--- Day changed --- Log opened Tue Apr 18 23:59:03 2006 23:59 < TheFirst> i dont run irssi on my node 00:00 < taupehat> O RLY 00:00 < taupehat> =P 00:00 < taupehat> so you have ircproxy setup and you're using mirc at home =P 00:00 < TheFirst> i'd not touch mirc with a 1034789473289574289346238794 foot pole 00:00 < taupehat> yah sure 00:01 < taupehat> xchat is like the same =P 00:01 < TheFirst> wouldn't touch that either 00:01 < TheFirst> irssi....just chews up too much ram to run on the node 00:01 < taupehat> bitchx? 00:01 -!- TheFirst_ [~GaveUp@CPE-70-92-72-102.new.res.rr.com] has quit [Quit: You're a bloody puppet!] 00:03 -!- taupehat_ [~3fe0c9f4@webuser.linode.com] has quit [Quit: CGI:IRC (Ping timeout)] 00:04 < linbot> New news from forums: Reboot: host56 (2006-04-18) in Xen Public Beta 00:11 < TheFirst> taupehat: must be blind to think bitchx ;) 00:12 < taupehat> lol 00:12 < mikegrb> lolz 00:12 < taupehat> I'm out of ideas then 00:12 < taupehat> unless you're using freaking telent 00:12 < taupehat> telnet* 00:12 < TheFirst> [11:01.17PM] < TheFirst> irssi....just chews up too much ram to run on the node 00:13 < taupehat> so eh 00:13 < TheFirst> so eh what? 00:13 < taupehat> you think irssi is a ram pig, from one reading of that 00:13 < TheFirst> it's too much of a ram pig to run on my node 00:13 < taupehat> hah 00:13 < TheFirst> i have no qualms running it on my home box 00:13 < taupehat> it is no ram pig 00:13 < TheFirst> 3589 gaveup 12 0 11788 11m 4512 S 0.0 2.4 0:48.59 irssi 00:14 < TheFirst> it's a pig 00:14 < taupehat> ooh, 11 megs! 00:14 < TheFirst> oink, oink! 00:14 < taupehat> sigh 00:14 * taupehat ran irssi on his 64 00:15 < TheFirst> bleh running irssi means i'd have to stop running other things...and why do that when i can gowith this setup 00:24 < TheFirst> i assume nodes are still booting but at any rate.... Timing buffered disk reads: 20 MB in 3.34 seconds = 5.99 MB/sec 00:30 < caker> ok, I idled them -- try now? 00:34 -!- taupehat [me@taupehat.com] has quit [Ping timeout: 480 seconds] 00:35 < caker> huh .. taupehat's domain pancied 00:35 < caker> *panicked 00:41 < TheFirst> Timing buffered disk reads: 12 MB in 3.06 seconds = 3.92 MB/sec 01:10 -!- taupehat_ [~3fe0c9f4@webuser.linode.com] has joined #linode-xenbeta 01:10 < taupehat_> oof! 01:10 < taupehat_> oof! 01:15 < TheFirst> Timing buffered disk reads: 10 MB in 3.36 seconds = 2.97 MB/sec 01:15 < TheFirst> :( 01:55 < TheFirst> getting worse 01:55 < TheFirst> Timing buffered disk reads: 6 MB in 3.86 seconds = 1.55 MB/sec 02:34 -!- taupehat_ [~3fe0c9f4@webuser.linode.com] has quit [Quit: CGI:IRC (Ping timeout)] 02:35 -!- taupehat [me@taupehat.com] has joined #linode-xenbeta 02:35 < taupehat> whee! 02:51 < caker> ? 02:52 < taupehat> oh you know 02:52 < taupehat> server falls down, I spend five minutes muttering that I need to fix my irssi config when it comes back up, then it goes down again. 02:53 < taupehat> but at least I don't look like this guy: http://news.bbc.co.uk/2/hi/business/4919990.stm 02:53 < caker> that time, just your node 03:26 < linbot> New news from forums: Kernel: 2.6.16.1-linode18 with NPTL/TLS support in Linode.com Announcements 03:44 < TheFirst> taupehat: see this is why irssi on node bad ;P 09:01 -!- bendy24 [~scott@dsl-216-110-238-70.wightman.ca] has joined #linode-xenbeta 09:05 < TheFirst> Timing buffered disk reads: 4 MB in 3.59 seconds = 1.12 MB/sec 09:05 < bendy24> is that bad? 09:08 < TheFirst> yes 09:09 < TheFirst> when things are all happy it's >30 or >40 09:26 < linbot> New news from forums: Upgrading from Fedora Core 3 to Fedora Core 4 in Xen Public Beta 09:37 < linbot> New news from forums: Reboot: host39 in System and Network Status 12:28 < linbot> New news from forums: Reboot: Host51 in System and Network Status 12:34 < linbot> New news from forums: Lost connection to MySQL server during query in Linux, Apache, Mysql and PHP (LAMP) Forum 14:21 < TheFirst> still on the low side ... Timing buffered disk reads: 38 MB in 3.06 seconds = 12.41 MB/sec 16:34 -!- bendy24 [~scott@dsl-216-110-238-70.wightman.ca] has quit [Quit: leaving] 17:27 < TheFirst> hey caker 17:28 < caker> TheFirst: yes? 17:28 < TheFirst> Timing buffered disk reads: 4 MB in 3.16 seconds = 1.27 MB/sec 17:28 < TheFirst> problems again 17:29 < caker> crash. 17:29 < TheFirst> ? 17:30 < caker> I ran hdparm -t /dev/sda, and it locked 17:31 < caker> TheFirst: your ndoe still running? 17:35 -!- TheFirst_ [~GaveUp@CPE-70-92-72-102.new.res.rr.com] has joined #linode-xenbeta 17:35 < TheFirst_> nope, node is not running 17:35 < TheFirst_> what did you do? :P 17:35 < caker> dom0 crashed, but I *think* the sub-domains were still up 17:35 < caker> which is quite weird 17:36 -!- taupehat [me@taupehat.com] has quit [Ping timeout: 480 seconds] 17:37 < TheFirst_> Job Entered 01/04/1974 12:00:00 AM Status In Queue 17:37 < caker> :) 17:37 < caker> ma bday 17:38 < TheFirst_> last time i checked servers couldnt time travel 17:39 -!- TheFirst [gaveup@your.friendly.neighborhood.hellmouth.info] has quit [Ping timeout: 480 seconds] 17:40 < TheFirst_> and 74? hmmm same birth year as the redhead witch 17:41 -!- TheFirst [gaveup@your.friendly.neighborhood.hellmouth.info] has joined #linode-xenbeta 17:42 -!- TheFirst_ [~GaveUp@CPE-70-92-72-102.new.res.rr.com] has quit [Quit: You're a bloody puppet!] 17:44 < linbot> New news from forums: Complex passwords in Feature Request/Bug Report 17:45 < TheFirst> fyi, io still sucking 17:48 -!- taupehat [me@taupehat.com] has joined #linode-xenbeta 17:48 < taupehat> zoinks 17:48 < taupehat> caker: what happen? =] 17:48 < TheFirst> the evil taupehat returns 17:48 < TheFirst> taupehat: he p0rked it 17:48 < taupehat> if you say "somebody set up us the bomb" I'm gonna slap TheFirst 17:49 < TheFirst> ummm that phrase does not parse 17:49 < taupehat> sigh 17:49 < TheFirst> he did a hdparm and is borked things... 17:50 < taupehat> really 17:55 < TheFirst> yah really, i don't lie 18:03 < taupehat> weird 18:04 < taupehat> hdparm shouldn't make it fall over 18:04 < TheFirst> [04:30.33PM] <@caker> I ran hdparm -t /dev/sda, and it locked 18:05 < taupehat> lame 18:05 < taupehat> lolz0r tho 18:05 < TheFirst> shouldnt be calling caker lame...he might not appreciate that very much 18:06 < taupehat> bah, you take things too personal 18:06 < taupehat> besides, I wasn't calling caker lame, I was saying that hdparm making the host die was lame 18:07 < TheFirst> i take nothing personal 18:07 < taupehat> haha 18:07 < taupehat> so not true 18:07 < TheFirst> dry sarcasm just doesn't come across well on irc 18:07 < TheFirst> ok except for the one arse...he pissed me off 18:07 < TheFirst> that rarely happens, though 18:08 < taupehat> only he wasn't doing anything 18:11 < TheFirst> i make no apologies nor regret a thing...it's done, it's over and it's no use arguing over it 18:51 < linbot> New news from forums: Tuning Apache in Linux, Apache, Mysql and PHP (LAMP) Forum 19:31 -!- taupehat [me@taupehat.com] has quit [Remote host closed the connection] 19:38 -!- taupehat [me@taupehat.com] has joined #linode-xenbeta 19:45 < linbot> New news from forums: Lost connection to MySQL server during query in Linux, Apache, Mysql and PHP (LAMP) Forum 20:11 < TheFirst> yo caker...things are slowed again 20:53 < caker> host looks fine 20:53 < caker> I'm afraid to do anything 21:09 < taupehat> heh 21:09 < taupehat> caker: did you get a good dump from it last time it fell over? 21:39 < TheFirst> yah things are good now 21:47 -!- taupehat [me@taupehat.com] has quit [Ping timeout: 480 seconds] 21:47 -!- TheFirst [gaveup@your.friendly.neighborhood.hellmouth.info] has quit [Ping timeout: 480 seconds] 21:53 -!- petert [~peter@130.57.22.69] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- fo0bar [fo0bar@38.99.66.211] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- warewolf [warewolf@warewolf.org] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- gpd [~gpd@70.85.16.173] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- adinardi [~angelo@tux.csh.rit.edu] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- encode [~encode@blah.i.hate.w1ndo.ws] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- linbot [~supybot@ns.theshore.net] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- caker [~caker@caker.netrep.oftc.net] has quit [arion.oftc.net helium.oftc.net] 21:53 -!- gsf [g813bQV4Ar@panix3.panix.com] has quit [arion.oftc.net helium.oftc.net] 21:54 -!- gsf [g813bQV4Ar@panix3.panix.com] has joined #linode-xenbeta 21:54 -!- encode [~encode@blah.i.hate.w1ndo.ws] has joined #linode-xenbeta 21:54 -!- caker [~caker@caker.netrep.oftc.net] has joined #linode-xenbeta 21:54 -!- linbot [~supybot@ns.theshore.net] has joined #linode-xenbeta 21:54 -!- adinardi [~angelo@tux.csh.rit.edu] has joined #linode-xenbeta 21:54 -!- mode/#linode-xenbeta [+o caker ] by nobelium.oftc.net 21:57 -!- gpd [~gpd@70.85.16.173] has joined #linode-xenbeta 21:57 -!- warewolf [warewolf@warewolf.org] has joined #linode-xenbeta 21:57 -!- fo0bar [fo0bar@38.99.66.211] has joined #linode-xenbeta 21:57 -!- petert [~peter@130.57.22.69] has joined #linode-xenbeta 22:13 -!- TheFirst_ [~GaveUp@CPE-70-92-72-102.new.res.rr.com] has joined #linode-xenbeta 22:13 < TheFirst_> ok...that was odd...couldn't resolve irc.oftc.net....so what happened to host56? 22:15 -!- taupehat_ [~3fe0c9f4@webuser.linode.com] has joined #linode-xenbeta 22:15 < taupehat_> ffs 22:15 < taupehat_> what happened?! 22:15 < taupehat_> node died, then I couldn't resolve OFTC 22:15 < taupehat_> anyhow 22:15 < taupehat_> ping caker 22:16 -!- bleppard [~414a01e5@webuser.linode.com] has joined #linode-xenbeta 22:16 -!- jnagro [~183d4a2a@webuser.linode.com] has joined #linode-xenbeta 22:16 * jnagro waves 22:16 < jnagro> host56 problems? 22:16 * taupehat_ waves back 22:16 < taupehat_> yeah, bemw 22:16 < taupehat_> bewm 22:17 < taupehat_> mikegrb: you might want to let caker know that 56 is wedged again 22:17 < TheFirst_> taupehat_: you werent the only one 22:17 < taupehat_> the only one...? 22:18 < TheFirst_> that couldnt connect here 22:18 < taupehat_> ahh 22:18 < taupehat_> seemed to be a dns burp 22:18 < TheFirst_> or whose node died 22:18 < TheFirst_> yah it did 22:19 < mikegrb> it's not wedged, it rebooted 22:19 < mikegrb> linodes are comming up now 22:20 < jnagro> should we do anything in particular? 22:21 * taupehat_ can't supress a chuckle at the misspelling 22:21 < caker> gah 22:21 < taupehat_> hi caker 22:21 < caker> yo 22:21 < caker> mike just called me 22:21 < taupehat_> and here you are 22:21 * caker looks at console logs 22:22 < TheFirst_> oh sure...you show up when things come back up.... 22:22 -!- TheFirst [gaveup@your.friendly.neighborhood.hellmouth.info] has joined #linode-xenbeta 22:22 < taupehat_> TheFirst_: back up, you say, eh? 22:22 * taupehat_ is still doing the 'waiting on host' rhumba 22:23 < jnagro> my queue dropped 22:23 < jnagro> from 9 - 4 22:23 < jnagro> so something is happening 22:23 < taupehat_> ahh here we go 22:23 -!- TheFirst_ [~GaveUp@CPE-70-92-72-102.new.res.rr.com] has quit [Quit: You're a bloody puppet!] 22:24 < caker> jnagro: thanks for the ticket 22:24 < caker> looks like we hit the same bug we hit a few days ago 22:24 < caker> (I think there are multiple issues) 22:25 < caker> (XEN) domain_crash_sync called from entry.S (ff157585) 22:25 < taupehat_> man 22:25 < taupehat_> it didn't go slow 22:25 < TheFirst> i think so do 22:25 < taupehat_> just _stopped_ 22:25 -!- egatenby [~egatenby@itsb149.itsnpt.com] has joined #linode-xenbeta 22:25 < TheFirst> right after caker said he was afraid to touch anything no less 22:25 < caker> fortunately, I've had a chance to regression test the existing host code with UML, in fact host57 (live) is running it now 22:26 -!- bleppard [~414a01e5@webuser.linode.com] has quit [Quit: CGI:IRC (Ping timeout)] 22:26 < caker> so, if this gets worse, I can reboot us back into UML in a snap 22:26 < TheFirst> i assume nodes are still booting? 22:26 < caker> yes 22:26 < TheFirst> was gonna say io bites :P 22:27 -!- taupehat [me@taupehat.com] has joined #linode-xenbeta 22:27 < jnagro> caker: should i be doing anything? or just chillin out for the moment 22:27 -!- bleppard [~414a01e5@webuser.linode.com] has joined #linode-xenbeta 22:28 < caker> jnagro: it should boot eventually 22:28 < caker> (XEN) Fault while accessing guest memory. 22:28 < caker> hmm 22:28 * caker ponders faulty RAM 22:29 < jnagro> my logview says my system has halted, the status says its running 22:30 -!- taupehat_ [~3fe0c9f4@webuser.linode.com] has quit [Quit: CGI:IRC (Ping timeout)] 22:41 < caker> I'm rather disenchanted with Xen at the moment... 22:41 < caker> I'm wondering how much UML has improved with softints and the other stuff Jeff's done recently 22:41 < caker> clearly, Xen isn't ready for us, yet ... 22:41 < caker> we're ready for it, but not the other way around 22:41 < taupehat> yeah, seems that way 22:42 < taupehat> although have you yet ruled out bad ram? 22:42 < caker> no, I suggested that in my last post (5 minutes ago). Remebmer, I did send one chip back 22:42 < caker> but I ran memtest for 24+ hrs on the rest 22:42 < caker> not that it means much 22:43 < caker> replacing it is going to be a pain .. 8 chips, memtest here for a LONG time, send to HE, have them replace and send the orig 8 back, test locally 22:43 < caker> ... 22:43 < taupehat> not much joy to be had with that 22:43 < caker> I think before I would do that, I would boot us back into UML 22:43 -!- Battousai [~bryan@24.238.95.163.res-cmts.sth.ptd.net] has quit [Read error: Connection reset by peer] 22:44 < taupehat> sure 22:44 < caker> # ll /vbin/pids/ | wc -l 22:44 < caker> 20 22:44 < caker> ^-- workersWorking 22:45 -!- Battousai [~bryan@24.238.95.163.res-cmts.sth.ptd.net] has joined #linode-xenbeta 22:45 < taupehat> I've not been complaining much, but the bleeding edge is starting to drain one a bit 22:45 < caker> agreed 22:45 < caker> this is way beyond the number of problems I expected to have for you guys 22:46 < taupehat> aye 22:46 < caker> ok .. next crash, we're booting back into UML 22:46 < caker> hmmm 22:46 < caker> that won't be easy with the mods we've made to inittab and fstab 22:46 < caker> mikegrb: ? 22:46 < petert> i don't mind this level of instability, but if it doesn't look like things will improve, it's probably not worth the time 22:47 < caker> petert: yeah -- I'll give the Xen guys a day to make suggestions based on my last two emails 22:47 < caker> try those out (if any) 22:47 < mikegrb> caker: the code will migrate back the other way 22:47 < caker> mikegrb: ok, just wanted to make sure 22:47 < Battousai> panics? 22:47 < caker> mikegrb: for both inittab and fstab? 22:47 < bleppard> I am willing to wait this out if things have a chance if being fixed. 22:47 < mikegrb> yeah 22:47 < caker> mikegrb: excellent 22:48 < mikegrb> in fact when testing, files that went uml -> xen -> uml were identical to the originals 22:48 < mikegrb> I expected them to be functionaly equivalent 22:48 < caker> Yeah -- I'd only boot back into UML for the "meantime" -- we'd likely boot back to Xen once potential fixes are submitted 22:57 -!- bleppard [~414a01e5@webuser.linode.com] has quit [Quit: CGI:IRC (Ping timeout)] 23:07 < TheFirst> yah i gotta agree with tau...not one to complain but it is starting to wear thin on the nerves 23:23 < caker> mikegrb: kudos on your regex magic 23:23 < caker> he's a freaking regex wiz, I tell ya 23:27 < TheFirst> tell him to tweak the nutty regex then 23:28 < TheFirst> cuz that one bugs me and i'm lazy 23:45 -!- Electric1lf [~dbharris@69.158.54.160] has joined #linode-xenbeta 23:56 -!- ElectricElf [~dbharris@electricelf.noc.oftc.net] has quit [Read error: Connection timed out] 23:58 < jnagro> thanks for all your help guys 23:58 -!- jnagro [~183d4a2a@webuser.linode.com] has quit [Quit: CGI:IRC] --- Log closed Wed Apr 19 23:59:00 2006