similar to: BVT scheduler settings examples

Some users are hitting this panic in network_alloc_rx_buffers() when running a big network intensive app: /* Check return status of HYPERVISOR_dom_mem_op(). */ if ( rx_mcl[nr_pfns].args[5] != nr_pfns ) panic("Unable to reduce memory reservation\n"); I''m not clear on what is happening here. Are the domains changing size? Which memory reservation is being

Currently with the credit scheduler, cpu_weight cannot be assigned to guest domains at boot time.(it can be set with xm sched-weight after booting) This patch allows CPU weight, and CAP to be set by the Xen configuration files. Specification: The following can be added to the Xen configuration files. 1.CPU WEIGHT [OPTIONAL] cpu_weight = cpu weight value -sets the cpu time ratio to be

Hi everyone, I''m running Xen on an SMP machine. Couple of things: a) is dom0 pinned to a particular CPU? if so which? can I control the choice? b) with the 2.6.10 Xenolinux kernel, cat /proc/cpuinfo shows only a single CPU on my SMP machine. Is this a known problem/behavior? c) if I understand correctly, the BVT scheduler parameters are CPU specific -- they don''t aggregate

Hi folks BVT and EDF are both xen scheduler. It is expected that administrator will choose the scheduler most appropriate to their application and configure the machine to boot with that scheduler. I just wonder What''s the main difference between BVT and EDF? What kind of scenario to use them? Thanks _______________________________________________ Xen-tools mailing list

Hello I''m in trouble using the bvt scheduler with the command line. the command "xm sched-bvt help" explain that it need 6 argument but that''s all. I have read a previous conversation for bvt example with command line, but it doesn''t work I try (5 is the id of the concerned

Hi everyone, I understand BVT is not the default scheduler anymore, but perhaps this would be of interest to some people. Some changes in the current BVT scheduler compared to the BVT code in Xen 3.0 has affected its correctness. In the original (Xen 3.0) BVT scheduler the weights resulted in correct CPU allocations. However, the current BVT scheduler (CS 10647:8e55c5c11475) does not do it

I''m attempting to migrate from vmware to xen, however I need to be able to run more than one bridge. Think of it this way: xen0 xenU-1 xenU-2 xenU-3 ------------------------------------------------------------------------ Inside_bridge_1: eth0 vm1_eth0 vm2_eth0 virtual_switch_2: vm1_eth1 vm2_eth1 vm3_eth1 Outside_bridge_3: eth1 vm2_eth2 vm3_eth0 Now, I can modify the existing

hi all, im am trying to allocate cpu to the various domains using a bvt scheduler. so now lets say i want to give the first virtual machine a weight of 1 and the second a weight of 2. this should result in domain1 using 33% of the cpu and domain2 66%. however since xm sched-bvt takes inverse of the weights as input so i do 1/1 and 1/2 and hence do "xm sched-bvt vm1 2 0 0 0 0" for the

Has anyone expirienced problems with the aic79xx controller and xen 2.0.3 (liinux-2.6.10)? I have got FC3 running and compiled xen-2.0.3 from the sources. The compile ssems to work fine but after rebooting the xen0 domain the server stops during boot at the aic79xx message - no harddisks are recognized. I''ve searched through the mailinglist up and down, asked google but

I am seeing a kernel message, "hdc: lost interrupt", when running LTP on the xen0 domain. The first time I saw the ''kernel: hdc: lost interrupt'' in /var/log/messages, I was running LTP on both xen0 and xenU domains. The xenU domain was totally hung at this point. Suspecting a setup error, I re-checked the installation and reran LTP on xen0 alone, without having

Name: python-install.patch Description: Use --root instead of --home --home causes python''s distutils to install into /usr/lib/python/, while --root causes it to install into /usr/lib/python$ver/site-packages, which is the more correct location. Signed-off-by: Adam Heath <doogie@brainfood.com> DiffStat: tools/python/Makefile | 4 ++-- 1 files changed, 2 insertions(+), 2

Does anyone in the devel team recall how the ttylinux rootfs was created, by which I mean what changes were needed? Nothing detailed, just "oh, just /etc/fstab" or whatever. I haven''t yet compared myself, though I''ll figure it eventually. For XenCD, I''d like to ship a pristine ttylinux instance on the ISO image, and have the XenCD startup process copy that

Hi everyone, This is for Xen 2.0.3. I''m really interested in the functionality of atropos (enforcing CPU partitioning in a non work-conserving fashion). As I had reported earlier, atropos seemed broken in 2.0. It still seems broken now: $ xm list Name Id Mem(MB) CPU State Time(s) Console Domain-0 0 123 0 r---- 49.1 vm1 1 47

I am trying to setup mysql on XEN. I need to set it up on NFS so I can migrate the domain when needed. I am getting unexpected results and wanted to get some feedback. Here is my setup: NFS server Dual 2.0 Ghz AMD Opteron 2GB of RAM Broadcom GB NIC Standard Fedora Core 3 (FC3) Mysql w/tpc-c medium databases on the NFS share XenU filesystem on the NFS share Xen machine

Currently xcs is run by xend in xen-unstable by simply making it a child process. If you launch xend from an ssh session, the session won''t exit because the xcs still is connected to it''s controlling terminal. xcs should daemonize itself to prevent this from happening. This patch does that along with making the domain id => port mapping dynamically allocated. Regards, --

Sorry, hit send instead of attach again. Rest of patches included. -- Anthony Liguori Samba, Linux/Windows Interoperability Linux Technology Center (LTC) - IBM Austin E-mail: aliguori@us.ibm.com Phone: (512) 838-1208 Tie Line: 678-1208

This patch for linux-2.6 defconfig more than quadrupled iperf throughput, restoring the gigethernet network performance to wire speed at long last. Applies to xen-2.0-testing.bk xen-2.0.bk and xeno-unstable.bk The throughput on linux-2.4.29 seems fine. I hadn''t tried it since 2.4.27. The relevant sccs comment, from Dec1: ======== linux-2.6.10-xen-sparse/arch/xen/configs/xen0_defconfig

Hey all, This utility (from Qemu) might be useful to anyone who has multiple partitions on a file-backed VBD and wants occasionally to mount them in dom0. http://www.dad-answers.com/qemu/utilities/QEMU-HD-Mounter/lomount/ You can tell it what partition to mount out of the file and it sorts out the offsets, etc. by parsing the partition table. This allows you to get around the loop

# HG changeset patch # User Lutz.Dube # Node ID ca2c8c262dbaa6b2521cec60af7cd688dabdf850 # Parent 8992134dcfd0b9e1e86f4111e68a8aa48bd33c3c Values of cpu_weight and cpu_cap are lost after xend restart For managed domains in state ''halted'' I always get default values for cpu_cap / cpu_weight after xend restart. This is because the names of parameters differ between a SXP file to

Under xen, either stock xen-2.0.1+linux-2.6.9 or Fedora''s latest (2.6.10-1.1109_FC4), drdb (<http://www.drbd.org/>),as soon as I try to write to one of its devices, causes "Badness" in the kernel and, ultimately, a spontaneous reboot. Under non-xen 2.6.10-1.1109_FC4 and 2.6.9-1.678_FC3, drbd works fine. The error: Jan 25 21:01:23 turing kernel: Badness in blk_plug_device