similar to: TAP:AOI - ext2 or ext3?

Hello, I'm wondering if anyone out there is doing tap:aio disk devices on a Xen HVM vm with any success. Please let me know if you are, and perhaps your version info and a config file snippet. I've posted this to the xen-users list, and what I'm trying to do seems to be correct, works on Ubuntu, Debian, and XenSource; but it doesn't work on CentOS. Here's the snippet from my

Hi there I am analyzing disk performance. I'm testing raw (tap: aio) and lvm (phy :). The tests I'm doing on a SLES11SP3, cpu I7, 4GBRam, disco-SATAII 7200rpm. With phy: lvm achievement 70-80MiB / s (an acceptable value) With tap: aio: file.raw achievement 5-9MiB / s, which is very low ... 10MiB / s is what you should expect access to a tap: aio: file.raw? or I have something

Hello, I''m running Xen 3.0.4 on a test server and I''ve been having several file system corruption problems using the tap:aio driver. This message shows up in dmesg on different machines. EXT2-fs error (device sda1): ext2_check_page: bad entry in directory #114914: rec_len is smaller than minimal - offset=0, inode=0, rec_len=0, name_len=0 EXT2-fs error (device sda1):

Hi, I''ve been testing Xen 4.0.1 with kernel 2.6.34.5 + http://gentoo-xen-kernel.googlecode.com/files/xen-patches-2.6.34-4.tar.bz2, and one of the things that I noticed immediately is there are two problems with tapdisk and this combination. First, the syntax "disk = [''tap:tapdisk:aio: ..." no longer works. When tested with HVM domU, it boots, but there was no disk

Hello, I installed Xen 3.2.1 on Debian Lenny from packages. Then created image files with 'xen-create-image --size=2Gb --swap=128Mb --dhcp --dir=/xen --hostname=test'. Now I'm trying to run Debian in PV mode using the following configuration file: kernel = "/boot/vmlinuz-2.6.26-1-xen-686" ramdisk = "/boot/initrd.img-2.6.26-1-xen-686" memory = 128 name =

Package: xen-utils-3.2-1 Version: 3.2.1-2 Severity: important /usr/lib/xen-3.2-1/bin/blktapctrl searches for tapdisk executable in /usr/bin while is in /usr/lib/xen-3.2-1/bin this makes tap:aio unusable I've linked to /usr/bin and everything went fine perhaps the idea is to patch sources to pick executable from the right directory Regards -- System Information: Debian Release: 5.0

Maybe it''s something I''m doing wrong, but I have a 15gb image that I use with disk = [ "tap:aio:/root/images/vista32.img,hda,w" ] It was working fine on Friday, but today it failed to boot with an error message. The same works fine when I replace "tap:aio:" with "file:". It seems like qemu-dm tries to open the file with the "aio:" still

Can anyone explain to me why tap:aio sucks so badly? We''ve got numerous CentOS 5 dom0s running file-backed domUs with tap:aio. The moment any one of them starts doing something disk-intensive, idle CPU in dom0 decreases, iowait increases, and disk IO for every other domU on the system suffers. Where lies the problem, and what to do about it? Sincerely, Ray Barnes

Hello folks, After I upgrade xen-tools to 4.1-unstable, the vm can''t start with disk = [ ''tap:aio:/path/to/image.img,xvda1,w'' ] The vm can''t connect to blk back-end because xm command doesn''t set tapdisk2 (tap-ctl) correctly. But with xl command, everything work right. Any help to xm? I need python support provided by xm in vm config file. Thanks.

Hello folks, After I upgrade xen-tools to 4.1-unstable, the vm can''t start with disk = [ ''tap:aio:/path/to/image.img,xvda1,w'' ] The vm can''t connect to blk back-end because xm command doesn''t set tapdisk2 (tap-ctl) correctly. But with xl command, everything work right. Any help to xm? I need python support provided by xm in vm config file. Thanks.

Hi, xen-3.0.3-41.el5 on RHEL5.1 I''m trying to use tap:aio thusly: disk = [ ''file:/var/lib/xen/images/webmail.golden.net.img,hda,w'' _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users

Hello! First, I must mention that I am not too experienced with virtual machines, so please be gentle :-) It''s my first experiment, and I''ve been working on getting things to work during the past weeks. I''m getting close, but now it seems I''m completely stuck. I''m in the process of testing Xen with Open Nebula, but I have run into some problems.

I have never been able to get tap:aio devices running. When I try it in a Linux PV domain, it says: XENBUS: Waiting for devices to initialise: 295s... And they don''t work in my GPLPV drivers, which is the problem I am trying to solve, but I''d like to see them work under Linux first. Is there anything extra I need to do? I have loaded the xenblktap module (forgot to do this

I''m running SLES10 SP1 and have been using file:/ for my file-backed domUs. The domUs sit on a shared OCFS2 SAN-backed filesystem and are run on my three or four XEN servers. I''m having issues with the loopback devices not being released when the domUs shutdown or migrate, so I decided to switch over to tap:aio for my file-backed domUs. This isn''t working, either.

Hi, I am able to get Xend running on Fedora 8 but when I try to create any VM it fails. The xm create osc.cfg throws following error - [root@asds174 vm_images]# xm create osc.cfg Modified arg=osc.cfg stop3 Using config file "./osc.cfg". group_id=None [''create'', ''osc.cfg''] Stop 1 None [''vm'', [''name'',

[RFC] Virtual Machine Device Queues (VMDq) support on KVM Network adapter with VMDq technology presents multiple pairs of tx/rx queues, and renders network L2 sorting mechanism based on MAC addresses and VLAN tags for each tx/rx queue pair. Here we present a generic framework, in which network traffic to/from a tx/rx queue pair can be directed from/to a KVM guest without any software copy.

[RFC] Virtual Machine Device Queues (VMDq) support on KVM Network adapter with VMDq technology presents multiple pairs of tx/rx queues, and renders network L2 sorting mechanism based on MAC addresses and VLAN tags for each tx/rx queue pair. Here we present a generic framework, in which network traffic to/from a tx/rx queue pair can be directed from/to a KVM guest without any software copy.

Hello, I read the blktap readme; there is a section there titled: Mounting images in Dom0 using the blktap driver. It says there that you can mount an image by: xm block-attach 0 tap:aio:<FILENAME> /dev/xvda1 w 0 mount /dev/xvda1 /mnt/disk <--- don''t use loop driver This option also appears in: http://wiki.rpath.com/wiki/Xen_DomU_Guide I assume that this option is not

Hi everyone, as what I''ve learned form this link<http://wiki.xensource.com/xenwiki/blktap>, i know that when i specify tap:aio I’m actually using the blktap driver and finally using "tapdisk" to wirite to raw image file. but the truth is even when i delete /usr/sbin/tapdisk the domU can still boot on my machine with tap:aio protocol after a deeper look into the scene,

Hi All, I sent the patch to make blktap work with PV-on-HVM. I corrected the part that had been pointed out in the Xen community. ・All xvdN disk is looked like hdN. ・All tap disks are checked.(tap:aio, tap:sync, tap:vmdk, etc.) We cannot use blktap for the volume of the system with PV-on-HVM and are embarrassed. Could you apply this patch? Or, please give the comment to me. Signed-off-by: