Quantcast
Channel: CentOS Bug Tracker - Issues
Viewing all articles
Browse latest Browse all 19115

0005878: All ioatdma channels floods dmesg with DRHD faults, strange dma behavior

$
0
0
On a brand new hardware (HP ProLiant BL460c Gen8, BIOS I31, dual Xeon E5-2670 with 64Gig's of ram) with clean minimal network install of Centos x86_64 issued problems with dma and lot's of messages about DRHD/INTR-REMAP.<br /> <br /> Here is dmesg log after boot <a href="http://pastebin.com/FhzMsMD6">http://pastebin.com/FhzMsMD6</a> [<a href="http://pastebin.com/FhzMsMD6" target="_blank">^</a>] .<br /> Here is lspci -vv log <a href="http://pastebin.com/0i4fj3nS">http://pastebin.com/0i4fj3nS</a> [<a href="http://pastebin.com/0i4fj3nS" target="_blank">^</a>] .<br /> Kernel 2.6.32-279.2.1.el6.x86_64.<br /> Default bios settings.<br /> <br /> After all kind of network load none of the counters in /sys/class/dma*/memcpy_count incremented.<br /> <br /> Adding intel_iommu=off to the kernel command line in grub nothing changed.<br /> <br /> For example Gentoo kernel branch 3.3.* works good without such errors.

Viewing all articles
Browse latest Browse all 19115

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>