On 15-Mar-05 Nivedita Singhvi wrote:
Chuck Ebbert wrote:
quoted
This patch optimizes the loopback driver's statistics by using a single
counter for rx and tx stats instead of one for rx and one for tx. It also
adds unlikely() to the test for TSO since it's no longer supported by default.
(Maybe the TSO code should be bracketed by "#if 0" ?)
Hmm, some of us want those counters separate - if this is really
needed, could it be a configurable option, please?
But they _are_ separately reported -- get_stats() takes care of that.
Everything looks exactly the same to userspace after this patch.
--
Chuck
Chuck Ebbert wrote:
On 15-Mar-05 Nivedita Singhvi wrote:
quoted
Chuck Ebbert wrote:
quoted
This patch optimizes the loopback driver's statistics by using a single
counter for rx and tx stats instead of one for rx and one for tx. It also
adds unlikely() to the test for TSO since it's no longer supported by default.
(Maybe the TSO code should be bracketed by "#if 0" ?)
Hmm, some of us want those counters separate - if this is really
needed, could it be a configurable option, please?
But they _are_ separately reported -- get_stats() takes care of that.
Everything looks exactly the same to userspace after this patch.
--
Chuck
Hmm, I see the following in your patch:
+ stats->rx_bytes += lb_stats->rx_tx_bytes;
+ stats->tx_bytes = stats->rx_bytes;
Doesn't that mean RX is now twice what it should be
and so is TX? They are separately reported, but if
so, their real value should be half of rx_tx_bytes
each, correct?
thanks,
Nivedita
Hmm, I see the following in your patch:
+ stats->rx_bytes += lb_stats->rx_tx_bytes;
+ stats->tx_bytes = stats->rx_bytes;
Doesn't that mean RX is now twice what it should be
and so is TX? They are separately reported, but if
so, their real value should be half of rx_tx_bytes
each, correct?
Ah, just beat me silly with a cluestick.
I see what you're doing now..it's fine.
thanks,
Nivedita