similar to: >2GB RAM issue for passed through VF devices

Greetings Xen user community, I am interested in using Mellanox ConnectX cards with SR-IOV capabilities to passthrough pci-e Virtual Functions (VFs) to Xen guests. The hope is to allow for the use of InfiniBand directly within virtual machines and thereby enable a plethora of high performance computing applications that already leverage InfiniBand interconnects. However, I have run into some

CentOS Errata and Enhancement Advisory 2012:0739 Upstream details at : https://rhn.redhat.com/errata/RHEA-2012-0739.html The following updated files have been uploaded and are currently syncing to the mirrors: ( sha256sum Filename ) i386: cd17436881234bf53282fef05c00d459d58b88d804b1de21843c55270463c925 kmod-mlx4_core-1.1.32.269-1.el6_2.i686.rpm x86_64:

Hi We are trying to configure RDMA for an infiniband connection between our data server (running CentOS 6.8) and our compute nodes (running CentOS 6.6).? We have been trying to follow the instructions in https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/7/html/networking_guide/sec-configuring_the_base_rdma_subsystemedit however we are getting conflicting information on

Send CentOS-announce mailing list submissions to centos-announce at centos.org To subscribe or unsubscribe via the World Wide Web, visit http://lists.centos.org/mailman/listinfo/centos-announce or, via email, send a message with subject or body 'help' to centos-announce-request at centos.org You can reach the person managing the list at centos-announce-owner at centos.org When

hi people I wonder if anybody experience any problems with vols in replica mode that run across IPoIB links and libvirt stores qcow image on such a volume? I wonder if maybe devel could confirm it should just work, and then hardware/Infiniband I should blame. I have a direct IPoIB link between two hosts, gluster replica volume, libvirt store disk images there. I start a guest on hostA and

On Mon, May 22, 2023 at 10:37:09AM +0200, Juergen Gross wrote: > In normal cases PCI passthrough in PV guests requires to start the guest > with e820_host=1. So it should be rather easy to limit allocating the > 64MB in PV guests to the cases where the memory map has non-RAM regions > especially in the first 1MB of the memory. > > This will cover even hotplug cases. The only case

Folks, I got this warning today. I cant tell when and why this happened, so I do not know yet how to reproduce. Maybe someone has a quick idea. [85109.572032] WARNING: CPU: 30 PID: 197360 at net/core/flow_dissector.c:764 __skb_flow_dissect+0x1f0/0x1318 [85109.572036] Modules linked in: vhost_net vhost macvtap macvlan tap vfio_ap vfio_mdev mdev vfio_iommu_type1 vfio kvm xt_CHECKSUM ipt_MASQUERADE

Hi, Here is a list of packages for 6.3 for which upstream SRPMS are available but which aren't built on CentOS. i686 only (these *are* being built, but won't show up in a x86_64 ls): xorg-x11-drv-geode xorg-x11-drv-neomagic PPC: iprutils libehca libica librtas libvpd (still available as rpm) lsvpd powerpc-utils ppc64-diag ppc64-utils servicelog yaboot S390: compat-gcc-295 openssl-ibmca

Hi, The fact that apparently the last tigervnc update from upstream was missed triggered me to check for missing updates and packages in 6.3. Here are my results. Sorry for any false positives that might have crept in, but note that some of the 6_x updates actually are updates and not a parsing error. And perhaps an occasional false positive due to having to compare upstream SRPMS vs downstream

Hi I need the e820_host option for a passthrough of an digitaldevices dvb-s2 card. Without this I'cant initialize the card in the domU. On an all my domU's with high IO load like an file server I need to set max_grant_frames = 64 or higher. Without this I get a lot of messages on dom0/domU and kernel exceptions. I've read it should be ok to set it = 256 on all domU's

On 07.06.23 15:12, Christoph Hellwig wrote: > On Mon, May 22, 2023 at 10:37:09AM +0200, Juergen Gross wrote: >> In normal cases PCI passthrough in PV guests requires to start the guest >> with e820_host=1. So it should be rather easy to limit allocating the >> 64MB in PV guests to the cases where the memory map has non-RAM regions >> especially in the first 1MB of the

On Wed, Jul 06, 2016 at 01:45:58PM -0400, Craig Gallek wrote: > On Thu, Jun 30, 2016 at 2:45 AM, Jason Wang <jasowang at redhat.com> wrote: > > Hi all: > > > > This series tries to switch to use skb array in tun. This is used to > > eliminate the spinlock contention between producer and consumer. The > > conversion was straightforward: just introdce a tx skb

On 09.06.23 17:38, Juergen Gross wrote: > On 07.06.23 15:12, Christoph Hellwig wrote: >> On Mon, May 22, 2023 at 10:37:09AM +0200, Juergen Gross wrote: >>> In normal cases PCI passthrough in PV guests requires to start the guest >>> with e820_host=1. So it should be rather easy to limit allocating the >>> 64MB in PV guests to the cases where the memory map has

On 19.05.23 12:10, Marek Marczykowski-G?recki wrote: > On Fri, May 19, 2023 at 06:04:05AM +0200, Christoph Hellwig wrote: >> On Thu, May 18, 2023 at 08:18:39PM +0200, Marek Marczykowski-G?recki wrote: >>> On Thu, May 18, 2023 at 03:42:51PM +0200, Christoph Hellwig wrote: >>>> Remove the dangerous late initialization of xen-swiotlb in >>>>

On Thu, Jun 30, 2016 at 2:45 AM, Jason Wang <jasowang at redhat.com> wrote: > Hi all: > > This series tries to switch to use skb array in tun. This is used to > eliminate the spinlock contention between producer and consumer. The > conversion was straightforward: just introdce a tx skb array and use > it instead of sk_receive_queue. I'm seeing the splat below after

On Thu, Jun 30, 2016 at 2:45 AM, Jason Wang <jasowang at redhat.com> wrote: > Hi all: > > This series tries to switch to use skb array in tun. This is used to > eliminate the spinlock contention between producer and consumer. The > conversion was straightforward: just introdce a tx skb array and use > it instead of sk_receive_queue. I'm seeing the splat below after

Let's say I have libvirt [root@vmhost2 ~]# virsh version Compiled against library: libvirt 4.5.0 Using library: libvirt 4.5.0 Using API: QEMU 4.5.0 Running hypervisor: QEMU 2.12.0 [root@vmhost2 ~]# running on centos 8 and then I have this card [root@vmhost2 ~]# virsh nodedev-dumpxml pci_0000_01_00_0 <device> <name>pci_0000_01_00_0</name>

Hi Does someone know how it is possible these parameters: e820_host max_grant_frames to set with libvirt xml config? I use them with xl config but I want to change to libvirt config/tools. (with libvirt 4.10 it is possible to start pvh domains) -- ------ Greetz

On 20.12.2018 10:12, Ido Schimmel wrote: > +Willem > > On Thu, Dec 20, 2018 at 08:45:40AM +0100, Christian Borntraeger wrote: >> Folks, >> >> I got this warning today. I cant tell when and why this happened, so I do not know yet how to reproduce. >> Maybe someone has a quick idea. >> >> [85109.572032] WARNING: CPU: 30 PID: 197360 at

Hi, trying to pass through a intel x520 VF on a Dell R620, I''m getting in domU: [ 58.162639] pci 0000:00:00.6: address space collision: [mem 0xd500c000-0xd500ffff 64bit pref] conflicts with System RAM [mem 0x00100000-0x176ffffff] [ 58.162654] pcifront pci-0: Could not claim resource 0000:00:00.6/0! Device offline. Try using e820_host=1 in the guest config. and in dom0 (XEN)