| --- | Log | opened Fri Apr 01 00:00:39 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 | --- | User: *** 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 | --- | User: *** demon is now known as mon |
| 09:41 | --- | User: *** 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 | --- | Channel: 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 :) |
| 13:04 | @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) |
| 13:43 | 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 | --- | Channel: 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 | @cw | eigood: depends what you are doing, for some things the uml overhead is *way* more and sometimes a fiar bit less |
| 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 | @cw | eigood: generally speaking though the uml overhead for most people is huge compared to xen |
| 16:13 | @cw | well, xen+balloon+vm-hacks might let you overcommit there in a sense, im not sure it's worth it |
| 16:14 | riel | rharper: backing up a few days? this is rawhide ... ;) |
| 16:14 | rharper | haha |
| 16:14 | sleon | eigood, how much ram do you have |
| 16:14 | eigood | sleon: we have an athlon xen, and a p4 xen; the later has hyperthreading |
| 16:14 | riel | I'm here to run into and fix bugs, not to avoid them |
| 16:14 | | * eigood notes xen+hyperthreading is a little stupid |
| 16:14 | riel | I'll leave avoiding bugs to users |
| 16:14 | riel | it's not a developer thing |
| 16:14 | eigood | hyperthreading is poor when 2 completely separate processes are running side-by-side |
| 16:14 | sleon | eigood, dual or simple? hype means 2 cpu are simualted |
| 16:14 | eigood | and 2 completely separate OSes will have nothing in common |
| 16:14 | rharper | riel: im running 20050401 snapshot as smp domU with constant kernel compiles... what were you running in domU? repeatable? |
| 16:14 | rharper | riel: happen on boot? |
| 16:14 | riel | yeah, happens on boot |
| 16:14 | riel | but ... with vcpus=3 |
| 16:14 | 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 | sleon | eigood, do they only have 4 gigs ram? |
| 16:14 | eigood | sleon: the p4 has 4g, the athlon has 1.5(the latter doesn't support more on the mobo) |
| 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 | --- | <<-- jimix [~jimix@ip13.194.susc.suscom.net] has quit (Quit: Download Gaim: http://gaim.sourceforge.net/) |
| 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 | --- | Netsplit xenon.oftc.net <-> oxygen.oftc.net quits: DEac-, rharper, LaidBack_01, jeroney, mael, Shaun, surriel, hollis, schweeb, muligone, (+9 more, use /NETSPLIT to show all of them) |
| 16:16 | --- | Netsplit xenon.oftc.net <-> oxygen.oftc.net quits: mon, muli, sleon, homebaum, sunny |
| 16:16 | --- | Netsplit xenon.oftc.net <-> oxygen.oftc.net quits: knewt, jonmason, JViz, riel, apw, Mark, aliguori |
| 16:17 | --- | Netsplit over, joins: schweeb, Nigelenki, Mark, homebaum, sleon, hollis, jeroney, rharper, matta-lt, DEac- (+21 more) |
| 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? |
| 16:23 | 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 |
| 16:31 | 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 | --- | User: *** 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 | --- | User: *** riel is now known as unriel |
| 17:46 | 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 | --- | Channel: mode/#xen [+oo unriel surriel] by cw |
| 17 |
![[FSF Associate Member]](/assets/fsf.png){kind=small}
