[00:10] 1st one is done, took 57 minutes [00:13] http://pastebin.com/TrVyaw3L [00:14] http://pastebin.com/L5g7Qswt [00:15] http://pastebin.com/jwkqCXHB [00:15] seems my home server is by far the fastest [00:16] but the first one is xen [00:24] i think this test is mostly just cpu and system overheads [01:08] *** kevr has quit IRC (Quit: ZNC - http://znc.in) [01:10] *** kevr has joined #arpnetworks [01:30] *** kevr has quit IRC (Quit: ZNC - http://znc.in) [01:38] *** kevr has joined #arpnetworks [02:31] hmm i only had to enable cache for java to make ipmi java kvm thingy work [04:46] *** Erick- has joined #arpnetworks [04:46] *** Erick- has left [06:03] *** dj_goku has quit IRC (Remote host closed the connection) [08:16] *** mordacw has joined #arpnetworks [10:57] *** sga0 has joined #arpnetworks [11:12] Is garry in europe, or just a workaholic? He was setting my VPS up at 2am PST. ;) [11:12] heh [11:12] he just works late. [11:14] cool. [11:18] workaholic, yep [11:18] Actually mordacw, he's in Cali like you :P [11:34] at least you can honestly use PST now. [11:34] drives me nuts when people use that during the summer. [11:36] Ditto [11:37] If someone write PDT in June, I'm showing up an hour off [11:38] skype seems to do something like that with my timezone [11:38] on windows hah. but it seems to have it's own time zone idea and tell people it's a different time than it is for me. [11:39] although it says it's daylight saving when it's not. [11:41] brycec - why an hour off? [11:41] or was that a typo [11:41] PDT in June is correct [11:41] Oh right, right [11:41] hahahaha [11:41] my point remains... [11:42] in spite of my typo [11:42] i think daylight saving should just be done with . [11:42] yeah, and when I have to schedule international skype calls, it's really crazy [11:43] because of stuff like this: http://www.timeanddate.com/news/time/ [11:43] constant fiddling around with time zones. [11:43] international skype calls can be hard for me even without time zones changing [11:45] california is one of the easiest though, and it's even easier with daylight saving shifting difference to 21 hours. [11:45] europe on the other hand.. [11:47] hmm it seems a few areas are moving to daylight saving all the time [11:54] 21 hours for dst difference? [11:54] yeah, year-round dst doesn't make sense to me [11:54] why wouldn't you want the sun mostly overhead at noon. [11:55] well it was 19 hours a few months back [11:55] ahh.. so it's 19, 20, or 21 then [11:55] yeah [11:55] unless your dst shifts are alighned [11:56] but I think of it was 3 to 5 hours difference [11:56] nah not aligned. [11:56] i think of it 3 to 5 ahead, and a day behind. [11:56] so it'd be tuesday 11:56 am atm [11:57] but the weird thing i find, is with europe etc, it's kind of disconcerting talking to someone when it's your morning and their evening. [11:58] i don't see why you'd want the sun overhead at noon myself. [11:59] but it's often hotter here at 1 to 3 pm [11:59] After the return to PST, the sun is at "high noon" around 11am :/ [12:00] well - tradition [12:00] and when daylight saving starts people tend to get up in the dark [12:00] get on up [12:00] and DANCE [12:00] * BryceBot dances :D-< [12:00] * BryceBot dances :D|-< [12:00] * BryceBot dances :D/-< [12:00] for a gun fight RandalSchwartz ? [12:11] https://letsencrypt.org/ [12:14] * RandalSchwartz sets up letsdecrypt.org [12:20] heh [12:20] well it's interesting at the least. [12:20] % whois letsdecrypt.org [12:20] NOT FOUND [12:20] That's what she said!! [12:20] you should register it :) [12:22] my main arguement against encryption everywhere is caching, but if there was secure connection to proxy that then does secure connection to web sites i'd be happy with that [12:22] and if it shows rather than being captured mitm [13:58] *** mordacw has quit IRC (Quit: 403 attention redirect) [15:04] mordac: i'm a workaholic [15:05] and i tend to find that if i work late, more gets done (less distractions) [16:36] *** kevr has quit IRC (Quit: ZNC - http://znc.in) [16:37] *** kevr has joined #arpnetworks [17:28] less distraction... or perhaps fewer distraction*s* [17:32] *** dj_goku has joined #arpnetworks [17:34] are you grammar raping me RandalSchwartz ? [17:47] up_the_irons: any chance you can add openbsd 5.6 to the ISO list? [17:49] I think you mean "rapping". [17:55] does OpenVPN just have really sucky performance in general? [17:55] I'm having trouble getting > 200 mbit/sec with encryption disabled [17:55] on a 3.0GHz Pentium IV [17:55] it could do [17:56] you may get better performance with l2tp [17:56] but i'd avote for upgrading from a pentium 4 if at all possible [17:56] yea, probably going to have to [17:56] l2tp is kernel-based. [17:57] I looked at that a bit [17:57] I know I get super good performance with kernel-based GRE [17:57] it's pretty easy to setup on linux, freebsd, openbsd. [17:57] mordac: yeah i'll do it soon. can you give me a URL to curL? [17:57] up_the_irons: it's on your server :) [17:57] mercutio: where? :) [17:57] http://mirrors.arpnetworks.com/OpenBSD/5.6/amd64/install56.iso [17:57] danke [17:58] you may want to include the i386 version too [17:58] i dunno which mordac is running [17:58] i will [17:58] it's just s/amd64/i386/ [17:59] yep [18:00] up_the_irons: http://ftp5.usa.openbsd.org/pub/OpenBSD/5.6/amd64/install56.iso [18:00] up_the_irons: http://ftp5.usa.openbsd.org/pub/OpenBSD/5.6/i386/install56.iso [18:00] redwood city mirror :) [18:00] oh ftp5 is back? [18:01] mordac: arp has it's own mirror :) [18:01] 105 MB/sec hmm [18:02] they're up there now, i'm syncing them to each server now [18:04] ok, should be ready [18:04] ahh i assumed you would nfs them for some reason [18:04] nope [18:04] better to have local anyway :) [18:04] i don't want a network problem to cause VMs to hang [18:04] when local storage is cheap enough anyway [18:05] oh true i'd just think it'd be installing, but maybe some people leave them mounted. [18:05] yeah [18:05] KVM always tries to stat the ISO file when a VM boots [18:06] yeah nfs is nasty :) [18:06] That's what she said!! [18:09] up_the_irons: thank you [18:10] mordac: np [18:23] up_the_irons: i/o load may be high on this vps. copying files off the cd is stalling periodically. it's making progress. this is not an problem for me, personally. it'll get there. [18:23] s/vps/vps host/ [18:23] up_the_irons: i/o load may be high on this vps host. copying files off the cd is stalling periodically. it's making progress. this is not an problem for me, personally. it'll get there. [18:25] it's copying at like 11kB/s, if that's helpful. [18:28] i'm not sure which host you are referring to [18:29] Sorry if unclear: I mounted the obsd 5.6 CD into my VPS. I'm copying files. It's copying at 100kB/s. Since it's on-disk, that seems really slow. However, it's not at all a problem for me, but since you're the admin, it might be a point of data that is relevant to you. [18:31] i thank you for the information. what is your VNC host? (this will tell me on which host your vps runs) [18:31] so i can check out the load right now and see what's up... [18:31] kvr09 [18:31] cool [18:31] hmm... not too bad [18:32] 18:31:35 up 188 days, 18:03, 2 users, load average: 2.05, 2.14, 1.71 [18:32] that's pretty average... maybe IDE emulation is slow on KVM/QEMU.. dunno [18:32] I did this same thing off the 5.5 CD earlier today and it was moving at 1-3MB/s [18:33] * mordac shrugs [18:33] hmm. quite a bit faster [18:33] * up_the_irons shrugs too [18:34] ide emulation is slow on kvm [18:34] virtio made a huge diff [18:34] it's not 100kb/sec slow normally though [18:35] i wonder what WCHAN my host process is in [18:35] and if process is in d-state a lot [18:35] the upgrade is done, anyway. :) [18:35] oh you were doing an upgrade? [18:35] you can just use bsd.rd you know? :) [18:36] you just wget the new bsd.rd and do http install [18:37] yeah. i'm a creature of habit :) [18:37] 5.6 is a bit of a pita [18:37] you can't run 5.5 binarys. [19:16] but you can watch 2 and a half men. :) [19:28] mercutio: here is the full unix bench of that liquidweb dedi: http://pastebin.com/0bbM7Ys6 [19:29] i kind of decided unixbench was crap [19:29] That's what she said!! [19:29] well not representitive of real world performance [19:30] have an alternate I can run? [19:30] nope [19:30] i don't actually know any good ways to test performance [19:30] have you tried sysbench [19:31] even a kernel compile is a better test in some ways [19:31] but like that test shows virtualisation having way more of an impact than it does in real world [19:31] and it makes ssd performance seem no better than hard-disk performance [19:32] like my ssd raid system is getting slower file results :) [19:32] i suppose you'd want to test php and mysql and so on for a better test [19:34] benchmarking is quite a complex issue in some ways, .. and things like static file serving performance matter very little in the real world. [19:34] but dynamic can matter. [19:34] like for most web sites whether you can do 23000 or 26000 static pages/sec makes 0 dfif. [19:35] but dynamic page performance can maek a diff [19:36] and like for i/o it's not really burst perofmrance that matters, it's how slow it gets [19:38] that said, i have no idea why my ssd system benchs disks slower, it has faster cpu. [19:38] and all 3 systems i tested were mdadm raid 10 for / [19:40] i suppose a good test would be some kind of chroot package of php/mysql/nginx or something [19:42] even ssd vs hard-disk in real world mostly benefits write-heavy work loads. as usually reads can be cached in ram, as most people have datasets smaller than ram that are hot. [19:45] they have good benchmarks for desktop windows systems specifically gaming benchmarks [19:45] yeah mostly people focus in gaming / 3d benchmarks. [19:45] which don't tend to show ssds benefitting as much as they do too [19:46] my windows system is slow :( [19:46] chrome seems to be getting slower over time. [19:46] but chrome benchmarks high. it's probably my profile or something. [19:47] http://www.passmark.com/download/pt_download.htm try that one on Windows [19:47] actually chrome is slow on my linux box too, but that's a diff issue i think [19:47] i found a display fps thing, and it onyl ever seems to go up to 30 fps [19:48] i didn't see anything to disable vsync. [19:48] yeh i've tried passmark before too, it's kind of useless. [19:48] it's way too synthetic. [19:48] i mean it gives a basic idea. [19:49] linux chrome seems slowest at scrolling pages which i suppose isn't benchmarked. [19:57] *** dj_goku has quit IRC (Remote host closed the connection) [19:59] *** joepie91 has quit IRC (Ping timeout: 256 seconds) [20:01] *** joepie91 has joined #arpnetworks [20:17] *** kevr has quit IRC (Quit: ZNC - http://znc.in) [20:21] *** kevr has joined #arpnetworks [20:24] mercutio: do you do any hardware RAID on your systems? [20:24] nah mdadm+zfs [20:24] actually i use hardware raid on openbsd. [20:25] software raid is generally better than hardware raid these days [20:32] *** kevr has quit IRC (Quit: ZNC - http://znc.in) [20:33] *** kevr has joined #arpnetworks [20:34] also you can do fancy things like raid 10 on 3 hard-disks [20:35] and split raid10/raid5 [20:38] And soft-raid is a lot more portable between machines [20:38] (such as if the raid controller itself has failed... ) [20:39] (in which case you need to find another of the same controller or the existing raid volume will probably not be recognized) [20:43] i actually hate mdadm :) [20:44] the performance is good, but it can be a bit weird about failing drives. [20:45] but zfs is amazing [20:45] pity it can't be included in linux by default :( [20:50] hi nerds! [20:55] up_the_irons: do you care a lot about ip justification / is VPN or SSL/TLS proxying/termination acceptable justification for 5 IPs, one of my friends needs to basically proxy traffic from another host in LA to reach china telecom [20:55] via arp it's 180ms, direct it's about 300ms over cogent or he.net or something [21:00] *** dj_goku has joined #arpnetworks [21:00] *** dj_goku has quit IRC (Changing host) [21:00] *** dj_goku has joined #arpnetworks [21:22] eww cogent [21:22] can he.net reach cogent over ipv6 yet? (and vice versa) [21:42] I can, yes [21:42] Looks like a direct handoff too [21:42] oh wait, nevermind [21:43] I didn't let mtr finish its thing... [21:44] From ge2-6.core1.sea1.he.net to "???" [23:21] I wonder if cogent and he.net specify in their terms of service: IPv6 transit to all IPv6 hosts, except he.net/cogent respectively [23:22] how did the route go before? [23:27] *** dj_goku has quit IRC (Ping timeout: 250 seconds) [23:30] ^ lol [23:30] i really really hate dealing with asian traffic [23:30] i have a box somewhere else in LA [23:30] it's 300-600ms, ~20% packetloss to any china telecom ip [23:30] isn't packet loss the norm for china traffic? :) [23:30] and there are actually times like peak/offpeak where its completely unusable [23:30] not really on arp, 180-200ms <1% loss [23:31] it's actually tolerable [23:31] *** dj_goku has joined #arpnetworks [23:31] *** dj_goku has quit IRC (Changing host) [23:31] *** dj_goku has joined #arpnetworks [23:31] i think sometimes there is icmp loss when normal traffic gets through [23:31] i knew someone who was on fibre(?) in china and they got 10 megabitish [23:31] but if talking to them on skype and they browsed us web sites skype woudl break up [23:32] i have to detect chinese ips and use different templates for them [23:32] if you use google cdn for jquery or google web fonts or etc [23:32] your whole page is generally blocked [23:32] i think there's some weird magic or something [23:32] or the js is injected with malicious scripts [23:32] so it's doing deep page inspection? [23:32] it's always done [23:33] gfw is basically line-rate DPI by american hardware [23:33] south korea's censorship/gfw system is far shittier [23:33] it's american hardware? [23:33] can a huawei even do 10mbit dpi without catching fire? [23:33] *** dne_ is now known as dne [23:33] i heard huawei routers were good. [23:34] they're getting popular here. [23:34] i've only seen them in conjunction with ridiculous vulnerability reports or CVEs [23:34] juniper and huwaei are both pretty popular here. [23:35] at medium to high end [23:35] i have no idea about the vulnerabilities on them. [23:36] i think they're all bad? [23:47] hazardous: for 5 IPs, that is fine [23:48] if he wanted a /24, i'd say gtfo [23:53] *** pyvpx has quit IRC (Remote host closed the connection)