> v7:
> * Reword bridge.rst documentation to better explain the use of the
> -recirc option and provide examples. This is all based on feedback
> from Sunil.
> ---
> Documentation/topics/dpdk/bridge.rst | 32 ++--
> lib/dpif-netdev-private-extract.c| 23
Hi Amber,
One comment below , rest looks good to me.
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Thursday, October 6, 2022 3:54 PM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v6 6/9]
> -Original Message-
> From: David Marchand
> Sent: Friday, October 7, 2022 4:46 PM
> To: d...@openvswitch.org
> Cc: Stokes, Ian ; ktray...@redhat.com;
> maxime.coque...@redhat.com; Pai G, Sunil
> Subject: [PATCH dpdk-latest v2 2/3] netdev-dpdk: Drop reference
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Thursday, October 6, 2022 3:54 PM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v6 9/9] mfex-avx512: Add support for tunnel
> packets in avx512
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Thursday, October 6, 2022 3:54 PM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v6 8/9] mfex-study: Modify study func to select
> outer and inner
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Thursday, October 6, 2022 3:54 PM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v6 7/9] dpif-mfex: Change MFEX fn pointer
> prototype to include
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Thursday, October 6, 2022 3:54 PM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v6 5/9] dpif-netdev: Add function pointer for
> dpif re-circulate.
> -Original Message-
> From: dev On Behalf Of Cian Ferriter
> Sent: Friday, September 16, 2022 3:42 PM
> To: ovs-dev@openvswitch.org
> Subject: [ovs-dev] [PATCH 2/2] dpif-netdev/mfex: Add AVX512 NVGRE traffic
> profiles.
>
> A typical NVGRE encapsulated packet starts with the
> -Original Message-
> From: dev On Behalf Of Cian Ferriter
> Sent: Friday, September 16, 2022 3:42 PM
> To: ovs-dev@openvswitch.org
> Subject: [ovs-dev] [PATCH 1/2] dpif-netdev/dpcls: Specialize 8, 1 and 5, 2
> signatures.
>
> The subtable signatures being specialized here were found
> > Hey Amber,
> >
> > I'm OK with the API changes in this patch if we need them, but after
> > looking at the later 2 patches in the series, I can see that you're
> > using another check in the heart of the MFEX AVX512 code
> (mfex_avx512_process()):
> > /* Dummy pmd dont always pass
Hi Amber,
Few comments inline.
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Friday, August 26, 2022 5:01 AM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v5 6/9] dpif-mfex: Modify set/get mfex
Hi Amber,
Couple of comments/suggestions inline.
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Friday, August 26, 2022 5:01 AM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v5 5/9] dpif-netdev:
Hi Amber,
Minor nit inline, rest looks good.
> diff --git a/lib/dpif-netdev-avx512.c b/lib/dpif-netdev-avx512.c index
> a36f4f312..1db20c1cf 100644
> --- a/lib/dpif-netdev-avx512.c
> +++ b/lib/dpif-netdev-avx512.c
> @@ -61,7 +61,7 @@ struct dpif_userdata { static inline int32_t
>
Hi Amber,
One minor nit inline.
> diff --git a/lib/dpif-netdev-private-dpif.h b/lib/dpif-netdev-private-
> dpif.h index b3e75b7a2..46ce4ecf6 100644
> --- a/lib/dpif-netdev-private-dpif.h
> +++ b/lib/dpif-netdev-private-dpif.h
> @@ -86,8 +86,16 @@ dp_netdev_input(struct dp_netdev_pmd_thread
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Friday, August 26, 2022 5:01 AM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v5 2/9] dpif-netdev: Refactor hash function to
> own header.
>
> The
> -Original Message-
> From: dev On Behalf Of Kumar Amber
> Sent: Friday, August 26, 2022 5:01 AM
> To: ovs-dev@openvswitch.org
> Cc: i.maxim...@ovn.org; f...@sysclose.org; Amber, Kumar
>
> Subject: [ovs-dev] [PATCH v5 1/9] dpif-netdev: Refactor per thread recirc
> data allocation.
>
> -Original Message-
> From: dev On Behalf Of David Marchand
> Sent: Monday, September 26, 2022 2:37 PM
> To: d...@openvswitch.org
> Cc: maxime.coque...@redhat.com
> Subject: [ovs-dev] [PATCH dpdk-latest] netdev-dpdk: Report device bus
> specific information.
>
> 22.11 dropped direct
Hi David,
Generally, looks good, one minor nit inline.
> -Original Message-
> From: dev On Behalf Of David Marchand
> Sent: Thursday, August 25, 2022 3:55 PM
> To: d...@openvswitch.org
> Subject: [ovs-dev] [PATCH 3/3] netdev-dpdk: Cleanup mempool selection
> code.
>
> Propagating
> -Original Message-
> From: dev On Behalf Of David Marchand
> Sent: Thursday, August 25, 2022 3:55 PM
> To: d...@openvswitch.org
> Subject: [ovs-dev] [PATCH 2/3] netdev-dpdk: Move DPDK netdev related
> configuration.
>
> vhost related configuration and per port memory are netdev-dpdk
>
> -Original Message-
> From: dev On Behalf Of David Marchand
> Sent: Thursday, August 25, 2022 3:55 PM
> To: d...@openvswitch.org
> Subject: [ovs-dev] [PATCH 1/3] netdev-dpdk: Cleanup code when DPDK is
> disabled.
>
> Remove one unused stub: netdev_dpdk_register() can't be called if
> >> Signed-off-by: Sunil Pai G
> >
> > Thanks Sunil. Checked on master and branch-3.0 and working fine.
> >
> > Acked-by: Kevin Traynor
>
> Hi. I have one question: Does this test require testpmd?
>
> I mean, if we're not testing vhost-user specifically, we should, probably,
> reduce the
> Thanks for the suggestion. These tests look like a good addition. If you
> want to send them formally to the mailing list, I can Ack them.
>
> thanks,
> Kevin.
Hi Kevin,
Sure, patch available on the mailing list here:
> -Original Message-
> From: dev On Behalf Of Cian Ferriter
> Sent: Thursday, August 11, 2022 4:07 PM
> To: ovs-dev@openvswitch.org
> Subject: [ovs-dev] [PATCH] acinclude: Improve vpopcntdq build check.
>
> Support for vpopcntdq instruction generation by the compiler was already
>
> > Subject: RE: [ovs-build] |fail| pw1663325 [ovs-dev,branch-2.17] dpif-
> netdev:
> > Simplify AVX512 build time checks to enhance readability.
> >
> > Hi Mike,
> >
> > It seems CI failed for this patch(see below). But I don’t see any
> > reasons why it should fail as the patch is
> Sent: Wednesday, August 3, 2022 8:09 PM
> To: ovs-bu...@openvswitch.org; Pai G, Sunil
> Subject: [ovs-build] |fail| pw1663325 [ovs-dev,branch-2.17] dpif-netdev:
> Simplify AVX512 build time checks to enhance readability.
>
> Test-Label: intel-ovs-compilation
&g
> >
> >
> Sending a friendly ping here to check for any comments/objections
> on
> >> this patch from maintainers.
> >>>
> >>> Hi, Sunil. I think, Ian wanted to apply the patch, we discussed
> >>> that on a meeting last week.
> >>
> >> It's probably just a PTO season. :)
> >> (Got a
> >> Sending a friendly ping here to check for any comments/objections on
> this patch from maintainers.
> >
> > Hi, Sunil. I think, Ian wanted to apply the patch, we discussed that
> > on a meeting last week.
>
> It's probably just a PTO season. :)
> (Got a few OOO replies here)
Thanks Ilya
> > -Original Message-
> > From: Pai G, Sunil
> > Sent: Monday 4 July 2022 13:27
> > To: d...@openvswitch.org
> > Cc: echau...@redhat.com; Finn, Emma ; Van Haaren,
> > Harry ; Ferriter, Cian
> >
> > Subject: [PATCH v2] dpif-netdev
Hi Ilya,
> >>
> >> It also complains about AC_PROG_CC_C99, but I'm not sure if we want
> >> to or how to correctly replace it.
> >> Suggested AC_PROG_CC enables C11 by default and that might not be a
> >> desired behavior.
> >
> > Not an expert in this area, but to ensure C99 support, the
> >
> -Original Message-
> From: dev On Behalf Of Ilya Maximets
> Sent: Tuesday, July 26, 2022 7:00 PM
> To: ovs-dev@openvswitch.org
> Cc: Ilya Maximets
> Subject: [ovs-dev] [PATCH] checkpatch: Add check for a Fixes tag.
>
> A new check for common mistakes while formatting a 'Fixes:'
Hi Ilya,
Thanks for both the patches.
I tested them on Ubuntu 22.04 (autoconf (GNU Autoconf) 2.71) as well as Ubuntu
20.04 (autoconf (GNU Autoconf) 2.69) and both works as expected,
i.e don't see any warnings(except about AC_PROG_CC_C99) generated with autoconf
2.71 after patch applied and no
> > The DPDK commit [1] improves the socket layer logs in the vhost
> > library to ease log filtering and debugging.
> > Update the system-dpdk vhost tests to reflect this change.
> >
> > [1] c85c35b1d447 ("vhost: improve socket layer logs")
> >
> > Signed-off-by: Sunil Pai G
> >
>
> Thanks for
Hi Mike, Amber,
Thanks for working on this. Couple of comments below, rest looks good.
> -Original Message-
> From: dev On Behalf Of Amber, Kumar
> Sent: Friday, July 22, 2022 2:36 PM
> To: d...@openvswitch.org
> Cc: Ilya Maximets
> Subject: Re: [ovs-dev] [PATCH] system-dpdk: Add
Hi Mike,
> -Original Message-
> From: dev On Behalf Of Michael Phelan
> Sent: Friday, July 15, 2022 6:56 PM
> To: d...@openvswitch.org
> Cc: maxime.coque...@redhat.com; i.maxim...@ovn.org
> Subject: [ovs-dev] [PATCH v3] tests: Add OVS-DPDK QoS unit tests
>
> This adds 4 new unit tests
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian
> Subject: [PATCH v10 10/10] odp-execute
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian
> Subject: [PATCH v10 09/10] odp-execute
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian
> Subject: [PATCH v10 08/
Hi Harry/Amber,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
>
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
>
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
> Like patch 1 and 4, GHA couldn't complete its run for this patch because
> of infra reasons, so I manually triggered one on my forked repo to be more
> confident, and it succeeds:
> https://github.com/Sunil-Pai-G/ovs/actions/runs/2668424540
Seems GHA passed on the first run on patchwork, I
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
>
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
Hi Harry/Emma,
> -Original Message-
> From: Van Haaren, Harry
> Sent: Wednesday, July 13, 2022 11:58 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org; echau...@redhat.com; Amber, Kumar
> ; Pai G, Sunil ; Finn, Emma
> ; Stokes, Ian ; Van Haaren,
> Harry
>
Hi Mike,
Thanks for adding more testcases !
Patch generally looks good, although it might require a rebase.
Minor nits inline.
> -Original Message-
> From: dev On Behalf Of Michael Phelan
> Sent: Wednesday, June 29, 2022 4:19 PM
> To: d...@openvswitch.org
> Cc:
Hi Emma,
Thanks for the patch, couple of comments inline.
> diff --git a/lib/automake.mk b/lib/automake.mk index 5c3b05f6b..e6335ccac
> 100644
> --- a/lib/automake.mk
> +++ b/lib/automake.mk
> @@ -31,6 +31,9 @@ lib_LTLIBRARIES += lib/libopenvswitchavx512.la
> lib_libopenvswitch_la_LIBADD +=
Hi Amber/Emma,
Thanks for the patch, couple of minor nits below.
> -Original Message-
> From: dev On Behalf Of Emma Finn
> Sent: Thursday, July 7, 2022 9:09 PM
> To: d...@openvswitch.org; echau...@redhat.com; Van Haaren, Harry
> ; Amber, Kumar
> Cc: i.maxim...@ovn.org
> Subject:
Hi Emma,
Thanks for the patch, generally looks good, one comment below.
> diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c index
> 58be9d0f0..b618ecba0 100644
> --- a/lib/dpif-netdev.c
> +++ b/lib/dpif-netdev.c
> @@ -63,6 +63,7 @@
> #include "netdev-vport.h"
> #include "netlink.h"
>
Hi Emma,
Thanks for the patch, generally looks good, few comments inline.
> diff --git a/lib/odp-execute-private.c b/lib/odp-execute-private.c new
> file mode 100644 index 0..b10880ed9
> --- /dev/null
> +++ b/lib/odp-execute-private.c
> @@ -0,0 +1,92 @@
> +/*
> + * Copyright (c) 2022
Hi Emma,
Thanks for the series.
As discussed internally, I looked over the patches and have few comments. Hope
you can address them.
> -Original Message-
> From: dev On Behalf Of Emma Finn
> Sent: Thursday, July 7, 2022 9:09 PM
> To: d...@openvswitch.org; echau...@redhat.com; Van
Adding Amber on CC since he missed this patch on mailing list.
> -Original Message-
> From: Ferriter, Cian
> Sent: Thursday, July 7, 2022 6:35 PM
> To: ovs-dev@openvswitch.org
> Cc: Van Haaren, Harry ; Pai G, Sunil
> ; Ferriter, Cian
> Subject: [PATCH v2 1/2]
Adding Amber on CC since he missed this patch on mailing list.
> -Original Message-
> From: Ferriter, Cian
> Sent: Thursday, July 7, 2022 6:35 PM
> To: ovs-dev@openvswitch.org
> Cc: Van Haaren, Harry ; Pai G, Sunil
> ; Ferriter, Cian
> Subject: [PATCH v2 2/2] dpi
Adding Amber on CC since he missed this patch on mailing list.
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Adding Amber on CC since he missed this patch on mailing list.
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Hi Kevin,
Responses inline.
> > > +static struct user_mempool_config *user_mempools = NULL; static int
> > > +n_user_mempools;
> >
> > Should we consider restricting n_user_mempools to some max value ?
> >
>
> We could do. There is no issue with having many values, it just might not
> make
oque...@redhat.com; Phelan, Michael
> ; Pai G, Sunil
> Subject: [PATCH v3] tests: Add OVS-DPDK MTU unit tests.
The title should be "system-dpdk:" instead of "tests:", didn't catch this
earlier,
but I guess this can be changed when applying, might not require another
Hi Mike,
Thanks for adding these tests, few comments inline.
> +dnl
> +---
> +---
> +dnl MTU increase phy port
> +AT_SETUP([OVS-DPDK - MTU increase phy port])
> +AT_KEYWORDS([dpdk])
> +
> +OVS_DPDK_PRE_PHY_SKIP()
>
Hi Kevin,
Thanks for the patch.
LGTM in general, couple of minor comments/thoughts inline.
> +struct user_mempool_config {
> +int adj_mtu;
> +int socket_id;
> +};
> +
> +static struct user_mempool_config *user_mempools = NULL; static int
> +n_user_mempools;
Should we consider
Hi Kevin,
Thanks for the patch, one comment below, let me know your thoughts.
> -Original Message-
> From: dev On Behalf Of Kevin Traynor
> Sent: Friday, June 24, 2022 3:43 PM
> To: d...@openvswitch.org
> Cc: david.march...@redhat.com
> Subject: [ovs-dev] [PATCH v5 3/3] system-dpdk:
Hi Kevin,
Thanks for the patch, changes LGTM,
> -Original Message-
> From: dev On Behalf Of Kevin Traynor
> Sent: Friday, June 24, 2022 3:43 PM
> To: d...@openvswitch.org
> Cc: david.march...@redhat.com
> Subject: [ovs-dev] [PATCH v5 2/3] system-dpdk: Split ovsdb creation and
>
> -Original Message-
> From: Ferriter, Cian
> Sent: Thursday, July 7, 2022 6:35 PM
> To: ovs-dev@openvswitch.org
> Cc: Van Haaren, Harry ; Pai G, Sunil
> ; Ferriter, Cian
> Subject: [PATCH v2 1/2] dpif-netdev: Refactor simple match lookup
> functions.
&g
> -Original Message-
> From: Ferriter, Cian
> Sent: Thursday, July 7, 2022 6:35 PM
> To: ovs-dev@openvswitch.org
> Cc: Van Haaren, Harry ; Pai G, Sunil
> ; Ferriter, Cian
> Subject: [PATCH v2 2/2] dpif-avx512: Add support for simple match lookup.
>
>
Hi Cian,
> +if (!f) {
> +/* Any miss in Simple Match means an upcall is needed.
> Fall
> + * back to the scalar DPIF to do this. */
> +return -1;
> +}
> +
> +rules[i] = >cr;
> +n_simple_hit++;
> +
> -Original Message-
> From: Ilya Maximets
> Sent: Tuesday, June 28, 2022 1:07 AM
> To: David Marchand ; d...@openvswitch.org
> Cc: i.maxim...@ovn.org; amu...@redhat.com; Van Haaren, Harry
> ; Ferriter, Cian ;
> Pai G, Sunil
> Subject: Re: [PATCH] dpif-netdev:
> Checking for each of the required AVX512 ISA separately will allow the
> compiler to generate some AVX512 code where there is some support in the
> compiler rather than only generating all AVX512 code when all of it is
> supported or no AVX512 code at all.
>
> For example, in GCC 4.9 where
Hi Cian,
Few comments inline.
> diff --git a/acinclude.m4 b/acinclude.m4 index 61e88105f..7b2889a40 100644
> --- a/acinclude.m4
> +++ b/acinclude.m4
> @@ -73,16 +73,13 @@ AC_DEFUN([OVS_CHECK_DPIF_AVX512_DEFAULT], [
>
> dnl OVS_CHECK_AVX512
> dnl
> -dnl Checks if compiler and binutils
> -Original Message-
> From: Ferriter, Cian
> Sent: Friday, April 29, 2022 8:34 PM
> To: ovs-dev@openvswitch.org
> Cc: Ferriter, Cian ; Van Haaren, Harry
> ; Pai G, Sunil
> Subject: [PATCH v4 4/5] automake.mk: Remove -mavx512dq CFLAG from AVX512
> library.
&
> -Original Message-
> From: Ferriter, Cian
> Sent: Friday, April 29, 2022 8:34 PM
> To: ovs-dev@openvswitch.org
> Cc: Ferriter, Cian ; Van Haaren, Harry
> ; Pai G, Sunil
> Subject: [PATCH v4 3/5] dpif-netdev-extract: Remove unnecessary compiler
> targets.
&
Hi Flavio, Mike,
> From: Flavio Leitner
>
> This patch split out the common code between vhost and dpdk transmit paths
> to shared functions to simplify the code and fix an issue.
>
> The issue is that the packet coming from non-DPDK device and egressing on
> a DPDK device currently skips the
> Subject: [ovs-dev] [PATCH] netdev-dpdk: Remove a leftover lock annotation.
>
> A lock annotation was left behind after removing the nonpmd mutex.
> Remove it.
>
> Fixes: 1166b0d82043 ("netdev-dpdk: Remove useless nonpmd_mempool_mutex.")
> Signed-off-by: David Marchand
> ---
>
> -Original Message-
> From: dev On Behalf Of David Marchand
> Sent: Friday, April 22, 2022 5:55 PM
> To: d...@openvswitch.org
> Cc: i.maxim...@ovn.org
> Subject: [ovs-dev] [PATCH] netdev-dpdk: Fix tx drops statistic for a down
> netdev.
>
> Dropped packets were not counted as
Hi Cian,
Thanks for the patch, comments inline.
> Checking for AVX512BW and AVX512DQ separately will allow the compiler to
> generate some AVX512 code where it is supported. For example, in GCC 4.9
> where there is just support for AVX512F, this patch will allow the
> AVX512 DPIF to be built.
>
> -Original Message-
> From: dev On Behalf Of Cian Ferriter
> Sent: Thursday, March 3, 2022 10:35 PM
> To: ovs-dev@openvswitch.org
> Subject: [ovs-dev] [PATCH v3 3/6] dpif-netdev-extract: Remove ISA compiler
> target for mfex.
>
> There are no instructions from this ISA used. The
> -Original Message-
> From: dev On Behalf Of Cian Ferriter
> Sent: Thursday, March 3, 2022 10:35 PM
> To: ovs-dev@openvswitch.org
> Subject: [ovs-dev] [PATCH v3 2/6] dpif-netdev-lookup: Fix GCC 5 warning.
>
> GCC 5 gave an incompatible pointer type warning for pkt_blocks when it's
>
> -Original Message-
> From: dev On Behalf Of Cian Ferriter
> Sent: Thursday, March 3, 2022 10:35 PM
> To: ovs-dev@openvswitch.org
> Subject: [ovs-dev] [PATCH v3 1/6] dpif-netdev-private-extract: Fix typo
> VMBI -> VBMI.
>
> Signed-off-by: Cian Ferriter
Hi Cian,
Thanks for the
> -Original Message-
> From: Richardson, Bruce
> Sent: Tuesday, April 5, 2022 5:38 PM
> To: Ilya Maximets ; Chengwen Feng
> ; Radha Mohan Chintakuntla ;
> Veerasenareddy Burru ; Gagandeep Singh
> ; Nipun Gupta
> Cc: Pai G, Sunil ; Stokes, Ian
> ; Hu, Jiayu ; Fe
Sent: Thursday, March 24, 2022 9:07 PM
To: Pai G, Sunil; Hu, Jiayu; Ferriter, Cian; Van Haaren, Harry; Ilya
Maximets; Maxime Coquelin (maxime.coque...@redhat.com);
ovs-dev@openvswitch.org; d...@dpdk.org
Cc: Mcnamara, John; O'Driscoll, Tim; Finn, Emma
Subject: OVS DPDK DMA-Dev
> Hi, Sunil.
>
> Mail-list strips attachments. So, if you want to share the presentation,
> upload it somewhere accessible and provide a link instead.
Hi ,
Thanks for the suggestion, Ilya.
Here is a publicly accessible link to the presentation:
Hi all,
Please see attached PDF which will be presented in the call.
Thanks and Regards,
Sunil
-Original Appointment-
From: Stokes, Ian
Sent: Tuesday, March 15, 2022 6:47 PM
To: Stokes, Ian; Ilya Maximets; Maxime Coquelin
(maxime.coque...@redhat.com); Pai G
> > > >>> This version of the patch seems to have negative impact on
> > > >>> performance
> > > >> for burst traffic profile[1].
> > > >>> Benefits seen with the previous version (v2) was up to ~1.6x for
> > > >>> 1568 byte
> > > >> packets compared to ~1.2x seen with the current design (v3) as
>
> >>> This version of the patch seems to have negative impact on
> >>> performance
> >> for burst traffic profile[1].
> >>> Benefits seen with the previous version (v2) was up to ~1.6x for
> >>> 1568 byte
> >> packets compared to ~1.2x seen with the current design (v3) as
> >> measured on new
Hi Maxime,
> > This version of the patch seems to have negative impact on performance
> for burst traffic profile[1].
> > Benefits seen with the previous version (v2) was up to ~1.6x for 1568 byte
> packets compared to ~1.2x seen with the current design (v3) as measured on
> new Intel hardware
> -Original Message-
> From: dev On Behalf Of Kevin Traynor
> Sent: Thursday, January 13, 2022 9:53 PM
> To: d...@openvswitch.org
> Cc: david.march...@redhat.com
> Subject: [ovs-dev] [PATCH] netdev-dpdk: Update to use RTE_ETH
> namespace defines.
>
> This patch updates OVS to use DPDK
Hi ,
This version of the patch seems to have negative impact on performance for
burst traffic profile[1].
Benefits seen with the previous version (v2) was up to ~1.6x for 1568 byte
packets compared to ~1.2x seen with the current design (v3) as measured on new
Intel hardware that supports DSA
Hi Eelco,
> > - Could not find DPDK library in default search path, update
> > + Failed to link with DPDK, check config.log for more details.
> > + Could not find working DPDK library in default search path,
> > + update
> >PKG_CONFIG_PATH for pkg-config to
Hi Kevin ,
Thanks for adding this.
> +
> +$ ovs-appctl dpif-netdev/pmd-perf-show
> +
> +Detailed performance metrics for ``pmd-perf-show`` can also be enabled::
> +
> +$ ovs-vsctl set Open_vSwitch . other_config:pmd-perf-metrics=true
> +
> +See the `ovs-vswitchd(8)`_ manpage for more
LGTM
Acked-by: Sunil Pai G
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
LGTM .
Acked-by: Sunil Pai G
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Hi Kevin,
> > I wonder if we could use the term 'overloaded' instead of 'above the
> threshold' ?
> > Don't have a strong preference tbh.
> >
>
> I tried to avoid using 'overloaded' here because it might suggest that the CPU
> is at 100% utilization processing packets, and the datapath is in
Hi Kevin ,
Couple of minor nits below.
> @@ -240,29 +240,29 @@ PMD Automatic Load Balance (experimental)
> -
>
> -Cycle or utilization based allocation of Rx queues to PMDs gives efficient -
> load distribution but it is not adaptive to change in
Hi Kevin,
Minor nit in commit message below.
> PMD Auto Load Balance was introduced as an experimental feature in OVS
> 2.11. It is used to detect that the Rx to PMD assignments are no longer
Rxq to PMD assignments ?
> balanced and it would be better to reassign.
Rest LGTM.
With that fixed
Hi Kevin,
One comment below.
> diff --git a/Documentation/topics/dpdk/pmd.rst
> b/Documentation/topics/dpdk/pmd.rst
> index 16b8b7b03..5beb2ea97 100644
> --- a/Documentation/topics/dpdk/pmd.rst
> +++ b/Documentation/topics/dpdk/pmd.rst
> @@ -60,8 +60,17 @@ To show current stats::
> $
Hi Kevin,
> .. todo::
> @@ -115,5 +115,5 @@ or can be triggered by using::
> In addition, the output of ``pmd-rxq-show`` was modified to include
> Rx queue utilization of the PMD as a percentage. Prior to this, tracking
> of
> - stats was not available.
> + individual Rx queue
LGTM Kevin.
Acked-by: Sunil Pai G
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
Hi Ilya,
> Hi, Sunil.
>
> I don't think that printing parts of a config.log is a good thing to do.
> Primarily
> because if ./configure failed, users need to look at config.log anyway.
> That's
> a normal thing for all automake based build systems.
>
> One thing that we can improve is the
Hi Michael,
Thanks for the review , responses inline.
> > Before:
> > checking whether linking with dpdk works... no
> > configure: error: Could not find DPDK library in default search path,
> > update PKG_CONFIG_PATH for pkg-config to find the .pc file in
> > non-standard location
> >
> >
Hi Huang,
Thanks for the patch.
The problem is a bit more generic i.e not restrcited to MLX4/MLX5.
Could you try this patch instead ?
http://patchwork.ozlabs.org/project/openvswitch/patch/2020100744.204072-1-sunil.pa...@intel.com/
Thanks and regards,
Sunil
Hi Kevin,
> > v3:
> > - add minor fixes from v2 that were not committed
> > - add unit tests for dry run config checking
> > - Keeping Acks as there is just additional UTs added here (Let me know
> > if any issue with that)
Good to see test cases added, confirming my ack as well.
Thanks and
Hi Kevin,
> >
> > I wonder if the logs in the above function be INFO instead of DBG ?
> > Don't have a strong preference TBH. But if they were info, we need not
> remove any test cases no ?
> >
>
> The reason they are debug is so they won't pollute the logs when a rebalance
> cannot occur
Yup,
1 - 100 of 152 matches
Mail list logo