13

After tearing my hair out on newly arrived lovely R730xd with 16 3.5" disk slots spinning fans at 15k RPM when Intel X520-DA2 10G card is in any PCI slot, I've found following solution for CentOS 6.7 to quiesce fans in jet mode, although it is brute force, not taking into account 10G card's temperature probe - may result it card burnout from overheating, but ...


6

This sounds like a speed/duplex mismatch causing collisions and retransmits. Misconfiguration between the server and the other side could cause this. Another reason for the mismatch could be failing autonegotiation. Make sure both ends of the connection are configured identically regarding speed and duplex.


5

Yes. MSI-X needs interrupt remapping enabled to fully work. From a Intel PDF: Intel® Virtualization Technology for Directed I/O Architecture Specification October 2014 5.1 Interrupt Remapping The interrupt-remapping architecture enables system software to control and censor external interrupt requests generated by all sources including those from interrupt ...


4

So after the chat in the comments I have some probably bad news. Dell hardware that ships with a server as a configured item - which IIRC those broadcoms where - is almost never comparable between generations. Dell tends to put custom firmware that hooks into all their management systems on these things. So the short of it is the part is probably not ...


3

Honestly, the short answer is that you need to switch to Intel nics. Broadcom has been trying to fix this problem for over a year and they still haven't licked it. Avoid Networking Issues Hyper V Virtual machines lose network connectivity when you use Broadcom That second link brings you to a Microsoft site which will link you out again to driver pages ...


3

Please update your ESXi hosts. This is the one thing you've really missed in the troubleshooting steps. Your 5.5 installation is almost 1 year old!! As of this writing, the current version of ESXi 5.5 is 2718055. The current ESXi 6.0 build number is 2809209. Dell, HP, doesn't matter... you're still supposed to update your ESXi installations. Many people ...


2

I believe you should investigate if any of the NIC driver/Windows NDIS offload settings relate to your problem. I am most suspicious of the LSO (Large Send Offload) function as I've seen it totally wreck a service (Dell server w. Broadcom NIC) in a manner which defied all troubleshooting book definitions of anything. The actual effect of LSO when it ...


2

Root cause is Virtual Machine Queue which can be found under the advanced properties of your network adapter. Disable it and all problems will go away. I have noticed this issue primarily with broadcom adapters but other adapters may be effected. Thorough explanation to come.


2

The problem was hardware, not software. And apparently very simple one. Once the blade has been shut down, physically removed from the chassis and then reattached (at the same slot), we have finally attained a proper 10G link. Just that :)


2

Well, looks like it's Cisco bug https://tools.cisco.com/bugsearch/bug/CSCug68370 and upgrading to one of the "known fixed" IOS versions (15.1(2) SG4) seems to have fixed it.


1

It should be the Solid State Cache disk policy for LSI CacheCade 2.0. When using CacheCade 2.0, you can set the cache device as writethrough (similar to how CacheCade 1.0 worked) or writeback (to increase random write performance).


1

Most likely the switch isn't letting the packets through. Some pcaps might also be diagnostically useful.


1

Not sure if this is exactly an "answer" or not, but it did solve my issue, as far as this particular case is concerned. This seems to be related to ACPI. I edited my /etc/grub.conf file to add the following to the end of the kernel line: noapic acpi=off pci=noacpi I'm now no longer seeing any errors in the log. Could it be that power saving features were ...


1

Well, this is a known issue as described in this Microsoft kb article: https://support.microsoft.com/en-us/kb/2986895 What really helped us in our case, was not only to disable the VMQ in all affected Network adapters properties as suggested by Microsoft, but also to disable it in the Virtual machine's properties (to uncheck “Enable Virtual Machine Queue” ...


1

I've seen this problem with Dell servers. Go into the system (hardware) setup and look for a conflicting network adapter assignment such as Static with a useless default IP address. If you wish to continue assigning a dynamic IP address to that NIC, make sure the BIOS is configured for the same at boot-up.


1

Just wanted to point out to official Microsoft KB about this: Virtual machines lose network connectivity when you use Broadcom NetXtreme 1-gigabit network adapters As I understand this VMQ thing not properly implemented in cheap NICs and as vendors tend to deliver drivers which are targeted to whole product family of NICs not for specific one (i.e. one ...


1

This can also be "advanced" NIC atributes, like PowerManagement ones or IRQ priority. Assuming you have the same version of drivers. Go to: Device Manager -> Network Interfaces -> Properties for the NIC -> Advanced Tab. Check and compare all values here.


1

always look at the networking device for clues..... so, if cisco, do a "show interfaces f0/11" or whatever it may be in your case. retransmits can also be due to a bad ethernet port/nic/cable, such as due to "crosstalk"..... show int on the switch should show you these error stats, if thats the case, and it will be obviously way too high EDIT: as this is ...


Only top voted, non community-wiki answers of a minimum length are eligible