search for: paravitualization

With virt_spin_lock() being guarded by a static key the bare metal case can be optimized by patching the call away completely. In case a kernel running as a guest it can decide whether to use paravitualized spinlocks, the current fallback to the unfair test-and-set scheme, or to mimic the bare metal behavior. V3: - remove test for hypervisor environment from virt_spin_lock(9 as suggested by

With virt_spin_lock() being guarded by a static key the bare metal case can be optimized by patching the call away completely. In case a kernel running as a guest it can decide whether to use paravitualized spinlocks, the current fallback to the unfair test-and-set scheme, or to mimic the bare metal behavior. V3: - remove test for hypervisor environment from virt_spin_lock(9 as suggested by

Hi All, I was hoping to run a Windows 2003 server in production on Centos 5.2 however the performance isn't very good. The host is Centos 5.2 64 bit. I did some file transfers and I'm seeing about 12Mb/s on a Windows 2003 VM and about 8Mb/s on a Windows 2003 32 bit VM. Numbers are measured using the builtin Windows 2003 server networking monitor (Press Ctrl Alt Del in Windows and go

Hello everyone, I''m studying XEN these days, and totally a newbie for XEN world. Recently, I''m assigned to move our OS to run on XEN, I means, paravitualization. I know a bit about XEN technique, and I tried to look into Linux code, but it seems too many threads to get understood it ... Now, I have no idea how to proceed my project... Can anyone give some advice? Any suggestion from you will be greatly appreciated! Thank you in advance! Sean __________...

Ping? On 06/09/17 19:36, Juergen Gross wrote: > With virt_spin_lock() being guarded by a static key the bare metal case > can be optimized by patching the call away completely. In case a kernel > running as a guest it can decide whether to use paravitualized > spinlocks, the current fallback to the unfair test-and-set scheme, or > to mimic the bare metal behavior. > > V3:

Hello all, I don''t know if it is a silly question but I am really unsure. I informed myself about the OpenBuildService project which was initialized by OpenSUSE. Now I am really interested in setting up an OpenBuildService VM where I can package some programs and so on for example own software and software I wan''t to use on a few systems which have for example newer versions

HW = HPQ DC7700 DuoCore 1.8GHz, 4 x 2GB RAM, 1 x 1TB SATA (AHCI) OS = CentOS-5.2 ix_64 (xen) I am experimenting with Xen and with virtual machines in general for the first time. In consequence I have many questions. However, the one that I wish answered at the moment is simple: Given a DVD containing the CentOS-5.2_Final (i386) distribution mounted at /media/CentOS_5.2_Final on Dom0, what

Hi, We''ve been using Amazon EC2 a fair bit. We''ve discovered that to run a proprietary, commerical bioinformatics piece of software that is liscenced by physical SOCKET instead of cores, we needed to use a virtualization technology that converts multiple cores into a single socket. (This proprietary software will allow us to use up to 4 cores per physical socket, so

Hi there, I have a Dell T3400 Workstation with CentOS5.1 as dom0. I have hidden a network interface in dom0 to pass it to domU. The domU can come up with the NIC when it''s OS is CentOS5.1 or RHEL5. But when it comes to RedHat4.5 , the NIC can not be found. As I type the command "lspci" in RHEL4.5 domU, it returned: pcilib: Cannot open /proc/bus/pci

Protected Virtualisation protects the memory of the guest and do not allow a the host to access all of its memory. Let's refuse a VIRTIO device which does not use IOMMU protected access. Signed-off-by: Pierre Morel <pmorel at linux.ibm.com> --- drivers/s390/virtio/virtio_ccw.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/s390/virtio/virtio_ccw.c

Protected Virtualisation protects the memory of the guest and do not allow a the host to access all of its memory. Let's refuse a VIRTIO device which does not use IOMMU protected access. Signed-off-by: Pierre Morel <pmorel at linux.ibm.com> --- drivers/s390/virtio/virtio_ccw.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/s390/virtio/virtio_ccw.c

With virt_spin_lock() being guarded by a static key the bare metal case can be optimized by patching the call away completely. In case a kernel running as a guest it can decide whether to use paravitualized spinlocks, the current fallback to the unfair test-and-set scheme, or to mimic the bare metal behavior. V2: - use static key instead of making virt_spin_lock() a pvops function Juergen Gross

With virt_spin_lock() being guarded by a static key the bare metal case can be optimized by patching the call away completely. In case a kernel running as a guest it can decide whether to use paravitualized spinlocks, the current fallback to the unfair test-and-set scheme, or to mimic the bare metal behavior. V2: - use static key instead of making virt_spin_lock() a pvops function Juergen Gross

With virt_spin_lock() being a pvops function the bare metal case can be optimized by patching the call away completely. In case a kernel running as a guest it can decide whether to use paravitualized spinlocks, the current fallback to the unfair test-and-set scheme, or to mimic the bare metal behavior. Juergen Gross (4): paravirt: add generic _paravirt_false() function paravirt: switch

With virt_spin_lock() being a pvops function the bare metal case can be optimized by patching the call away completely. In case a kernel running as a guest it can decide whether to use paravitualized spinlocks, the current fallback to the unfair test-and-set scheme, or to mimic the bare metal behavior. Juergen Gross (4): paravirt: add generic _paravirt_false() function paravirt: switch

Hi Folks, I find myself trying to expand a 2-node high-availability cluster from to a 4-node cluster. I'm running Xen virtualization, and currently using DRBD to mirror data, and pacemaker to failover cleanly. The thing is, I'm trying to add 2 nodes to the cluster, and DRBD doesn't scale. Also, as a function of rackspace limits, and the hardware at hand, I can't separate