All of lore.kernel.org
 help / color / mirror / Atom feed
* TX vs RX pause frame question
@ 2017-03-26 10:11 Benjamin Herrenschmidt
  2017-03-26 17:55 ` John Fastabend
  0 siblings, 1 reply; 3+ messages in thread
From: Benjamin Herrenschmidt @ 2017-03-26 10:11 UTC (permalink / raw)
  To: netdev

Hi !

It's not 100% clear to me looking at various drivers what is
considered "rx_pause" and what is "tx_pause" (from the ethtool
terminology).

Is "rx_pause" about receiving pause frame to throttle the transmitter
or is it about sending pause frames when the receiver gets full ?

Thanks,
Ben.

^ permalink raw reply	[flat|nested] 3+ messages in thread
* Re: TX vs RX pause frame question
  2017-03-26 10:11 TX vs RX pause frame question Benjamin Herrenschmidt
@ 2017-03-26 17:55 ` John Fastabend
  2017-03-26 21:08   ` Benjamin Herrenschmidt
  0 siblings, 1 reply; 3+ messages in thread
From: John Fastabend @ 2017-03-26 17:55 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, netdev

On 17-03-26 03:11 AM, Benjamin Herrenschmidt wrote:
> Hi !
> 
> It's not 100% clear to me looking at various drivers what is
> considered "rx_pause" and what is "tx_pause" (from the ethtool
> terminology).
> 
> Is "rx_pause" about receiving pause frame to throttle the transmitter
> or is it about sending pause frames when the receiver gets full ?
> 
> Thanks,
> Ben.
> 

The common implementation, at least on the Intel devices, is rx_pause
should be enabled so the device will respond to receiving a pause frame, e.g.
stop sending packets. And tx_pause is for enabling/disabling sending of
pause frames.

Thanks,
John

^ permalink raw reply	[flat|nested] 3+ messages in thread
* Re: TX vs RX pause frame question
  2017-03-26 17:55 ` John Fastabend
@ 2017-03-26 21:08   ` Benjamin Herrenschmidt
  0 siblings, 0 replies; 3+ messages in thread
From: Benjamin Herrenschmidt @ 2017-03-26 21:08 UTC (permalink / raw)
  To: John Fastabend, netdev

On Sun, 2017-03-26 at 10:55 -0700, John Fastabend wrote:
> On 17-03-26 03:11 AM, Benjamin Herrenschmidt wrote:
> > Hi !
> > 
> > It's not 100% clear to me looking at various drivers what is
> > considered "rx_pause" and what is "tx_pause" (from the ethtool
> > terminology).
> > 
> > Is "rx_pause" about receiving pause frame to throttle the transmitter
> > or is it about sending pause frames when the receiver gets full ?
> > 
> > Thanks,
> > Ben.
> > 
> 
> The common implementation, at least on the Intel devices, is rx_pause
> should be enabled so the device will respond to receiving a pause frame, e.g.
> stop sending packets. And tx_pause is for enabling/disabling sending of
> pause frames.

Thanks, I'll have my driver match that.

Cheers,
Ben.

^ permalink raw reply	[flat|nested] 3+ messages in thread
end of thread, other threads:[~2017-03-26 21:08 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-03-26 10:11 TX vs RX pause frame question Benjamin Herrenschmidt
2017-03-26 17:55 ` John Fastabend
2017-03-26 21:08   ` Benjamin Herrenschmidt

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.