Re: [dpdk-stable] [dpdk-dev] [PATCH v7 8/9] ip_pipeline: fix lcore mapping for varying SMT threads as in ppc64

Re: [dpdk-stable] [dpdk-dev] [PATCH v7 8/9] ip_pipeline: fix lcore mapping for varying SMT threads as in ppc64

[Yuanhan Liu]

On Thu, Sep 08, 2016 at 10:18:10PM +0530, Gowrishankar wrote:
> From: Gowrishankar Muthukrishnan <gowrishankar.m@linux.vnet.ibm.com>
> 
> This patch fixes ip_pipeline panic in app_init_core_map while preparing cpu
> core map in powerpc with SMT off. cpu_core_map_compute_linux currently prepares
> core mapping based on file existence in sysfs ie.
> 
> /sys/devices/system/cpu/cpu<LCORE_NUM>/topology/physical_package_id
>   /sys/devices/system/cpu/cpu<LCORE_NUM>/topology/core_id
> 
> These files do not exist for lcores which are offline for any reason (as in
> powerpc, while SMT is off). In this situation, this function should further
> continue preparing map for other online lcores instead of returning with -1
> for a first unavailable lcore.
> 
> Also, in SMT=off scenario for powerpc, lcore ids can not be always indexed from
> 0 upto 'number of cores present' (/sys/devices/system/cpu/present). For eg, for
> an online lcore 32, core_id returned in sysfs is 112 where online lcores are
> 10 (as in one configuration), hence sysfs lcore id can not be checked with
> indexing lcore number before positioning lcore map array.
> 
> Signed-off-by: Gowrishankar Muthukrishnan <gowrishankar.m@linux.vnet.ibm.com>
> Acked by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
> Acked-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>

FYI, this patch has been applied to stable branch v16.07.

It hasn't been pushed to http://dpdk.org/browse/dpdk-stable/ yet.
It will be pushed if I get no objections in around TWO days. So 
please shutout if you have objections.

Thanks.

	--yliu

Re: [dpdk-stable] [PATCH v7 0/9] enable lpm, acl and other missing libraries in ppc64le

[gowrishankar muthukrishnan]

On Friday 09 September 2016 09:29 PM, Thomas Monjalon wrote:
>>> v7 changes:
>>> - removed enforcing cache alignment for table hash structs and
>>>    instead check only for multiples of 64 bytes.
>>>
>> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
> Applied, thanks
>
> We now have some AltiVec code in DPDK!
>
>
Thank you Thomas, could this also go into stable tree ? (Added 
stable@dpdk.org in CC).

-- 
Regards,
Gowrishankar M

Re: [dpdk-stable] [PATCH v7 0/9] enable lpm, acl and other missing libraries in ppc64le

[Yuanhan Liu]

On Tue, Sep 27, 2016 at 12:16:32PM +0530, gowrishankar muthukrishnan wrote:
> On Friday 09 September 2016 09:29 PM, Thomas Monjalon wrote:
> >>>v7 changes:
> >>>- removed enforcing cache alignment for table hash structs and
> >>>   instead check only for multiples of 64 bytes.
> >>>
> >>Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
> >Applied, thanks
> >
> >We now have some AltiVec code in DPDK!
> >
> >
> Thank you Thomas, could this also go into stable tree ? (Added
> stable@dpdk.org in CC).

This patchset is more like enabling DPDK on a new platform, so, it's
a new feature to me, which is not a good candidate for a stable release:
the basic rule of it is only bug fixing patches are allowed.

The reason I picked "examples/ip_pipeline: fix lcore mapping for ppc64"
to stable branch is it looks like a bug fixing patch to me, while others
are not. OTOH, it also looks like a PPC enabling patch to me; from this
point of view, I may need drop it.

IBM guys, does it make sense to pick that one only to stable branch?
Or, should I drop it?

Thanks.

	--yliu