OK, I have noticed the last couple of days that I am getting extremely bad
file transfer (reads) response between systems here I have running various
recent flavors of 2.4.9-ac10, 2.4.10-ac12, and 2.4.12-ac3
The nfs server is running the 2.4.12-ac3 or 2.4.10-ac12. I have tried updating
the nfs-utils on it from the stuff supplied with SuSE-7.1 (0.2.1-17) to the
current 0.3.3 stuff with no change.
The clients are running either mount-2.9z or the more current mount-2.11l.
The client system running 2.9z has a 2.4.9-ac10 kernel and the other with
the 2.11l version of mount is running 2.4.10-ac12
This is most noticeable when I have a directory mounted from the server to the
clients that contains bzipped patch files and when I execute the following on
a client:
bzcat /mnt/net/archive/patch-2.4.12-ac3.bz2 |patch -p1
It just sits there for a LONG time waiting for the transfer to start.
I have tried playing around with various -onfsvers options when I mount
the remote directory but it seems to get worse when I try nfsvers=2 (I have
the above command hung in limbo right now on one of the client systems
where I tried -onfsvers=2
When I compile kernels I turn on the "Provide NFSv3 server support" options.
Also scp'ing the files between the systems proceeds at what seems like a
normal rate.
I have looked in the syslog and dmesg outputs when this occurs but nothing
unusual seems to be getting logged.
-- Steven A. DuChene sad@ale.org linux-clusters@mindspring.com sduchene@mindspring.comhttp://www.mindspring.com/~sduchene/ - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Oct 23 2001 - 21:00:19 EST