Re: [ovs-dev] [PATCH] dpif-netdev: Refactor datapath flow cache

Thanks William for your comments. Some replies inline. -Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of William Tu > Sent: Wednesday, January 3, 2018 1:32 AM > To: Wang, Yipeng1 > Cc:

Re: [ovs-dev] [PATCH v3 2/5] conntrack: add commands to r/w CT parameters.

Sure, that's perfect. Thanks, Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Friday, December 15, 2017 7:23 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; > d...@openvswitch.org > Subject: Re: [ovs-dev] [PATC

Re: [ovs-dev] [PATCH v3 5/5] doc: ConnTracker cfg parameters.

Thanks Darrell and Stephen for your suggestions. I'll rework accordingly in v4. Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Monday, December 11, 2017 6:02 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; > d...@open

Re: [ovs-dev] [PATCH v3 2/5] conntrack: add commands to r/w CT parameters.

; From: Darrell Ball [mailto:db...@vmware.com] > Sent: Monday, December 11, 2017 6:44 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; > d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH v3 2/5] conntrack: add commands to r/w CT > parameters. > > One extra note inli

Re: [ovs-dev] [PATCH v6 8/8] NEWS: Add keepalive support information in NEWS.

I think this needs a trivial rebase, other than that it's ok. Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday, December

Re: [ovs-dev] [PATCH v6 6/8] keepalive: Add support to query keepalive status and statistics.

LGTM, Tested-by: Antonio Fischetti Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday,

Re: [ovs-dev] [PATCH v6 5/8] bridge: Update keepalive status in OVSDB.

LGTM, Tested-by: Antonio Fischetti Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday,

Re: [ovs-dev] [PATCH v6 4/8] keepalive: Retrieve PMD status periodically.

LGTM, Tested-by: Antonio Fischetti Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday,

Re: [ovs-dev] [PATCH v6 3/8] dpif-netdev: Enable heartbeats for DPDK datapath.

LGTM, Tested-by: Antonio Fischetti Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday,

Re: [ovs-dev] [PATCH v6 2/8] dpif-netdev: Register packet processing cores to KA framework.

LGTM, Tested-by: Antonio Fischetti Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday,

Re: [ovs-dev] [PATCH v6 1/8] Keepalive: Add initial keepalive configuration.

LGTM, Tested-by: Antonio Fischetti Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Bhanuprakash Bodireddy > Sent: Friday,

Re: [ovs-dev] [PATCH v6 0/8] Add OVS DPDK keep-alive functionality.

Hi Bhanu, I've tested v6 and LGTM, works as expected. To check the behavior I blocked one or more of the PMD with the trick of attaching cgdb. So with utilities/ovs-appctl keepalive/pmd-health-show I could see for example 2 of the 3 PMDs - those I intentionally blocked - correctly

Re: [ovs-dev] [PATCH v4 2/2] netdev-dpdk: Add debug appctl to get mempool information.

n <heetae82@samsung.com>; Fischetti, Antonio > <antonio.fische...@intel.com>; Loftus, Ciara <ciara.lof...@intel.com>; > Stokes, Ian <ian.sto...@intel.com>; Wojciechowicz, RobertX > <robertx.wojciechow...@intel.com>; Flavio Leitner <f...@redhat.com> &g

Re: [ovs-dev] [PATCH V4 2/2] netdev-dpdk: vHost IOMMU support

ian.sto...@intel.com>; d...@openvswitch.org > Cc: maxime.coque...@redhat.com; jan.scheur...@ericsson.com; Mooney, Sean > K <sean.k.moo...@intel.com>; Fischetti, Antonio > <antonio.fische...@intel.com>; Bie, Tiwei <tiwei@intel.com>; > Mcnamara, John <john.

Re: [ovs-dev] [PATCH 3/2] vswitchd: Document netdev-dpdk commands.

Thanks, LGTM. -Antonio Acked-by: Antonio Fischetti <antonio.fische...@intel.com> > -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Tuesday, October 31, 2017 3:18 PM > To: ovs-dev@openvswitch.org > Cc: Heetae Ahn <heetae82

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: Add debug appctl to get mempool information.

@samsung.com] > Sent: Tuesday, October 31, 2017 11:35 AM > To: ovs-dev@openvswitch.org > Cc: Heetae Ahn <heetae82@samsung.com>; Fischetti, Antonio > <antonio.fische...@intel.com>; Loftus, Ciara <ciara.lof...@intel.com>; > Kavanagh, Mark B <mark.b.kavan...

Re: [ovs-dev] [PATCH 4/4] netdev-dpdk: Remove unused MAX_NB_MBUF.

-- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Monday, October 30, 2017 12:53 PM > To: ovs-dev@openvswitch.org > Cc: Heetae Ahn <heetae82@samsung.com>; Fischetti, Antonio > <antonio.fische...@intel.com>; Loftus, Ciara <ciara.lof...@intel

Re: [ovs-dev] [PATCH 3/4] netdev-dpdk: Factor out struct dpdk_mp.

Thanks Ilya, it's a good rework especially for netdev_dpdk_mempool_configure() fn. LGTM Acked-by: Antonio Fischetti ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH 2/4] netdev-dpdk: Fix dpdk_mp leak in case of EEXIST.

LGTM Acked-by: Antonio Fischetti <antonio.fische...@intel.com> > -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Monday, October 30, 2017 12:53 PM > To: ovs-dev@openvswitch.org > Cc: Heetae Ahn <heetae82@samsung.

Re: [ovs-dev] [PATCH 1/3] dpif-netdev: Rename rxq_interval.

LGTM, makes the code more readable. Acked-by: Antonio Fischetti > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Kevin Traynor > Sent: Friday, October 20, 2017 11:37 AM > To: Darrell Ball

Re: [ovs-dev] [PATCH v8 6/6] netdev-dpdk: Rename dpdk_mp_put as dpdk_mp_free.

> -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 20, 2017 9:44 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Darrell Ball <dlu...@gmail.com>; Loftus, Ciara <ciara.lof...@intel.com>; > Kevin

Re: [ovs-dev] [PATCH v8 4/6] netdev-dpdk: manage failure in mempool name creation.

> -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 20, 2017 10:28 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Darrell Ball <dlu...@gmail.com>; Loftus, Ciara <ciara.lof...@intel.com>; > Kevin

Re: [ovs-dev] [PATCH v8 0/6] netdev-dpdk: Fix mempool management and other cleanup.

> -Original Message- > From: Stokes, Ian > Sent: Thursday, October 19, 2017 6:22 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v8 0/6] netdev-dpdk: Fix mempool management and > other cleanup. &g

Re: [ovs-dev] [PATCH v8 4/6] netdev-dpdk: manage failure in mempool name creation.

> -Original Message- > From: Stokes, Ian > Sent: Thursday, October 19, 2017 6:23 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v8 4/6] netdev-dpdk: manage failure in mempool > name creation. >

Re: [ovs-dev] [PATCH v7 2/6] netdev-dpdk: Fix mempool names to reflect socket id.

nal Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Thursday, October 19, 2017 11:33 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Kavanagh, Mark B <mark.b.kavan...@intel.com>; Aaron Conole > <acon...@redh

Re: [ovs-dev] [PATCH v6 1/5] netdev-dpdk: fix management of pre-existing mempools.

> -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Fischetti, Antonio > Sent: Wednesday, October 18, 2017 10:43 AM > To: Kavanagh, Mark B <mark.b.kavan...@intel.com>; d...@openvswitch.org > Subject:

Re: [ovs-dev] [PATCH v6 1/5] netdev-dpdk: fix management of pre-existing mempools.

> -Original Message- > From: Kavanagh, Mark B > Sent: Tuesday, October 17, 2017 10:14 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Kevin Traynor <ktray...@redhat.com>; Aaron Conole <acon...@redhat.com>; > Darre

Re: [ovs-dev] [PATCH v6 5/5] netdev-dpdk: Rename dpdk_mp_put as dpdk_mp_free.

Thanks Mark, comments inline. -Antonio > -Original Message- > From: Kavanagh, Mark B > Sent: Tuesday, October 17, 2017 2:36 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Darrell Ball <dlu...@gmail.com>; Loftus, Ci

Re: [ovs-dev] [PATCH v6 3/5] netdev-dpdk: manage empty mempool names.

Thanks Mark for your suggestions, I'll rework accordingly. -Antonio > -Original Message- > From: Kavanagh, Mark B > Sent: Tuesday, October 17, 2017 2:35 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Darrell Ball <dlu...@g

Re: [ovs-dev] [PATCH v6 2/5] netdev-dpdk: skip init for existing mempools.

> -Original Message- > From: Kavanagh, Mark B > Sent: Tuesday, October 17, 2017 2:34 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Darrell Ball <dlu...@gmail.com>; Loftus, Ciara <ciara.lof...@intel.com>; > Kevin

Re: [ovs-dev] [PATCH v6 1/5] netdev-dpdk: fix management of pre-existing mempools.

Thanks Mark, comments inline. -Antonio > -Original Message- > From: Kavanagh, Mark B > Sent: Tuesday, October 17, 2017 2:34 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Cc: Kevin Traynor <ktray...@redhat.com>; Aaron

Re: [ovs-dev] [PATCH v2] dpctl: manage ret value when dumping CT entries.

Any comment on v2? Thanks, Antonio > -Original Message- > From: Fischetti, Antonio > Sent: Tuesday, September 26, 2017 10:45 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v2] dpctl: manage ret

Re: [ovs-dev] [PATCH v5 0/6] netdev-dpdk: Fix management of pre-existing mempools.

Thanks Mark for your review, some comment inline. -Antonio > -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 13, 2017 3:46 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v5

Re: [ovs-dev] [PATCH v5 5/6] netdev-dpdk: Reword mp_size as n_mbufs.

> -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 13, 2017 3:48 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v5 5/6] netdev-dpdk: Reword mp_size as n_mbufs. > > >From: o

Re: [ovs-dev] [PATCH v5 1/6] netdev-dpdk: fix management of pre-existing mempools.

Thanks Mark for your review, I've added my answers inline. -Antonio > -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 13, 2017 4:56 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATC

Re: [ovs-dev] [PATCH v5 4/6] netdev-dpdk: assert mempool names.

+ CC Darrell to the loop because we already discussed about this. > -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 13, 2017 5:07 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v5 4/6

Re: [ovs-dev] [PATCH v5 4/6] netdev-dpdk: assert mempool names.

> -Original Message- > From: Kavanagh, Mark B > Sent: Friday, October 13, 2017 3:47 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v5 4/6] netdev-dpdk: assert mempool names. > > >From: o

Re: [ovs-dev] [PATCH v5 02/10] Keepalive: Add initial keepalive support.

Hi Bhanu, a couple of minor comments below. -Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Bhanuprakash Bodireddy > Sent: Friday, September 15, 2017 5:40 PM > To: d...@openvswitch.org > Subject: [ovs-dev]

Re: [ovs-dev] [PATCH v5 05/10] dpif-netdev: Enable heartbeats for DPDK datapath.

A couple of minor comments inline. -Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Bhanuprakash Bodireddy > Sent: Friday, September 15, 2017 5:40 PM > To: d...@openvswitch.org > Subject: [ovs-dev] [PATCH v5

Re: [ovs-dev] [PATCH v5 04/10] dpif-netdev: Register packet processing cores to KA framework.

Hi Bhanu, a couple of minor comments inline. -Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Bhanuprakash Bodireddy > Sent: Friday, September 15, 2017 5:40 PM > To: d...@openvswitch.org > Subject: [ovs-dev]

Re: [ovs-dev] [PATCH v3 1/5] netdev-dpdk: fix mempool management with vhu client.

> -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Wednesday, October 11, 2017 2:37 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; Róbert Mulik > <robert.mu...@ericsson.com>; d...@openvswitch.org > Subject: Re: [ovs-d

Re: [ovs-dev] [PATCH v3 1/5] netdev-dpdk: fix mempool management with vhu client.

> -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Wednesday, October 11, 2017 11:40 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; Róbert Mulik > <robert.mu...@ericsson.com>; d...@openvswitch.org > Subject: Re: [ovs-d

Re: [ovs-dev] [PATCH v3 1/5] netdev-dpdk: fix mempool management with vhu client.

ome light? I may have missed some detail as I didn't follow this implementation since the very beginning. Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Fischetti, Antonio > Sent: Wednesday, Octobe

Re: [ovs-dev] [PATCH v3 1/5] netdev-dpdk: fix mempool management with vhu client.

Thanks Robert for reporting this and for all the clear details you provided. I'll look into this and get back to you. Antonio > -Original Message- > From: Róbert Mulik [mailto:robert.mu...@ericsson.com] > Sent: Tuesday, October 10, 2017 4:19 PM > To: Fischetti, Antonio <

Re: [ovs-dev] [PATCH v2 0/4] Conntrack: add commands to r/w CT parameters.

Thanks Kevin, I'll rework a v3. Antonio > -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Tuesday, October 3, 2017 11:11 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH v

Re: [ovs-dev] [PATCH v3 1/5] netdev-dpdk: fix mempool management with vhu client.

Thanks Ciara, will respin a v4. Comments inline. Antonio > -Original Message- > From: Loftus, Ciara > Sent: Friday, October 6, 2017 11:40 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v3 1/5] net

Re: [ovs-dev] [PATCH v2 1/4] netdev-dpdk: fix mempool management with vhu client.

I'll rework this patch and post a V3. Thanks, Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Fischetti, Antonio > Sent: Tuesday, October 3, 2017 4:25 PM > To: Kevin Traynor <ktray

Re: [ovs-dev] [PATCH v2 1/4] netdev-dpdk: fix mempool management with vhu client.

Thanks Kevin for your feedback. Below some details on what happens, how to replicate the issue and some comments inline. -Antonio > -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Monday, October 2, 2017 6:38 PM > To: Fischetti, Antonio <

Re: [ovs-dev] [PATCH v2 0/4] Conntrack: add commands to r/w CT parameters.

Thanks Kevin, comments inline. -Antonio > -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Monday, October 2, 2017 11:46 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH v

Re: [ovs-dev] [PATCH 3/4] netdev-dpdk: log an err message when a mempool name is empty.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, September 26, 2017 9:22 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 3/4] netdev-dpdk: log an err message when a &g

Re: [ovs-dev] [PATCH 2/4] netdev-dpdk: if mempool already exists don't reinit packet areas.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, September 26, 2017 9:02 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 2/4] netdev-dpdk: if mempool already exists &g

Re: [ovs-dev] [PATCH 1/4] netdev-dpdk: fix mempool management with vhu client.

Thanks Darrell, replies inline. -Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, September 26, 2017 9:04 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH

Re: [ovs-dev] [PATCH v2] dpctl: manage ret value when dumping CT entries.

Actually I forgot to add in the commit message Reviewed-by: Greg Rose Can this please be added later? Thanks, Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of antonio.fische...@intel.com

Re: [ovs-dev] [PATCH 1/2] dpctl: manage ret value when dumping CT entries.

Thanks Darrell, comments inline. I'll post a v2 based on your suggestions. -Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Monday, September 25, 2017 8:31 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch

Re: [ovs-dev] [PATCH 2/2] dpctl: init CT entry variable.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Monday, September 25, 2017 8:35 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 2/2] dpctl: init CT entry variable. > >

Re: [ovs-dev] [PATCH 2/2] dpctl: init CT entry variable.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Friday, September 22, 2017 9:26 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 2/2] dpctl: init CT entry variable. > >

Re: [ovs-dev] [PATCH 1/2] dpctl: manage ret value when dumping CT entries.

ent: Friday, September 22, 2017 8:42 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 1/2] dpctl: manage ret value when dumping CT > entries. > > Few comments Antonio > > Darrell > > On 9/

Re: [ovs-dev] [patch v2 4/5] conntrack: Add function print_conn_info().

Looks a good improvement to report on an intentional exploit, or other issues. LGTM, just one comment. Now this new print fn is called just from create_un_nat_conn but in the future it could potentially be called from any other CT function. As the function call could affect the performance,

Re: [ovs-dev] [PATCH 1/5] conntrack: add commands to r/w conntrack parameters.

; From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Tuesday, September 19, 2017 2:11 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 1/5] conntrack: add commands to r/w conntrack > parameters. > > On 09/18

Re: [ovs-dev] [PATCH 3/5] conntrack: r/w clean-up interval.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, September 19, 2017 9:28 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 3/5] conntrack: r/w clean-up interval. >

Re: [ovs-dev] [PATCH 2/5] conntrack: r/w upper limit value for connections.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, September 19, 2017 9:05 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 2/5] conntrack: r/w upper limit va

Re: [ovs-dev] [PATCH 1/5] conntrack: add commands to r/w conntrack parameters.

Thanks Darrell for your comments, I'll re-spin a V2 based on your feedback. Other details inline below. -Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, September 19, 2017 8:50 AM > To: Fischetti, Antonio <antonio.fische..

Re: [ovs-dev] [PATCH v4 7/7] keepalive: Add support to query keepalive status and statistics.

Comments inline. > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Bhanuprakash Bodireddy > Sent: Tuesday, August 22, 2017 10:41 AM > To: d...@openvswitch.org > Cc: i.maxim...@samsung.com > Subject: [ovs-dev] [PATCH v4

Re: [ovs-dev] [PATCH v4 5/7] keepalive: Retrieve PMD status periodically.

Comments inline. > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Bhanuprakash Bodireddy > Sent: Tuesday, August 22, 2017 10:41 AM > To: d...@openvswitch.org > Cc: i.maxim...@samsung.com > Subject: [ovs-dev] [PATCH v4

Re: [ovs-dev] [PATCH v4 2/7] Keepalive: Add initial keepalive support.

Comments inline. > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Bhanuprakash Bodireddy > Sent: Tuesday, August 22, 2017 10:41 AM > To: d...@openvswitch.org > Cc: i.maxim...@samsung.com > Subject: [ovs-dev] [PATCH v4

Re: [ovs-dev] [PATCH v4 0/7] Add OVS DPDK keep-alive functionality.

Hi Bhanu, I added some comments on patches #2, 5 and 7. Besides that LGTM. I applied this patch series to commit 84d2723305064e25402cb89a16bf7ad1aa2cda70 and it works as expected. -Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org

Re: [ovs-dev] [PATCH v4] dpif-netdev: Avoid reading RSS hash when EMC is disabled

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Friday, August 25, 2017 6:19 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH v4] dpif-netdev: Avoid reading RSS hash when EMC

Re: [ovs-dev] [PATCH v3 2/4] dpif-netdev: Avoid reading RSS hash when EMC is disabled

Sure Darrell, I'll do that. Thanks! Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Friday, August 25, 2017 9:59 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH v3 2/

Re: [ovs-dev] [PATCH v3] netdev-dpdk: Create separate memory pool for each port

> -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Tuesday, August 22, 2017 7:58 PM > To: Aaron Conole <acon...@redhat.com>; Fischetti, Antonio > <antonio.fische...@intel.com> > Cc: Wojciechowicz, RobertX <robe

Re: [ovs-dev] [PATCH v3 1/4] dpif-netdev: Skip EMC lookup/insert for recirc packets

> -Original Message- > From: Jan Scheurich [mailto:jan.scheur...@ericsson.com] > Sent: Thursday, August 17, 2017 1:42 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; Darrell Ball > <db...@vmware.com>; d...@openvswitch.org > Subject: RE: [ovs-d

Re: [ovs-dev] [PATCH v3] netdev-dpdk: Create separate memory pool for each port

Hi Kevin, pls see comments inline. I'm going to rebase and rework this patch on behalf of Robert. Thanks, Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] > On Behalf Of Kevin Traynor > Sent: Tuesday, April 11, 2017 9:37 AM >

Re: [ovs-dev] [PATCH v3 1/4] dpif-netdev: Skip EMC lookup/insert for recirc packets

periodically increases the probability again to probe for changed > traffic patterns. > > Once we have that I think the same dynamic probability could be possible to > use > also for probabilistic EMC insertion. > > BR, Jan > > > -Original Message- > > Fro

Re: [ovs-dev] [PATCH v3 1/4] dpif-netdev: Skip EMC lookup/insert for recirc packets

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Wednesday, August 16, 2017 9:09 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH v3 1/4] dpif-netdev: Skip EMC lookup/insert

Re: [ovs-dev] [PATCH 0/5] dpif-netdev: Cuckoo-Distributor implementation

Any comment on this patchset? Adding Jan in CC. In one of the last bi-weekly meeting there was some interest in testing this patchset in conjunction with the patch to avoid using EMC for recirculated packets - this is contained inside the patchset

Re: [ovs-dev] [PATCH v2 2/2] dpif-netdev: Fix emc replacement policy.

> -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Tuesday, August 8, 2017 8:16 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; Ilya Maximets > <i.maxim...@samsung.com>; ovs-dev@openvswitch.org > Cc: Heetae Ahn <heetae

Re: [ovs-dev] [PATCH v3 1/2] dpif-netdev: Decrease range of values for EMC probability.

ung.com>; Kevin Traynor > <ktray...@redhat.com>; > Loftus, Ciara <ciara.lof...@intel.com>; Fischetti, Antonio > <antonio.fische...@intel.com> > Subject: Re: [PATCH v3 1/2] dpif-netdev: Decrease range of values for EMC > probability. > > > > -Or

Re: [ovs-dev] [PATCH v3 2/2] dpif-netdev: Fix emc replacement policy.

rell Ball <db...@vmware.com>; > Wang, Yipeng1 <yipeng1.w...@intel.com>; Kevin Traynor <ktray...@redhat.com>; > Loftus, Ciara <ciara.lof...@intel.com>; Fischetti, Antonio > <antonio.fische...@intel.com>; Ilya Maximets <i.maxim...@samsung.com> > Subjec

Re: [ovs-dev] [PATCH v2 1/2] dpif-netdev: Decrease range of values for EMC probability.

My reply inline. Acked-by: Antonio Fischetti <antonio.fische...@intel.com> > -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Friday, August 4, 2017 12:38 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; ovs-dev@openvswi

Re: [ovs-dev] [PATCH v2 1/2] dpif-netdev: Decrease range of values for EMC probability.

LGTM, just wondering if a further comment would help, eg something like +/* random_uint32() returns a value in the [0; UINT32_MAX] range. + For our checking to be correct we would need instead a random value + in the range [0; UINT32_MAX - 1]. To avoid further computation + we use a

Re: [ovs-dev] [PATCH v2 2/2] dpif-netdev: Fix emc replacement policy.

LGTM. I think this patch could work fine in conjunction with the one I posted https://mail.openvswitch.org/pipermail/ovs-dev/2017-July/335940.html where I'm targeting a congestion usecase with recirculated packets. The goal is still to limit thrashing and the criteria is to avoid EMC lookup and

Re: [ovs-dev] [PATCH v2 3/5] dpif-netdev: Skip EMC lookup/insert for recirc packets.

> -Original Message- > From: O Mahony, Billy > Sent: Tuesday, August 1, 2017 11:51 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v2 3/5] dpif-netdev: Skip EMC lookup/insert for > recirc

Re: [ovs-dev] [PATCH v2 2/5] dpif-netdev: Avoid reading RSS hash when EMC is disabled.

> -Original Message- > From: O Mahony, Billy > Sent: Monday, July 31, 2017 5:22 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH v2 2/5] dpif-netdev: Avoid reading RSS hash when > EMC is d

Re: [ovs-dev] [patch_v2] dpdk: Fix device cleanup.

> -Original Message- > From: Aaron Conole [mailto:acon...@redhat.com] > Sent: Sunday, July 30, 2017 4:19 PM > To: Darrell Ball <dlu...@gmail.com> > Cc: d...@openvswitch.org; Fischetti, Antonio <antonio.fische...@intel.com>; > Ilya Maximets <i.maxim...@sam

Re: [ovs-dev] [patch_v1] dpdk: Fix device cleanup.

LGTM I agree with this safe approach. I did some basic testing with a Niantic NIC but I couldn't replicate the issue. Below some details on my testing. To cause the issue I killed and restarted vswitchd only, so that it could find and run with an existing database with the devices already

Re: [ovs-dev] [PATCH RFC 2/4] dpif-netdev: Skip EMC lookup/insert for recirculated packets.

://mail.openvswitch.org/pipermail/ovs-dev/2017-July/335938.html -Antonio > -Original Message- > From: O Mahony, Billy > Sent: Wednesday, July 26, 2017 9:55 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH RFC 2/4] dpif-ne

Re: [ovs-dev] [PATCH v4] dpctl: Add new 'ct-bkts' command.

Hi Darrell, I posted a v5 at http://patchwork.ozlabs.org/patch/792723/ where I added all your suggestions. Thanks, -Antonio > -Original Message- > From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Fischetti, Antonio > Sent: Mon

Re: [ovs-dev] [PATCH v4] dpctl: Add new 'ct-bkts' command.

Thanks Darrell, I will apply your suggetions. -Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Sunday, July 23, 2017 6:28 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PAT

Re: [ovs-dev] [PATCH v3] dpctl: Add new 'ct-bkts' command.

Thanks Darrell, I agree with all your suggestions. I'll rework and post a new version. -Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Friday, July 21, 2017 8:12 AM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d.

Re: [ovs-dev] [PATCH RFC v2] Conntrack: Avoid recirculation for established connections.

Thanks Sugesh for your comments, pls see replies inline. -Antonio > -Original Message- > From: Chandran, Sugesh > Sent: Friday, June 23, 2017 4:20 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH RFC

Re: [ovs-dev] [PATCH 1/4] dpif-netdev: Avoid reading RSS hash when EMC is disabled.

vs-dev-boun...@openvswitch.org [mailto:ovs-dev- > boun...@openvswitch.org] On Behalf Of Fischetti, Antonio > Sent: Friday, June 23, 2017 10:53 PM > To: O Mahony, Billy <billy.o.mah...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH 1/4] dpif-netdev: Avoid rea

Re: [ovs-dev] [PATCH v2] dpctl: Add new 'ct-bkts' command.

Thanks Darrel for your feedback, I'll post a v3 soon. Antonio > -Original Message- > From: Darrell Ball [mailto:db...@vmware.com] > Sent: Monday, July 17, 2017 6:03 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: Re: [ovs-

Re: [ovs-dev] [PATCH 3/3] dpctl: Add new 'ct-bkts' command.

> -Original Message- > From: Ben Pfaff [mailto:b...@ovn.org] > Sent: Friday, July 14, 2017 7:29 PM > To: Fischetti, Antonio <antonio.fische...@intel.com> > Cc: CC: <d...@openvswitch.org> > Subject: Re: [ovs-dev] [PATCH 3/3] dpctl: Add new 'ct-bkts' command. &

Re: [ovs-dev] [PATCH 3/3] dpctl: Add new 'ct-bkts' command.

Thanks Ben for your feedback, my replies inline. > -Original Message- > From: Ben Pfaff [mailto:b...@ovn.org] > Sent: Tuesday, July 11, 2017 8:54 PM > To: Fischetti, Antonio <antonio.fische...@intel.com> > Cc: d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH

Re: [ovs-dev] [PATCH v5 0/2] conntrack : Add support for rx checksum offload.

Hi Sugesh and Darrell, I reviewed this patchset v5 and it LGTM. I've also tested it with 10 UDP flows, 64B packets and a firewall setup as below. table=0, priority=100,ct_state=-trk,ip actions=ct(table=1) table=0, priority=10,arp actions=NORMAL table=0, priority=1 actions=drop table=1,

Re: [ovs-dev] [PATCH 4/4] dp-packet: Use memcpy to copy dp_packet fields.

Hi Billy, thanks for your review. Replies inline. /Antonio > -Original Message- > From: O Mahony, Billy > Sent: Friday, June 23, 2017 2:27 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH 4/4] dp-packe

Re: [ovs-dev] [PATCH 1/4] dpif-netdev: Avoid reading RSS hash when EMC is disabled.

7 5:23 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH 1/4] dpif-netdev: Avoid reading RSS hash > when EMC is disabled. > > Hi Antonio, > > > -Original Message- > > From: Fischetti, Antonio > > S

Re: [ovs-dev] [PATCH RFC 2/4] dpif-netdev: Skip EMC lookup/insert for recirculated packets.

Thanks a lot Billy, really appreciate your feedback. My replies inline. /Antonio > -Original Message- > From: O Mahony, Billy > Sent: Friday, June 23, 2017 6:39 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev]

Re: [ovs-dev] [PATCH 1/4] dpif-netdev: Avoid reading RSS hash when EMC is disabled.

tonio > -Original Message- > From: O Mahony, Billy > Sent: Friday, June 23, 2017 1:54 PM > To: Fischetti, Antonio <antonio.fische...@intel.com>; d...@openvswitch.org > Subject: RE: [ovs-dev] [PATCH 1/4] dpif-netdev: Avoid reading RSS hash > when EMC is disabled. >

Re: [ovs-dev] [PATCH RFC] dpif-netdev: Add Cuckoo Distributor to Accelerate Megaflow Search

@vmware.com>; d...@openvswitch.org; ja...@ovn.org; > jan.scheur...@ericsson.com > Cc: Tai, Charlie <charlie@intel.com>; Wang, Ren <ren.w...@intel.com>; > Gobriel, Sameh <sameh.gobr...@intel.com>; Fischetti, Antonio > <antonio.fische...@intel.com> > Subject: RE:

Re: [ovs-dev] [patch_v2 3/3] conntrack: Add hash_finish() to conn_key_hash().

Hi Darrell, it seems in lib/hash.h there's already a hash_finish() function for the Intrinsic mode where the 1st parm is a uint64_t: static inline uint32_t hash_finish(uint64_t hash, uint64_t final) so I'm getting some errors when building with CFLAGS="-O2 -march=native -g" lib/hash.h:180:24:

  1   2   >