Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Am 13.06.2012 um 17:45 schrieb Arnold Krille: > On Wednesday 13 June 2012 09:26:45 Felix Frank wrote: >> On 06/12/2012 08:23 PM, Dennis Jacobfeuerborn wrote: >>>> Don't use crossover cables.. In my experience use crossover >>>> cables for >>>> two >>>> >>>>> node cluster make only problems... use a simple switch.. >>> >>> Why would a setup with 2 cables and a switch be more reliable than >>> just a >>> single cable? That doesn't make sense. >> >> Uhm, I don't think that was Eduardo was suggesting. >> >> Someone on this list (Digimer?) has made a good point some time about >> switches allowing for better forensics in case of link problems >> (i.e., >> the switch can help you identify the side with a faulty NIC/cable). >> >> On the other hand, a switch introduces one more (two really, counting >> the extra required cable) possible point of replication failure. I've >> never had negative experiences with back-to-back connections either. > > A switch also has input- and output-buffers introducing another step > of > latency. > > We would use a direct link-cable if that scaled for more then 2 > servers. (We > actually though about just adding more network-cards, connect three > servers > with three cables directly and use bridges with (r)stp for the > storage ring. > But now we will just use the additional cards for more redundancy to > have > trunked connections to two switches...) Two switches can also be a problem: We have bonding with 2 interfaces connected to 2 switches, each switch connected to a different uplink in HSRP mode. Some weeks ago we experienced high packet loss with the result, that the delivered web- services were more or less unusable. After change of the switches the problems were gone. For the direct cluster connection we have 2 bonded Gbit-interfaces, but one connection only runs on 100 Mbit. Maybe a switch would help in this case for diagnosis. But I will just put additional 2 interfaces into the nodes. Helmut Wollmersdorfer