[dpdk-dev] mk: disable SCHED_VECTOR in the default config
Commit Message
As it causes issues when building with RTE_MACHINE=default due to SSE4.x
requirements and in other discussions was so far rated "lightly tested and
doesn't provide really significant performance improvement" let us disable
that in the default config.
(=> http://dpdk.org/ml/archives/dev/2015-November/029067.html)
Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
---
[diffstat]
common_bsdapp | 2 +-
common_linuxapp | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
[diff]
Comments
On Tue, 1 Dec 2015 16:13:23 +0100
Christian Ehrhardt <christian.ehrhardt@canonical.com> wrote:
> As it causes issues when building with RTE_MACHINE=default due to SSE4.x
> requirements and in other discussions was so far rated "lightly tested and
> doesn't provide really significant performance improvement" let us disable
> that in the default config.
> (=> http://dpdk.org/ml/archives/dev/2015-November/029067.html)
>
> Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Hi,
2015-12-01 16:13, Christian Ehrhardt:
> As it causes issues when building with RTE_MACHINE=default due to SSE4.x
> requirements and in other discussions was so far rated "lightly tested and
> doesn't provide really significant performance improvement" let us disable
> that in the default config.
> (=> http://dpdk.org/ml/archives/dev/2015-November/029067.html)
Is your issue fixed with the following patch?
http://dpdk.org/browse/dpdk/commit/?id=1985903e4454
Hi Thomas,
no it is not fixed by that commit.
Even with it applied the remaining include subsequently at
rte_vect.h:67 pulls in x86intrin.h which still ends up including
smmintrin.h.
Long story short is that the mentioned issues like the following still occur:
/usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:67:1: error:
inlining failed in call to always_inline ‘_mm_testz_si128’: target
specific option mismatch
_mm_testz_si128 (__m128i __M, __m128i __V)
So I'd ask to still disable CONFIG_RTE_SCHED_VECTOR in the default
config via my patch.
Kind Regards,
Christian
On Wed, Dec 2, 2015 at 11:14 PM, Thomas Monjalon
<thomas.monjalon@6wind.com> wrote:
> Hi,
>
> 2015-12-01 16:13, Christian Ehrhardt:
>> As it causes issues when building with RTE_MACHINE=default due to SSE4.x
>> requirements and in other discussions was so far rated "lightly tested and
>> doesn't provide really significant performance improvement" let us disable
>> that in the default config.
>> (=> http://dpdk.org/ml/archives/dev/2015-November/029067.html)
>
> Is your issue fixed with the following patch?
> http://dpdk.org/browse/dpdk/commit/?id=1985903e4454
>
2015-12-01 07:20, Stephen Hemminger:
> On Tue, 1 Dec 2015 16:13:23 +0100
> Christian Ehrhardt <christian.ehrhardt@canonical.com> wrote:
>
> > As it causes issues when building with RTE_MACHINE=default due to SSE4.x
> > requirements and in other discussions was so far rated "lightly tested and
> > doesn't provide really significant performance improvement" let us disable
> > that in the default config.
> > (=> http://dpdk.org/ml/archives/dev/2015-November/029067.html)
> >
> > Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
>
> Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Looks safe for the release 2.2.
May be re-enabled in 2.3.
Applied, thanks
@@ -440,7 +440,7 @@
CONFIG_RTE_SCHED_COLLECT_STATS=n
CONFIG_RTE_SCHED_SUBPORT_TC_OV=n
CONFIG_RTE_SCHED_PORT_N_GRINDERS=8
-CONFIG_RTE_SCHED_VECTOR=y
+CONFIG_RTE_SCHED_VECTOR=n
#
# Compile the distributor library
@@ -451,7 +451,7 @@
CONFIG_RTE_SCHED_COLLECT_STATS=n
CONFIG_RTE_SCHED_SUBPORT_TC_OV=n
CONFIG_RTE_SCHED_PORT_N_GRINDERS=8
-CONFIG_RTE_SCHED_VECTOR=y
+CONFIG_RTE_SCHED_VECTOR=n
#
# Compile the distributor library