Whamcloud - gitweb
Make server bulk RPC timeouts shorter than the client timeouts, so we don't
authoradilger <adilger>
Fri, 12 Sep 2003 10:43:36 +0000 (10:43 +0000)
committeradilger <adilger>
Fri, 12 Sep 2003 10:43:36 +0000 (10:43 +0000)
commit2de13382b974b8130d49d81888854c17db67b8a4
tree5144365290653de813eb87c5083a012469aa7773
parent935498e08a760f859d1a61accd49c58db6ea70d6
Make server bulk RPC timeouts shorter than the client timeouts, so we don't
have cascading failures.  Server bulk timeout is 1/4 of the client timeout.
Also fix /proc variables to be int, as that is what the functions expect.
b=1845
lustre/include/linux/obd_support.h
lustre/mds/handler.c
lustre/obdclass/class_obd.c
lustre/ost/ost_handler.c
lustre/ptlbd/rpc.c