--- Day changed

--- Log opened Thu Mar 31 23:59:02 2005
00:07 -!- jeroney [~jeroney@rrcs-24-173-250-83.sw.biz.rr.com] has quit [Read error: Connection reset by peer]
00:24 -!- totempole [~TotemPole@c-24-99-72-195.hsd1.ga.comcast.net] has joined #xen
00:25 < totempole> Hi Folks, I have a very basic question, what is ioemu (what is its relevance to xen)
00:40 -!- totempole [~TotemPole@c-24-99-72-195.hsd1.ga.comcast.net] has quit [Quit: Leaving]
01:08 -!- shaleh [~shaleh@dsl017-044-048.sfo4.dsl.speakeasy.net] has joined #xen
01:37 -!- shaleh [~shaleh@dsl017-044-048.sfo4.dsl.speakeasy.net] has quit [Quit: Leaving]
02:11 -!- rusty [~rusty@bh02i525f01.au.ibm.com] has quit [Quit: Client exiting]
02:46 -!- sleon [test@p54A15705.dip.t-dialin.net] has joined #xen
02:47 < sleon> how to select additional bootparameters in domain config file?
03:30 -!- anthill333 [~larsr@palwebproxy2.core.hp.com] has quit [Remote host closed the connection]
03:37 < mael> hi guys
05:00 -!- DEac- [~deac@xdsl-81-173-139-25.netcologne.de] has quit [Ping timeout: 480 seconds]
05:09 -!- hebutterworth [~harry@blueice3n1.uk.ibm.com] has joined #xen
05:11 -!- DEac- [~deac@xdsl-213-196-203-102.netcologne.de] has joined #xen
05:22 < hebutterworth> Anyone know Mark Williamson's handle?
06:32 < knewt> on here? MarkW
06:37 -!- DEac- [~deac@xdsl-213-196-203-102.netcologne.de] has quit [Quit: Leaving]
06:37 < hebutterworth> thanks
06:38 -!- DEac- [~deac@xdsl-213-196-203-102.netcologne.de] has joined #xen
07:04 < buggs> on my notebook it fails to bring up eth0 (tigon3)
07:07 -!- perry [~perry@fw.office.netland.nl] has joined #xen
07:08 -!- hebutterworth [~harry@blueice3n1.uk.ibm.com] has quit [Quit: Leaving]
07:25  * riel yawns
07:25 < riel> (good morning)
07:26 < mael> hi
07:26 < mael> its 2pm here :)
07:37 < riel> 7 am here
07:37 < riel> or it was, when I woke up ;)
08:43 -!- Method [Method@pcp0010742058pcs.howard01.md.comcast.net] has quit [Ping timeout: 480 seconds]
08:54 -!- Method [~Method@stanford.columbia.tresys.com] has joined #xen
08:55 -!- riel is now known as surriel
08:56 < mael> surriel:  where are u in the states? west coast?
08:56 < surriel> east coast
08:56 < surriel> and about to head to over to the office
08:56 < surriel> aka "that place they pay me to hang out at"
08:59 < mael> :)
08:59 < mael> I thought surriel was you work nick
09:00 < mael> uh no
09:00 < mael> this is with you home ip
09:33 -!- demon is now known as mon
09:41 -!- unriel is now known as riel
09:42 -!- matta-lt [~matta@69.93.28.254] has joined #xen
09:52 -!- perry [~perry@fw.office.netland.nl] has left #xen []
09:55 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has joined #xen
09:55 -!- rharper [~rharper@pixpat.austin.ibm.com] has joined #xen
10:08 -!- plars [~plars@pixpat.austin.ibm.com] has quit [Read error: Operation timed out]
10:20 -!- plars [~plars@pixpat.austin.ibm.com] has joined #xen
10:46 < knewt> didn't get the job :(
10:48 < riel> ;(
11:05 -!- jeroney [~jeroney@pixpat.austin.ibm.com] has joined #xen
11:51 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has quit [Quit: leaving]
11:55 -!- plars [~plars@pixpat.austin.ibm.com] has quit [Ping timeout: 480 seconds]
12:04 -!- plars [~plars@pixpat.austin.ibm.com] has joined #xen
12:15 -!- hollis [~hollis@pixpat.austin.ibm.com] has joined #xen
12:28 < sleon> hi
12:28 < sleon> is it possible to set additional  kernelbootparamers to the xen's guaest domain??
12:29 < Sir_Ahzz> yes
12:29 < rharper> sleon: yes, you can add them to the extra variable in your domain configuration file
12:34 < sleon> rharper, how is it called? i can not find its name in the documentation
12:36 < rharper> sleon: in /etc/xen/xmexample1: extra = "ro"  <--- that appends ro to the kernel parameters when launching that domain.  you can just add to the 'extra' variable 
12:37 < sleon> rharper, aaha thx, it is not documented though
12:39 < rharper> sure, sounds like a documentation patch could help, I'm sure they will take it
12:42 < sleon> rharper, also in the .patch format?
12:43 < rharper> generated with diff -u original_file changed_file > mychanges.patch 
12:45 < sleon> rharper, i talk about the webpage docu, not the sourcedocu
12:45 < sleon> i didn't even look at the source docu
12:45 < sleon> cause it looks very very strange
12:45 < sleon> it is unclear where to get information from
12:46 < eigood> Sir_Ahzz: I get to have fun this weekend(I hope)
12:46 < Sir_Ahzz> oh?
12:46 < eigood> trying to get $10k worth of hardward into a deployable state
12:46 < Sir_Ahzz> you finally get a date or somethign? :)
12:46 < eigood> 2 indentical machines, 15 SATA slots, 3U
12:46 < Sir_Ahzz> well, I spose $10k in hardware counts as a date for you. ;)
12:46 < Sir_Ahzz> nice.
12:46 < Sir_Ahzz> I need one of those for here.
12:46 < eigood> first has 8 160g drives, second has 8 300g drives
12:47 < rharper> sleon: ahh, sure.  There supposedly is a wiki (wiki.xensource.com) which might be open to those changes.
12:47 < sleon> eigood, uiuiui
12:47 < eigood> the way we(I) build machines now is rather slick
12:47 < sleon> eigood, and cpu's?
12:47 < eigood> netboot the new machine, copy the nfsroot image to the drive, reboot
12:47 < Sir_Ahzz> wanna rent me 3 units so I can develop out a software package for agregated iSCSI SAN solution? :)
12:47 < sleon> rharper, a nice thx
12:47 < rharper> sleon: welcome
12:47 < eigood> single(but dual capable) p4-3.2g, 12 dimm slots(2 gig atm), dual gig-e
12:47 < eigood> Sir_Ahzz: we only have 2
12:48 < sleon> eigood, and it costs 10k$?!
12:48 < eigood> the 8x160 machine will be the new xen fileserver; using raid10
12:48 < eigood> sleon: 2 boxes
12:48 -!- Sir_Ahzz changed the topic of #xen to: Xen Homepage->  http://www.cl.cam.ac.uk/Research/SRG/netos/xen/index.html || Xen Wiki -> http://wiki.xensource.com
12:48 < Sir_Ahzz> eigood software or 3ware?
12:48 < eigood> software; gives us more control
12:48 < Sir_Ahzz> *nod* takes more cpu time though.
12:48 < eigood> 3ware cards are too expensive
12:49 < sleon> eigood, how much ram?
12:49 < eigood> plus their sata implementation is stupid; they have pata controllers combined with pata<->sata on their card
12:49 < Sir_Ahzz> how are you getting so many sata in one box then? pci cards, or 4-way SATA splitters?
12:49 < eigood> an 8-port 3ware is too tall to fit in the box.
12:49 < sleon> what are the 3ware caeds?
12:49 < eigood> Sir_Ahzz: 8 port rockraid cards
12:49 < Sir_Ahzz> eigood: wait another 2 months, 3ware has a native sata in the pipeline.
12:49 < eigood> sleon: read scrollback
12:50 < sleon> eigood, what is scrollback?
12:50 < eigood> Sir_Ahzz: can't
12:50 < sleon> eigood, sorry
12:50 < Sir_Ahzz> they claim the new xor engine can sustain 150MB/sec on 12 drives.
12:50 < Sir_Ahzz> I know doogie. 8-P
12:50 < eigood> sleon: I already said it, at the same time I gave the cpu specs
12:50 < sleon> eigood, aa ok :)
12:50 < eigood> Sir_Ahzz: we get 200MB/s on these
12:50 < sleon> eigood, excuse me
12:50 < cw> Sir_Ahzz: 150MB/s across 12-drives is horrible
12:51 < eigood> each drive does 50MB by itself
12:51 < cw> you can get about 70MB/s+ from each spindle on modern disks
12:51 < eigood> in raid10, that's 200MB, so we are getting full speed, using software
12:51 < Sir_Ahzz> cw considering the curent setup 3ware offers get's 80MB/sec. it's an improvement. :)
12:51 < eigood> well, 50-55MB/s
12:52 -!- shuri [sjnesjd@dsl.speedline209.226.electronicbox.net] has joined #xen
12:53 < sleon> eigood, aaa it is serial ata raid controller
12:53  * Sir_Ahzz looks at his 3 year old ide's and poiuts at their measly 22MB/sec. 8-P
12:53  * eigood has a personal 3x250g raid5 set, holding tv shows
12:53 < sleon> i will buy me dual opteron server soon
12:54 < sleon> with tyan board
12:57 < Sir_Ahzz> get a quad with dual core when it's out. :)
12:58 < tab> or wait for quadri core :)
13:00 < Sir_Ahzz> that'l be a while I think. :)
13:00 < matta-lt> Sir_Ahzz: how many drives with the 3ware/80MB combo?
13:00 < Sir_Ahzz> I'll settle for a dual with dual core for the next boxen. get single cores minimal speed cpus for now.
13:00 < Sir_Ahzz> matta-lt: visit 3ware.com
13:01 < Sir_Ahzz> they have 2,4,8,and 12 drive sata and pata controllers.
13:01 < matta-lt> I can get about 85MB/s w/ a 3ware 8000 series with 4 7200 RPM drives... RAID-5
13:01 < matta-lt> which I don't consider bad at all
13:01 < Sir_Ahzz> sounds about right from the benchmarks i've read on ata raid.
13:01 < matta-lt> RAID-10 is a bit faster
13:01 < matta-lt> oh, that's in a 64-bit/66mhz PCI slot
13:01 < Sir_Ahzz> i'm geting 72MB/sec on 6 60GB ides on 4 ports.
13:01 < matta-lt> in 32-bit it's limited to about 70MB/s
13:02 < matta-lt> Sir_Ahzz: PATA?
13:02 < Sir_Ahzz> pIII-700 512MB ram.
13:02 < Sir_Ahzz> parallel ata.
13:02 -!- sleon [test@p54A15705.dip.t-dialin.net] has quit [Ping timeout: 480 seconds]
13:02 < Sir_Ahzz> the old standard.
13:02 < Sir_Ahzz> funny thing is writes happen at 72MB/sec and reads at 70MB/sec
13:02 < Sir_Ahzz> probably limitations of the PCI bus and 2 drives per channel setup I have.
13:03 < Sir_Ahzz> that and the drives are only 2MB/sec max.
13:03 < Sir_Ahzz> err 22MB/sec
13:03 < Sir_Ahzz> 5400rpm
13:03 < Sir_Ahzz> so my setup is pretty cheap. :)
13:03 < Sir_Ahzz> seems to serve 3 xen boxes with 12 domains decently enough over 100Mbps ether.
13:03 < matta-lt> well, it's xen :)
13:03 < Sir_Ahzz> all athlon XP 2000+ w/ 1G
13:04 < Sir_Ahzz> my setup is like this, 2 raid array machines disk1 and disk2, connected via bonded 100Mbps ether (2 links per machine) to a concentrator that runs EVMS (handles management of all disks) which pipes out of 2 100Mbps ethernet ports (separate IPs)
13:05 < Sir_Ahzz> bount 1.3TB total capacity on it.
13:05 < Sir_Ahzz> less available due to raid-1 on a few volumes in EVMS.
13:05 < Sir_Ahzz> attempting to create an open source SAN management setup.
13:06 < Sir_Ahzz> nothing releasable yet.
13:06 < shuri> nice project
13:06 < Sir_Ahzz> grew from necessity.
13:07 < Sir_Ahzz> raiding the entire array was too wastefull and caused IO conflicts.
13:07 < Sir_Ahzz> so it's inteligently split the raid1 between the two disk servers.
13:07 < shuri>  "inteligently"  :) 
13:07 < Sir_Ahzz> for high bandwidth it's striped across 6 disks 3 per disk box.
13:08 < Sir_Ahzz> my typing sucks today.
13:08 < Sir_Ahzz> I'll probably GPL it and offer support services and pre-built setups.
13:08 < Sir_Ahzz> primary target will be supporting Xen clusters.
13:09 < Sir_Ahzz> right now the PHP code and logic is rather rough. get's things wrong more often than not. 8-P
13:09 < Sir_Ahzz> and I can't implement auto-rebuild on a third disk target until I get another raid array machien setup.
13:10 < Sir_Ahzz> but for now (minus the IETD lockups) it's kept my xen cluster up non-stop for 8 months. despite loosing 4 disks of the set of 18
13:10 < Sir_Ahzz> but IETD is improving rapidly. :)
13:10 < Sir_Ahzz> it's exporting via iSCSI, NFS, and samba. could export via any open source method in the future.
13:11 < Sir_Ahzz> after the auto-rebuild is workign i'll tackle handling redundant concentrator boxes.
13:11 -!- sleon [test@p54A17B26.dip.t-dialin.net] has joined #xen
13:11 < Sir_Ahzz> that way it'll be 100% fault tolerant.
13:12 < Sir_Ahzz> I just wish Linux was capable of recognising and using expanded target volumes in iSCSI.
13:12 < Sir_Ahzz> that would make the ultimate in managed storage IMO. dirt cheap too.
13:12 < Sir_Ahzz> cost me ~ $5k 3 years ago for the setup.
13:21 -!- homebaum [~michael@wbar1.sea1-4-5-031-104.sea1.dsl-verizon.net] has joined #xen
13:21 < aliguori> hey homebaum.. i like the nick :-)
13:22 < homebaum> Working from home today - in case it was not obvious
13:23 < aliguori> indeed :-)
13:36 -!- jimix [~jimix@ip13.194.susc.suscom.net] has joined #xen
13:37 -!- Mark [~Mark@maw48.kings.cam.ac.uk] has joined #xen
13:37 < muli> hey jimix :-)
13:37 < jimix> muli: heya
13:38 -!- jimix [~jimix@ip13.194.susc.suscom.net] has left #xen []
13:38 -!- jimix [~jimix@ip13.194.susc.suscom.net] has joined #xen
13:38 < matta-lt> yay
13:38 < matta-lt> x86_64!
13:39 < knewt> anyone here in the uk know of any jobs going? (london/oxford preferred)
13:42 < hollis> Mark: I guess nobody builds non-SMP now, huh?
13:43 < Mark> hollis: I do
13:44 < hollis> Mark: oh, really? there are at least 2 breaks now; Ian's opt_noht is the new one
13:44 < Mark> but not on the latest 2.6, since at the moment I'm either preoccupied with the 2.4 kernel's USB
13:44 < aliguori> hollis: i just built a non-SMP build and it worked fine
13:44 < hollis> Mark: I mean the Xen core, not Linux
13:44 < aliguori> grabbed it from bitkeeper last night
13:44 < Mark> or the XenFS in my private tree
13:44 < Mark> oh right, I see
13:44 < aliguori> oh, the hv..
13:44 < Mark> hollis: i'm not sure anyone has *ever* built non SMP Xen on a regular basis
13:45 < hollis> Mark: hmm, ok...
13:45 < Mark> hollis: probably somebody should do so if the option's there
13:46 < Mark> but most of the test machines here are SMP anyhow, so for the past few years I imagine UP builds have been the exception rather than the norm
13:46 < hollis> well it's set in include/asm-x86/config.h, so I don't think anybody would run across it by accident
13:47 < hollis> Mark: but for a new arch port, it would be easier to do the UP port first and worry about SMP issues later
13:47 < hollis> but not even x86 builds UP, so that's not possible right now
13:48 < Mark> i think there's an argument for having regular UP builds here
13:48 < Mark> so that people notice when things break
13:49 < hollis> sounds fine to me :) I was just wondering if nobody cared any more
13:49 < Mark> Ian might be good to ask about the test build system
13:50 -!- cw [cw@adsl-63-202-174-57.dsl.snfc21.pacbell.net] has left #xen [grrr]
13:50 < Mark> I don't think there's been a definitive decision not to support UP builds
13:50 -!- cw [cw@adsl-63-202-174-57.dsl.snfc21.pacbell.net] has joined #xen
13:50 -!- mode/#xen [+o cw] by ChanServ
13:50 < hollis> ok
13:50 < Mark> but equally well, they're not really tested.
13:53 < tab> :)
13:54 < tab> hey Mark not in the office ? :)
13:55 < Mark> tab: not today
13:55 < Mark> i was there late last night squishing a bug
13:55 < Mark> and it didn't really seem worth coming in by the time I'd got up
13:56 < tab> so basicly never when I'm in ;)
13:57 < Mark> might be in over the weekend, probably back in during monday
13:58 < tab> ok
14:00 < tab> oh no x86_64 support announce just after my vbds .. nobody going to test :)
14:14 < aliguori> tab: don't worry, i'm testing as we speak :-)
14:29 < caker> Is it normal for xend to be using 40M+ RAM?
14:31 < riel> caker: not afaik ;)
14:31 < matta-lt> caker: nope
14:31 < caker> Yeah .. I didn't think so.  It might increase with each Xen boot/reboot ..
14:31 < matta-lt> here is an interesting bug I have found in 2.0 / -testing
14:31 < matta-lt> boot up host
14:31 < matta-lt> start xend
14:31 < matta-lt> start a domain
14:31 < matta-lt> stop xend
14:31 < matta-lt> then try starting xend, it won't start... only xfrd will
14:32 < matta-lt> note, if you omit the "start a domain" part you can stop/start xend to your hearts delight
14:32 < matta-lt> not a major problem, just scary that if xend dies on a running host that it then needs to be rebooted
14:32 < matta-lt> should be easily reproduceable (I know I can)
14:32 < caker> matta-lt: odd.  I've noticed that with stable doing that is ok..
14:32 < rharper> you might try killing xcs 
14:33 < rharper> I've seen that before, and if you kill off all of the progs spawned, xend will launch again 
14:33 < matta-lt> rharper: I don't believe xcs lives in anything but -unstable...
14:33 < rharper> ah, thats probably right
14:33  * rharper lives in unstable land
14:34 < caker> My stable bug is: boot a domain with an invalid kernel (/bin/true, or whatever, doesn't matter). xend gives an error, but starts a domain with a generic name (Domain-#), including consuming the ram
14:34 < matta-lt> caker: what distro is the host?
14:34 < caker> matta-lt: CentOS 4
14:34 < matta-lt> i get that also
14:34 < matta-lt> my kernels are always valid
14:34 < matta-lt> I wrote a script to find the dupe domain (it's always a dupe), xm destroy it twice and then start the real domain
14:35 < caker> ahh
14:35 < mikegrb> ahh hah!
14:35 < matta-lt> ie.
14:35 < matta-lt> if it lists Domain-16 which is of course... id 16
14:36 < matta-lt> there will be another domain named 'userx' (or whatever it's named) with id of 16
14:36 < matta-lt> other times...
14:36 < matta-lt> if I only run xm destroy 16 once...
14:36 < matta-lt> Domain-57         57        0    0  --p--      0.0
14:36 < matta-lt> i get that
14:36 < caker> matta-lt: and when does this scneario occur?
14:37 < matta-lt> caker: have not traced it down, seems to be when running xendomains init script... but I haven't had any reboots since last tweaking
14:37 < matta-lt> but it seems it could happen whenever
14:37 < matta-lt> since xendomains just runs xm create
14:37 < caker> odd -- haven't seen that one (don't use xendomains)
14:38 < matta-lt> on mine the domain starts, it's just a dupe...
14:49 < eigood> I wish we had an amd64 machine
14:49 < matta-lt> i wish i had a stable x86_64 port :)
14:49 < matta-lt> apparently my wish will be fairly soon though :)
15:27 < sleon> hey gals
15:27 < sleon> what are you using xen for?
15:28 < hollis> aliguori: you're too kind. I would have told the guy to run a LOC counter himself
15:41 < hollis> ugh... hate header dependency trees :(
15:42 < eigood> sleon: insert  pinky and the brain reference
15:42 < eigood> hollis: aren't using gcc's dep generator?
15:43 < hollis> eigood: the xen core isn't, but that wouldn't help here anyways. it's the usual header1 needs header2 needs header1 problem
15:48 < aliguori> hollis: I was a bit curious myself :-)
15:48 < sleon> eigood, haha
15:49 < aliguori> yeah, I agree with you hollis btw.. I don't know why headers aren't explicitly included where they're needed
15:49 < aliguori> the problem trickles all the way down to userspace
15:49 < aliguori> all of the public headers use u8, u16, etc types but it's not defined anywhere in the public headers
15:49 < aliguori> it's really annoying because you have to define them yourself before you can include any xen header
15:50 < hollis> to paraphrase Christian's explanation: there are too many implicit includes already, so we should rely on more implicit includes
15:51 < aliguori> might as well have one 'includes.h' if that's goign to be the attitude.
15:54 < aliguori> something's really fishy with the linux smp build for domU.  i get the feeling that when every somethign is being schedule on two cpus at the same time i get an oops
15:55 < aliguori> like if i put something in the background from the shell
15:56 < rharper> aliguori: shouldnt, I run smp domU all the time
15:56 < rharper> you have an oops?
15:56 < rharper> in unstable?
15:59 < eigood> all headers should directly include headers that define symbols they directly use
15:59 < eigood> I consider not complying with that a bug.
15:59 < eigood> my own software follows that
16:01 < hollis> eigood: I agree, but I was the only one on-list advocating it
16:02 < eigood> when was this on the list?
16:02  * rharper wouldnt have thought such practices needed advocating now-a-days
16:02 < eigood> it'd be nice if sparse could check for that
16:03 < rharper> the thread subjuct is [Xen-devel] [patch] final header fixes
16:03 < eigood> when did it start?
16:03 < rharper>  Wed, 23 Mar 2005
16:03 < hollis> it's come up a few times, but the most recent was 26 Mar 2005
16:05 < greenrd> chalk up another reason why C sucks ;)
16:06 < sleon> eigood, are you running numeric simulations on your xen?
16:06 < hollis> greenrd: no argument here
16:06 < eigood> sleon: no, real apps
16:06 < sleon> eigood, like?
16:06 < sleon> eigood, isp?
16:07 < jimix> greenrd: programmers suck, leave poor C alone :)
16:07 < sleon> eigood, virtual servers for clients?
16:07 < eigood> kaffe.brainfood.com(runs several tinderboxes), mail.brainfood.com(the free mail domains, not work domains)
16:07 < eigood> all over nfsroot; very busy machine
16:07 < sleon> eigood, nfsroot interesting
16:07 < sleon> eigood, for /home?
16:07 -!- niv [~niv@bi01p1.co.us.ibm.com] has joined #xen
16:07 < eigood> our xen boxes are diskless
16:07 < eigood> everything is nfs
16:08 < eigood> even xen0, even grub
16:08 < sleon> eigood, so you have lots of xen thin clients?
16:08 < sleon> or how does it work
16:08 < eigood> bios -> pxe -> grub -> nfsroot-dom0 -> nfsroot-domU
16:08 < shuri> nice!
16:08 < eigood> 2 xen machines, 20(or so) instances
16:08 < sleon> eigood, what for?
16:08 < sleon> eigood, why do you need so many?
16:08 < riel> gorgeous
16:08 < riel> <flood>
16:08 < riel> Unable to handle kernel paging request at virtual address cb4b197c
16:08 < riel>  printing eip:
16:08 < riel> c015681a
16:08 < riel> *pde = ma 076f7067 pa 0004b067
16:08 < riel> *pte = ma 3678b061 pa 0b4b1061
16:08 < riel>  [<c0156999>] copy_page_range+0xc9/0x110
16:09 < riel>  [<c011b1f1>] copy_mm+0x301/0x400
16:09 < eigood> we are interested in kexec+multiboot, which would let us use pxelinux instead of grub, 'cuz grub's networking impl. sucks ass
16:09 < riel>  [<c011bd24>] copy_process+0x524/0xe20
16:09 < riel>  [<c011c695>] do_fork+0x75/0x1f5
16:09 < riel>  [<c0216520>] copy_to_user+0x60/0xa0
16:09 < eigood> sleon: better than having 20 separate machines
16:09 < riel>  [<c01089fc>] sys_clone+0x3c/0x40
16:09 < riel>  [<c010a0a7>] syscall_call+0x7/0xb
16:09 < riel> </flood>
16:09 < sleon> eigood, are these desktops?
16:09 < eigood> dump 4g of ram in a box, and load it up
16:09 < eigood> sleon: no, the 2 xen machines are 1U machines at a colo
16:10 < eigood> it's simpler to make a xen context to host a client's resources, then to try to have them all hosted in a single environment
16:10 < sleon> eigood, why can't you have one machine?
16:10 < sleon> eigood, aha interesting
16:10 < rharper> riel: nice one
16:10 < eigood> the problem with doing it on a single machine, is when one client needs some special feature, you have to figure out if it will affect other configs
16:10 < sleon> eigood, what kind of tasks are these 20 machines doing?
16:10 < rharper> toss that Kier's way =)
16:10 < eigood> mostly web serving
16:11 < sleon> eigood, hmm interesting
16:11 < sleon> eigood, why not usermode linux for each?
16:11 < riel> rharper: now to figure out why it only happens in xenU, and not in xen0
16:11 < eigood> all the xen instances are sitting in a dmz; we can either snat/dnat their private ip to a public one, or use squid in reverse-proxy mode to just export their web server
16:11 < rharper> riel: hrm.  smp domU?
16:11 < eigood> sleon: xen has a 2-3% overhead; uml has 40-60%
16:11 < riel> rharper: yes
16:11 < riel> but smp dom0 too
16:11 < sleon> eigood, insteresting
16:12 -!- Nigelenki [~bluefox@pcp484971pcs.whtmrs01.md.comcast.net] has quit [Read error: Connection reset by peer]
16:12  * riel tries vcpus=1
16:12 < sleon> eigood, and it runs only on a dual cpu machines?
16:12 < rharper> riel: right. you tried backing up a day or two? theres been a lot of changes in mm and pages tables that affect smp... thought why domU only is strange
16:12 < eigood> uml let's you overcommit on memory(xen doesn't), but the hardware cost is so small when amortized out over time, that having huge amounts of real ram is a no-brainer
16:12 -!- Nigelenki [~bluefox@pcp484971pcs.whtmrs01.md.comcast.net] has joined #xen
16:12 < riel> rharper: backing up a few days?   this is rawhide ... ;)
16:12 < rharper> haha
16:13 < sleon> eigood, how much ram do you have
16:13 < eigood> sleon: we have an athlon xen, and a p4 xen; the later has hyperthreading
16:13 < riel> I'm here to run into and fix bugs, not to avoid them
16:13  * eigood notes xen+hyperthreading is a little stupid
16:13 < riel> I'll leave avoiding bugs to users
16:13 < riel> it's not a developer thing
16:13 < eigood> hyperthreading is poor when 2 completely separate processes are running side-by-side
16:13 < sleon> eigood, dual or simple? hype means 2 cpu are simualted
16:13 < eigood> and 2 completely separate OSes will have nothing in common
16:13 < rharper> riel: im running 20050401 snapshot as smp domU with constant kernel compiles... what were you running in domU? repeatable?
16:13 < rharper> riel: happen on boot?
16:13 < riel> yeah, happens on boot
16:13 < riel> but  ... with vcpus=3
16:13 < rharper> ouch
16:14 < sleon> eigood, are you using simple pc hardware, or are these special boards?
16:14 < riel> on a single cpu w/ hyperthreading system
16:14 < rharper> ooo, whats the hardware?
16:14 < eigood> sleon: the p4 has 4g, the athlon has 1.5(the latter doesn't support more on the mobo)
16:14 < sleon> eigood, do they only have 4 gigs ram?
16:14 < riel> P4 w/ HT, 1GB memory
16:14 < riel> nothing special
16:14 < rharper> yeah, wonder if Ian's ht cpu distribution has something to do with it
16:14 < eigood> simple machines, ie, whiteboxes
16:14 < rharper> you saw that changes go in? yesterday
16:14 < riel> rharper: I suspect it's to do with #vcpus > #physicalcpus
16:14 < rharper> I dont have an HT box
16:14 < sleon> eigood, and they are 24/7 up?
16:14 < eigood> sleon: definately
16:14 < rharper> no, I run that fine, vcpus=4,8 , no problem
16:14 < eigood> the only problems we have are with nfs(the .nfs################ deleted file crap)
16:15 < sleon> eigood, but nfsroot is raidarray?
16:15 < riel> rharper: mmm ok
16:15 < eigood> xen 2.0 is rock solid
16:15 < riel> rharper: and an odd number of cpus ?
16:15 < rharper> riel: on my two-way
16:15  * rharper boots domU with vcpus=7
16:15 < eigood> sleon: yes, raid5 on the fileserver
16:15 < sleon> eigood, have you already heard about parallel nfs ?
16:15 < eigood> we have plans to switch to iscsi or some such thing for importing block devices, and not using nfs at all
16:16 -!- niv [~niv@bi01p1.co.us.ibm.com] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- jimix [~jimix@ip13.194.susc.suscom.net] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- plars [~plars@pixpat.austin.ibm.com] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- shuri [sjnesjd@dsl.speedline209.226.electronicbox.net] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- Method [~Method@stanford.columbia.tresys.com] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- greenrd [~greenrd@66-188-75-198.cpe.ga.charter.com] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- crisen [~crisen@spank.terdmonk.com] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- Tv [~Tv@hq.inoi.fi] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- cw [cw@adsl-63-202-174-57.dsl.snfc21.pacbell.net] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- caker [~caker@ns.theshore.net] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 -!- mikegrb [~michael@mikegrb.netop.oftc.net] has quit [oxygen.oftc.net xenon.oftc.net]
16:16 < sleon> eigood, what is the hardware or nfsroot?
16:16 < sleon> eigood, is nfs really so slow?
16:16 < eigood> it's not slow, just not good under high load
16:16 < riel> rharper: does it work ?
16:16 < rharper> riel: boot 7 vcpus on a two-way fine
16:17 < rharper> can you distable HT?
16:17 < sleon> eigood, i heard that parallel nfs should have been solved that issue
16:17 < rharper> or back out ian's changes
16:17 < eigood> fileserver is athlon 1900(1600mhz), 1g ram, 160g raid5
16:17 -!- niv [~niv@bi01p1.co.us.ibm.com] has joined #xen
16:17 -!- cw [cw@adsl-63-202-174-57.dsl.snfc21.pacbell.net] has joined #xen
16:17 -!- shuri [sjnesjd@dsl.speedline209.226.electronicbox.net] has joined #xen
16:17 -!- plars [~plars@pixpat.austin.ibm.com] has joined #xen
16:17 -!- Method [~Method@stanford.columbia.tresys.com] has joined #xen
16:17 -!- greenrd [~greenrd@66-188-75-198.cpe.ga.charter.com] has joined #xen
16:17 -!- caker [~caker@ns.theshore.net] has joined #xen
16:17 -!- mikegrb [~michael@mikegrb.netop.oftc.net] has joined #xen
16:17 -!- Tv [~Tv@hq.inoi.fi] has joined #xen
16:17 -!- crisen [~crisen@spank.terdmonk.com] has joined #xen
16:17 -!- mode/#xen [+o cw   ] by iridium.oftc.net
16:17 < sleon> or coda, andrew fs
16:17 < eigood> all this running on 100M
16:17 < rharper> riel: http://lists.xensource.com/archives/html/xen-changelog/2005-03/msg00278.html
16:17 < sleon> eigood, 100M???
16:18 < sleon> eigood, maybe this is a bottleneck?
16:18 < eigood> sleon: I  never discussed the speed
16:18 < sleon> eigood, interesting
16:18 < eigood> the speed isn't a problem; nfs just isn't stable
16:18  * riel looks
16:18 < sleon> eigood, interesting
16:18 < eigood> the biggest issue tho, with nfs, is when you delete an open file
16:18 < sleon> eigood, so when i have lots of parallel accesses it brakes??
16:19 < sleon> eigood, i heard it has fiellocking mecahnism
16:19 < eigood> since the client still needs to keep the file around, it renames it to .nfs#############, and then that breaks when something is trying to delete an entire directory
16:19 < sleon> eigood, is it nfsv3 or nfsv4?
16:19 < eigood> 3, I believe
16:19 < eigood> actually, that's probably just a stpuid bug
16:20 < eigood> if a dir is deleted that contains .nfs#### files, rename the dir to .nfs######
16:20 < sleon> eigood, have you tryed anrew or coda filesystems?
16:20 < rharper> riel: maybe I spoke too soon on the 7 vcpus... xen just rebooted, lemme try to repeat that test
16:20 < eigood> I didn't think coda was being developed anymore
16:20 < sleon> i think it is developed
16:20 < sleon> the last time i heard about it
16:20 < sleon> eigood, i spoke with parallel nfs developer
16:20 < eigood> and using a network filesystem is not the way we want to go; that requires the domU kernels/OS to know how to access the remote fs, which means more config, and more things to go wrong
16:20 < sleon> eigood, the try to solve this problems
16:21 < eigood> using block devices means only dom0 has to know about them, and can just export as virtual devices to domU
16:21 < sleon> eigood, understood
16:21 < sleon> eigood, why don't you use networkblockdevices capability of kernel?
16:21 < sleon> is it not fast enough?
16:21 < rharper> riel: yeah, 7 vcpus in domU hoses xen up, hard reboot, nothing on seriel either
16:22 < rharper> riel: here some 
16:22 < rharper> (XEN) Assertion '(x & PGT_count_mask) != 0' failed, line 1087, file mm.c
16:22 < rharper> (XEN) BUG at mm.c:1087
16:22 < rharper> (XEN) CPU:    1
16:22 < eigood> the (e)nbd doesn't really support high-count setups
16:22 < sleon> what does high-count mean?
16:22 < riel> rharper: so an even number of vcpus works, an odd number breaks?
16:22 < eigood> I tried AoE; it would only ever get me 5 megabyte/s, on a 100m lan; even their website confirmed that they had only gotten that in speed tests
16:23 < eigood> which is stupid to me; nfs can do 11.5MB/s on a 100m lan easy
16:23 < eigood> sleon: lots and lots and lots of devices
16:23 < sleon> eigood, AoE?
16:23 < riel> sleon: coraid.com
16:23 < eigood> ATA over Ethernet
16:23 < rharper> riel: lemme try it with even
16:23 < eigood> dead simple to configure(unlike iscsi)
16:24 < sleon> eigood, why not to export one raid device
16:24 < Sir_Ahzz> iscsi isn't hard to configure either.
16:24 < eigood> it's nice that 2.6 now has kernel-side iscs initiator code
16:24 < sleon> eigood, and then make lots of virtual discs from it in domain0?
16:24 < eigood> but the other half of the equation still sucks for configuring
16:24 < eigood> sleon: the fileserver hosts the separate devices, and exports them as separate devices
16:24 < rharper> riel: vcpus = 4 failed too, I think you had it right, vcpus > physical 
16:24 < eigood> that way a domU instance could roam easily
16:24 < sleon> eigood, i thought it was one big raid5
16:24 < riel> rharper: ok ;)
16:24 < riel> rharper: flushing problem I guess
16:24 < rharper> riel: was just running with vcpus=2 fine
16:25 < eigood> sleon: it is, we are now speaking hypothetical
16:25 < rharper> riel: yeah =(
16:25 < eigood> are you guys breaking xen?
16:25 < rharper> eigood: yes
16:25 < riel> then I don't have to worry about FC4 test2
16:25 < riel> few people are running with vcpus>cpus
16:25 < rharper> you have a surprise for them if they do =)
16:25 < eigood> riel: I think that would be the point of having smp support
16:25 < sleon> eigood, hmm interesting thank you very much for explanations
16:25 < eigood> I mean, UML supports that
16:26 < eigood> we've been running xen stuff for over a year now(deployed the first in february of 2004)
16:26 < eigood> well, end of january
16:26 < eigood> then, my dad died feb 5, and I went away for a week to his funeral
16:26 < eigood> machine stayed up the entire time I was gone, which was good
16:27 < riel> eigood: yeah, but how many of your virtual machines have more cpus than the physical system has ? ;)
16:27 < rharper> eigood: not really, you can have many domUs with vcpus < physicals, such that you can run domUs in parallel, you can also run with vcpus > physical cpus, but there is a performance penality since you will be switching cpu context more often 
16:27 < eigood> riel: running 2.0.4 on them, so none
16:27 < sleon> eigood, what are you using for tracking if services are up or down ?
16:27 < sleon> or behaive correctly?
16:27 < eigood> if you have 4 real cpus, 10 domU, with each one having vcpu=2, is it possible to have 4 domU running at once?
16:27 < sleon> snmp?
16:28 < eigood> or does xen only swap the entire domU?
16:28 < eigood> sleon: nagios
16:28 < sleon> eigood, is it free?
16:28 < eigood> we don't have anything magic yet
16:28 < eigood> apt-get install nagios
16:28 < rharper> eigood: xen swaps vcpus within a domU and the entire domain, you have a timer for each domU, and within that slice, xen-unstable schedules each vcpu as a thread
16:28 < sleon> eigood, cause it have lots of problems when squid for example crashes due lack of resources
16:29 < eigood> rharper: I have no idea what that means
16:30 < riel> ok, office social event!
16:30 < rharper> eigood: heh, ok.  I guess in short, with xen-unstable, you can overcommit your physical processors, as it allows you to have up to 32 virtual processors in each domain
16:30  * riel backs away from the bugs
16:30 < sleon> rharper, coool
16:30 < rharper> riel: you send an oops to the list yet?
16:30 < sleon> rharper, so i can simualate quad cpu system??! :D
16:30 < sleon> JAJAJAJAJAJAJA
16:30 < sleon> COOOl
16:30 < sleon> :))
16:31 < riel> rharper: not yet, will do afterwards
16:31 < rharper> riel: ok
16:31 < riel> rharper: unless you beat me to it ;)
16:31 < rharper> riel: =)
16:31  * rharper notes he has an office social as well
16:31 < sleon> rharper, does it mean i can have a 4 cpu system on a 1 cpu machine?
16:31 < rharper> sleon: yes, at the moment, there is no performance advantage for doing so... 
16:31 < rharper> sleon: yes
16:31 < caker> What, if any, is the current solution for preventing a swap-thrashing domain from storming the host?  Are there any disk QoS features planned?
16:31 < sleon> rharper, ok but it is cool 
16:31 < aliguori> ah, ok, i'm not crazy.  i was seeing the same thing
16:32 < rharper> sleon: build unstable with CONFIG_SMP in domU config 
16:32 < rharper> aliguori: it seems =)
16:32 < sleon> rharper, sure there is no performance advantages, but it is good for testing parallelising software
16:32 < aliguori> not to mention the fact that once domU oop's, xend eats up 100% of the cpu in dom0
16:32 < rharper> sleon: indeed
16:32 < rharper> aliguori: my xen crashes hard, so no cpu gobbling 
16:32 < sleon> rharper, how can i find out if i am using stable or unstable?
16:32 < aliguori> i don't have smp enabled in dom0
16:33 < rharper> you should see that when you boot, try xm dmesg, unstable says Xen 3.0 -devel 
16:33 < rharper> aliguori: ahh
16:33 < sleon> rharper, 2.0.4
16:34 < rharper> sleon: Xen version 3.0-devel <--- thats in my xm dmesg, you should see something in the 2.X range if you are testing or stable 
16:34 -!- Method [~Method@stanford.columbia.tresys.com] has quit [Ping timeout: 480 seconds]
16:34 < rharper> sleon: I believe that is stable
16:34 < sleon> rharper, where should i select CONFIG_SMP feature? by domU kernel?
16:34 < sleon> rharper, what prevents binary nvidia driver from working properly with xen?
16:34 < sleon> rharper, or do they work with unstable?
16:35 < cw> sleon: it probably can be made to work if it doesn't
16:35 < rharper> sleon: only with xen-unstable, yes, select CONFIG_SMP in the domU kernel config 
16:35 < sleon> cw, i get kernel panik on agp
16:35 -!- yuval [~yuval@line104-133.adsl.actcom.co.il] has joined #xen
16:35 < cw> sleon: with the recent agp fixes?
16:35 < sleon> cw, when i switch agp off,, and only use mtrr i get errors in the modules internal funktions
16:35 < rharper> sleon: not sure, the agp drivers have been troublesome because they execute priviledged instructions that xen might not emulate 
16:36 < sleon> guys
16:36 < sleon> as i say even without agp nvidia binary does not work
16:36 < sleon> i can search in chatlogs for exact error i get
16:36 < rharper> I didnt think the nvidia card works without an agp driver... 
16:36 < sleon> yes it does
16:37  * rharper learns new things all the time
16:37 < sleon> there is option: nvagp kernl agp or no agp
16:37 < sleon> i compiled kernel without agp
16:39 < sleon> rharper, i can load the module now
16:39 < sleon> it is laoded :))
16:39 < rharper> =)
16:39 < sleon> but as i said
16:39 < sleon> then when i really start X server with glx
16:39 < sleon> i get problems
16:40 < rharper> might email the list, Ian and the rest might be able to help you out.
16:40 < sleon> i try it again to reproduce an eror
16:40 < niv> eigood: was that nfs over udp or tcp?
16:40 < rharper> cool
16:40  * rharper bails for the social
16:41 < sleon> rharper, what is "social office"?
16:41 < sleon> (EE) NVIDIA(0): Failed to initialize the NVIDIA kernel module!
16:41 < sleon> (EE) NVIDIA(0):  *** Aborting ***
16:41 < sleon> (EE) Screen(s) found, but none have a usable configuration.
16:42 < sleon> moment i try to finish current X
16:42 < sleon> i am back in a minute
16:42 -!- sleon [test@p54A17B26.dip.t-dialin.net] has quit [Remote host closed the connection]
16:42 -!- yuval [~yuval@line104-133.adsl.actcom.co.il] has quit [Quit: Leaving]
16:46 -!- yuval [~yuval@line104-133.adsl.actcom.co.il] has joined #xen
16:47 -!- yuval [~yuval@line104-133.adsl.actcom.co.il] has quit [Quit: ]
16:47 < jonmason> anyone seeing a build break on xen-unstable (downloaded 20 minutes ago)
16:47 < jonmason> ../memory/libmemory.a(misc_mem.o)(.text+0x3fb): In function `bx_mem_c::init_memory(int)':
16:48 < jonmason> : undefined reference to `xc_get_pfn_list'
16:51 < jonmason> Is anyone else seeing this?
16:57 < jonmason> guess not
16:57 < jonmason> well, you were warned
16:57 < cw> jonmason: i just built it here w/o problems
16:57 < jonmason> really
16:58 < jonmason> I can't even get to the part where it downloads the linux kernel
16:58 < cw> gcc -v ?
16:59 < jonmason> gcc version 3.3.5  (Gentoo Linux 3.3.5-r1, ssp-3.3.2-3, pie-8.7.7.1)
16:59 < jonmason> I can run 2.0.5 w/o problems
16:59 -!- sleon|tuX [test@p54A17B26.dip.t-dialin.net] has joined #xen
16:59 < sleon|tuX> re
16:59 < cw> dunno, i just build xen and tools in the last minute w/o problems
17:00 < sleon|tuX> so i get simply a blank screen
17:00 < sleon|tuX> when i look at the Xorg log
17:00 < sleon|tuX> there is no problems seen
17:00 < sleon|tuX> it ends with lines alocated 16 bit framebuffer
17:00 < sleon|tuX> rharper: ideas?
17:00 < sleon|tuX> rharper: i have framebuffer device off
17:01 < sleon|tuX> in kernel
17:01 < jonmason> sleon|tuX: I think rharper stepped away from his desk
17:01 < sleon|tuX> jonmason: hmmm :((
17:01 < sleon|tuX> jonmason: for long time?
17:01 < jonmason> sleon|tuX: can be sure, free food in the cafeteria
17:02 < sleon|tuX> hrrhrhr
17:02 < sleon|tuX> jonmason: will he be in 15 minutes back=
17:02 < sleon|tuX> ?
17:02 < cw> jonmason: w/o more information it's hard to say ... check it's a clean clone of the tree
17:04 < sleon|tuX> is 3.x.x xen stable enough for running at home desktop?
17:05 < eigood> 5there is no 3.x.x xen(yet)
17:05 < eigood> s/^5//
17:05 < cw> -unstable calls itself 3
17:06 < eigood> is there any interest in a frontend/backend driver for vfs stuff?
17:06 < eigood> yes, I know you could use nfs, samba, coda, etc, but just for kicks, fun, and giggles
17:07 < eigood> a smart implementation could use page sharing/borrowing for speed
17:07 < cw> eigood: what do you mean? for shared fs access?
17:07 -!- matta-lt [~matta@69.93.28.254] has quit [Quit: If you are going to walk on thin ice, you may as well dance.]
17:07 -!- anthill333 [~larsr@palwebproxy2.core.hp.com] has joined #xen
17:07 < eigood> yes
17:08 < cw> nfs works for most people
17:08 < cw> beyond that there is lustre, gfs, ocfs2, cxfs, etc. if you wanted to put some effort into it
17:09 < sleon|tuX> pnfs
17:09 < sleon|tuX> :))
17:09 < eigood> lustre doesn't really support HA metadata nodes
17:09 < eigood> gfs looks like a pain to configure(haven't tried, but the docs don't make it sound simple)
17:09 < eigood> never heard of ocfs2 nor cxfs
17:10 < cw> eigood: why isn't nfs good enough for you?
17:10 < niv> eigood: talk to Mark W about XenFS
17:11 < eigood> cw: it'd just be an interesting experiment
17:11 < eigood> well, if dom0 was importing a large FS, reexporting that with nfs would be poor performance; all the data would be copied
17:11 < eigood> a smart XenFS would just do page sharing, which would be fast
17:11 < cw> sounds more like some gentoo-users desire to muck about and waste time to me :)
17:11 < eigood> cw: doing NIH can be a good way to learn a system
17:12 < cw> sure, a little research probably wouldn't hurt either though
17:15 -!- mon is now known as demon
17:16  * eigood reads about ocfs2
17:16 < eigood> not many docs
17:21 < eigood> ocfs2 was announced/released, then it looks like development disappeared
17:22 < eigood> is cxfs free?
17:23 < cw> nope
17:23 < cw> cxfs you get from sgi for $
17:25 < eigood> bah
17:25 < eigood> ocfs2 at least is gpl
17:25 < aliguori> nfs is kinda crappy as far as network file systems go
17:25 < aliguori> it's fast as heck but nfs < v3 has no security
17:25 < sleon|tuX> loool
17:25 < aliguori> plus, the posix semantics kill you.
17:25 < cw> jonmason: ok, i did a clean pull & build w/o problems here including letting it download, etc.
17:25 < aliguori> if we had a sharable fs in xen, it would be very nice to make it as posix-neutral as possible
17:26  * eigood hates bitkeeper
17:26 < eigood> my free software projects don't let me work with anything that uses bk
17:26 < cw> i hear they are accepting patches, im sure any contributed fs work wouldn't go amiss
17:26 < cw> eigood: there is a free bk-pull client thingy
17:26 < aliguori> eigood: there's an opensource bk client now
17:28 < eigood> I heard about that; didn't actually appear to really be open
17:28 < aliguori> turns out it's a very simple protocol
17:28 < eigood> I'm a dpkg developer; dpkg contains dpkg-source; this could be considered a revision control system; this matches the definition in the bk license
17:29 < aliguori> it took me about an hour to write my own client
17:30 < aliguori> but yeah, the bk licensing is a bit evil
17:34 < knewt> eigood: it is actually. the no whining license was just a joke. lm suggested bsd as the real one. i'm using it now which is probably a good thing cause i shouldn't really use the full thing
17:37 -!- homebaum [~michael@wbar1.sea1-4-5-031-104.sea1.dsl-verizon.net] has quit [Quit: Client exiting]
17:41 -!- DEac- [~deac@xdsl-213-196-203-102.netcologne.de] has quit [Ping timeout: 480 seconds]
17:45 -!- riel is now known as unriel
17:45 < unriel> rharper: aim7 seems to run well on the xenU domain
17:46 < unriel> rharper: (single cpu xenU domain though ...)
17:46  * unriel disappears
17:52 -!- mode/#xen [+oo unriel surriel] by cw
17:53 -!- DEac- [~deac@xdsl-81-173-160-118.netcologne.de] has joined #xen
18:17 -!- jeroney [~jeroney@pixpat.austin.ibm.com] has left #xen [Leaving]
18:18 < jonmason> cw: ya, it is clean.  might be my version of gcc
18:19 < cw> jonmason: gentoo right?
18:19 < jonmason> yup
18:19 < jonmason> I'm a bit of a gentoo whore
18:19 < cw> well, unless they have weird patches it doesn't (looking) at the version seem that weird
18:20 < cw> but for whatever reason(s) gentoo people get more than their fair-share of problems
18:20 < jonmason> of course
18:20 < jonmason> that's the fun of running gentoo
18:21 < sleon|tuX> what is aim7??
18:21 < sleon|tuX> unriel: 
18:24 < cw> aim7 is a benchmark/stress-test that's fairly popular for beating on kernels and machines
18:24 -!- hollis [~hollis@pixpat.austin.ibm.com] has quit [Quit: leaving]
18:25 < sleon|tuX> cw: like spec2000?
18:25 -!- surriel is now known as riel
18:25 < cw> sleon|tuX: not really, it's more useful to beat the crap out of a system and see if it breaks or if there are regression relative to kernel changes
18:25 < cw> and it's open
18:26 < sleon|tuX> cw: thank you good to know
18:26 < riel> very importantly, it's rediculously easy to start
18:27 < sleon|tuX> can it be used to dos systems?
18:27 < riel> and it can search for the "breaking point" all by itself
18:27 < cw> true... and change around, i used to chasing SHub IO bugs when i had a few hundred disks to play with
18:27 < cw> (and 64 cpus)
18:28 < riel> I just set it to go to crossover mode
18:28 < riel> if it survives that far, the kernel is probably robust ;)
18:28 < cw> riel: has anyone beaten xen on a 8x machine or thereabouts?
18:29 < riel> cw: dunno - but I certainly haven't
18:29 < aliguori> 8x?  gees, i don't think so
18:30 < aliguori> xen think pae's going to prevent that on must hardware
18:30 < aliguori> ah, s/xen/i/
18:30 < cw> eh? what?
18:30 < aliguori> and must=>most.. gees, i'm glad it's friday
18:30 < aliguori> most 8-way machines have > 4gb of memory
18:30 < eigood> muwahahaha
18:30  * eigood sends 4-1 mail
18:32 -!- rharper [~rharper@pixpat.austin.ibm.com] has quit [Quit: Leaving]
18:37 -!- niv [~niv@bi01p1.co.us.ibm.com] has left #xen []
18:43 < knewt> pleeeeeese say that the latest -dev post is an AFJ *g*
18:44 < sleon|tuX> does unstable crash only one time per day?
18:44 < eigood> knewt: who, me?
18:44 < knewt> well, /was/ the latest post. not any more
18:44 < eigood> mips2java really *does* exist
18:46 -!- shuri [sjnesjd@dsl.speedline209.226.electronicbox.net] has quit [Quit: ]
19:18 -!- sleon|tuX [test@p54A17B26.dip.t-dialin.net] has quit [Remote host closed the connection]
19:37 < Mark> eigood: my current project is a VFS level split driver
19:37 < Mark> sounds rather like what you're proposing
19:37 < Mark> i should probably stick some information up on the web somewhere
19:39 -!- shaleh [~shaleh@dsl017-044-048.sfo4.dsl.speakeasy.net] has joined #xen
19:42 -!- shaleh [~shaleh@dsl017-044-048.sfo4.dsl.speakeasy.net] has quit [Quit: ]
20:12 -!- Chang [~coffmant@cpe-24-93-161-148.neo.res.rr.com] has joined #xen
20:12 -!- niv [~Nivedita_@c-67-171-167-143.hsd1.or.comcast.net] has joined #xen
20:45 < caker> riel: no attachment on your last email, btw
20:46 < riel> that's corret
20:46 < riel> attachments are usually annoying
20:46 < caker> ahh, read it incorrectly -- nm :)
20:48 -!- griffinn [~griffinn@pcd584162.netvigator.com] has joined #xen
20:48 < mikegrb> caker: you are fired
20:48 < caker> mikegrb: who writes the checks?
20:49 < mikegrb> oh
20:49 < mikegrb> never mind then boss, as you were
20:49 < riel> luckily it only seems to happen when vcpus>cpus
20:50 < riel> so I can ship FC4 test2 xen this way, if there's no low risk fix
20:51  * cw wonders what's the largest initramfs image he can get away with
20:51 -!- LaidBack_01 [~jax@69.146.20.246] has quit [Quit: Leaving]
20:51 < caker> When running with vcpus > 1, the dom still runs on only one real cpu -- is that correct?
20:51 < eigood> cw: default limit(compile time option in kernel) is 4meg
20:59 -!- griffinn [~griffinn@pcd584162.netvigator.com] has left #xen []
21:04 -!- Chang [~coffmant@cpe-24-93-161-148.neo.res.rr.com] has left #xen []
21:11 < cw> eigood: for initramfs? it's also more about the bootloader than the kernel
21:11 < riel> caker: no
21:11 < riel> caker: I think the domain can get multiple CPUs
21:12 < riel> if you allow xen to spread te virtual cpus around
21:13 < eigood> oh, initramfs, no idea
21:13 < eigood> what I said was for initrd
21:47 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has joined #xen
22:08 -!- Davidh [~chatzilla@mail.messagegate.com] has joined #xen
22:10 -!- niv_ [~Nivedita_@c-67-171-167-143.hsd1.or.comcast.net] has joined #xen
22:12 -!- Davidh [~chatzilla@mail.messagegate.com] has left #xen []
22:13 -!- niv [~Nivedita_@c-67-171-167-143.hsd1.or.comcast.net] has quit [Read error: Operation timed out]
22:14 -!- plars [~plars@pixpat.austin.ibm.com] has quit [Ping timeout: 480 seconds]
22:23 -!- plars [~plars@pixpat.austin.ibm.com] has joined #xen
22:28 -!- Mark [~Mark@maw48.kings.cam.ac.uk] has quit [Remote host closed the connection]
22:49 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has quit [Quit: leaving]
22:59 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has joined #xen
23:24 -!- Chang [~coffmant@cpe-24-93-161-148.neo.res.rr.com] has joined #xen
--- Log closed Fri Apr 01 23:59:00 2005