similar to: Sluggish server with big array

Hi, The following 4 patches enable direct device assignment (PCI passthru) for HVM guest on AMD IOMMU platforms. Please apply them against C/S 16491 as the named order. To enable AMD IOMMU, please add "enable_amd_iommu" as xen boot parameter. 1-cleanup.patch: code cleanup, bug fix, minor enhancements to existing amd-iommu codes. 2-passthru-amd.patch: passthru support, modifications to

Since good server designs have come up in the past, I wanted to point out a "low-cost" server option that has good I/O, and the vendor offers _your_choice_ of not only Fedora Core or Red Hat Enterprise Linux, but _also_ CentOS _shipped_ with it! IN-A-NUTSHELL ... Starting at just over $750, you can get a single Socket-939 Opteron 1xx (dual-core is an option) system with up to 4GiB of

Hi, I just installed CentOS 4.4 x86_64 on our new 2 x Dual Core Opteron Server. First the system was unstable, but I after turning of Power-now it runs stable (anyone else experienced this?). However the following line in dmesg puzzles me: tg3: eth0: No interrupt was generated using MSI, switching to INTx mode. Please report this failure to the PCI maintainer and include system chipset

I have used the SYSLINUX 3.35 successfully to boot up vesamenu.c32 as well as menu.c32 on an HP Intel PC (Intel 965 chipset) and a few other types of PCs. But when I use those very same SYSLINUX menus on an AMD Opteron server (IBM x326m), it is capable of loading up vesamenu.c32 and menu.c32 and displaying a list of menu items. But as soon as I select any item whatsoever in the menu list, the

Hi all, I have a machine that won't boot syslinux 4.02 but will boot syslinux 3.53. We've installed syslinux 4.02 on a number of machines but only this one has a problem. The problem is that the machine hangs entirely after printing "boot:" on the tty. The stanza being booted in /boot/extlinux.conf is: label xe # XenServer kernel mboot.c32 append /boot/xen.gz

In this thread: http://syslinux.zytor.com/archives/2007-February/008014.html I reported that IBM Opteron servers with Broadcom BCM5780 chipsets would freeze randomly in the PXE menus from the SYSLINUX 3.35 tools vesamenu.c32 and menu.c32. There did not seem to be any reason for this nor systematics in when the servers would lock up. The solution is now available: Upgrade your IBM servers to

Anyone using boards with this chipset? I've gotten some dual core single cpu boxes along with the physical dual cpu boxes I just received and they're using the Serverworks HT1000 (Broadcom 5785) chipset. My CentOS 4.2 DVD doesn't want to recognize the chipset so I can't see any of the SATA drives in the integrated SATA ports. Drives on 3Ware cards work as expected, but I

On Mon, Nov 10, 2008 at 10:01 AM, Fernan Aguero <fernan@iib.unsam.edu.ar> wrote: > > Date: Wed, 29 Oct 2008 14:05:22 -0300 > From: Fernan Aguero <fernan@iib.unsam.edu.ar> > To: Kirk Strauser <kirk@strauser.com> > Cc: freebsd-stable@freebsd.org, d@delphij.net, > John Baldwin <jhb@freebsd.org>, re@freebsd.org > Subject: Re: [FreeBSD] Fix for

Hi all, So I have an XFS file system within LVM which has an external log. My mount option in FSTAB is; /dev/vg_spock_data/lv_data /data xfs logdev=/dev/sdc1,nobarrier,logbufs=8,noatime,nodiratime 1 1 All is well no issues and very fast. Now I'd like to snapshot this bad boy and then run rsnapshot to create a few days backup. A snapshot volume is created w/o issue; lvcreate -L250G -s

[This is fairly far from the topic of the mailing-list: we may want to take further discussion to email or the tech list] Jeremy writes: > it violates the principle of > least suprises for the nfs user. ie. They may get access > denied when the UNIX perms say they should be granted access. Paul replies: > But wouldn't it also be a "surprise" when an NFS user finds

This hook script tries to address the fact that a RHEV-H installation will format all the storage devices available in the machine in order to create HostVG and AppVG with all the available space. It may be the case that RHEV-H needs to respect and co-exist with a proposed partitioning scheme, not getting all the storage space for HostVG and AppVG volume groups. The proposed solution adds the

Processing commands for control at bugs.debian.org: > # Saturday 2 February 19:03:31 UTC 2013 > # Tagging as pending bugs that are closed by packages in NEW > # http://ftp-master.debian.org/new.html > # > # Source package in NEW: cliff-tablib > tags 699594 + pending Bug #699594 [wnpp] ITP: cliff-tablib -- tablib formatters for cliff Added tag(s) pending. > # Source package

Hi folks, an Asterisk (www.asterisk.org) box will be built with the following specs and I wanted to know if CENTOS has a built process/config/parameter/special distro to target the AMD Opteron Dual Core plataform: 2 amd opteron 265 dual core 1.8 Ghz 2mb l2 cache 2x1024 ocz c2-6400 dual channel gold GX XTC 2 Seagate 16mb cache 300 GB barracuda 7200 drives another 2 Seagate 500 GB 16mb cache

We're using PXELINUX for bootstrapping the network install our Linux cluster nodes. We just got some new IBM 326m dual-Opteron servers with Broadcom NetXtreme BCM5780 dual-Gigabit Ethernet ports. These dual-Ethernet servers work in an annoying way with PXELINUX when we configure for booting from the local hard disk as the PXE-client downloads this file from the DHCP/TFTP server: label

for all three nodes:=0A= =0A= Brick1: gluster-0-0:/mseas-data-0-0=0A= Brick2: gluster-0-1:/mseas-data-0-1=0A= Brick3: gluster-data:/data=0A= =0A= =0A= Which node are you trying to mount to /data? If it is not the=0A= gluster-data node, then it will fail if there is not a /data directory.=0A= In this case, it is a good thing, since mounting to /data on gluster-0-0=0A= or gluster-0-1 would not

for all three nodes: Brick1: gluster-0-0:/mseas-data-0-0 Brick2: gluster-0-1:/mseas-data-0-1 Brick3: gluster-data:/data Which node are you trying to mount to /data? If it is not the gluster-data node, then it will fail if there is not a /data directory. In this case, it is a good thing, since mounting to /data on gluster-0-0 or gluster-0-1 would not accomplish what you need. To clarify, there

Hi, I have a server (Dell PowerEdge SC1435, ServerWorks HT1000) on which I'd like to try installing FreeBSD. I've already failed to make 7.0 work on this box and was wondering if you have information about the behavior of the upcoming 7.1 on this hardware. I've been following the "HT1000 chipset errata saga" thread, and the commits by sos@ to CVS (around Jan 2008), but have

Hi, how could I get better debugging output from the dom0 kernel? The kernel crashes after some time and debugging output to the console is being scrolled off by messages about NMI stuff trying to do something. I'm using Debian stable and would like to make a bug report, but without any useful information there's no point. So far, all I can say is that it seems to take over 12 and less

fwiw erver icecast 1.3.7 / ices 0.0.1beta5 erver on a dsl line (384kbps) client on a LAN separate to it going through several hops winamp has the drop client problems. And recently another weird problem, it spawns with only one channel balance way over to the right. this can suck if your windows has no balance control for its audio! onique: stays connected for hours and hours xmms/unix .

I am pretty sure that the integrity of my mp3's is okay. I know that music match shreds the mp3 data and produces mp3 files that are not ISO compliant. I always use WaveLab and the radium codec to encode my sets and enable the ISO compatibility option at all times. This problem only seemed to come about with winamp 2.7 but if sonique is doing it to, I don't know... What about relaying? Do