b=6019
- workaround for cascading timeouts when failure of 1 server node causes failures of unrelated connections. this caused different problems. for example, lock cancel timeouts.
Showing
- lustre/include/linux/lustre_ha.h 3 additions, 0 deletionslustre/include/linux/lustre_ha.h
- lustre/include/linux/lustre_import.h 6 additions, 1 deletionlustre/include/linux/lustre_import.h
- lustre/ldlm/ldlm_lockd.c 21 additions, 0 deletionslustre/ldlm/ldlm_lockd.c
- lustre/ldlm/ldlm_request.c 4 additions, 0 deletionslustre/ldlm/ldlm_request.c
- lustre/obdclass/genops.c 1 addition, 0 deletionslustre/obdclass/genops.c
- lustre/ptlrpc/client.c 9 additions, 1 deletionlustre/ptlrpc/client.c
- lustre/ptlrpc/import.c 10 additions, 2 deletionslustre/ptlrpc/import.c
- lustre/ptlrpc/niobuf.c 0 additions, 1 deletionlustre/ptlrpc/niobuf.c
- lustre/ptlrpc/pinger.c 124 additions, 40 deletionslustre/ptlrpc/pinger.c
- lustre/ptlrpc/recover.c 1 addition, 0 deletionslustre/ptlrpc/recover.c
Loading
Please register or sign in to comment