Skip to contentSkip to conversation

natsemi: Messages being noisy

PATCH In review Ingo Oeser 3 participants 5 messages Sep 13, 2006 – Sep 15, 2006

Subsystems (2)
lore
Share & tools
lore

Ingo Oeser

author
#0 lore raw

PATCH 1/1 natsemi: Messages being noisy

Hi there,

I get the following message when trying to transfer big files (via FTP or SCP) since Linux 2.6.16.27. It didn't happen with Linux 2.6.13.4.

[702238.242237] eth1: increased tx threshold, txcfg 0xd0f01008.
[702238.242649] eth1: increased tx threshold, txcfg 0xd0f0100a.

What about putting this message at the message level "DEBUG" or even under pr_debug()?

This NIC is just used for PPPoE in our setups.

The other message "tx underrun with maximum tx threshold" is much more useful, since it indicates a real problem.

So I would suggest the following patch:

drivers/net/natsemi.c renamed from drivers/net/natsemi.c~ +1 -2
@@ -2338,8 +2338,7 @@
 		if ((np->tx_config & TxDrthMask) < TX_DRTH_VAL_LIMIT) {
 			np->tx_config += TX_DRTH_VAL_INC;
 			if (netif_msg_tx_err(np))
-				printk(KERN_NOTICE
-					"%s: increased tx threshold, txcfg %#08x.\n",
+				pr_debug("%s: increased tx threshold, txcfg %#08x.\n",
 					dev->name, np->tx_config);
 		} else {
 			if (netif_msg_tx_err(np))
author
#1 lore raw

Hi there,

Quoted 8 lines · Ingo Oeser

I get the following message when trying to transfer big files (via FTP or SCP) since Linux 2.6.16.27. It didn't happen with Linux 2.6.13.4.

[702238.242237] eth1: increased tx threshold, txcfg 0xd0f01008.
[702238.242649] eth1: increased tx threshold, txcfg 0xd0f0100a.

What about putting this message at the message level "DEBUG" or even under pr_debug()?

Now I even know, that this happens together with a small disruption of traffic, which makes applications hang for a second or less.

Is it possible to have the maximum value right from the start? May I tune it somewhere to be the maximum from the start?

Would you accept patches for this?

Regards

Ingo Oeser

#2 lore raw
Quoted 12 lines · Ingo Oeser

Hi there,

Quoted 8 lines · Ingo Oeser

I get the following message when trying to transfer big files (via FTP or SCP) since Linux 2.6.16.27. It didn't happen with Linux 2.6.13.4.

[702238.242237] eth1: increased tx threshold, txcfg 0xd0f01008.
[702238.242649] eth1: increased tx threshold, txcfg 0xd0f0100a.

What about putting this message at the message level "DEBUG" or even under pr_debug()?

Quoted 7 lines

Now I even know, that this happens together with a small disruption of traffic, which makes applications hang for a second or less.

Is it possible to have the maximum value right from the start? May I tune it somewhere to be the maximum from the start?

Would you accept patches for this?

This will (if I recall) increase transmit latency. It's a fine line. You might tune it up, but this fallback path probably should not be removed..

author
#3 lore raw

Hi Tim,
Hi Jeff,

Quoted 5 lines · [email protected] wrote:
Quoted 4 lines · Ingo Oeser
Quoted 3 lines · Ingo Oeser

I get the following message when trying to transfer big files (via FTP or SCP) since Linux 2.6.16.27. It didn't happen with Linux 2.6.13.4.

Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
[702238.242237] eth1: increased tx threshold, txcfg 0xd0f01008.
[702238.242649] eth1: increased tx threshold, txcfg 0xd0f0100a.

Is it possible to have the maximum value right from the start? May I tune it somewhere to be the maximum from the start?

This will (if I recall) increase transmit latency. It's a fine line. You might tune it up, but this fallback path probably should not be removed..

Will implementing "ethtool_ringparam" be the right thing for this?

Or is there simply no ethtool mechanism for setting up thresholds, yet?

If not, I would simply like to have my original pr_debug patch included. The actual value of the tx threshhold can be queried
via "ethtool -d eth0" already.

What do you think?

Regards

Ingo Oeser

#4 lore raw
In reply to [email protected]
Quoted 7 lines · On Thu, Sep 14, 2006 at 08:46:07AM -0700, [email protected] wrote:
Quoted 2 lines · Ingo Oeser

Is it possible to have the maximum value right from the start? May I tune it somewhere to be the maximum from the start?

This will (if I recall) increase transmit latency. It's a fine line. You might tune it up, but this fallback path probably should not be removed..

Yes, raising the limit there will increase transmit latency since it causes the chip to wait for more data to be DMAed before it begins pushing the frame out. I guess the dropped packet could be worked around by resubmitting the dropped packet when we reconfigure the chip, though obviously that's not ideal.

It would be interesting to understand what caused this to start happening. The main change in natsemi itself between 2.6.13.4 and 2.6.16.27 is the introduction of NAPI although it could be some other change causing PCI bandwidth to become more scarce.

Signature · 1 line
"You grabbed my hand and we fell into it, like a daydream - or a fever."