Re: [ovs-dev] [PATCH v2 0/3] dpdk: Add support for TSO

On Fri, Jan 11, 2019 at 8:22 AM Ilya Maximets wrote: > Nothing significantly changed since the previous versions. > This patch set effectively breaks following cases if multi-segment > mbufs enabled: > > 1. Host <-> VM communication broken. > > With this patch applied VMs has offloading

Re: [ovs-dev] [PATCH v2 0/3] dpdk: Add support for TSO

On 11/01/2019 19:37, Ian Stokes wrote: > On 1/11/2019 4:14 PM, Ilya Maximets wrote: >> Nothing significantly changed since the previous versions. >> This patch set effectively breaks following cases if multi-segment >> mbufs enabled: >> > > Hi Ilya, thanks for your feedback. A few queries and

Re: [ovs-dev] [PATCH v2 0/3] dpdk: Add support for TSO

On 11/01/2019 16:14, Ilya Maximets wrote: [snip] > One more thing I wanted to mention is that I was surprised to not see > the performance comparison of TSO with usual Jumbo frames in your slides > on a recent OVS Conference [1]. You had a comparison slide with 1500 MTU, > TSO and the kernel

Re: [ovs-dev] [PATCH v2 0/3] dpdk: Add support for TSO

On 1/11/2019 4:14 PM, Ilya Maximets wrote: Nothing significantly changed since the previous versions. This patch set effectively breaks following cases if multi-segment mbufs enabled: Hi Ilya, thanks for your feedback. A few queries and clarifications for discussion below. From reading the

Re: [ovs-dev] [patch v1] conntrack: Fix FTP seq_skew boundary adjustments.

On Thu, Jan 10, 2019 at 12:58 PM Darrell Ball wrote: > > > On Thu, Jan 10, 2019 at 1:03 AM David Marchand > wrote: > >> Hello, >> >> On Wed, Jan 9, 2019 at 4:44 AM Darrell Ball wrote: >> >>> Fixes: bd5e81a0e596 ("Userspace Datapath: Add ALG infra and FTP.") >>> Signed-off-by: Darrell Ball >>>

Re: [ovs-dev] [PATCH 8/8] ofproto: Handle flow monitor requests with multiple parts.

> On Aug 30, 2018, at 1:00 PM, Ben Pfaff wrote: > > Signed-off-by: Ben Pfaff > --- > ofproto/ofproto.c | 84 +-- > 1 file changed, 44 insertions(+), 40 deletions(-) > > diff --git a/ofproto/ofproto.c b/ofproto/ofproto.c > index

Re: [ovs-dev] [RFC 2/2] lib/tc: add set ipv6 traffic class action offload via pedit

On Fri, Jan 11, 2019 at 05:35:45PM +, Pieter Jansen van Vuuren wrote: > On 11/01/2019 16:49, Ben Pfaff wrote: > > On Fri, Jan 11, 2019 at 11:51:53AM +, Pieter Jansen van Vuuren wrote: > >> +/* These functions specifically help shifting words in network > >> + * byte order, given that they

Re: [ovs-dev] [RFC 2/2] lib/tc: add set ipv6 traffic class action offload via pedit

On 11/01/2019 16:49, Ben Pfaff wrote: > On Fri, Jan 11, 2019 at 11:51:53AM +, Pieter Jansen van Vuuren wrote: >> +/* These functions specifically help shifting words in network >> + * byte order, given that they are specified in host order. */ >> +static inline uint32_t >>

Re: [ovs-dev] [RFC 2/2] lib/tc: add set ipv6 traffic class action offload via pedit

On Fri, Jan 11, 2019 at 11:51:53AM +, Pieter Jansen van Vuuren wrote: > +/* These functions specifically help shifting words in network > + * byte order, given that they are specified in host order. */ > +static inline uint32_t > +shift_ovs_be32_left(uint32_t word, int shift) > +{ > +

Re: [ovs-dev] [PATCH v2 0/3] flake8 fixes

On Fri, Jan 11, 2019 at 03:48:44PM +0530, Numan Siddique wrote: > On Fri, Jan 11, 2019 at 4:54 AM Ben Pfaff wrote: > > > This is needed to make OVS work with flake8 3.6. > > > > > Tested all the patches in this series on fedora 29 with flake8 3.7 and it > fixes all > the flake8 issues. > > Ack

Re: [ovs-dev] [PATCH] ovs-actions: Remove unneded unicode symbols.

On Fri, Jan 11, 2019 at 12:36:52PM +0300, Ilya Maximets wrote: > Fixes manpage-check warnings on FreeBSD 11.2: > > lib/ovs-actions.7:1389: warning: invalid input character code 128 > lib/ovs-actions.7:1389: warning: invalid input character code 128 > lib/ovs-actions.7:1389: warning: can't find

Re: [ovs-dev] [PATCH] vconn: Fix using of uninitialized deadline.

On Fri, Jan 11, 2019 at 11:09:19AM +0300, Ilya Maximets wrote: > Typo introduced while making minor refactoring before applying the > patch. > > Fixes logic and the clang build: > > lib/vconn.c:707:47: error: > variable 'deadline' is uninitialized when > used within its own

Re: [ovs-dev] [PATCH v2 2/3] netdev-dpdk: Consider packets marked for TSO.

Hi Ian, Agreed with all that's said below and will work on the changes, just a small comment in-line. On 11/01/2019 12:26, Ian Stokes wrote: > On 1/10/2019 4:58 PM, Tiago Lam wrote: >> Previously, TSO was being explicity disabled on vhost interfaces, >> meaning the guests wouldn't have TSO

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/11/2019 4:11 PM, David Marchand wrote: On Fri, Jan 11, 2019 at 5:07 PM Ian Stokes > wrote: On 1/11/2019 3:45 PM, Lam, Tiago wrote: > Thanks for bringing this up. I can see from the thread that this is > pretty much clarified by now, but do we

Re: [ovs-dev] [PATCH v2 0/3] dpdk: Add support for TSO

Nothing significantly changed since the previous versions. This patch set effectively breaks following cases if multi-segment mbufs enabled: 1. Host <-> VM communication broken. With this patch applied VMs has offloading enabled by default. This makes all the packets that goes out

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On Fri, Jan 11, 2019 at 5:07 PM Ian Stokes wrote: > On 1/11/2019 3:45 PM, Lam, Tiago wrote: > > Thanks for bringing this up. I can see from the thread that this is > > pretty much clarified by now, but do we still want to include a comment? > > Since the docs are also versioned, and David's

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/11/2019 3:45 PM, Lam, Tiago wrote: Hi Ian, Thanks, comments in-line. [snip] +/* Validate the burst of packets for Tx. */ +nb_prep = rte_eth_tx_prepare(dev->port_id, qid, pkts, cnt); So one of the gotchas here is that rte_eth_tx_prepare is experimental although I

Re: [ovs-dev] [PATCH v2 3/3] netdev-dpdk: Enable TSO when using multi-seg mbufs

On 1/10/2019 4:58 PM, Tiago Lam wrote: TCP Segmentation Offload (TSO) is a feature which enables the TCP/IP network stack to delegate segmentation of a TCP segment to the hardware NIC, thus saving compute resources. This may improve performance significantly for TCP workload in virtualized

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

Hi Ian, Thanks, comments in-line. On 11/01/2019 10:50, Ian Stokes wrote: > On 1/10/2019 4:58 PM, Tiago Lam wrote: >> Given that multi-segment mbufs might be sent between interfaces that >> support different capabilities, and may even support different layouts >> of mbufs, outgoing packets should

Re: [ovs-dev] [PATCH v13 06/11] dp-packet: Add support for data "linearization".

On 11/01/2019 11:29, Ilya Maximets wrote: > Not a full review. > Comments inline. Thanks Ilya, responses in-line. > > Best regards, Ilya Maximets. > > On 09.01.2019 21:05, Tiago Lam wrote: >> Previous commits have added support to the dp_packet API to handle >> multi-segmented packets, where

Re: [ovs-dev] [PATCH v2 2/3] netdev-dpdk: Consider packets marked for TSO.

On 1/11/2019 12:26 PM, Ian Stokes wrote: On 1/10/2019 4:58 PM, Tiago Lam wrote: Previously, TSO was being explicity disabled on vhost interfaces, meaning the guests wouldn't have TSO support negotiated in. With TSO negotiated and enabled, packets are now marked for TSO, through the

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On Fri, Jan 11, 2019 at 1:49 PM Ian Stokes wrote: > On 1/11/2019 12:29 PM, Ferruh Yigit wrote: > > On 1/11/2019 11:20 AM, Andrew Rybchenko wrote: > >> On 1/11/19 2:11 PM, David Marchand wrote: > >>> Indeed, the documentation tells it is experimental, but the > experimental tag > >>> has always

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/11/2019 12:29 PM, Ferruh Yigit wrote: On 1/11/2019 11:20 AM, Andrew Rybchenko wrote: On 1/11/19 2:11 PM, David Marchand wrote: On Fri, Jan 11, 2019 at 11:56 AM Ian Stokes mailto:ian.sto...@intel.com>> wrote: On 1/10/2019 4:58 PM, Tiago Lam wrote: > +        /* Validate the

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/11/2019 11:20 AM, Andrew Rybchenko wrote: > On 1/11/19 2:11 PM, David Marchand wrote: >> >> On Fri, Jan 11, 2019 at 11:56 AM Ian Stokes > > wrote: >> >> On 1/10/2019 4:58 PM, Tiago Lam wrote: >> >> > +        /* Validate the burst of packets for Tx. */ >>

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/11/2019 11:20 AM, Andrew Rybchenko wrote: > On 1/11/19 2:11 PM, David Marchand wrote: >> >> On Fri, Jan 11, 2019 at 11:56 AM Ian Stokes > > wrote: >> >> On 1/10/2019 4:58 PM, Tiago Lam wrote: >> >> > +        /* Validate the burst of packets for Tx. */ >>

Re: [ovs-dev] [PATCH v2 2/3] netdev-dpdk: Consider packets marked for TSO.

On 1/10/2019 4:58 PM, Tiago Lam wrote: Previously, TSO was being explicity disabled on vhost interfaces, meaning the guests wouldn't have TSO support negotiated in. With TSO negotiated and enabled, packets are now marked for TSO, through the PKT_TX_TCP_SEG flag. In order to deal with this type

[ovs-dev] (no subject)

___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH v4] Adding support for PMD auto load balancing

On 01/11/2019 07:45 AM, Nitin Katiyar wrote: > Port rx queues that have not been statically assigned to PMDs are currently > assigned based on periodically sampled load measurements. > The assignment is performed at specific instances – port addition, port > deletion, upon reassignment request via

[ovs-dev] [RFC 1/2] lib/tc: add set ipv4 dscp and ecn action offload via pedit

Add setting of ipv4 dscp and ecn fields in tc offload using pedit. Signed-off-by: Pieter Jansen van Vuuren Signed-off-by: Louis Peens Reviewed-by: Simon Horman --- lib/netdev-tc-offloads.c | 6 +- lib/tc.c | 5 + lib/tc.h | 1 + 3 files changed, 11

[ovs-dev] [RFC 0/2] extend ovs-tc offload for more pedit action

Hi all, This set extends the ovs-tc pedit interface to allow setting ipv4 dscp and ecn fields as well as ipv6 traffic class in tc via pedit. Patch 2 in this set also introduces the notion of boundary shifts to allow translating non-byte-aligned fields like traffic class and flow limit for IPv6 to

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/11/19 2:11 PM, David Marchand wrote: On Fri, Jan 11, 2019 at 11:56 AM Ian Stokes mailto:ian.sto...@intel.com>> wrote: On 1/10/2019 4:58 PM, Tiago Lam wrote: +/* Validate the burst of packets for Tx. */ +nb_prep = rte_eth_tx_prepare(dev->port_id, qid, pkts, cnt); So one

Re: [ovs-dev] [PATCH v13 06/11] dp-packet: Add support for data "linearization".

Not a full review. Comments inline. Best regards, Ilya Maximets. On 09.01.2019 21:05, Tiago Lam wrote: > Previous commits have added support to the dp_packet API to handle > multi-segmented packets, where data is not stored contiguously in > memory. However, in some cases, it is inevitable and

Re: [ovs-dev] [PATCH] vconn: Fix using of uninitialized deadline.

On 01/11/2019 08:09 AM, Ilya Maximets wrote: > Typo introduced while making minor refactoring before applying the > patch. > > Fixes logic and the clang build: > > lib/vconn.c:707:47: error: > variable 'deadline' is uninitialized when > used within its own initialization

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On Fri, Jan 11, 2019 at 11:56 AM Ian Stokes wrote: > On 1/10/2019 4:58 PM, Tiago Lam wrote: > > > +/* Validate the burst of packets for Tx. */ > > +nb_prep = rte_eth_tx_prepare(dev->port_id, qid, pkts, cnt); > > So one of the gotchas here is that rte_eth_tx_prepare is

Re: [ovs-dev] [PATCH v2 1/3] netdev-dpdk: Validate packets burst before Tx.

On 1/10/2019 4:58 PM, Tiago Lam wrote: Given that multi-segment mbufs might be sent between interfaces that support different capabilities, and may even support different layouts of mbufs, outgoing packets should be validated before sent on the egress interface. Thus, netdev_dpdk_eth_tx_burst()

Re: [ovs-dev] [PATCH v2] Monitor Database table to manage lifecycle of IDL client.

On Fri, Jan 4, 2019 at 5:26 PM Numan Siddique wrote: > Hi Ted, > > This patch is failing the below test cases for me. All are python3 > related. Can you please > take a look if that's the case with you as well ? > ** > 2139: simple idl, writing via IDL with unicode - Python3 FAILED ( >

Re: [ovs-dev] [PATCH v2 0/3] flake8 fixes

On Fri, Jan 11, 2019 at 4:54 AM Ben Pfaff wrote: > This is needed to make OVS work with flake8 3.6. > > Tested all the patches in this series on fedora 29 with flake8 3.7 and it fixes all the flake8 issues. Ack for the whole series. Acked-by: Numan Siddique Tested-by: Numan Siddique Thanks

Re: [ovs-dev] [PATCH v13 06/11] dp-packet: Add support for data "linearization".

On 11/01/2019 01:34, Darrell Ball wrote: > thanks; not a full review Thanks, responses in-line. > > On Wed, Jan 9, 2019 at 10:06 AM Tiago Lam > wrote: > > Previous commits have added support to the dp_packet API to handle > multi-segmented packets, where

[ovs-dev] [PATCH] ovs-actions: Remove unneded unicode symbols.

Fixes manpage-check warnings on FreeBSD 11.2: lib/ovs-actions.7:1389: warning: invalid input character code 128 lib/ovs-actions.7:1389: warning: invalid input character code 128 lib/ovs-actions.7:1389: warning: can't find character with input code 144 Fixes: be51cd417343 ("ovs-actions: New

Re: [ovs-dev] Support for match & set ICMPv6 reserved and options type fields

Bleep bloop. Greetings Vishal Deep Ajmera, I am a robot and I have tried out your patch. Thanks for your contribution. I encountered some error that I wasn't expecting. See the details below. checkpatch: WARNING: Line is 83 characters long (recommended limit is 79) #502 FILE:

[ovs-dev] [PATCH] vconn: Fix using of uninitialized deadline.

Typo introduced while making minor refactoring before applying the patch. Fixes logic and the clang build: lib/vconn.c:707:47: error: variable 'deadline' is uninitialized when used within its own initialization [-Werror,-Wuninitialized] ? time_msec() +