just a note that most normal devices do not use more then 32 bits for
traffic counters, and I include the high-end Cisco routers in this. They
figure that if you are monitoring the traffic numbers and know when they
will wrap (at 32 bits) you can detect the wrap and include it in your
stats, they even make comments about the need to monitor the really high
speed ATM connections more frequently then others so that you can detect
the wrap anc account for it.
longer counters would be nice (it's always nice when Linux is ahead of the
industry :-) but they are not a mandatory feature (and now that I think
about it they will break some monitoring software.)
David Lang
On Mon, 24 Aug 1998, Juha Virtanen wrote:
> David Luyer writes:
> :>beat it, I believe). Generally on highly multi-user machines, the first one
> :>to wrap is the context switch count.
>
> It's not. Quickest wrappers are network interface byte
> counters. Do have some real value they should be 64 bits wide.
>
> :>had? Is there some low priority job scheduler in the kernel to do this
> :>kind of thing (weekly or so tasks which belong in kernel space)?
>
> Could idle task do this?
>
> :>We can be fairly certain that the stats won't wrap within a week, or we
>
> Depends on counter. 4 GB of network traffic isn't that much at
> all (my home box has about 0.5 GB network traffic daily and it
> mostly consists of running X apps over network).
>
> Theoretically, it takes only 344 seconds to push over 4 GB stuff
> out to 100 Mb/s ethernet.
>
> Also, IDE devices tend to generate huge amounts of interrupts on
> busy machine.
>
> :>for a more active Ultrix box). If I had a Linux box like that, I'd like an
> :>accurate uptime report (but again, it's not vital, just nice).
>
> I'd like to see accurate counters especially for network traffic.
> But, as we're now in code-freeze, I suppose 64-bit counters will
> be one of the new features in 2.3.x series.
>
>
> Juha
> --
> <URL:http://www.iki.fi/jiivee/>
>
> Säästä paperia - älä tulosta tätä meiliä.
> Save paper - do not print this e-mail.
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.rutgers.edu
> Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html
>
-----BEGIN PGP SIGNATURE-----
Version: PGP for Personal Privacy 5.0
Charset: noconv
iQEVAwUBNeHQuj7msCGEppcbAQG3iAf/blT9kuRq/8ju4kUf9mN/WcpILqN9Ss9/
X2z03iCoUkFVERKzHSJy6P1KwedjaCsn4o5vj/1kOGK+Pu+n6mJ85t8rfQDwYBFH
hjcp2mGDzoI/iDGaIr/jruR4580FoYJY05nz5bUZDXddehYAs9DtZfe0ZlepBBrV
BnsEeyALwk2EWFK0bsdy0PkMSO1jyYjE6Li+A09f+M6/C7Ldmoc3ZCKP66+A3fh2
Danm5k2szUf059Ui8PhnFFvqxQc3Sf1bg0jWmP/jYW146QHnG5uhSNxD/Y5yqc8m
dYklfwE1lgIsyibaQ02rRDqbqp3sxEs6TWAIbggU+JfBTbmgq6YWlg==
=/X55
-----END PGP SIGNATURE-----
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html