| To: | Dmitrii Tisnek <dima@xxxxxxxxx> |
|---|---|
| Subject: | Re: netdev.stats change suggestion |
| From: | Chris Wedgwood <cw@xxxxxxxx> |
| Date: | Thu, 24 Jan 2002 03:20:23 -0800 |
| Cc: | netdev@xxxxxxxxxxx |
| In-reply-to: | <Pine.OSF.4.30.0201231450280.15676-100000@kosh.hut.fi> |
| References: | <Pine.OSF.4.30.0201231450280.15676-100000@kosh.hut.fi> |
| Sender: | owner-netdev@xxxxxxxxxxx |
| User-agent: | Mutt/1.3.26i |
On Wed, Jan 23, 2002 at 03:02:14PM +0200, Dmitrii Tisnek wrote:
I've discovered that struct net_device_stats defines counters like
rx_bytes and tx_bytes as unsigned long, which on x86 is, sadly, 32
bits.
How fast is our IO? For most everyone, 32-bits is plenty enough.
Have a daemon/whatever check it from time-to-time and detect overflow.
(although it seems uint64 is used in some headers, so perhaps it's
enough to use that)
In theory we could use 'long long' on 32-bit architectures, but then
we can't do atomic add/sub operations...
--cw
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: netdev.stats change suggestion, Dmitrii Tisnek |
|---|---|
| Next by Date: | Re: netdev.stats change suggestion, Jeff Garzik |
| Previous by Thread: | Re: netdev.stats change suggestion, Dmitrii Tisnek |
| Next by Thread: | Re: netdev.stats change suggestion, Jeff Garzik |
| Indexes: | [Date] [Thread] [Top] [All Lists] |