[DRBD-user] drbd + 10gig network

Mike Lovell mike at dev-zero.net
Fri Oct 30 20:52:40 CET 2009

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.

Todd Denniston wrote:
> Mike Lovell wrote, On 12/23/-28158 02:59 PM:
>>> On 10/23/2009 10:40 PM, Mike Lovell wrote:
>>>> exaggerated the problem. when the sync hangs, the drbd module is 
>>>> almost completely unresponsive. i tried doing a pause-sync and then 
>>>> resume-sync thinking that it would nudge the module into working 
>>>> but the commands timeout on talking to the module. i can still cat 
>>>> /proc/drbd but that is about it until i take down the network 
>>>> interface and drbd detects the network change. if i then bring back 
>>>> up the interface, drbd detects it can talk again but then only 
>>>> syncs a couple of megabytes before stalling again. i have tried 
>>>> every way i can think of to check the integrity of the network link 
>>>> between the hosts and everything says they are fine except for 
>>>> during a ping flood there will be a few out of a couple h
>> yes, i am using software raid. i guess i didn't try changing that 
>> during my hardware changes. i'll see if i can scrounge up some raid 
>> controllers to test this with.
>> mike
> One other thing I would suggest looking at, which I don't think anyone 
> else mentioned.
> Network equipment in between the mirrors. (switches, cables, crossovers)
> What is your MTU?
> I experienced a problem _very_ similar with the set I maintained when 
> a 10/100baseT hub/switch was placed between the units instead of the 
> crossover cable I had been using.  The base problem was that the hub 
> only supported MTUs smaller than 1500, and I was using 6000.  If you 
> are using Gig equipment I would expect a considerably larger maximum 
> MTU, but there _may_ be a limit somewhere there.
> hope this helps.
i am essentially using a crossover cable between the boxes and a mtu of 
9000. i did try with the standard 1500 and 9000 frame sizes and had 
failures with both.


More information about the drbd-user mailing list