similar to: tap:aio / blktap slowness

Hopefully I summed up the jist of the problem in the subject line. ;) I have a GFS cluster with ten Xen 3.0 dom0s sharing an iSCSI LUN. There are on average 8 domUs running on each Xen server. The dom0 on each server is hard-coded to 2 CPUs and 2GB of RAM with no ballooning, and has 2GB of partition-based swap. When creating a new domU on any of the Xen servers, just after the completion of

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 =

Hi all, I am not sure if this is the right list. I implemented a network store based on blktap, a IO consumes100 ms, however tapdisk stops every 10 seconds, as a result previous io''s completion will be sent to kernel until 10 seconds later. This makes the performance suffer. Am I using blktap wrong ? Thanks, Yongqiang -- Best Wishes Yongqiang Yang

Dear all, I have installed DRBD 8.3.11 compiled from sources. However the backend block will freeze if there is high IO load. I use Remus to support high availability and checkpointing is controlled by remus for each 400ms. If I check the Iostat I got the idle CPU will decreasing extremely each checkpointing and when its reach 0% of idle cpu the local backing device will freeze and damage the

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! 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.

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, 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 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.

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

Package: wnpp Severity: wishlist Owner: Debian Xen Team <pkg-xen-devel at lists.alioth.debian.org> * Package name : blktap-dkms Version : 2.0.90 Upstream Author : Jon Ludlam <jonathan.ludlam at eu.citrix.com> * URL : http://www.xen.org/ * License : GPL-2 Programming Lang: C Description : Xen blktap kernel component DKMS package This package

I did some additional testing - I stopped Kafka on the host, and kicked off a disk check, and it ran at the expected speed overnight. I started kafka this morning, and the raid check's speed immediately dropped down to ~2000K/Sec. I then enabled the write-back cache on the drives (hdparm -W1 /dev/sd*). The raid check is now running between 100000K/Sec and 200000K/Sec, and has been for several

Hello, I hope this is the mailing list to discuss this issue, but if not sorry for spamming! I just discovered a really slow IO performance on DomUs running debian wheezy over wheezy dom0s, any operation that requires disk read or write takes a lot of time. Here are the hardware parameters: Single Xeon 5120 (dual core) 8GB of ram Hardware raid 2x250GB drives raid 1 his is the configuration

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.

Issue: Vista reads slowly from a samba server. This appears to pop up periodically here and elsewhere. My samba.conf file has: [homes] ... vfs objects = readahead As suggested elsewhere. Writes are approximately 17-18MB/s which is acceptable. Reads are in the 8MB/s range which is appalingly slow. Using linux smbclient and windows XP clients I can read at 25+MB/s. I've enabled vfs

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

Package: blktap-dkms Severity: grave Justification: renders package unusable Hi, blktap-dkms FTBFS against linux 3.10-1 from unstable: Cheers, Moritz CC [M] /var/lib/dkms/blktap/2.0.91/build/control.o In file included from /var/lib/dkms/blktap/2.0.91/build/control.c:30:0: /var/lib/dkms/blktap/2.0.91/build/blktap.h:75:41: warning: variably modified ?pending? at file scope [enabled by

Accepted: -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA256 Format: 1.8 Date: Thu, 17 Dec 2015 10:38:51 +0200 Source: blktap-dkms Binary: blktap-dkms Architecture: source Version: 2.0.93-0.5 Distribution: unstable Urgency: high Maintainer: Debian Xen Team <pkg-xen-devel at lists.alioth.debian.org> Changed-By: Chrysostomos Nanakos <cnanakos at debian.org> Description: blktap-dkms - Xen