| --- | Log | opened Fri Mar 09 00:00:43 2007 |
| 00:05 | |-| | schultmc [~schultmc@zealot.progeny.com] has joined #xen |
| 00:27 | |-| | gthouvenin [~gthouveni@129.184.84.11] has quit [Quit: Leaving] |
| 00:29 | |-| | mastermind [~mastermin@mastermind.kaltenbrunner.cc] has quit [Quit: Client exiting] |
| 00:33 | |-| | paelzer [~kvirc@blueice4n1.de.ibm.com] has joined #xen |
| 00:53 | |-| | gthouvenin [~guill@129.184.84.11] has joined #xen |
| 00:56 | |-| | gthouvenin [~guill@129.184.84.11] has quit [Remote host closed the connection] |
| 01:11 | |-| | mejlholm|uni [~mejlholm@optiplex19.cs.aau.dk] has joined #xen |
| 01:26 | |-| | gthouvenin [~gthouveni@129.184.84.11] has joined #xen |
| 01:28 | |-| | DoberMann_ changed nick to DoberMann |
| 01:51 | |-| | DavidS [~david@chello062178045213.16.11.tuwien.teleweb.at] has joined #xen |
| 01:57 | |-| | Shaun2222 [~shaun@ip68-4-212-221.oc.oc.cox.net] has joined #xen |
| 02:33 | |-| | visik7 [~visi@host180-35.pool80183.interbusiness.it] has joined #xen |
| 02:35 | |-| | DoberMann changed nick to DoberMann[PullA] |
| 02:47 | |-| | Crypticfortune [~krisp@gw.dna.bio.keio.ac.jp] has joined #xen |
| 02:49 | <Crypticfortune> | ack. i have a japanese keyboard layout but while running VNC to the guest windows domU stuff gets sent by the US keyboard layout =( |
| 02:51 | <Crypticfortune> | setting the windows keyboard layout to windows causes all sorts of crazy stuff to happen. half the keys work, half of them don't. very strange. |
| 02:51 | <Crypticfortune> | er sorry: s/layout to windows/layout to japanese/p |
| 03:01 | |-| | weasel [weasel@asteria.debian.or.at] has joined #xen |
| 03:06 | |-| | DavidS [~david@chello062178045213.16.11.tuwien.teleweb.at] has quit [Quit: Leaving.] |
| 03:13 | |-| | vivierl [~vivierl@129.184.84.11] has joined #xen |
| 03:14 | |-| | vivierl [~vivierl@129.184.84.11] has left #xen [] |
| 03:15 | |-| | vivierl [~vivierl@129.184.84.11] has joined #xen |
| 03:18 | |-| | DoberMann[PullA] changed nick to DoberMann |
| 03:48 | |-| | visik7 [~visi@host180-35.pool80183.interbusiness.it] has quit [Remote host closed the connection] |
| 03:48 | |-| | visik7 [~visi@host180-35.pool80183.interbusiness.it] has joined #xen |
| 03:53 | |-| | sputhenp [~sputhenp@202.80.58.210] has quit [Ping timeout: 480 seconds] |
| 04:02 | <Crypticfortune> | if i were to buy a cheap little sound card exclusively for use in a winxp HVM domU, that should (theoretically) work right? there's no weird stuff like needing xen aware drivers for an HVM domU right? |
| 04:02 | <Crypticfortune> | (this is i think the whole idea of HVM...but im new at this...) |
| 04:07 | |-| | Crypticfortune [~krisp@gw.dna.bio.keio.ac.jp] has left #xen [] |
| 04:23 | |-| | mejlholm|uni [~mejlholm@optiplex19.cs.aau.dk] has quit [Remote host closed the connection] |
| 04:43 | |-| | mcp [~hightower@wolk-project.de] has joined #xen |
| 05:00 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has joined #xen |
| 05:15 | <mcp> | I have a problem booting up xandros server with xen 3.0.3. there's no keyboard detected and unfortunately xandros boot prompt waits for a keypress :( |
| 05:22 | <matti> | Hi mcp. |
| 05:22 | |-| | sputhenp [~sputhenp@202.41.228.162] has joined #xen |
| 05:22 | <mcp> | hi matti |
| 05:46 | <hensema> | hmmm, I attempted a live migration on a domain, which aborted with "Error: /usr/lib64/xen/bin/xc_save 10 17 11 0 0 1 failed" |
| 05:46 | <hensema> | and now I'm stuck with a Zombie-$domainname in state ----cd |
| 05:47 | <hensema> | the zombie domain can't be destroyed :/ |
| 05:47 | <hensema> | I'd better reboot, I guess? |
| 05:50 | <hensema> | the target server said: |
| 05:50 | <hensema> | [2007-03-09 12:36:41 xend][2007-03-09 12:36:41 xend] ERROR (XendCheckpoint:230) xc_linux_restore start: max_pfn = 20800 |
| 05:50 | <hensema> | [2007-03-09 12:36:41 xend][2007-03-09 12:36:41 xend] ERROR (XendCheckpoint:230) Increased domain reservation by 82000 KB |
| 05:50 | <hensema> | [2007-03-09 12:36:41 xend][2007-03-09 12:36:41 xend] ERROR (XendCheckpoint:230) Reloading memory pages: 0% |
| 05:50 | <hensema> | [2007-03-09 12:36:42 xend][2007-03-09 12:36:42 xend] ERROR (XendCheckpoint:230) Error when reading batch size: 0 |
| 05:50 | <hensema> | [2007-03-09 12:36:42 xend][2007-03-09 12:36:42 xend] ERROR (XendCheckpoint:230) Restore exit with rc=1 |
| 06:05 | |-| | bernarde [~bernarde@32.104.18.240] has joined #xen |
| 06:20 | |-| | mejlholm|uni [~mejlholm@optiplex19.cs.aau.dk] has joined #xen |
| 06:28 | |-| | jimix [~jimix@c-67-189-187-152.hsd1.ny.comcast.net] has joined #xen |
| 06:57 | |-| | mulix [~mulix@87.69.40.180.cable.012.net.il] has joined #xen |
| 07:22 | <hensema> | right, now I've got live migrations working in a production environment \o/ |
| 07:40 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has quit [Quit: Parti] |
| 07:50 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has joined #xen |
| 07:54 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has quit [Remote host closed the connection] |
| 08:02 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has joined #xen |
| 08:04 | |-| | visik7 [~visi@host180-35.pool80183.interbusiness.it] has quit [Read error: Connection reset by peer] |
| 08:06 | |-| | agrif_away changed nick to agriffis |
| 08:07 | |-| | hollisb [~hollisb@bi01p1.co.us.ibm.com] has joined #xen |
| 08:07 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has quit [Remote host closed the connection] |
| 08:08 | |-| | clalance [~clalance@nat-pool-bos.redhat.com] has joined #xen |
| 08:12 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has joined #xen |
| 08:18 | |-| | mdday [~mdday@cpe-024-163-122-235.nc.res.rr.com] has quit [Remote host closed the connection] |
| 08:19 | |-| | mdday [~mdday@cpe-024-163-122-235.nc.res.rr.com] has joined #xen |
| 08:29 | |-| | m0rg0th [~manugarg@220.225.228.97] has joined #xen |
| 08:37 | |-| | cableman [~cableman@3e6b3c0a.rev.stofanet.dk] has joined #xen |
| 08:38 | |-| | sputhenp [~sputhenp@202.41.228.162] has quit [Quit: Leaving] |
| 08:43 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 08:56 | |-| | surriel [~riel@74.92.59.66] has joined #xen |
| 08:58 | |-| | surriel changed nick to riel |
| 09:02 | |-| | agriffis changed nick to agrif_away |
| 09:03 | |-| | m0rg0th [~manugarg@220.225.228.97] has quit [Quit: Leaving] |
| 09:06 | |-| | gthouvenin [~gthouveni@129.184.84.11] has quit [Quit: Leaving] |
| 09:07 | |-| | paelzer [~kvirc@blueice4n1.de.ibm.com] has quit [Quit: KVIrc 3.2.0 'Realia'] |
| 09:16 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Ping timeout: 480 seconds] |
| 09:26 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 09:34 | |-| | michal` [~michal@www.rsbac.org] has quit [Ping timeout: 480 seconds] |
| 09:35 | |-| | rharper [~rharper@bi01p1.co.us.ibm.com] has joined #xen |
| 09:37 | |-| | mejlholm|uni [~mejlholm@optiplex19.cs.aau.dk] has quit [Quit: Leaving] |
| 09:41 | |-| | michal` [~michal@www.rsbac.org] has joined #xen |
| 10:00 | |-| | ahs3_away [~ahs3@156.153.254.66] has quit [Ping timeout: 480 seconds] |
| 10:09 | |-| | agrif_away changed nick to agriffis |
| 10:12 | |-| | aw [~awilliam@c-24-9-84-32.hsd1.co.comcast.net] has quit [Quit: Leaving] |
| 10:12 | |-| | danp1 [~berrange@nat-pool-bos.redhat.com] has joined #xen |
| 10:32 | |-| | aw [~awilliam@156.153.254.66] has joined #xen |
| 10:35 | |-| | sunnyDay [~sunnyDay@CBL217-132-99-176.bb.netvision.net.il] has joined #xen |
| 10:37 | |-| | mastermind [~mastermin@mastermind.kaltenbrunner.cc] has joined #xen |
| 10:43 | |-| | danp1 [~berrange@nat-pool-bos.redhat.com] has quit [Quit: Leaving.] |
| 10:43 | |-| | danp1 [~berrange@nat-pool-bos.redhat.com] has joined #xen |
| 10:48 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Ping timeout: 480 seconds] |
| 10:56 | <sunnyDay> | Does anybody know: when using bonding in Xen, should it be done in domain U ? or in dom0 ? |
| 10:57 | <murb> | sunnyDay: what are you trying to do? |
| 10:57 | <sunnyDay> | I have a machine with 2 nics |
| 10:58 | |-| | jerone [~jerone@bi01p1.co.us.ibm.com] has joined #xen |
| 10:58 | <sunnyDay> | I want to use bonding for better bandwidth |
| 10:58 | <murb> | sunnyDay: in dom0 most probably. |
| 10:58 | <murb> | unless you export the hardware to the domU |
| 10:59 | <sunnyDay> | murb, this is what I thought; because when I am in domU in that machine , ifconfig shows only eth0 |
| 10:59 | <sunnyDay> | and I think that even this etho is not real |
| 10:59 | <sunnyDay> | because modprbe.conf shows : alias eth0 xennet |
| 10:59 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 11:07 | |-| | danp1 [~berrange@nat-pool-bos.redhat.com] has quit [Quit: Leaving.] |
| 11:07 | <murb> | sunnyDay: it maybe possible to export both your physical interfaces to the domU. |
| 11:07 | |-| | danp1 [~berrange@nat-pool-bos.redhat.com] has joined #xen |
| 11:09 | <sunnyDay> | murb, how? |
| 11:18 | <murb> | sunnyDay: you tell xen what pci ids of the devices you want to export to a domU |
| 11:18 | <murb> | but i've not played with that since xen2 and a lot has changed since. |
| 11:19 | <sunnyDay> | murb, I think I remember I read something about pci-hiding in boot and picback ... |
| 11:19 | <murb> | if you are having more than one domU it will get very complicated. |
| 11:19 | |-| | tessier [~treed@adsl-75-5-99-178.dsl.sndg02.sbcglobal.net] has quit [Ping timeout: 480 seconds] |
| 11:20 | <icblenke> | the question is really "do you need too?". is bonding in dom0 enough to address your needs? |
| 11:20 | <sunnyDay> | I think that it is enough; just wondered what domu exporting is |
| 11:22 | <sunnyDay> | so in fact there is no difference between bonding in xen and bonding in non-xen machine ?? |
| 11:23 | <murb> | sunnyDay: no except the default xen networking stuff likes to takeover the real ethernet interfaces in dom0 |
| 11:23 | <sunnyDay> | I thought that when using bridging (the default) , than peth0 is the physical interface |
| 11:23 | <icblenke> | sunnyDay: renaming eth0 to peth0 is the default behavior of the network-bridge script, yes. |
| 11:24 | <sunnyDay> | so if I will have "SLAVE" in the ifcfg-eth it will do the job automatically? |
| 11:24 | <murb> | you should probably turn that stuff off. |
| 11:24 | <icblenke> | as for bonding, that's a linux kernel layer thing. though I have read issues in the past getting bonding to work under xenified kernels, as there were apparently some xen introduced driver issues in the past. |
| 11:24 | |-| | kurios [~nada@71-13-79-30.static.aldl.mi.charter.com] has joined #xen |
| 11:25 | |-| | icblenke [~icblenke@magic.skylab.org] has quit [Quit: Leaving] |
| 11:25 | <sunnyDay> | i remember |
| 11:25 | |-| | icblenke [~icblenke@magic.skylab.org] has joined #xen |
| 11:26 | <sunnyDay> | http://lists.xensource.com/archives/html/xen-users/2006-04/msg00186.html |
| 11:26 | <sunnyDay> | Re: [Xen-users] Bonding not working with network-bridge |
| 11:26 | |-| | stephan [~stephan@141.76.44.131] has joined #xen |
| 11:26 | <icblenke> | right. I believe that has been addressed, however. |
| 11:30 | |-| | tessier [~treed@adsl-75-5-99-178.dsl.sndg02.sbcglobal.net] has joined #xen |
| 11:32 | |-| | kurios [~nada@71-13-79-30.static.aldl.mi.charter.com] has quit [Ping timeout: 480 seconds] |
| 11:32 | |-| | DoberMann changed nick to DoberMann[PullA] |
| 11:37 | |-| | danp1 [~berrange@nat-pool-bos.redhat.com] has quit [Ping timeout: 480 seconds] |
| 11:57 | |-| | sunnyDay [~sunnyDay@CBL217-132-99-176.bb.netvision.net.il] has quit [Quit: Leaving] |
| 12:02 | |-| | DoberMann[PullA] changed nick to DoberMann |
| 12:05 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Quit: Leaving] |
| 12:32 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 12:36 | |-| | Basic_java [~Basic@warden.real-time.com] has quit [Quit: Leaving] |
| 12:45 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Ping timeout: 480 seconds] |
| 12:46 | |-| | KriP [kp@yancey.unixworld.dk] has joined #xen |
| 12:48 | |-| | aliguori [~anthony@cpe-72-179-63-62.austin.res.rr.com] has quit [Quit: Leaving] |
| 12:54 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 13:05 | |-| | aliguori [~anthony@bi01p1.co.us.ibm.com] has joined #xen |
| 13:30 | |-| | mejlholm [~mejlholm@port79.ds1-abc.adsl.cybercity.dk] has joined #xen |
| 13:39 | |-| | agriffis changed nick to agrif_away |
| 13:39 | |-| | KriP [kp@yancey.unixworld.dk] has quit [Read error: Connection reset by peer] |
| 13:43 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Ping timeout: 480 seconds] |
| 13:48 | |-| | jimix [~jimix@c-67-189-187-152.hsd1.ny.comcast.net] has quit [Quit: jimix] |
| 13:52 | |-| | Basic_py [~Basic@gatekeeper.real-time.com] has joined #xen |
| 13:53 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 14:16 | |-| | agrif_away changed nick to agriffis |
| 14:27 | |-| | visik7 [~visi@host96-108-dynamic.56-82-r.retail.telecomitalia.it] has joined #xen |
| 14:43 | |-| | visik7 [~visi@host96-108-dynamic.56-82-r.retail.telecomitalia.it] has quit [Ping timeout: 480 seconds] |
| 14:53 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Ping timeout: 480 seconds] |
| 14:59 | |-| | visik7 [~visi@host96-108-dynamic.56-82-r.retail.telecomitalia.it] has joined #xen |
| 15:02 | |-| | bernarde [~bernarde@32.104.18.240] has quit [Remote host closed the connection] |
| 15:03 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has joined #xen |
| 15:03 | |-| | dykman [~dykman@bi-02pt1.bluebird.ibm.com] has quit [Ping timeout: 480 seconds] |
| 15:04 | |-| | stephan [~stephan@141.76.44.131] has quit [Read error: No route to host] |
| 15:11 | |-| | DoberMann changed nick to DoberMann[ZZZzzz] |
| 15:13 | |-| | dykman [~dykman@bi-02pt1.bluebird.ibm.com] has joined #xen |
| 15:32 | |-| | cableman [~cableman@3e6b3c0a.rev.stofanet.dk] has quit [Quit: Leaving] |
| 15:43 | <hollisb> | hey brendan, do you know how I set XENFEAT_auto_translated_physmap ? looks like I need a new ELF note segment? |
| 15:45 | <brendan> | you don't have a XEN_ELFNOTE_FEATURES section? |
| 15:45 | <brendan> | i386 uses an ELFNOTE macro to create those bits |
| 15:46 | <hollisb> | I don't think we do |
| 15:46 | <brendan> | in head-xen.s |
| 15:46 | <brendan> | .S |
| 15:46 | |-| | visik7 [~visi@host96-108-dynamic.56-82-r.retail.telecomitalia.it] has quit [Ping timeout: 480 seconds] |
| 15:48 | <hollisb> | are those bits described somewhere? |
| 15:48 | <hollisb> | I'm confused by dom->shadow_enabled vs xc_dom_feature_translated() |
| 15:50 | <brendan> | er, I don't think they are. |
| 15:50 | <hollisb> | awesome |
| 15:51 | <brendan> | and I don't know what auto_translated_physmap does |
| 15:51 | <hollisb> | I *think* that means that guests always use pfns |
| 15:52 | <hollisb> | whereas dom->shadow_enabled means dom0 uses pfns to access domU |
| 15:52 | <hollisb> | but that latter doesn't really make sense, so I don't know |
| 15:53 | <brendan> | er, shadow_enabled means xen's managing shadow page tables, right? |
| 15:53 | <brendan> | tbh I never got clean on the distinction between gmfn and mfn. I should be trying to figure that stuff out now actually :) |
| 15:54 | <hollisb> | :) |
| 15:55 | <hollisb> | http://wiki.xensource.com/xenwiki/XenTerminology explains gmfn |
| 15:57 | <brendan> | hmm yeah, I never use auto-translated. What's it for? |
| 15:58 | <hollisb> | I think it's for domains that communicate via GPFNs rather than MFNs |
| 15:58 | <hollisb> | (where traditional x86 domains only do MFNs) |
| 15:58 | <brendan> | but why do they need to do that? |
| 15:58 | <hollisb> | well, that's how PowerPC and IA64 domU work |
| 15:59 | <hollisb> | I'm not sure if there's an auto-translate mode for x86 domains |
| 15:59 | <hollisb> | HVM works like that of course, but I don't know how the ELF feature would apply there |
| 15:59 | <hollisb> | I guess honestly I don't know how this feature applies at all |
| 16:00 | <riel> | probably some legacy thing from Xen 1 or 2 |
| 16:00 | <riel> | haven't seen any code for it in Xen 3 |
| 16:07 | <hollisb> | rharper: btw, did you see that terminology URL above? you mentioned gmfns recently too |
| 16:07 | <aliguori> | auto_translated_physmap is for ia64 |
| 16:08 | <hollisb> | aliguori: well what does it do? because ia64 domU work like PPC domU |
| 16:09 | <aliguori> | hollisb: i thought that ia64 didn't ever expose mfn's to the guest |
| 16:09 | <hollisb> | right, and neither does PPC |
| 16:09 | <aliguori> | okay |
| 16:10 | <hollisb> | actually they do expose MFNs to dom0 (I think) |
| 16:10 | <hollisb> | PPC will be doing that soon |
| 16:10 | <aliguori> | yeah |
| 16:10 | <aliguori> | there dom0's and domU's work differently |
| 16:10 | <hollisb> | so that still leaves me with the question: do I need to set this feature? |
| 16:11 | <aliguori> | hollisb: quite a lot of xenolinux code depends on it |
| 16:11 | <aliguori> | for instance, the netfront driver behaves differently if it's set |
| 16:12 | <hollisb> | hmmm |
| 16:12 | <hollisb> | the netfront driver already works for us |
| 16:12 | <hollisb> | so I guess I don't need it then? |
| 16:12 | <aliguori> | hollisb: probably not |
| 16:12 | <aliguori> | the other suspects are balloon and blktap |
| 16:13 | <aliguori> | i'm not sure why blktap |
| 16:19 | |-| | KriP [kp@yancey.unixworld.dk] has joined #xen |
| 16:19 | <rharper> | hollisb: I've seen that url, but not since I've started talking about gmfns |
| 16:19 | [~] | rharper checks it out |
| 16:30 | <mejlholm> | hollisb, set features = 'auto_translated_physmap' in your domain config |
| 16:31 | <hollisb> | mejlholm: ah, neat, ok |
| 16:31 | <mejlholm> | x86 domains work as well |
| 16:32 | <hollisb> | x86 domains don't do the p2m translation then? |
| 16:33 | <mejlholm> | normally they do, but not with translated mode |
| 16:33 | <hollisb> | yeah |
| 16:33 | <hollisb> | ok, thanks |
| 16:33 | <mejlholm> | :) np |
| 16:36 | |-| | jerone [~jerone@bi01p1.co.us.ibm.com] has quit [Quit: jerone] |
| 16:49 | |-| | mejlholm [~mejlholm@port79.ds1-abc.adsl.cybercity.dk] has quit [Quit: Leaving] |
| 16:53 | |-| | kalden [~kalden@fac34-3-82-231-26-11.fbx.proxad.net] has quit [Ping timeout: 480 seconds] |
| 16:55 | |-| | aliguori [~anthony@bi01p1.co.us.ibm.com] has quit [Remote host closed the connection] |
| 16:56 | |-| | aliguori [~anthony@bi01p1.co.us.ibm.com] has joined #xen |
| 17:00 | |-| | clalance [~clalance@nat-pool-bos.redhat.com] has quit [Quit: Leaving] |
| 17:24 | |-| | aliguori [~anthony@bi01p1.co.us.ibm.com] has quit [Quit: Leaving] |
| 17:25 | |-| | aw [~awilliam@156.153.254.66] has quit [Quit: Leaving] |
| 17:32 | |-| | rharper [~rharper@bi01p1.co.us.ibm.com] has quit [Quit: Leaving] |
| 17:55 | |-| | aw [~awilliam@c-24-9-84-32.hsd1.co.comcast.net] has joined #xen |
| 17:57 | |-| | aliguori [~anthony@cpe-72-179-63-62.austin.res.rr.com] has joined #xen |
| 17:57 | |-| | bestorga [~bestorga@rchp4.rochester.ibm.com] has quit [Quit: Leaving] |
| 18:07 | |-| | aliguori [~anthony@cpe-72-179-63-62.austin.res.rr.com] has quit [Read error: Connection reset by peer] |
| 18:08 | |-| | aliguori_ [~anthony@cpe-72-179-63-62.austin.res.rr.com] has joined #xen |
| 18:09 | |-| | dansmith [~dan@gw0.danplanet.com] has quit [Remote host closed the connection] |
| 18:10 | |-| | hollisb [~hollisb@bi01p1.co.us.ibm.com] has quit [Quit: leaving] |
| 18:17 | |-| | KriP [kp@yancey.unixworld.dk] has quit [Read error: Connection reset by peer] |
| 18:29 | |-| | pvanhoof [~pvanhoof@d54C0EE14.access.telenet.be] has quit [Remote host closed the connection] |
| 18:31 | |-| | sputhenp [~sputhenp@202.80.58.210] has joined #xen |
| 18:46 | <cdub> | autotranslate is useful for 3 things on x86 |
| 18:46 | <cdub> | 1) HVM |
| 18:47 | <cdub> | 2) minimizing pv changes to kernel (e.g. the early domU patches we did for upstream linux were autotranslate) |
| 18:47 | <cdub> | 3) finding bugs in the hypervisor ;-) |
| 18:47 | <brendan> | heh |
| 18:47 | <cdub> | last i checked there were two ways to crash the hypervisor with x86 domU in autotranslate mode |
| 18:48 | |-| | visik7 [~visi@host96-108-dynamic.56-82-r.retail.telecomitalia.it] has joined #xen |
| 18:49 | <brendan> | so in plain shadow the guest is still sending mfns to the page tables, they're just wrong? and you could run shadow with autotranslated too? |
| 18:50 | <cdub> | yeah, just a question of who maintains the p2m map |
| 18:50 | <brendan> | ok |
| 18:52 | <brendan> | little curious about those crashes too :) |
| 18:54 | |-| | aliguori_ [~anthony@cpe-72-179-63-62.austin.res.rr.com] has quit [Read error: Connection reset by peer] |
| 19:03 | <cdub> | brendan: they weren't always easy to trigger |
| 19:03 | <cdub> | brendan: and the shadow code is not particularly easy to debug |
| 19:04 | <cdub> | brendan: and it's essentially not a supported runtime mode, so upstream xen-devel didn't want |
| 19:04 | <cdub> | to spend tons of time on it |
| 19:05 | <brendan> | the bugs are in some separate area from HVM then... |
| 19:08 | |-| | Basic_py [~Basic@gatekeeper.real-time.com] has quit [Quit: Leaving] |
| 19:10 | <cdub> | yeah |
| 19:11 | <cdub> | one was in shadow2 (I can't quite recall where, but it hit a BUG(), that had a comment saying, "this needs to be fixed") |
| 19:11 | <cdub> | unfortunately there wasn't a simple fix, hence the comment |
| 19:12 | <cdub> | the other was quite obscure (i don't recall anymore, but it was failing a condition somewhere like traps.c) |
| 19:33 | <tessier_> | How can I tell how much of the actual physical cpu on a box is in use? |
| 19:33 | <tessier_> | I have 6 hard working virtual machines on a quad core xen box and I am wondering how busy the cpu's are |
| 19:34 | <tessier_> | top in each virtual domain only tells me the cpu usage in that virtual domain. I am looking at xentop but I'm not sure if that isn't telling me the same thing as regular top in each domain |
| 20:50 | |-| | hollisb [~hollisb@user-0vvdf2d.cable.mindspring.com] has joined #xen |
| 22:59 | |-| | VS_ChanLog [~stats@ns.theshore.net] has left #xen [Rotating Logs] |
| 22:59 | |-| | VS_ChanLog [~stats@ns.theshore.net] has joined #xen |
| 23:16 | |-| | DoberMann_ [~james@AToulouse-156-1-56-20.w90-16.abo.wanadoo.fr] has joined #xen |
| 23:18 | |-| | DoberMann[ZZZzzz] [~james@AToulouse-156-1-18-97.w86-196.abo.wanadoo.fr] has quit [Ping timeout: 480 seconds] |
| 23:51 | |-| | hollisb [~hollisb@user-0vvdf2d.cable.mindspring.com] has quit [Quit: Leaving] |
| --- | Log | closed Sat Mar 10 00:00:52 2007 |