* Re: [dpdk-stable] [dpdk-dev] [PATCH v7 8/9] ip_pipeline: fix lcore mapping for varying SMT threads as in ppc64 [not found] ` <1ba7bc01d7083769a7b1bd1417efdf6b94b8ae5b.1473349652.git.gowrishankar.m@linux.vnet.ibm.com> @ 2016-09-27 6:28 ` Yuanhan Liu 0 siblings, 0 replies; 3+ messages in thread From: Yuanhan Liu @ 2016-09-27 6:28 UTC (permalink / raw) To: Gowrishankar; +Cc: dpdk stable, Chao Zhu, Cristian Dumitrescu, Pradeep 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 ^ permalink raw reply [flat|nested] 3+ messages in thread
[parent not found: <3EB4FA525960D640B5BDFFD6A3D8912647A66EBC@IRSMSX108.ger.corp.intel.com>]
[parent not found: <2096077.zsYv3Q4577@xps13>]
* Re: [dpdk-stable] [PATCH v7 0/9] enable lpm, acl and other missing libraries in ppc64le [not found] ` <2096077.zsYv3Q4577@xps13> @ 2016-09-27 6:46 ` gowrishankar muthukrishnan 2016-09-27 7:01 ` Yuanhan Liu 0 siblings, 1 reply; 3+ messages in thread From: gowrishankar muthukrishnan @ 2016-09-27 6:46 UTC (permalink / raw) To: Thomas Monjalon Cc: Dumitrescu, Cristian, dev, Chao Zhu, Richardson, Bruce, Ananyev, Konstantin, Pradeep, stable 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 ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [dpdk-stable] [PATCH v7 0/9] enable lpm, acl and other missing libraries in ppc64le 2016-09-27 6:46 ` [dpdk-stable] [PATCH v7 0/9] enable lpm, acl and other missing libraries in ppc64le gowrishankar muthukrishnan @ 2016-09-27 7:01 ` Yuanhan Liu 0 siblings, 0 replies; 3+ messages in thread From: Yuanhan Liu @ 2016-09-27 7:01 UTC (permalink / raw) To: gowrishankar muthukrishnan Cc: Thomas Monjalon, Dumitrescu, Cristian, dev, Chao Zhu, Richardson, Bruce, Ananyev, Konstantin, Pradeep, stable 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 ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2016-09-27 7:01 UTC | newest] Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- [not found] <cover.1473349652.git.gowrishankar.m@linux.vnet.ibm.com> [not found] ` <1ba7bc01d7083769a7b1bd1417efdf6b94b8ae5b.1473349652.git.gowrishankar.m@linux.vnet.ibm.com> 2016-09-27 6:28 ` [dpdk-stable] [dpdk-dev] [PATCH v7 8/9] ip_pipeline: fix lcore mapping for varying SMT threads as in ppc64 Yuanhan Liu [not found] ` <3EB4FA525960D640B5BDFFD6A3D8912647A66EBC@IRSMSX108.ger.corp.intel.com> [not found] ` <2096077.zsYv3Q4577@xps13> 2016-09-27 6:46 ` [dpdk-stable] [PATCH v7 0/9] enable lpm, acl and other missing libraries in ppc64le gowrishankar muthukrishnan 2016-09-27 7:01 ` Yuanhan Liu
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).