[PATCH] doc: announce ixgbe MTU setting limitation

[PATCH] doc: announce ixgbe MTU setting limitation

[Wenzhuo Lu]

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 doc/guides/nics/ixgbe.rst | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
index 3b6851b..1f7d6b3 100644
--- a/doc/guides/nics/ixgbe.rst
+++ b/doc/guides/nics/ixgbe.rst
@@ -185,8 +185,11 @@ As in the case of l3fwd, set configure port_conf.rxmode.hw_ip_checksum=0 to enab
 In addition, for improved performance, use -bsz "(32,32),(64,64),(32,32)" in load_balancer to avoid using the default burst size of 144.
 
 
+Limitations or Known issues
+---------------------------
+
 Malicious Driver Detection not Supported
-----------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 The Intel x550 series NICs support a feature called MDD (Malicious
 Driver Detection) which checks the behavior of the VF driver.
@@ -207,7 +210,7 @@ it by default.)
 
 
 Statistics
-----------
+~~~~~~~~~~
 
 The statistics of ixgbe hardware must be polled regularly in order for it to
 remain consistent. Running a DPDK application without polling the statistics will
@@ -230,6 +233,15 @@ be calculated as follows:
 
 In order to ensure valid results, it is recommended to poll every 4 minutes.
 
+MTU setting
+~~~~~~~~~~~
+
+Although user can set MTU separately on PF and VF ports, ixgbe only supports
+one global MTU per physical port.
+So when user sets different MTUs on PF and VF ports in one physical port, the
+real MTU for all these PF and VF ports is the biggest one.
+This behavior is leveraged from kernel driver.
+
 
 Supported Chipsets and NICs
 ---------------------------
-- 
1.9.3

Re: [PATCH] doc: announce ixgbe MTU setting limitation

[Ferruh Yigit]

On 2/7/2017 6:22 AM, Wenzhuo Lu wrote:
> Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
> ---
>  doc/guides/nics/ixgbe.rst | 16 ++++++++++++++--
>  1 file changed, 14 insertions(+), 2 deletions(-)
> 
> diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
> index 3b6851b..1f7d6b3 100644
> --- a/doc/guides/nics/ixgbe.rst
> +++ b/doc/guides/nics/ixgbe.rst
> @@ -185,8 +185,11 @@ As in the case of l3fwd, set configure port_conf.rxmode.hw_ip_checksum=0 to enab
>  In addition, for improved performance, use -bsz "(32,32),(64,64),(32,32)" in load_balancer to avoid using the default burst size of 144.
>  
>  
> +Limitations or Known issues
> +---------------------------
> +
>  Malicious Driver Detection not Supported
> -----------------------------------------
> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This looks like the initial intention, thanks.

Also there are a few similar issues in the document:

1) "Feature not Supported by RX Vector PMD" is under "TX Constraint".

2) "Application Programming Interface" and "Sample Application Notes"
are under "Vector PMD for IXGBE"

Not sure if above are the intention.

What do you think converting this patch into a patchset, first patch
fixes headlines you already fixed and above ones if required.

And second patch is just to add "MTU setting" limitation note?

Thanks,
ferruh

>  
>  The Intel x550 series NICs support a feature called MDD (Malicious
>  Driver Detection) which checks the behavior of the VF driver.
> @@ -207,7 +210,7 @@ it by default.)
>  
>  
>  Statistics
> -----------
> +~~~~~~~~~~
>  
>  The statistics of ixgbe hardware must be polled regularly in order for it to
>  remain consistent. Running a DPDK application without polling the statistics will
> @@ -230,6 +233,15 @@ be calculated as follows:
>  
>  In order to ensure valid results, it is recommended to poll every 4 minutes.
>  
> +MTU setting
> +~~~~~~~~~~~
> +
> +Although user can set MTU separately on PF and VF ports, ixgbe only supports
> +one global MTU per physical port.
> +So when user sets different MTUs on PF and VF ports in one physical port, the
> +real MTU for all these PF and VF ports is the biggest one.
> +This behavior is leveraged from kernel driver.
> +
>  
>  Supported Chipsets and NICs
>  ---------------------------
> 

Re: [PATCH] doc: announce ixgbe MTU setting limitation

[Mcnamara, John]

> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Wenzhuo Lu
> Sent: Tuesday, February 7, 2017 6:23 AM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo <wenzhuo.lu@intel.com>
> Subject: [dpdk-dev] [PATCH] doc: announce ixgbe MTU setting limitation
> 
> Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
> ---
>  doc/guides/nics/ixgbe.rst | 16 ++++++++++++++--
>  1 file changed, 14 insertions(+), 2 deletions(-)
> 
> diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst index
> 3b6851b..1f7d6b3 100644
> --- a/doc/guides/nics/ixgbe.rst
> +++ b/doc/guides/nics/ixgbe.rst
> @@ -185,8 +185,11 @@ As in the case of l3fwd, set configure
> port_conf.rxmode.hw_ip_checksum=0 to enab  In addition, for improved
> performance, use -bsz "(32,32),(64,64),(32,32)" in load_balancer to avoid
> using the default burst size of 144.
> 
> 
> +Limitations or Known issues
> +---------------------------
> +
>  Malicious Driver Detection not Supported
> -----------------------------------------
> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> 
>  The Intel x550 series NICs support a feature called MDD (Malicious
> Driver Detection) which checks the behavior of the VF driver.
> @@ -207,7 +210,7 @@ it by default.)
> 
> 
>  Statistics
> -----------
> +~~~~~~~~~~
> 
>  The statistics of ixgbe hardware must be polled regularly in order for it
> to  remain consistent. Running a DPDK application without polling the
> statistics will @@ -230,6 +233,15 @@ be calculated as follows:
> 
>  In order to ensure valid results, it is recommended to poll every 4
> minutes.
> 
> +MTU setting
> +~~~~~~~~~~~
> +
> +Although user can set MTU separately on PF and VF ports, ixgbe only
> +supports one global MTU per physical port.
> +So when user sets different MTUs on PF and VF ports in one physical
> +port, the real MTU for all these PF and VF ports is the biggest one.
> +This behavior is leveraged from kernel driver.
> +

Would be slightly better as:

Although the user can set the MTU separately on PF and VF ports, the ixgbe
NIC only supports one global MTU per physical port.
So when the user sets different MTUs on PF and VF ports in one physical 
port, the real MTU for all these PF and VF ports is the largest value set.
This behavior is based on the kernel driver behavior.

Re: [PATCH] doc: announce ixgbe MTU setting limitation

[Lu, Wenzhuo]

Hi Ferruh,


> -----Original Message-----
> From: Yigit, Ferruh
> Sent: Thursday, February 9, 2017 12:12 AM
> To: Lu, Wenzhuo; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] doc: announce ixgbe MTU setting limitation
> 
> On 2/7/2017 6:22 AM, Wenzhuo Lu wrote:
> > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
> > ---
> >  doc/guides/nics/ixgbe.rst | 16 ++++++++++++++--
> >  1 file changed, 14 insertions(+), 2 deletions(-)
> >
> > diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
> > index 3b6851b..1f7d6b3 100644
> > --- a/doc/guides/nics/ixgbe.rst
> > +++ b/doc/guides/nics/ixgbe.rst
> > @@ -185,8 +185,11 @@ As in the case of l3fwd, set configure
> > port_conf.rxmode.hw_ip_checksum=0 to enab  In addition, for improved
> performance, use -bsz "(32,32),(64,64),(32,32)" in load_balancer to avoid using
> the default burst size of 144.
> >
> >
> > +Limitations or Known issues
> > +---------------------------
> > +
> >  Malicious Driver Detection not Supported
> > -----------------------------------------
> > +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> 
> This looks like the initial intention, thanks.
> 
> Also there are a few similar issues in the document:
> 
> 1) "Feature not Supported by RX Vector PMD" is under "TX Constraint".
> 
> 2) "Application Programming Interface" and "Sample Application Notes"
> are under "Vector PMD for IXGBE"
> 
> Not sure if above are the intention.
> 
> What do you think converting this patch into a patchset, first patch fixes
> headlines you already fixed and above ones if required.
> 
> And second patch is just to add "MTU setting" limitation note?
Thanks for your suggestion. I'll split this patch.

> 
> Thanks,
> ferruh
> 
> >
> >  The Intel x550 series NICs support a feature called MDD (Malicious
> > Driver Detection) which checks the behavior of the VF driver.
> > @@ -207,7 +210,7 @@ it by default.)
> >
> >
> >  Statistics
> > -----------
> > +~~~~~~~~~~
> >
> >  The statistics of ixgbe hardware must be polled regularly in order
> > for it to  remain consistent. Running a DPDK application without
> > polling the statistics will @@ -230,6 +233,15 @@ be calculated as follows:
> >
> >  In order to ensure valid results, it is recommended to poll every 4 minutes.
> >
> > +MTU setting
> > +~~~~~~~~~~~
> > +
> > +Although user can set MTU separately on PF and VF ports, ixgbe only
> > +supports one global MTU per physical port.
> > +So when user sets different MTUs on PF and VF ports in one physical
> > +port, the real MTU for all these PF and VF ports is the biggest one.
> > +This behavior is leveraged from kernel driver.
> > +
> >
> >  Supported Chipsets and NICs
> >  ---------------------------
> >

Re: [PATCH] doc: announce ixgbe MTU setting limitation

[Lu, Wenzhuo]

Hi John,

> -----Original Message-----
> From: Mcnamara, John
> Sent: Thursday, February 9, 2017 1:11 AM
> To: Lu, Wenzhuo; dev@dpdk.org
> Cc: Lu, Wenzhuo; Yigit, Ferruh
> Subject: RE: [dpdk-dev] [PATCH] doc: announce ixgbe MTU setting limitation
> 
> 
> 
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Wenzhuo Lu
> > Sent: Tuesday, February 7, 2017 6:23 AM
> > To: dev@dpdk.org
> > Cc: Lu, Wenzhuo <wenzhuo.lu@intel.com>
> > Subject: [dpdk-dev] [PATCH] doc: announce ixgbe MTU setting limitation
> >
> > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
> > ---
> >  doc/guides/nics/ixgbe.rst | 16 ++++++++++++++--
> >  1 file changed, 14 insertions(+), 2 deletions(-)
> >
> > diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
> > index
> > 3b6851b..1f7d6b3 100644
> > --- a/doc/guides/nics/ixgbe.rst
> > +++ b/doc/guides/nics/ixgbe.rst
> > @@ -185,8 +185,11 @@ As in the case of l3fwd, set configure
> > port_conf.rxmode.hw_ip_checksum=0 to enab  In addition, for improved
> > performance, use -bsz "(32,32),(64,64),(32,32)" in load_balancer to
> > avoid using the default burst size of 144.
> >
> >
> > +Limitations or Known issues
> > +---------------------------
> > +
> >  Malicious Driver Detection not Supported
> > -----------------------------------------
> > +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> >
> >  The Intel x550 series NICs support a feature called MDD (Malicious
> > Driver Detection) which checks the behavior of the VF driver.
> > @@ -207,7 +210,7 @@ it by default.)
> >
> >
> >  Statistics
> > -----------
> > +~~~~~~~~~~
> >
> >  The statistics of ixgbe hardware must be polled regularly in order
> > for it to  remain consistent. Running a DPDK application without
> > polling the statistics will @@ -230,6 +233,15 @@ be calculated as follows:
> >
> >  In order to ensure valid results, it is recommended to poll every 4
> > minutes.
> >
> > +MTU setting
> > +~~~~~~~~~~~
> > +
> > +Although user can set MTU separately on PF and VF ports, ixgbe only
> > +supports one global MTU per physical port.
> > +So when user sets different MTUs on PF and VF ports in one physical
> > +port, the real MTU for all these PF and VF ports is the biggest one.
> > +This behavior is leveraged from kernel driver.
> > +
> 
> Would be slightly better as:
> 
> Although the user can set the MTU separately on PF and VF ports, the ixgbe
> NIC only supports one global MTU per physical port.
> So when the user sets different MTUs on PF and VF ports in one physical port,
> the real MTU for all these PF and VF ports is the largest value set.
> This behavior is based on the kernel driver behavior.
Thanks for this. I'll use update it in the new version.

[PATCH v2 0/2] update ixgbe doc

[Wenzhuo Lu]

1, adjust the framework of the ixgbe doc.
2, announce the MTU setting limitation.

v2:
- split the patch to 2 to add more fixes.

Wenzhuo Lu (2):
  doc: fix framework of ixgbe doc
  doc: announce ixgbe MTU setting limitation

 doc/guides/nics/ixgbe.rst | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

-- 
1.9.3

[PATCH v2 1/2] doc: fix framework of ixgbe doc

[Wenzhuo Lu]

The framework of the ixgbe doc is not appropriate,
adjust it.

Fixes: 972e365bfe7a ("doc: nics guide")
CC: stable@dpdk.org

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 doc/guides/nics/ixgbe.rst | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
index 3b6851b..05ecc2a 100644
--- a/doc/guides/nics/ixgbe.rst
+++ b/doc/guides/nics/ixgbe.rst
@@ -129,7 +129,7 @@ The tx_rs_thresh value must be greater than or equal to RTE_PMD_IXGBE_TX_MAX_BUR
 but less or equal to RTE_IXGBE_TX_MAX_FREE_BUF_SZ.
 Consequently, by default the tx_rs_thresh value is in the range 32 to 64.
 
-Feature not Supported by RX Vector PMD
+Feature not Supported by TX Vector PMD
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 TX vPMD only works when txq_flags is set to IXGBE_SIMPLE_FLAGS.
@@ -148,16 +148,16 @@ The following MACROs are used for these three features:
 *   ETH_TXQ_FLAGS_NOXSUMTCP
 
 Application Programming Interface
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+---------------------------------
 
 In DPDK release v16.11 an API for ixgbe specific functions has been added to the ixgbe PMD.
 The declarations for the API functions are in the header ``rte_pmd_ixgbe.h``.
 
 Sample Application Notes
-~~~~~~~~~~~~~~~~~~~~~~~~
+------------------------
 
 testpmd
-^^^^^^^
+~~~~~~~
 
 By default, using CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=y:
 
@@ -172,21 +172,24 @@ When CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=n, better performance can be achieved:
     ./x86_64-native-linuxapp-gcc/app/testpmd -c 300 -n 4 -- -i --burst=32 --rxfreet=32 --mbcache=250 --txpt=32 --rxht=8 --rxwt=0 --txfreet=32 --txrst=32 --txqflags=0xf01 --disable-hw-vlan
 
 l3fwd
-^^^^^
+~~~~~
 
 When running l3fwd with vPMD, there is one thing to note.
 In the configuration, ensure that port_conf.rxmode.hw_ip_checksum=0.
 Otherwise, by default, RX vPMD is disabled.
 
 load_balancer
-^^^^^^^^^^^^^
+~~~~~~~~~~~~~
 
 As in the case of l3fwd, set configure port_conf.rxmode.hw_ip_checksum=0 to enable vPMD.
 In addition, for improved performance, use -bsz "(32,32),(64,64),(32,32)" in load_balancer to avoid using the default burst size of 144.
 
 
+Limitations or Known issues
+---------------------------
+
 Malicious Driver Detection not Supported
-----------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 The Intel x550 series NICs support a feature called MDD (Malicious
 Driver Detection) which checks the behavior of the VF driver.
@@ -207,7 +210,7 @@ it by default.)
 
 
 Statistics
-----------
+~~~~~~~~~~
 
 The statistics of ixgbe hardware must be polled regularly in order for it to
 remain consistent. Running a DPDK application without polling the statistics will
-- 
1.9.3

[PATCH v2 2/2] doc: announce ixgbe MTU setting limitation

[Wenzhuo Lu]

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 doc/guides/nics/ixgbe.rst | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
index 05ecc2a..aceeb13 100644
--- a/doc/guides/nics/ixgbe.rst
+++ b/doc/guides/nics/ixgbe.rst
@@ -233,6 +233,15 @@ be calculated as follows:
 
 In order to ensure valid results, it is recommended to poll every 4 minutes.
 
+MTU setting
+~~~~~~~~~~~
+
+Although the user can set the MTU separately on PF and VF ports, the ixgbe NIC
+only supports one global MTU per physical port.
+So when the user sets different MTUs on PF and VF ports in one physical port,
+the real MTU for all these PF and VF ports is the largest value set.
+This behavior is based on the kernel driver behavior.
+
 
 Supported Chipsets and NICs
 ---------------------------
-- 
1.9.3

Re: [PATCH v2 2/2] doc: announce ixgbe MTU setting limitation

[Mcnamara, John]

> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Wenzhuo Lu
> Sent: Thursday, February 9, 2017 1:28 AM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo <wenzhuo.lu@intel.com>
> Subject: [dpdk-dev] [PATCH v2 2/2] doc: announce ixgbe MTU setting
> limitation
> 
> Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>

Acked-by: John McNamara <john.mcnamara@intel.com>

Re: [dpdk-stable] [PATCH v2 1/2] doc: fix framework of ixgbe doc

[Mcnamara, John]

> -----Original Message-----
> From: stable [mailto:stable-bounces@dpdk.org] On Behalf Of Wenzhuo Lu
> Sent: Thursday, February 9, 2017 1:28 AM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo <wenzhuo.lu@intel.com>; stable@dpdk.org
> Subject: [dpdk-stable] [PATCH v2 1/2] doc: fix framework of ixgbe doc
> 
> The framework of the ixgbe doc is not appropriate, adjust it.
> 
> Fixes: 972e365bfe7a ("doc: nics guide")
> CC: stable@dpdk.org
> 
> Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>


Acked-by: John McNamara <john.mcnamara@intel.com>

Re: [PATCH v2 0/2] update ixgbe doc

[Ferruh Yigit]

On 2/9/2017 1:27 AM, Wenzhuo Lu wrote:
> 1, adjust the framework of the ixgbe doc.
> 2, announce the MTU setting limitation.
> 
> v2:
> - split the patch to 2 to add more fixes.
> 
> Wenzhuo Lu (2):
>   doc: fix framework of ixgbe doc
>   doc: announce ixgbe MTU setting limitation
> 
>  doc/guides/nics/ixgbe.rst | 28 ++++++++++++++++++++--------
>  1 file changed, 20 insertions(+), 8 deletions(-)
>

Series applied to dpdk-next-net/master, thanks.