Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On Tuesday 25 May 2010 15:06:43 Bart Coninckx wrote: > On Thursday 20 May 2010 21:57:43 Ben Timby wrote: > > On Thu, May 20, 2010 at 3:52 PM, Bart Coninckx <bart.coninckx at telenet.be> > > wrote: > > > Since testing with a switch resulted in even poorer results, I'll shy > > > away from that for now. Will have a go at investigating with Wireshark > > > though seeing the problem will probably not indicate a solution right > > > of the bat. > > > > Identifying the problem is half the solution. Good luck! > > Hi all, > > thought I'd report back about the issue. I didn't get round to sniffing and > analyzing the traffic, but I did try to change the value of > /proc/sys/net/ipv4/tcp_reordering to 127. > > This seemed to boost things by 50% and I ended up at about 180 MB/sec, > which I understand is a to be expected value. > > Results seemed only to be consisted after restart the bond0 driver after > changing tcp_reordering though. > > Glad I finally tackled this one. > > Cheers for your help, > > Bart > _______________________________________________ > drbd-user mailing list > drbd-user at lists.linbit.com > http://lists.linbit.com/mailman/listinfo/drbd-user > What still is an issue though, is the fact that if I take out a networkcable longer than 5 seconds, it will not go up again after reconnecting the cable. I don't have this problem with a switch, so I guess that both interfaces are disabled and do not send electrical signals over the wire which could encourage the other interface to wake up again.