Re: MSI-X vector count on 82754L

[fixing address of the netdev@ list, sorry - A.]

On Mon, Sep 19, 2011 at 1:31 AM, Arnaud Lacombe [off-list ref] wrote:

Hi folks,

In:

commit 4662e82b2cb41c60826e50474dd86dd5c6372b0c
Author: Bruce Allan [off-list ref]
Date:   Tue Aug 26 18:37:06 2008 -0700

   e1000e: add support for new 82574L part

   This new part has the same feature set as previous parts with the addition
   of MSI-X support.

   Signed-off-by: Bruce Allan [off-list ref]
   Signed-off-by: Jeff Kirsher [off-list ref]
   Signed-off-by: Jeff Garzik [off-list ref]

MSI-X support was added to the e1000e driver, later on slightly reworked by:

commit 8e86acd7d5968e08b3e1604e685a8c45f6fd7f40
Author: Jeff Kirsher [off-list ref]
Date:   Mon Aug 2 14:27:23 2010 +0000

   e1000e: Fix irq_synchronize in MSI-X case

   Based on original patch/work from Jean Delvare [off-list ref]
   Synchronize all IRQs when in MSI-X IRQ mode.

   Jean's original patch hard coded the sync with the 3 possible vectors,
   this patch incorporates more flexibility for the future and aligns
   with how igb stores the number of vectors into the adapter structure.

   CC: Jean Delvare [off-list ref]
   Cc: Jesse Brandeburg [off-list ref]
   Signed-off-by: Jeff Kirsher [off-list ref]
   Tested-by: Jeff Pieper [off-list ref]
   Acked-by: Bruce Allan [off-list ref]
   Signed-off-by: David S. Miller [off-list ref]

[It is unclear to what "Jean" does this commit log refers to, as the
support MSI-X was added Bruce, anyway...]

Why only 3 vectors are used when both the product brief and the
datasheet advertise up to 5 MSI-X vector usable by the chip ? That is
2*RX + 2*TX.

Thanks in advance,
 - Arnaud

On Sun, 2011-09-18 at 22:34 -0700, Arnaud Lacombe wrote:

[fixing address of the netdev@ list, sorry - A.]

On Mon, Sep 19, 2011 at 1:31 AM, Arnaud Lacombe [off-list ref] wrote:

quoted

Hi folks,

In:

commit 4662e82b2cb41c60826e50474dd86dd5c6372b0c
Author: Bruce Allan [off-list ref]
Date:   Tue Aug 26 18:37:06 2008 -0700

   e1000e: add support for new 82574L part

   This new part has the same feature set as previous parts with the addition
   of MSI-X support.

   Signed-off-by: Bruce Allan [off-list ref]
   Signed-off-by: Jeff Kirsher [off-list ref]
   Signed-off-by: Jeff Garzik [off-list ref]

MSI-X support was added to the e1000e driver, later on slightly reworked by:

commit 8e86acd7d5968e08b3e1604e685a8c45f6fd7f40
Author: Jeff Kirsher [off-list ref]
Date:   Mon Aug 2 14:27:23 2010 +0000

   e1000e: Fix irq_synchronize in MSI-X case

   Based on original patch/work from Jean Delvare [off-list ref]
   Synchronize all IRQs when in MSI-X IRQ mode.

   Jean's original patch hard coded the sync with the 3 possible vectors,
   this patch incorporates more flexibility for the future and aligns
   with how igb stores the number of vectors into the adapter structure.

   CC: Jean Delvare [off-list ref]
   Cc: Jesse Brandeburg [off-list ref]
   Signed-off-by: Jeff Kirsher [off-list ref]
   Tested-by: Jeff Pieper [off-list ref]
   Acked-by: Bruce Allan [off-list ref]
   Signed-off-by: David S. Miller [off-list ref]

[It is unclear to what "Jean" does this commit log refers to, as the
support MSI-X was added Bruce, anyway...]

Why only 3 vectors are used when both the product brief and the
datasheet advertise up to 5 MSI-X vector usable by the chip ? That is
2*RX + 2*TX.

Thanks in advance,
 - Arnaud

The e1000e driver is only a single queue driver so it does not need more
than 3 vectors, that is the reason we only use the 3 vectors.