Hello, We have installed Xen on our new server with the following specs: 2 x AMD Opteron 240s. 4Gb RAM (2x2GB Patriot) 3Ware RAID Controller 4x36Gb Raptors (Stripe 0) The core linux installation is Fedora Core 4-32bit. FC4 sees all 4GBs of RAM. The Xen Dom0, however, only sees 2Gb. I''ve tried the following: 1. Installing the pre-built FC4 Xen Kernels. Same result. 2. Installing the FC4-64bit. Could then see 4GB, but ran into other issues creating a guest system. 3. Downloading the latest Xen-unstable code, using menuconfig to set ensure the CONFIG_HIGHMEM4G setting was set (and it is) and building new kernels to FC4-32. The last is where I stand today. For some reason, however, I only see 2GB of RAM. That fact that I see 2GB leads me to believe the HIGHMEM is working (because it would be 800Mb otherwise, right?). Why can''t I see the rest? Could it have to do with having 2x2Gb sticks instead of 4x1Gb? I don''t believe I can use PAE, thats an intel thing, right? I''m at a loss. We really want to make use of our memory as we plan to run one DomU with 1GB and the rest with 512GB each. The Xen kernel version is 2.6.12.6 (unstable). FC has all the latest yum updates as of this morning. Thanks, Mark __________________________________ Yahoo! FareChase: Search multiple travel sites in one click. http://farechase.yahoo.com _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
> The core linux installation is Fedora Core 4-32bit. > FC4 sees all 4GBs of RAM. The Xen Dom0, however, only > sees 2Gb. > > I''ve tried the following: > 1. Installing the pre-built FC4 Xen Kernels. Same > result. > 2. Installing the FC4-64bit. Could then see 4GB, but > ran into other issues creating a guest system.OK...? Xen on 64 bit ought to work reasonably well. Was it a Xen problem or an FC4 problem that stopped you? If the former was the case (and it''s not fixed yet) you should probably scream about it ;-)> 3. Downloading the latest Xen-unstable code, using > menuconfig to set ensure the CONFIG_HIGHMEM4G setting > was set (and it is) and building new kernels to > FC4-32.That sounds like it ought to work...> The last is where I stand today. For some reason, > however, I only see 2GB of RAM. That fact that I see > 2GB leads me to believe the HIGHMEM is working > (because it would be 800Mb otherwise, right?). Why > can''t I see the rest? Could it have to do with having > 2x2Gb sticks instead of 4x1Gb? > > I don''t believe I can use PAE, thats an intel thing, > right?It should work on Opteron AFAIK. What you''re seeing seems pretty weird... can you check your normal kernel definitely isn''t using PAE? I guess it''s possible you need PAE to see all your memory, but "losing" 2Gig seems just bizarre to me. I''m not familiar with what Fedora supports by default. Maybe someone from Redhat can comment.> I''m at a loss. We really want to make use of our > memory as we plan to run one DomU with 1GB and the > rest with 512GB each. > > The Xen kernel version is 2.6.12.6 (unstable). FC has > all the latest yum updates as of this morning.It ought to work as you want... Cheers, Mark _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Mark Lassiter <mackdaddylassiter@yahoo.com> wrote:> I don''t believe I can use PAE, thats an intel thing, > right?No! I can confirm that an Opteron machine can use PAE under Xen. I first tried the xen-unstable binary with PAE enabled. It recognized all 8GB in my Dual Core AMD Opteron(tm) Processor 265 machine. It took me awhile to figure out how to make a PAE-enabled Xen. Here are the approximate steps I took. 1. hg clone http://xenbits.xensource.com/xen-unstable.hg 2. snarf http://www.cl.cam.ac.uk/Research/SRG/netos/xen/downloads/xen-unstable-install-x86_32p.tgz - | tar zx 3. cd xen-unstable.hg 4. cp ../xen-unstable-install/install/boot/config-2.6.12.6-xen0 ./linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_x86_32 5. cp ../xen-unstable-install/install/boot/config-2.6.12.6-xenU ./linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_x86_32 6. Edit ./Config.mk. Change "XEN_TARGET_X86_PAE ?= n" to "XEN_TARGET_X86_PAE ?= y". 7. Edit ./linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_x86_32 for other changes you need. (I enable LBD, ATA over Ethernet and serial console.) 8. make 9. make install 10. reboot xentop - 18:06:34 Xen 3.0-devel 1 domains: 1 running, 0 blocked, 0 paused, 0 crashed, 0 dying, 0 shutdown Mem: 8322620k total, 200316k used, 8122304k free CPUs: 4 @ 1793MHz However...do note that I was seeing 4GB *without* PAE. If you just want 4GB you shouldn''t need PAE. --kyler _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
PAE is supported in K6, K7/Athlon+Duron as well as K8/Athlon64+Opteron+Sempron. Absolutely sure about this. Obviously doesn''t help explaining what the problem is for Mark L. -- Mats [snip]> I don''t believe I can use PAE, thats an intel thing, > right?It should work on Opteron AFAIK. What you''re seeing seems pretty weird... can you check your normal kernel definitely isn''t using PAE? I guess it''s possible you need PAE to see all your memory, but "losing" 2Gig seems just bizarre to me. _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Mark Lassiter schrieb:> 3. Downloading the latest Xen-unstable code, using > menuconfig to set ensure the CONFIG_HIGHMEM4G setting > was set (and it is) and building new kernels to > FC4-32.Well, I recently had a Dual Xeon Server with 4GB of RAM. Installed Debian Sarge on it and had only 3,2GB RAM. I had to recompile the kernel with 64GB highmem support (PAE was enabled automatically when doing this). Then the kernel detected arround 4,8GB RAM, 800MB are reserved for PCI devices and voila, I have 4GB of RAM useable. (NOT with XEN, "just" an application server). Don''t know if this is of any use for you, just a hint from me. Greetings, Markus _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
I''m sorry, I did mean to CC everyone. In fact, I sent another message with the log file and bios information you suggested and did the same thing :) <== dork. I pasted it below again. I have since recompiled with PAE support and it works! Only problem was that I had to manually edit the Config.mk file in the root of the xen source tree and specify the XEN_TARGET_X86_PAE ?= y (was n). The instructions (README) indicate that I only need to run menuconfig from the xen0 and xenU source directories, but apparently this is necessary, otherwise you get an error about xen and dom0 PAE mode mismatch on boot. I can now see all 4GB. I still wonder why I can''t with CONFIG_HIGHMEM4G? Perhaps something along the lines of the PAE config problem above whereby the xen kernel is not actually being built with the same options as dom0 and domU? Perhaps I''m misreading the README on building the dist. Anyhow, my BIOS log entries from the previous (misaddressed) email:>From Fedora4 SMP Kernel======================Nov 9 19:02:03 localhost kernel: Linux version 2.6.13-1.1532_FC4smp (bhcompile@tweety.build.redhat.com) (gcc version 4.0.1 20050727 (Red Hat 4.0.1-5)) #1 SMP Thu Oct 20 01:51:51 EDT 2005 Nov 9 19:02:03 localhost kernel: BIOS-provided physical RAM map: Nov 9 19:02:03 localhost kernel: BIOS-e820: 0000000000000000 - 000000000009f400 (usable) Nov 9 19:02:03 localhost kernel: BIOS-e820: 000000000009f400 - 00000000000a0000 (reserved) Nov 9 19:02:03 localhost kernel: BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) Nov 9 19:02:03 localhost kernel: BIOS-e820: 0000000000100000 - 0000000080000000 (usable) Nov 9 19:02:03 localhost kernel: BIOS-e820: 00000000ff780000 - 0000000100000000 (reserved) Nov 9 19:02:03 localhost kernel: BIOS-e820: 0000000100000000 - 0000000180000000 (usable) Nov 9 19:02:03 localhost kernel: 5248MB HIGHMEM available. Nov 9 19:02:03 localhost kernel: 896MB LOWMEM available. Nov 9 19:02:03 localhost kernel: found SMP MP-table at 000ff780>From Xen:=================Nov 9 19:07:45 localhost kernel: Linux version 2.6.12.6-xen0 (root@localhost.localdomain) (gcc version 4.0.1 20050727 (Red Hat 4.0.1-5)) #2 SMP Wed Nov 9 09:00:37 EST 2005 Nov 9 19:07:45 localhost kernel: BIOS-provided physical RAM map: Nov 9 19:07:45 localhost kernel: Xen: 0000000000000000 - 00000000765c0000 (usable) Nov 9 19:07:45 localhost kernel: 1069MB HIGHMEM available. Nov 9 19:07:45 localhost kernel: 832MB LOWMEM available. Nov 9 19:07:45 localhost kernel: found SMP MP-table at 000ff780 --- Mark Williamson <mark.williamson@cl.cam.ac.uk> wrote:> Did you mean to cc the list on that last e-mail? > Probably worthwhile... > > Anyhow, it might be nice to compare the memory map > output in dmesg between > your different configurations... Native Linux''s > "dmesg" output and Xen''s "xm > dmesg" output should give us what we need here. > > Usually when people are missing lots of accessible > memory it''s because the > BIOS has reserved excessive amounts of physical > address space under 4Gig for > IO device registers... I''ve never heard of an > entire 2 gig disappearing on > it, though... Anyhow, *if* it turns out to be that, > the solution is to use > something that can address above 4Gig: either PAE or > 64-bit mode. > > Hopefully we can find something that suits. > > Cheers, > Mark > > On Wednesday 09 November 2005 21:30, you wrote: > > Thanks for your response. > > > > The 64 bit problems resulted in Kernel panics: > failed > > to sync. I can elaborate further, but would > prefer to > > do so in another thread. I''ll keep this one > focused > > on not seeing 4GB. > > > > I''ll try checking my kernel for PAE and see if > that > > option works. Perhaps that''s all I need. It is > > wierd. > > > > What I did: > > > > 1. Installed FC4-32. > > 2. yum -y update > > 3. Installed xen via yum and following the Redhat > > QuickStart. Could only see 2Gb. > > 4. Removed the xen packages and downloaded latest > > source (unstable). > > 5. make world > > 6. Ran the menuconfig in both the xen0 and xenU > > source directories, setting the HIGHMEM4G option. > > 7. Also selected the Operaton processor for my > target > > processor. > > 8. make dist > > 9. make install > > 10. ran mkinitrd and created an image. > > 11. Configured grub.conf > > 12. Booted Xen dom0. Ran free and only see 2Gb. > > > > Am I missing something? > > > > > > > > --- Mark Williamson <mark.williamson@cl.cam.ac.uk> > > > > wrote: > > > > The core linux installation is Fedora Core > > > > > > 4-32bit. > > > > > > > FC4 sees all 4GBs of RAM. The Xen Dom0, > however, > > > > > > only > > > > > > > sees 2Gb. > > > > > > > > I''ve tried the following: > > > > 1. Installing the pre-built FC4 Xen Kernels. > Same > > > > result. > > > > 2. Installing the FC4-64bit. Could then see > 4GB, > > > > > > but > > > > > > > ran into other issues creating a guest system. > > > > > > OK...? Xen on 64 bit ought to work reasonably > well. > > > Was it a Xen problem or > > > an FC4 problem that stopped you? If the former > was > > > the case (and it''s not > > > fixed yet) you should probably scream about it > ;-) > > > > > > > 3. Downloading the latest Xen-unstable code, > using > > > > menuconfig to set ensure the CONFIG_HIGHMEM4G > > > > > > setting > > > > > > > was set (and it is) and building new kernels > to > > > > FC4-32. > > > > > > That sounds like it ought to work... > > > > > > > The last is where I stand today. For some > reason, > > > > however, I only see 2GB of RAM. That fact > that I > > > > > > see > > > > > > > 2GB leads me to believe the HIGHMEM is working > > > > (because it would be 800Mb otherwise, right?). > > > > > > Why > > > > > > > can''t I see the rest? Could it have to do > with > > > > > > having > > > > > > > 2x2Gb sticks instead of 4x1Gb? > > > > > > > > I don''t believe I can use PAE, thats an intel > > > > > > thing, > > > > > > > right? > > > > > > It should work on Opteron AFAIK. > > > > > > What you''re seeing seems pretty weird... can you > > > check your normal kernel > > > definitely isn''t using PAE? I guess it''s > possible > > > you need PAE to see all > > > your memory, but "losing" 2Gig seems just > bizarre to > > > me. > > > > > > I''m not familiar with what Fedora supports by > > > default. Maybe someone from > > > Redhat can comment. > > > > > > > I''m at a loss. We really want to make use of > our > > > > memory as we plan to run one DomU with 1GB and > the > > > > rest with 512GB each. > > > > > > > > The Xen kernel version is 2.6.12.6 (unstable). > FC > > > > > > has > > > > > > > all the latest yum updates as of this morning. > > > > > > It ought to work as you want... > > > > > > Cheers, > > > Mark > > > > > > _______________________________________________ > > > Xen-users mailing list > > > Xen-users@lists.xensource.com > > > http://lists.xensource.com/xen-users > > > > __________________________________ > > Yahoo! Mail - PC Magazine Editors'' Choice 2005 > > http://mail.yahoo.com >__________________________________ Yahoo! Mail - PC Magazine Editors'' Choice 2005 http://mail.yahoo.com _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
> I pasted it below again. I have since recompiled with > PAE support and it works!Excellent stuff!> Only problem was that I had to manually edit the > Config.mk file in the root of the xen source tree and > specify the XEN_TARGET_X86_PAE ?= y (was n).Yep.> The instructions (README) indicate that I only need > to run menuconfig from the xen0 and xenU source > directories, but apparently this is necessary, > otherwise you get an error about xen and dom0 PAE mode > mismatch on boot. > I can now see all 4GB.The editof the toplevel makefile is necessary to make Xen itself be PAE enabled... I guess the README mightn''t have mentioned that.> I still wonder why I can''t with CONFIG_HIGHMEM4G? > Perhaps something along the lines of the PAE config > problem above whereby the xen kernel is not actually > being built with the same options as dom0 and domU? > Perhaps I''m misreading the README on building the > dist.CONFIG_HIGHMEM4G won''t fix your problem: access to 4Gigs of RAM isn''t enough on your system. See below...> Nov 9 19:02:03 localhost kernel: BIOS-e820: > 0000000000100000 - 0000000080000000 (usable)OK, that''s about 2 gig of your memory, mapped into a sane place in the physical address space...> Nov 9 19:02:03 localhost kernel: BIOS-e820: > 00000000ff780000 - 0000000100000000 (reserved)And this is an enormous hole, taking up the next 2 gigs of your physical address space. Even with 4G himem, your CPU will only be able to access this far: 2Gigs of your real memory, 2Gigs that your BIOS (for some reason) has reserved for IO regions. This means that your other 2Gig is mapped too high in the physical address space: with 4G himem there is simply no way to address it.> Nov 9 19:02:03 localhost kernel: BIOS-e820: > 0000000100000000 - 0000000180000000 (usable)And he''s the other 2Gig. This is mapped from 4Gig-6Gig in your physical address space, so isn''t mappable without PAE support. With PAE you can easily address this range, so the memory becomes usable for you. I''ve never *seen* a memory hole 2gigs in size. Maybe there''s a reason for it or maybe I just had a sheltered upbringing. Anyhow, glad you got it working. I really gotta go sleep before the sun rises! Cheers, Mark _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Ah, that explains so much! Thank you for all the help. This list rocks! --- Mark Williamson <mark.williamson@cl.cam.ac.uk> wrote:> > I pasted it below again. I have since recompiled > with > > PAE support and it works! > > Excellent stuff! > > > Only problem was that I had to manually edit the > > Config.mk file in the root of the xen source tree > and > > specify the XEN_TARGET_X86_PAE ?= y (was n). > > Yep. > > > The instructions (README) indicate that I only > need > > to run menuconfig from the xen0 and xenU source > > directories, but apparently this is necessary, > > otherwise you get an error about xen and dom0 PAE > mode > > mismatch on boot. > > I can now see all 4GB. > > The editof the toplevel makefile is necessary to > make Xen itself be PAE > enabled... I guess the README mightn''t have > mentioned that. > > > I still wonder why I can''t with CONFIG_HIGHMEM4G? > > Perhaps something along the lines of the PAE > config > > problem above whereby the xen kernel is not > actually > > being built with the same options as dom0 and > domU? > > Perhaps I''m misreading the README on building the > > dist. > > CONFIG_HIGHMEM4G won''t fix your problem: access to > 4Gigs of RAM isn''t enough > on your system. See below... > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > 0000000000100000 - 0000000080000000 (usable) > > OK, that''s about 2 gig of your memory, mapped into a > sane place in the > physical address space... > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > 00000000ff780000 - 0000000100000000 (reserved) > > And this is an enormous hole, taking up the next 2 > gigs of your physical > address space. > > Even with 4G himem, your CPU will only be able to > access this far: 2Gigs of > your real memory, 2Gigs that your BIOS (for some > reason) has reserved for IO > regions. > > This means that your other 2Gig is mapped too high > in the physical address > space: with 4G himem there is simply no way to > address it. > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > 0000000100000000 - 0000000180000000 (usable) > > And he''s the other 2Gig. This is mapped from > 4Gig-6Gig in your physical > address space, so isn''t mappable without PAE > support. With PAE you can > easily address this range, so the memory becomes > usable for you. > > I''ve never *seen* a memory hole 2gigs in size. > Maybe there''s a reason for it > or maybe I just had a sheltered upbringing. > > Anyhow, glad you got it working. I really gotta go > sleep before the sun > rises! > > Cheers, > Mark >__________________________________ Yahoo! FareChase: Search multiple travel sites in one click. http://farechase.yahoo.com _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
> > CONFIG_HIGHMEM4G won''t fix your problem: access to 4Gigs of RAM isn''t enough > on your system. See below... > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > 0000000000100000 - 0000000080000000 (usable) > > OK, that''s about 2 gig of your memory, mapped into a sane place in the > physical address space... > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > 00000000ff780000 - 0000000100000000 (reserved) > > And this is an enormous hole, taking up the next 2 gigs of your physical > address space. > > Even with 4G himem, your CPU will only be able to access this far: 2Gigs of > your real memory, 2Gigs that your BIOS (for some reason) has reserved for IO > regions. > > This means that your other 2Gig is mapped too high in the physical address > space: with 4G himem there is simply no way to address it. > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > 0000000100000000 - 0000000180000000 (usable) > > And here''s the other 2Gig. This is mapped from 4Gig-6Gig in yourphysical> address space, so isn''t mappable without PAE support. With PAE you can > easily address this range, so the memory becomes usable for you. > > I''ve never *seen* a memory hole 2gigs in size. Maybe there''s a reason for it > or maybe I just had a sheltered upbringing.I just booted a box like this :-) Linux version 2.4.29 (root@server.baremetal.com) (gcc version 2.96 20000731 (Red Hat Linux 7.1 2.96-81)) #3 Wed Oct 12 15:11:08 PDT 2005 BIOS-provided physical RAM map: BIOS-e820: 0000000000000000 - 000000000009fc00 (usable) BIOS-e820: 000000000009fc00 - 00000000000a0000 (reserved) BIOS-e820: 00000000000e8000 - 0000000000100000 (reserved) BIOS-e820: 0000000000100000 - 000000007fff0000 (usable) BIOS-e820: 000000007fff0000 - 000000007ffff000 (ACPI data) BIOS-e820: 000000007ffff000 - 0000000080000000 (ACPI NVS) BIOS-e820: 00000000ff780000 - 0000000100000000 (reserved) BIOS-e820: 0000000100000000 - 0000000180000000 (usable) Warning only 4GB will be used. Use a PAE enabled kernel. 3200MB HIGHMEM available. 896MB LOWMEM available. On node 0 totalpages: 1048576 <snip> Memory: 2044840k/4194304k available (1518k kernel code, 51860k reserved, 487k data, 284k init, 1179584k highmem) <snip> so, (for the reasons Mark outlined) the box is only showing 2 gig of memory on a kernel compiled for 4 gig... However it _did_ say there was an issue, and what one solution is. Now, if you look at the motherboard manual for this dual opteron system, you will see that half the memory is connected to one processor, and the other half of the memory is connected to the other processor. Since I only installed the memory a few hours ago, the image is fairly fresh in my mind :) Anyhow, I thought I would bring it up. The motherboard is described here: http://www.supermicro.com/Aplus/motherboard/Opteron/8132/H8DAR-T.cfm manual: http://www.supermicro.com/manuals/motherboard/A_8132/MNL-H8DAR-TE.pdf I haven''t had a chance to do much more than boot it, but while I can say that the Opteron supermicro products aren''t quite up to the standard of their P4/Xeon mainstream products (they just aren''t as polished -- the fans are loose, there was no system manual, and I''m ticked that heatsinks seem hard to get), I expect that we (baremetal.com) will focus on them... http://www.supermicro.com/Aplus/system/1U/1020/AS-1020A-T.cfm I have a pair of 270''s and 4 gig of memory (hopefully 8 before I go into production) in this box. Will report if we have any trouble (I don''t expect to). I believe that we can "just" run a 64 bit XEN and 64 bit kernel (e.g. amd64) with our normal 32 bit Linux distribution? I will know soon enough. -Tom _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
That makes sense. I suppose the mapping of memory to the CPUs is part of the NUMA architecture, but I''ll not speculate further as I''m outta my league there :) At some point when our project slows down, I''m going to revisit the 64bit FC4 and Xen. After working through some more problems, I''m beginning to think the problems were all related to my kernel builds and mistakes made in that process. I''ll post back when I have worked it out. Thanks, Mark --- Tom Brown <tbrown@baremetal.com> wrote:> > > > CONFIG_HIGHMEM4G won''t fix your problem: access to > 4Gigs of RAM isn''t enough > > on your system. See below... > > > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > > 0000000000100000 - 0000000080000000 (usable) > > > > OK, that''s about 2 gig of your memory, mapped into > a sane place in the > > physical address space... > > > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > > 00000000ff780000 - 0000000100000000 (reserved) > > > > And this is an enormous hole, taking up the next 2 > gigs of your physical > > address space. > > > > Even with 4G himem, your CPU will only be able to > access this far: 2Gigs of > > your real memory, 2Gigs that your BIOS (for some > reason) has reserved for IO > > regions. > > > > This means that your other 2Gig is mapped too high > in the physical address > > space: with 4G himem there is simply no way to > address it. > > > > > Nov 9 19:02:03 localhost kernel: BIOS-e820: > > > 0000000100000000 - 0000000180000000 (usable) > > > > And here''s the other 2Gig. This is mapped from > 4Gig-6Gig in your > physical > > address space, so isn''t mappable without PAE > support. With PAE you can > > easily address this range, so the memory becomes > usable for you. > > > > I''ve never *seen* a memory hole 2gigs in size. > Maybe there''s a reason for it > > or maybe I just had a sheltered upbringing. > > > I just booted a box like this :-) > > > Linux version 2.4.29 (root@server.baremetal.com) > (gcc version 2.96 > 20000731 (Red Hat Linux 7.1 2.96-81)) #3 Wed Oct > 12 15:11:08 PDT 2005 > BIOS-provided physical RAM map: > BIOS-e820: 0000000000000000 - 000000000009fc00 > (usable) > BIOS-e820: 000000000009fc00 - 00000000000a0000 > (reserved) > BIOS-e820: 00000000000e8000 - 0000000000100000 > (reserved) > BIOS-e820: 0000000000100000 - 000000007fff0000 > (usable) > BIOS-e820: 000000007fff0000 - 000000007ffff000 > (ACPI data) > BIOS-e820: 000000007ffff000 - 0000000080000000 > (ACPI NVS) > BIOS-e820: 00000000ff780000 - 0000000100000000 > (reserved) > BIOS-e820: 0000000100000000 - 0000000180000000 > (usable) > Warning only 4GB will be used. > Use a PAE enabled kernel. > 3200MB HIGHMEM available. > 896MB LOWMEM available. > On node 0 totalpages: 1048576 > <snip> > Memory: 2044840k/4194304k available (1518k kernel > code, 51860k reserved, > 487k data, 284k init, 1179584k highmem) > <snip> > > so, (for the reasons Mark outlined) the box is only > showing 2 gig > of memory on a kernel compiled for 4 gig... However > it _did_ say > there was an issue, and what one solution is. > > Now, if you look at the motherboard manual for this > dual opteron > system, you will see that half the memory is > connected to one > processor, and the other half of the memory is > connected to the > other processor. Since I only installed the memory a > few hours > ago, the image is fairly fresh in my mind :) > > Anyhow, I thought I would bring it up. > The motherboard is described here: > > >http://www.supermicro.com/Aplus/motherboard/Opteron/8132/H8DAR-T.cfm> > manual: > >http://www.supermicro.com/manuals/motherboard/A_8132/MNL-H8DAR-TE.pdf> > I haven''t had a chance to do much more than boot it, > but while I can say > that the Opteron supermicro products aren''t quite up > to the standard of > their P4/Xeon mainstream products (they just aren''t > as polished -- the > fans are loose, there was no system manual, and I''m > ticked that heatsinks > seem hard to get), I expect that we (baremetal.com) > will focus on them... > > >http://www.supermicro.com/Aplus/system/1U/1020/AS-1020A-T.cfm> > I have a pair of 270''s and 4 gig of memory > (hopefully 8 before I > go into production) in this box. Will report if we > have any > trouble (I don''t expect to). > > I believe that we can "just" run a 64 bit XEN and 64 > bit kernel > (e.g. amd64) with our normal 32 bit Linux > distribution? I will > know soon enough. > > -Tom > > >__________________________________ Yahoo! FareChase: Search multiple travel sites in one click. http://farechase.yahoo.com _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users