Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Hello, I use DRBD 0.7.13 on two RedHat ES4 systems (kernel 2.6.9-11ELSMP). The Primary is more powerful than the Secondary and during some batch processing, the amount of data being replicated can reach several Giga Bytes. In the same time, I experience frequently very slow response time on the replicated filesystems. For example, a "simple" "rm -r" that usually takes 2 seconds can last several minutes. I already upgraded DRBD since it appears there was a bug with the former version on SMP hosts. My questions are: what happens when there is a congestion somewhere (on the network, on the Secondary....), does it slow down the Primary ? Thanks, Jerome