--- Day changed

--- Log opened Mon Apr 18 23:59:02 2005
00:00 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has quit [Quit: leaving]
00:03 -!- N [~ca4bc809@webuser.thegrebs.com] has joined #xen
00:15 -!- rusty [~rusty@150.203.247.9] has quit [Ping timeout: 480 seconds]
00:27 -!- tierra [~tierra@dsl093-225-126.slc1.dsl.speakeasy.net] has quit [Quit: Everybody wants to go to heaven, but nobody wants to die.]
00:36 -!- monrad [~monrad@213083190130.sonofon.dk] has joined #xen
01:08 -!- rusty [~rusty@ppp219-83.lns2.syd3.internode.on.net] has joined #xen
01:27 -!- knewt [~jmb@zeus.pimb.org] has quit [Ping timeout: 480 seconds]
01:35 -!- knewt [~jmb@zeus.pimb.org] has joined #xen
02:18 -!- monrad [~monrad@213083190130.sonofon.dk] has quit [Read error: Operation timed out]
03:50 -!- deac [~deac@xdsl-195-14-219-144.netcologne.de] has quit [Ping timeout: 480 seconds]
03:59 -!- rusty [~rusty@ppp219-83.lns2.syd3.internode.on.net] has quit [Ping timeout: 480 seconds]
04:01 -!- deac [~deac@xdsl-213-196-199-92.netcologne.de] has joined #xen
04:05 -!- hebutterworth [~harry@blueice1n1.uk.ibm.com] has joined #xen
04:46 -!- athomas [~athomas@ppp-0-64.lond-a-4.access.uk.tiscali.com] has joined #xen
04:54 -!- muli [~muli@nesher3.haifa.il.ibm.com] has joined #xen
05:03 -!- N [~ca4bc809@webuser.thegrebs.com] has quit [Quit: http://thegrebs.com/oftc/ (Session timeout)]
05:15 -!- muli [~muli@nesher3.haifa.il.ibm.com] has quit [Ping timeout: 480 seconds]
06:32 -!- soffi [~soffi@Tolvudeild-SC-gw.vv.simnet.is] has joined #xen
07:46 -!- Beaky [~chatzilla@ncg-adsl.demon.co.uk] has joined #xen
07:46 -!- rene- [~crisen@spank.terdmonk.com] has quit [Quit: BitchX: often imitated, never duplicated!]
08:50 -!- N [~ca4bc809@webuser.thegrebs.com] has joined #xen
09:39 -!- unriel is now known as riel
09:43 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has joined #xen
09:44 -!- knewt [~jmb@zeus.pimb.org] has quit [Read error: Connection reset by peer]
09:45 -!- knewt [~jmb@zeus.pimb.org] has joined #xen
10:04 -!- soffi [~soffi@Tolvudeild-SC-gw.vv.simnet.is] has quit [Ping timeout: 480 seconds]
10:13 -!- matta-lt [~matta@69.93.28.254] has quit [Quit: Hey!  Where'd my controlling terminal go?]
10:15 -!- gyver [~gyver@adsl.bouton.name] has joined #xen
10:17 -!- gyver [~gyver@adsl.bouton.name] has quit [Quit: ]
10:19 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has quit [Quit: leaving]
10:20 -!- rharper [~rharper@pixpat.austin.ibm.com] has joined #xen
10:30 -!- knewt [~jmb@zeus.pimb.org] has quit [Ping timeout: 480 seconds]
10:41 -!- hbaum [~hbaum@bi01p1.co.us.ibm.com] has joined #xen
10:45 -!- knewt [~jmb@zeus.pimb.org] has joined #xen
11:04 -!- hollis [~hollis@pixpat.austin.ibm.com] has joined #xen
11:22 -!- cfreak [cfreak@dsl-084-056-099-139.arcor-ip.net] has joined #xen
11:28 -!- Jd0gg [Jdogg@c-24-1-174-133.hsd1.tx.comcast.net] has joined #xen
11:28 -!- Jdogg [Jdogg@c-24-1-174-133.hsd1.tx.comcast.net] has quit [Read error: Connection reset by peer]
11:29 -!- Jd0gg is now known as Jdogg
11:44 -!- itamarjp [lualele@200-225-242-015-dynamic.idial.com.br] has joined #xen
11:48 -!- caffeineOverload [~bob@c-67-172-227-54.hsd1.ut.comcast.net] has joined #xen
11:50 -!- caffeineOverload [~bob@c-67-172-227-54.hsd1.ut.comcast.net] has left #xen []
11:54 -!- Beaky [~chatzilla@ncg-adsl.demon.co.uk] has quit [Remote host closed the connection]
11:58 -!- muli [~muli@alhambra.mulix.org] has joined #xen
12:13 -!- itamarjp [lualele@200-225-242-015-dynamic.idial.com.br] has quit [Ping timeout: 480 seconds]
12:22 -!- knewt [~jmb@zeus.pimb.org] has quit [Read error: Connection reset by peer]
12:33 -!- knewt [~jmb@zeus.pimb.org] has joined #xen
12:34 -!- nextime [~nextime@213-140-6-96.fastres.net] has quit [Quit: No windows for this server]
12:45 -!- wmarvel [~wmarvel@bi01p1.co.us.ibm.com] has joined #xen
12:47 < knewt> has acpi stuff been moved into dom0 in -unstable yet?
12:52 -!- knewt [~jmb@zeus.pimb.org] has quit [Quit: leaving]
12:58 -!- knewt [~jmb@zeus.pimb.org] has joined #xen
13:15 -!- athomas [~athomas@ppp-0-64.lond-a-4.access.uk.tiscali.com] has quit [Quit: Leaving]
14:25 -!- mael_ [~Mael@kali.tirnamban.org] has joined #xen
14:31 -!- wmarvel [~wmarvel@bi01p1.co.us.ibm.com] has quit [Quit: Leaving]
14:37 -!- tierra [~tierra@dsl093-225-126.slc1.dsl.speakeasy.net] has joined #xen
14:44 -!- Jdogg [Jdogg@c-24-1-174-133.hsd1.tx.comcast.net] has quit [Read error: Connection reset by peer]
14:45 -!- Jdogg [~My@c-24-1-174-133.hsd1.tx.comcast.net] has joined #xen
15:12 -!- rharper [~rharper@pixpat.austin.ibm.com] has quit [Read error: Connection reset by peer]
15:26 -!- rharper [~rharper@pixpat.austin.ibm.com] has joined #xen
15:38 -!- niv [~nivedita@c-67-171-167-143.hsd1.or.comcast.net] has joined #xen
15:44 -!- cw [cw@adsl-67-124-119-21.dsl.snfc21.pacbell.net] has joined #xen
15:44 -!- mode/#xen [+o cw] by ChanServ
15:50 -!- mael_ [~Mael@kali.tirnamban.org] has left #xen [Fermeture du client]
16:09 -!- lars||| [~ledj@3E6B804D.rev.stofanet.dk] has joined #xen
16:23 -!- cfreak [cfreak@dsl-084-056-099-139.arcor-ip.net] has quit [Quit: .]
16:33 -!- lars||| [~ledj@3E6B804D.rev.stofanet.dk] has quit [Quit: using sirc version 2.211+KSIRC/1.3.11]
16:45 -!- Shaun [~ndci@ip68-111-70-41.oc.oc.cox.net] has joined #xen
16:53 -!- deac [~deac@xdsl-213-196-199-92.netcologne.de] has quit [Ping timeout: 480 seconds]
17:04 -!- deac [~deac@xdsl-84-44-215-62.netcologne.de] has joined #xen
17:46 -!- yarihm [~yarihm@80-218-3-32.dclient.hispeed.ch] has joined #xen
18:08 -!- niv [~nivedita@c-67-171-167-143.hsd1.or.comcast.net] has quit [Quit: Quitting]
18:14 -!- tierra|w_ [~tierra@dsl093-225-126.slc1.dsl.speakeasy.net] has joined #xen
18:14 -!- tierra [~tierra@dsl093-225-126.slc1.dsl.speakeasy.net] has quit [Read error: Connection reset by peer]
18:18 -!- riel is now known as unriel
18:24 -!- hollis [~hollis@pixpat.austin.ibm.com] has quit [Quit: leaving]
18:27 -!- hbaum [~hbaum@bi01p1.co.us.ibm.com] has quit [Quit: Client exiting]
18:53 -!- yarihm [~yarihm@80-218-3-32.dclient.hispeed.ch] has quit [Quit: Leaving]
18:57 -!- homebaum [~michael@wbar1.sea1-4-5-031-104.sea1.dsl-verizon.net] has joined #xen
19:07 -!- N [~ca4bc809@webuser.thegrebs.com] has quit [Quit: http://thegrebs.com/oftc/ (Session timeout)]
19:17 -!- lilo [~lilo@lilo.usercloak.oftc.net] has quit [Read error: Operation timed out]
19:21 -!- rharper [~rharper@pixpat.austin.ibm.com] has quit [Quit: Leaving]
19:57 -!- Jdogg [~My@c-24-1-174-133.hsd1.tx.comcast.net] has quit [Ping timeout: 480 seconds]
19:57 -!- itamarjp [lualele@200-225-242-004-dynamic.idial.com.br] has joined #xen
20:36 -!- tierra|w_ is now known as tierra
20:37 -!- matta [~matta@69.93.28.254] has quit [Quit: Sphinx may be image of a failed attempt to cross humans with lions.]
20:49 -!- matta [~matta@69.93.28.254] has joined #xen
20:49 -!- lilo [~lilo@lilo.usercloak.oftc.net] has joined #xen
20:56 -!- lilo [~lilo@lilo.usercloak.oftc.net] has quit [Quit: bbiab]
21:01 -!- lilo [~lilo@lilo.usercloak.oftc.net] has joined #xen
21:17 -!- anthony_ [~anthony@cpe-70-112-81-91.austin.res.rr.com] has joined #xen
21:17 -!- anthony_ is now known as aliguori_
21:18 < matta> aliguori_: you actually here?
21:19 < aliguori_> matta: I am
21:20 < matta> aliguori_: recommendation for vm-tools... right now it seems to only go by 'Domain-id' and 'id' for naming conventions
21:20 < matta> note a lot of people specifically name their vm's
21:21 < matta> so tasks such as 'vm list' should also print out the name given to the VM
21:21 < matta> this is 0.0.3 i'm using here so sorry if that was already addressed
21:21 < aliguori_> matta: that's a great suggestion but a bit more involved then it would appear
21:21 < aliguori_> but it's being addressed :-)
21:21 < aliguori_> we're working on a very big update to vm-tools that should be coming out within the next couple of weeks
21:21 < matta> [root@vm3 ~]# vm list | grep 20
21:21 < matta>         Domain-20       --b---  31MB    32MB
21:21 < matta> [root@vm3 ~]# xm li | grep 20
21:21 < matta> jamesn            20       31    1  -b---    138.4    9620
21:21 < aliguori_> indeed
21:22 < matta> oh yeah?
21:22 < aliguori_> the hypervisor doesn't have any concept of names
21:22 < aliguori_> only IDs
21:22 < matta> ok
21:22 < aliguori_> Xend maintains an ID=>name mapping
21:22 < matta> so it's xend that is keeping track of the names
21:22 < matta> gotcha
21:22 < matta> ok, explains why it's not as trivial as it seems
21:22 < aliguori_> we don't because we're distributed.. they're no central daemon
21:22 < aliguori_> the update is creating a very minimal central daemon which will allow us to keep track of that sort of stuff
21:23 < matta> is it written in C?
21:23 < aliguori_> yes
21:23 < matta> awsome
21:23 < aliguori_> it will also replace xcs
21:23 < matta> python is PITA
21:23 < matta> which I assume is your drive behind the vm-tools...
21:23 < aliguori_> so it'll be an overall reduction of daemon code
21:23 -!- itamarjp [lualele@200-225-242-004-dynamic.idial.com.br] has quit [Quit: ]
21:23 < aliguori_> yes
21:23 < aliguori_> it's one of them
21:23 < matta> another is easy direct API hooks?
21:24 < aliguori_> yes
21:24 < matta> via libxen
21:24 < matta> ok, i'll keep an eye out for the updates
21:24 < matta> I run only one server with -unstable so I can test stuff like vm-tools
21:24 < matta> but is enough to gain a feel for what is going on in unstable land
21:24 < aliguori_> we're actually looking to backport to 2.0.x in the very near future...
21:24 < matta> yeah?
21:25 < aliguori_> yeah, i'm working on it as we speak
21:25 < aliguori_> :-)
21:25 < matta> this will be part of the next release?
21:25 < matta> which you say will be in the next week or two?
21:25 < aliguori_> it's a low-priority feature for the next week
21:25 < aliguori_> that's the plan
21:25 < aliguori_> next release*
21:25 < aliguori_> and yes, the plan is for another release in the next week or two
21:26 -!- N [~ca4bc809@webuser.thegrebs.com] has joined #xen
21:26 < aliguori_> we're also now using libxen instead of libxc.. which makes the error paths much much better
21:26 < matta> cool, i'll keep an eye out... bye xend
21:26 < aliguori_> so the next release will be considerably more robust
21:26 < matta> heh, I find it increasingly difficult to get meaningful errors from xend on some issues
21:26 < matta> I sometimes experience the problem where it has the <name> as an id and then also Domain-id as id
21:26 < aliguori_> yes.  it's not just meaningful errors, xend just plan ignores a number of error conditions
21:26 < aliguori_> yes
21:26 < matta> so basically the same VM is using double the memory
21:27 < aliguori_> i do too
21:27 < matta> I think that is due to xend
21:27 < matta> not exactly yhe hypervisor
21:27 < matta> is that what you think?
21:27 < aliguori_> vm-tools shows it properly though :-)
21:27 < aliguori_> when xend is doing that
21:27 < aliguori_> it must be caching results or something..
21:27 < matta> hrm
21:27 < aliguori_> yes, it's xend, b/c i run xend and vm-tools in parallel and vm-list shows the right thing
21:27 < aliguori_> think*
21:27 < matta> that explains why xm info shows memory usage change when I kill off id and then start up the domain again
21:28 < matta> it's not actual memory being adjusted, but just what xend things is available
21:28 < matta> er, thinks
21:28 < aliguori_> probably
21:28 < matta> lol
21:28 < aliguori_> xend is a bit mysterous
21:28 < aliguori_> it's not very easy to groke through the code to figure out what its doing
21:28 < matta> i'm still not sure, python is foreign to me
21:28 < matta> I know a bit of C since it's what I started on
21:28 < aliguori_> i thought i was comfortable with python until i actually looked at xend
21:28 < matta> but i'm a perl monkey :(
21:29 < aliguori_> :-)
21:29 < aliguori_> the multiple tools design of xend is specifically for perl and shell monkeys :-)
21:29 < matta> at least with c programs I know how to use gdb and friends to find line numbers/files/etc
21:30 < aliguori_> yeah, well, my constant argument is that xend requires bindings to the hypervisor which take over 3,000 lines of C code to write.. vm-tools is under 2,000 lines of C
21:30 < matta> nice
21:30 < aliguori_> so I cannot understand why python is even considered as an option
21:30 < matta> and then the starting of xend when domains are running
21:30 < aliguori_> since it requires more C code than C...
21:30 < matta> the xend memory growing issue
21:30 < matta> vm-tools seems more and more attractive
21:31 < matta> ok I gotta jet now... good to know vm-tools is making progress :)
21:32 < matta> since next version will support 2.x i'm sure it will gain more testers 
21:32 < aliguori_> matta: thanks :-)
21:32 < matta> the backward compatibility with xm (via vm) is a nice touch
21:32 < matta> makes switching little more than changing the command (or creating a symlink)
21:32 < matta> anyhow, away for now
21:32 < matta> later.
21:35 < aliguori_> cya
21:42 -!- alx_ [foobar@213-152-38-2.dsl.eclipse.net.uk] has quit [Ping timeout: 480 seconds]
22:02 < caker> http://www.theshore.net/~caker/xen/host27.linode.com-memory-week.png <-- xend memory usage fun
22:02  * surriel is very frustrated with the VDSO changes
22:02 < surriel> still haven't gotten xen0 to run without 'vdso=0'
22:05 -!- aliguori- [~anthony@cpe-70-112-81-91.austin.res.rr.com] has joined #xen
22:05 -!- aliguori_ [~anthony@cpe-70-112-81-91.austin.res.rr.com] has quit [Read error: Connection reset by peer]
22:05 < aliguori-> wow, i just crashed xen really hard
22:13 -!- aliguori_ [~anthony@cpe-70-112-81-91.austin.res.rr.com] has joined #xen
22:13 -!- aliguori- [~anthony@cpe-70-112-81-91.austin.res.rr.com] has quit [Read error: Connection reset by peer]
22:13 < aliguori_> man, i seem to bring out the worst in xen
22:14 -!- aliguori_ [~anthony@cpe-70-112-81-91.austin.res.rr.com] has quit [Remote host closed the connection]
22:15 -!- homebaum [~michael@wbar1.sea1-4-5-031-104.sea1.dsl-verizon.net] has quit [Quit: Client exiting]
22:20 -!- anthony [~anthony@cpe-70-112-81-91.austin.res.rr.com] has joined #xen
22:20 -!- anthony is now known as aliguori-
22:23 < aliguori-> does anyone here have an opinion about using syslog in vm-tools?
22:24 < surriel> that may be useful in some situations
22:24 < surriel> but I'd keep it optional
22:24 < aliguori-> and have the option to just store to a flat file?
22:24 < surriel> yes
22:24 < aliguori-> yeah, that's not a bad idea..
22:25 < surriel> often it's easier to have a separate file per daemon
22:25 < aliguori-> are there any syslog demultiplexers or something?
22:25 < surriel> especially when you want to debug something
22:25 < surriel> I don't know
22:25 < aliguori-> gentoo comes with like three different syslog daemons..
22:27 < surriel> I consider that an argument in favor of per-daemon log files
22:27 < aliguori-> yeah, i'm coding up the option right now.
22:27 < surriel> after all, if any of the syslog daemons did the right thing, there wouldn't be a need for the other two
22:27 < aliguori-> syslog let's you do remote logging.. which is cool enough to support it
22:27 < surriel> absolutely
22:28  * surriel would probably use syslog on production systems, flat files on development systems
22:29 < aliguori-> yeah, i'll make it a command line option...
22:31  * mikegrb commands surriel's line
22:31 < surriel> better yet, a config file option ;)
22:32 < aliguori-> ewwww
22:32 < aliguori-> no
22:32 < aliguori-> :-)
22:32  * aliguori- hates config files
22:32 < aliguori-> besides, there's only logging in the long-running daemon
22:33 < surriel> oh ok, then /etc/sysconfig/xen works ;)
22:33 < aliguori-> heh, you silly redhat guys with your sysconfig stuff :-)
22:34 < surriel> hehe
22:34 < aliguori-> actually, i like it a lot..  that's why i want to keep everything command line..
22:34 < matta> surriel: http://xen.bkbits.net:8080/xen-2.0-testing.bk/cset@1.1827?nav=index.html|ChangeSet@-7d
22:34 < matta> that's for -testing, but might want to find the commit of it for -unstable and consider at least applying that patch to your FC4 RPM's
22:35  * surriel looks
22:35 < surriel> I'll just upgrade to the latest nightly snapshot
22:35 < surriel> there's no reason to not do that
22:36 < matta> yeah, commits have been slow lately
22:36 < matta> nothing big, mainly bugfixes
22:36 -!- Jdogg [Jdogg@c-24-1-174-133.hsd1.tx.comcast.net] has joined #xen
22:36 < matta> All domains terminated
22:36 < matta>  All domains terminated
22:36 < matta>  /etc/init.d/xendomains: line 38: log_success_msg: command not found
22:36 < matta> hrm
22:37 -!- hollis [~hollis@user-0vvde2g.cable.mindspring.com] has joined #xen
22:38 < aliguori-> matta: are you on a non-lsb compliant distro?
22:38 < matta> FC3
22:38 < aliguori-> log_success_msg is an lsb command.
22:38 < aliguori-> oh, that's not right :-)
22:38 < matta> ahhhh
22:38 < aliguori-> it should be aliased in /lib/lsb/init-functions
22:39 < aliguori-> perhaps you're missing a source /lib/lsb/init-functions?
22:42 < matta> it exists
22:42 < matta> i'll have to look at that later, minor error
22:43 < matta> i'm still quite amazed at how well xen's QoS works
22:43 < matta> even starting 50 VM's on boot dom0 is barely lagged
22:46 < aliguori-> :-)
22:49 < matta> surriel: http://xen.bkbits.net:8080/xeno-unstable.bk/cset@1.1159.256.93?nav=index.html|ChangeSet@-7d
22:52 < caker> matta: which QoS are you talking about -- afaik, there's no disk QoS yet
22:54 < matta> sure there is, didn't you read the white paper?  it's in a primitive state
22:54 < matta> unless it was removed in 2.0, which afaik it was not
22:55 < caker> hmm .. are there any knobs to tweak, or just a default fairness type o deal
22:55 < aliguori-> no
22:55 < caker> in 2.0 and 2.1, I can starve other domains fairly easily
22:55 < matta> from an early post
22:55 < aliguori-> er, sorry, wrong window
22:55 < matta>  4) I/O QoS - This is just round robin for now?  I see it on the
22:55 < matta> > roadmap.  I have already envisioned the scenario with someone purchasing
22:55 < matta> > a server with 64MB physical ram and adding a 512MB swap file inside
22:55 < matta> > their server and just completely thrashing the disks.  Is the current
22:55 < matta> > system good enough to handle this (assuming some good SCSI disks are
22:55 < matta> > being used) ?
22:56 < matta> to which Mark W replied
22:56 < matta> For network, you should be able to use any standard Linux QoS tools you want.  
22:56 < matta> For block IO, the requests are batched and serviced in a round robin fashion.  
22:56 < matta> This (obviously) doesn't provide service differentiation, or accounting.  I 
22:56 < matta> think this is still on the roadmap and would certainly be cool to have.
22:56 < caker> right
22:58 < matta> well, it is better than nothing
22:59 < matta> in my experience it does the job well
22:59 < matta> just need to iron out the last little stability quirks of xen
22:59 < caker> like what?
23:00 < matta> I fix em or report em as I find em
23:01 < matta> people need to take the plunge and put xen out in the open or else they won't be found, test suites will only do so much
23:23 -!- itamarjp [lualele@200-225-242-004-dynamic.idial.com.br] has joined #xen
23:23 -!- aliguori- [~anthony@cpe-70-112-81-91.austin.res.rr.com] has quit [Remote host closed the connection]
23:33 -!- itamarjp [lualele@200-225-242-004-dynamic.idial.com.br] has quit [Quit: ]
23:43 -!- JViz [Anomaly@cpe-024-163-002-218.triad.res.rr.com] has quit [Ping timeout: 480 seconds]
--- Log closed Tue Apr 19 23:59:00 2005