Search results

See: http://www.linuxquestions.org/questions/slackware-14/mtrr-allocation-failed-graphics-performance-may-suffer-intel-hd2000-igpu-4175430429/ https://lkml.org/lkml/2011/9/9/424 https://bugzilla.redhat.com/show_bug.cgi?id=584493 http://lmgtfy.com/?q=Intel+MTRR+problem

SATA seems to be better on writes, but it uses alot more CPU power and IO/s seems to lower then with VirtIO. Test on iSCSI @ 1Gbps (iometer) 4K READ 100% SEQ 512K WRITE 100% SEQ 4K WRITE 100% SEQ BUS IO/s CPU % READ SPEED BUS IO/s CPU % WRITE SPEED BUS IO/s CPU %...

Writeback will be faster but AFAIK is not that safe against hardware failures.

If i understand this correct: server does not respond to ping replies and you need to reboot it to get network back online again?

You're losing network connectivity or server just reboots?

Install java using this instructions: http://www.liberiangeek.net/2012/09/install-oracle-java-8-jdk-jre-in-ubuntu-12-04/ If you're on ubuntu. Tab does not work on ubuntu although i think it was working some time back. Not sure, maybe i was on pve2.2.

...and how did you get this numbers? What tool+parameters+vm configuration did you use?

Install latest BIOS version: http://www.dell.com/support/drivers/us/en/555/DriverDetails/Product/precision-t7600?driverId=29KNC&osCode=W764&fileId=2992765419 AFAIK you will need to install windows first and then run update Bios.

Could be this error related to filesystem (ext3 vs. etx4) or is this completely irrelevant which fs is used?

I guess the message shows again because kernel is missing driver or is not loaded or something like that.

I don't have no any experiences with this controllers so hard to say. Maybe replacing it with supported RAID controller + BBU if you have enough money or install PVE on Debian but i never tried this: http://pve.proxmox.com/wiki/Install_Proxmox_VE_on_Debian_Squeeze

The firmware seems to be the latest version: http://www.dell.com/support/drivers/us/en/555/DriverDetails/Product/precision-t7600?driverId=WM1VP&osCode=W764&fileId=3002882624 PVE is based on RHEL6x. https://pve.proxmox.com/wiki/Proxmox_VE_Kernel

Disable any device in BIOS you don't need (LAN, onboard video or sound card). Disable all power saving modes, hyper threading etc..Remove RAM modules and use only one slot, remove any unnecessary device attached to PCi-E slot. Update BIOS or firmware.

I was testing sheepdog cluster lately on 3 nodes pve cluster. If i disconnect one of the nodes the sheepdog storage is not usable any more and data can be lost. I guess this is expected in current version?

Why would you need this?

You can install it on dedicated hardware. Here is video how to install napp-it: https://www.youtube.com/watch?v=Li1Y9nI9v2g and basic configuration: https://www.youtube.com/watch?v=u70MlGpQTRM&feature=plcp

http://pve.proxmox.com/wiki/User_Management

I have no idea...It can be anything i guess. What is output of: apache2ctl -S :~# apache2ctl -S VirtualHost configuration: wildcard NameVirtualHosts and _default_ servers: *:8006 localhost (/etc/apache2/sites-enabled/pve.conf:33) Syntax OK

see what is running on p80: fuser -v -n tcp 80 or fuser -v -n tcp 8006 then try to kill: fuser -k -n tcp 80 and restart apache.

I see the point. Thanks. I did one more test because of strange I/Os and i can see i made something wrong? If i re-run the benchmark 3-4 times in period then i get results like above on the first run results are much lower.