A further point of information. Using tcpdump on the main two fileservers I see a lot of udp checksum errors. One of the machines has fragment reassembly timeouts, which probably explains the AFS delays.
I am a bit puzzled by tcpdump claiming errors in the UDP checksum for *outgoing* packets on one of the machines, however. At what point does tcpdump hook into the ethernet hardware? Seems like UDP checksums in outgoing packets should be impossible...
Is there a way to turn off the use of large datagrams on the server side? Given the udp problems, it might work better (at least) with fragmentation.
Joe Buehler
_______________________________________________ OpenAFS-info mailing list OpenAFS-info@openafs.org https://lists.openafs.org/mailman/listinfo/openafs-info