Let me explain a bit more. > <2> All data written on the unified volume is copied to a different > server by using a configuration file on server side. In other words, I don't want a file under one unified volume to be copied among four servers from the standpoint of network bandwidth, but I need the minimum redundancy that sytem still works when one of four servers stops, but donesn't work in case that two of four servers fails. 2007/12/11, Tsukasa Morii <tsukasa.morii@xxxxxxxxx>: > Hi, > > Please help me make a configuration file which meets the following > specification. I could't understand if it is feasible with glusterfs, even > though I spent a lot of time on it. > > [SITUATION] > There are four servers named SERVER_1, SERVER_2, SERVER_3, and SERVER_4. > There're also a few clients and each client unifies bricks exported > from the servers.(One unified volume is made up at the client side) > Name space of the unified volume is maintained on SERVER_1. > > In addition to the configuration above, I'd like to add two more > functions. > > <1> The name space on SERVER_1 is replicated to Server_2 for the purpose > of redundancy by using a configuration file on client side. > > <2> All data written on the unified volume is copied to a different > server by using a configuration file on server side. > > e.c. > Data_A written on SERVER_1 is copied to SERVER_2. > Data_B written on SERVER_2 is copied to SERVER_3. > Data_C written on SERVER_3 is copied to SERVER_4. > Data_D written on SERVER_4 is copied to SERVER_1. > [All data is maintained on two servers for redundancy.] >