PC3L-10600R-DDR3-1333-1-35V-/181768655729?pt=LH_DefaultDomain_0&hash=item2a52419371 [21:30] <mercutio> you could go for something like that... [21:31] <mercutio> if you're not paying for power you may want to just go dual cpu, second hand it makes not much difference to price [21:31] <mercutio> then there's whether you want to go for 2.5" or 3.5" hard-drives [21:31] <mercutio> 2.5" is handy for ssd's [21:31] <mercutio> but then you want to put a different raid controller in [21:32] <mercutio> http://www.ebay.com/itm/HP-Proliant-DL360-G6-Server-2-Quad-Core-X5570-2-93GHz-48GB-1-146HDD-/271928680850?pt=LH_DefaultDomain_0&hash=item3f50366192 [21:32] <mercutio> that's already got 48gb of ram. [21:33] <mnathani_> those are way more perfomance than we need [21:33] <mercutio> and faster cpu for mhz, but quad instead of hex core. [21:33] <mnathani_> currently running on ; Intel(R) Xeon(R) CPU E31240 @ 3.30GHz [21:33] <mercutio> e3 is fast [21:33] <mercutio> the 5500/5600 are like half the speed of e3 [21:34] <mercutio> dual cpu on the high end is similar in performance [21:34] <mercutio> as long as threadable [21:34] <mnathani_> 90% idle through the day though [21:34] <mercutio> i don't think e3s are cheap to buy second hand or new though [21:34] <mercutio> yeh if you don't need cpu you don't need cpu [21:34] <mercutio> my personal dedicated server is an i3 with 8gb of ram [21:34] <mercutio> it never seems slwo [21:34] *** Guest95570 has joined #arpnetworks [21:35] <mnathani_> any virtualization? [21:35] <mercutio> it's dl180g7 i think [21:35] <mercutio> nope [21:35] <mercutio> err dl120 [21:35] <mercutio> http://www.ebay.com/itm/NEW-HP-Proliant-DL120G7-12Gb-250Gb-Xeon-3-1Ghz-1U-Rack-Mount-Server-/271929110697?pt=LH_DefaultDomain_0&hash=item3f503cf0a9 [21:35] <mercutio> like that but i3 [21:35] <mercutio> oh hmm that's an e3 for ok cost [21:36] <mercutio> main caveat is single psu [21:36] <mercutio> but they take 4x3.5" hard-disks [21:36] <mercutio> and i stuck a ssd in hiding behind the hard-drives for ssd cache [21:36] <mercutio> they don't do hw raid, but you get the normal intel sata ahci ports (no sas) [21:36] <mercutio> and although there are 4 bays, there are 6 ports. [21:37] <mercutio> also they don't take registered ram [21:37] <mercutio> so yeah just figure out requirements, and you can probably find something cheap [21:38] <mnathani_> whats decent in terms of price for 1U / 2U colocation? [21:39] <mercutio> completely depends on location [21:39] <mercutio> i'd ballpark $50 to $200 for 1u [21:39] <mnathani_> I would probably have to figure out commit rate and 95th percentile [21:39] <mercutio> yeah or just get gb [21:39] <mercutio> it's usually cheaper where electricity/real estate is cheaper [21:40] <mercutio> and more expensive when known brand is on it [21:40] <mercutio> i don't think toronto is a "cheap" city [21:40] <acf_> gb? [21:40] <mercutio> gigabytes. [21:40] <acf_> is 1U the 'cheapest' unit? [21:41] <mercutio> yeah [21:41] <mercutio> 1u is what i linked [21:41] <mercutio> racks are usually 46 to 56u tall [21:41] <mercutio> err it seems some are 42 [21:42] <mercutio> you may have power limit as well [21:43] <acf_> is colocation or renting a dedicated server usually cheaper? [21:43] <mercutio> colocation long term dedicated short term [21:43] <mercutio> but colocation is a bitch if you're not in the same city [21:43] <mercutio> or if you don't want to have to go there :) [21:44] <acf_> it's annoying you have to email for quotes for colo [21:44] <mercutio> tehre's also the thing of how many servers you want... if you want 1 or 2 servers then it's harder to have spares then if you want 7 or 8 servers. [21:44] <mnathani_> dedicated has the advantage that replacing parts is someone else's responsibility [21:44] <mercutio> arp is listing colo price on their web site [21:44] <mercutio> mnathani_: yeh [21:44] <mercutio> hah ok it says contact for quote [21:45] <mercutio> but yeah, it /was/ a lot cheaper than dedicated [21:45] <mnathani_> main page says $99 / month [21:45] <acf_> so do you usually ask the datacenter for a quote? [21:45] <mercutio> but now dedicated doesn't cost that much more through some peopl [21:45] <mercutio> you don't have to deal with othe rpeople going into the dc and access and so on [21:45] <acf_> and a transit provider? [21:45] <mercutio> well like somewhere like arp you get bundled transit [21:46] <mercutio> but some places are just data centres and you can choose your transit [21:46] <mercutio> but if you're getting 1u you don't want to buy separate transit [21:46] <mercutio> if you're getting a rack it makes sense though [21:46] <mnathani_> other datacenters you can get a crossconnect and buy transit directly from the providers [21:46] <mercutio> mnathani_: yeh but crossconnects can bel ike $200 [21:46] <mercutio> plus the bandwidth cost [21:46] <acf_> $200 per month? [21:47] <mercutio> yeh [21:47] <acf_> woah [21:47] <mnathani_> like he said you would only do it if you had a rack or specific needs [21:47] <mercutio> yeh but if you pay $1000/month for transit then $200/month for cross connect it doesn't seem so bad. [21:47] <mercutio> it can vary a lot [21:48] <mercutio> but like where arp's located the data centre is spread across multiple buildings. [21:48] <mercutio> and like getting your own fibre between buildings is way more expensive than that [21:48] <acf_> so how is transit typically billed? [21:49] <mnathani_> commit rate and 95th percentile [21:49] <acf_> so commit rate is the minimum rate you have to pay for, regardless of what you actually use? [21:49] <mnathani_> I heard if you want gigabit, you need minimum 100 meg commit [21:49] <mnathani_> right [21:49] <mercutio> acf: 95th or flat rate. [21:50] <mercutio> mnathani_: varies [21:50] <mercutio> i'm sure arp would do gigabit line with lower than 100 megabit commit [21:50] <mercutio> link [21:50] <acf_> what's a typical rate ($/mbit/s)? [21:51] <mercutio> acf: there isn't one [21:51] <mercutio> it varies [21:51] <mercutio> cogent and he.net can be as low as 50c/megabit [21:51] <mercutio> but that's on high commit levels [21:51] <mercutio> and in areas they have excess capacity [21:51] <mercutio> generally speaking if you want to get 4x10gigabit links you can get good pricing easily. [21:52] <mercutio> but if you want to get 100 megabit, don't even think about going direct. [21:52] <brycec> fwiw here's a cheap colo deal https://www.fdcservers.net/colocation.php [21:52] <brycec> (they are *cheap* and not known for being "great") [21:52] <mercutio> level3 i've heard numbers like $3/megabit, but don't know anythign current [21:53] <acf_> do people like HE sell colocation outside of the datacenters they own? [21:53] <brycec> You can't sell someone else's space [21:53] <mercutio> dunno [21:53] <mercutio> fremont he.net has a really bad rep [21:53] <mercutio> brycec: you can resell [21:53] <brycec> (Well, you can resell technically, but that means you're selling your "own" generally) [21:54] <mercutio> so he.net might provide bandwidth and rack space in a dc they don't own [21:54] <mercutio> i wouldn't go with he.net primary for anything important [21:54] <acf_> in Canada they're looking pretty good [21:54] <mercutio> a blend is still probably better [21:56] <mercutio> http://www.caneris.com/Hosting#colocation [21:56] <mercutio> $125/month for 1u colocation, [21:56] <mercutio> wtf [21:56] <mercutio> 10mbps port [21:57] <mnathani_> I have 10 meg upload at my residence [21:58] <mnathani_> 60 meg down [21:58] <mnathani_> thats a joke [21:58] <mercutio> yeah it looks old [21:58] <mercutio> i'm sure they'd do 100 megabit for the same cost :/ [21:58] <mercutio> i have no idea if they're good, it's just the first quote i found in toronto [21:58] <mnathani_> there is 100 megabit then there is 100 megabit you can actually use and burst to [21:58] <mercutio> i wouldn't worry about 100 megbit generally these days [21:59] <mercutio> i'd be more concerned with transit providers / peering etc. [21:59] <mercutio> oh amanah might be ok [21:59] <mercutio> it's not 100tb on all servers [21:59] <mercutio> but ouch $200 [22:00] <mercutio> @exch 200 cad to usd [22:00] <BryceBot> 200 CAD -> 157.03579238298 USD (as of Tue, 14 Jul 2015 21:01:01 -0700) [22:00] <mercutio> oh not so bad [22:00] <mercutio> they charge $100 for 1u with 30tb/100 megabit [22:00] <mercutio> 1 amp [22:01] <mercutio> what voltage is canada? [22:01] <mercutio> ahh 110 [22:01] <mnathani_> 110 v for res [22:01] <mercutio> yeh i didn't know if it was the same as US or not [22:01] <mercutio> so yeah 1 amp is not much power [22:02] <mercutio> it's at 1 yonge street [22:02] <mercutio> do you know where that is? [22:02] <BryceBot> That's what she said!! [22:02] <mnathani_> yea [22:02] <mnathani_> its downtown [22:02] <mercutio> convenient? [22:02] <mnathani_> parking can be expensive [22:02] <mnathani_> but yea [22:02] <mercutio> i wonder if they provide parking [22:03] <mercutio> well it's like $80 usd/month cheaper for colo [22:04] <mnathani_> https://www.amanah.com/Network/ [22:04] <mercutio> and you get 30tb instead of 10tb but you get 100megabit instead of gigabit [22:04] <mercutio> it's bell.ca from here [22:05] <mercutio> oh front street west is the main building i think [22:05] <mnathani_> Because we’re located so close to the American border, we’re able to offer both Canadian- and US- geolocated IP addresses [22:05] <mnathani_> that is also downtown [22:05] <mercutio> that's not /because/ of that. [22:05] <mnathani_> convenient to get to also [22:06] <mercutio> swewet [22:06] <mercutio> well maybe go with colo there? [22:06] <mercutio> they're not on he.net [22:06] <mercutio> it doesn't look like [22:06] <mercutio> but he.net peer anyway :/ [22:06] <mercutio> erk they're on cogent :/ [22:08] <mercutio> y'know i don't know if they give you a vpn for ipmi [22:08] <BryceBot> <mercutio> ert they're f cfge t :/ [22:08] <acf_> BryceBot: ? [22:08] <mercutio> i think it's the y'know [22:08] <mercutio> y'know [22:08] <mercutio> hmm [22:09] <mercutio> erk [22:09] <mercutio> ok i'm lost what is it :) [22:09] <mercutio> cogent [22:09] <acf_> y'know i don't know if they give you a vpn for ipmi [22:09] <BryceBot> <mercutio> cfge t [22:09] <acf_> y'know i don't know if they give you a vpn for ipmi [22:09] <BryceBot> <mercutio> cfge t [22:09] <acf_> umm [22:09] <mercutio> i think he's laggy too [22:09] <acf_> y'know i don't [22:09] <BryceBot> <mercutio> i thint he's laggy too [22:09] <acf_> y'know i don [22:09] <brycec> Because y// is a valid perl operator [22:10] <brycec> equivalent of tr// [22:10] <mercutio> oh it's y/ [22:10] <mercutio> y'test/ [22:10] <brycec> y/t/r/ [22:10] <BryceBot> <mercutio> y'resr/ [22:10] <brycec> (and ' is a valid delimiter in sed) [22:10] <brycec> (and BryceBot just mashes it all up together) [22:11] <mercutio> heh [22:11] <brycec> So above it was the two y'know i don't [22:11] <brycec> that was y'' [22:12] <acf_> mercutio: what specifically is so bad about HE? [22:12] <acf_> their routing has always seemed sane to me [22:12] <mercutio> acf_: they're a cheap non-premium provider with reduced redundancy [22:13] <acf_> ah ok [22:13] <mercutio> i don't think being with any single provider is good fwiw [22:13] <mercutio> it depends what expectations you have [22:13] <mercutio> like he.net links to EU were unusable when new york had that flooding. [22:14] <mercutio> whether that matters or not is the question [22:14] <mercutio> i mean it was big news about the flooding etc. it's not like it's all the time etc. [22:14] <acf_> yea.. for my purposes redundancy isn't all too important [22:14] <mercutio> their fremont data centre had a lot of stability issues too. [22:14] <mercutio> then he.net is probably fine [22:14] <acf_> it seems like HE buys a lot of transit from others [22:15] <mercutio> also he.net is more likely to hit issues with at&t, verizon etc. [22:15] <acf_> which makes them not as susceptible to the peering snafus [22:15] <mercutio> you reckon? [22:15] <mercutio> it's hard to know really [22:15] <acf_> I may be very wrong :P [22:15] <mercutio> ntt had some peering congestion [22:15] <acf_> with HE? [22:15] <mercutio> and they're meant to be tier1 [22:15] <mercutio> nah [22:15] <mercutio> with at&t i think it was [22:15] <mercutio> i can't recall for sure [22:15] <acf_> Verizon [22:16] <acf_> I was the one always complaining about that :P [22:16] <mercutio> oh [22:16] <mercutio> ok verizon :) [22:16] <mercutio> verizon and at&t seem the same to me :) [22:16] <mercutio> i know they're totally different [22:16] <mercutio> well different companies [22:16] <mercutio> similar attitudes :) [22:16] <acf_> Verizon is especially bad I think [22:17] <mercutio> so is at&t [22:17] <mercutio> cogent<->at&t congestion was shocking [22:17] <acf_> when two stubborn assholes peer.. [22:17] <acf_> Cogent still won't IPv6 peer with HE [22:17] <mercutio> why! [22:18] <acf_> you can't traceroute cogent.net from HE .. [22:18] <mercutio> what is bell.ca like? [22:18] <acf_> idk.. I live in the US for another month [22:18] <acf_> then I'll find out :P [22:18] <mercutio> heh [22:18] <mercutio> tcore4-toronto21_hundredgige1-3-0-0.net.bell.ca [22:19] <mercutio> i've never seen anyone else say in their reverse lookups that they're using 100ge [22:19] <mercutio> he.net say 40gbe in some stuff i think [22:20] <acf_> http://paste.unixcube.org/k/b513bb [22:20] <acf_> so it looks like HE buys transit from Verizon [22:20] <mnathani_> my route used to be he.net [22:20] <acf_> (or peers, but that seems very unlikely) [22:20] <mnathani_> but switched to level3 now [22:20] <mnathani_> from Toronto to ARP [22:20] <acf_> so I'd hope they'd just pay up if they needed to upgrade the link [22:25] <mercutio> mnathani_: better or worse? [22:28] <mercutio> i don't have any routing issues to arp normally