In the last episode (Sep 27), Louis A. Mamakos said:
> And I don't disagree with you, it's wonderful work.
>
> What I guess I'm trying to get across is that like any tool, it ought to
> be used properly and in an informed way. For instance, you can mount a
> file system async or with soft updates, and each of these choices have
> their own trade-offs.
>
> Folks ought to consider the likelyhood of this class of data
> corruption, unlikely as it is, and weigh it along with the impact on
> your application, and the differences in performance and loading.
Something to do would be to enable hardware checksumming on 1/2 your
machines, and compare the bad packet counts at reported by netstat on
the unchanged machines for (say) a 1-month period before and after the
change. That should tell you whether you're gaining or losing
reliability. It'll be really easy for me, as my current (software
cksum) stats show no errors at all:
11:41PM up 11 days, 11:17, 18 users, load averages: 0.08, 0.04, 0.01
Name Mtu Network Address Ipkts Ierrs Opkts Oerrs Coll
ti0 1500 <Link#1> 00:02:e3:00:17:00 510130554 0 624290928 0 0
tcp:
300848337 packets received
0 discarded for bad checksums
udp:
127972686 datagrams received
0 with bad checksum
ip:
555526765 total packets received
0 bad header checksums
Each counter has probably rolled over at least 5 times (I have to ask,
why aren't these 64 bit counters?)
--
Dan Nelson
[EMAIL PROTECTED]
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
