Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.1.

-Original Message- From: on behalf of Michal Weglicki Date: Tuesday, July 25, 2017 at 5:34 AM To: "d...@openvswitch.org" Subject: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for

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

Commit 5dcde09c80a8 was introduced to make detaching more automatic without using an additional command beyond ovs-vsctl del-port . Sometimes, since commit 5dcde09c80a8, dpdk devices are not detached when del-port is issued; command example: sudo ovs-vsctl del-port br0 dpdk1 This can happen

Re: [ovs-dev] [PATCHv2] ovn: Add support for ACL logging.

> On Jul 28, 2017, at 4:57 PM, Ben Pfaff wrote: > > On Fri, Jul 28, 2017 at 03:48:38PM -0700, Justin Pettit wrote: >> Signed-off-by: Justin Pettit >> Acked-by: Han Zhou >> --- >> v1->v2: Incorporate Ben and Han's feedback. >>Improve

Re: [ovs-dev] [PATCHv2] ovn: Add support for ACL logging.

On Fri, Jul 28, 2017 at 03:48:38PM -0700, Justin Pettit wrote: > Signed-off-by: Justin Pettit > Acked-by: Han Zhou > --- > v1->v2: Incorporate Ben and Han's feedback. > Improve output of "ovn-nbctl acl-list". Thank you! I'm appending a few final

[ovs-dev] [PATCHv2] ovn: Add support for ACL logging.

Signed-off-by: Justin Pettit Acked-by: Han Zhou --- v1->v2: Incorporate Ben and Han's feedback. Improve output of "ovn-nbctl acl-list". --- NEWS| 1 + include/ovn/actions.h | 67

Re: [ovs-dev] [PATCH] ovn: Add support for ACL logging.

> On Jul 27, 2017, at 7:23 PM, Han Zhou wrote: > > On Thu, Jul 27, 2017 at 5:59 PM, Justin Pettit wrote: > > > > The log action may be more generic than just for ACL. So would it better > > > to avoid hardcode "ACL" here in the message? "ACL" could be

Re: [ovs-dev] [PATCH] ovn: Add support for ACL logging.

> On Jul 28, 2017, at 12:38 PM, Ben Pfaff wrote: > > On Wed, Jul 26, 2017 at 01:55:14PM -0700, Justin Pettit wrote: >> Signed-off-by: Justin Pettit > > checkpatch says: > >WARNING: Line has non-spaces leading whitespace >#856 FILE:

Re: [ovs-dev] [PATCH] ovn: Add support for ACL logging.

On Wed, Jul 26, 2017 at 01:55:14PM -0700, Justin Pettit wrote: > Signed-off-by: Justin Pettit checkpatch says: WARNING: Line has non-spaces leading whitespace #856 FILE: ovn/utilities/ovn-nbctl.c:1385: if (log_severity_from_string(severity) ==

[ovs-dev] [PATCH] rhel: Fix typo in README.RHEL.rst

Replace systemctk with systemctl Signed-off-by: Timothy Redaelli --- rhel/README.RHEL.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/rhel/README.RHEL.rst b/rhel/README.RHEL.rst index 1845e8fd..6affdba9 100644 --- a/rhel/README.RHEL.rst +++

Re: [ovs-dev] [PATCH] ovn: Add support for ACL logging.

On 28 July 2017 at 10:05, Ben Pfaff wrote: > On Thu, Jul 27, 2017 at 05:59:54PM -0700, Justin Pettit wrote: > > > > > On Jul 27, 2017, at 4:03 PM, Han Zhou wrote: > > > > > > > > > > > > On Wed, Jul 26, 2017 at 1:55 PM, Justin Pettit > wrote: >

Re: [ovs-dev] [PATCH] dpif-netdev: Simplify emc replacement policy.

Good catch. But I think the hash comparison is to "randomly" choose one of the two entries to replace when both entries are live. Your change would always replace the first one in such case. It might cause some thrashing issue for certain traffic. Meanwhile, to my experience, the original "hash

Re: [ovs-dev] [PATCH v2 00/19] Add OVS DPDK keep-alive functionality.

On 07/28/2017 10:56 AM, Darrell Ball wrote: Thanks for testing Greg We are at DPDK 16.11.2 now See this link http://docs.openvswitch.org/en/latest/faq/releases/ Darrell Well that explains things! Thanks, I'll give it another go with 16.11.2. - Greg -Original Message- From: Greg

Re: [ovs-dev] [PATCH v2 00/19] Add OVS DPDK keep-alive functionality.

Thanks for testing Greg We are at DPDK 16.11.2 now See this link http://docs.openvswitch.org/en/latest/faq/releases/ Darrell -Original Message- From: Greg Rose Date: Friday, July 28, 2017 at 10:51 AM To: "ovs-dev@openvswitch.org" ,

Re: [ovs-dev] [PATCH v2 00/19] Add OVS DPDK keep-alive functionality.

Bhanuprakash, After applying your patch series on top of current master and building I get the following error: libtool: compile: gcc -std=gnu99 -DHAVE_CONFIG_H -I. -I ./include -I ./include -I ./lib -I ./lib -Wstrict-prototypes -Wall -Wextra -Wno-sign-compare -Wpointer-arith -Wformat

[ovs-dev] Bug#870001: openvswitch-switch: switch takes a very long time to start or fails without upstream's SYSTEMCTL_SKIP_REDIRECT=yes

Package: openvswitch-switch Version: 2.6.2~pre+git20161223-3 Severity: important Dear Maintainer, I setup openvswitch-switch with a small number of switches that have one physical interface each. Upon boot, they get configured extremely slow, taking over half an hour to get basic networking

Re: [ovs-dev] [PATCH] ovn: Add support for ACL logging.

On Thu, Jul 27, 2017 at 05:59:54PM -0700, Justin Pettit wrote: > > > On Jul 27, 2017, at 4:03 PM, Han Zhou wrote: > > > > > > > > On Wed, Jul 26, 2017 at 1:55 PM, Justin Pettit wrote: > > > @@ -332,7 +333,7 @@ Logical switch commands:\n\ > > >ls-list

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

-Original Message- From: on behalf of Ilya Maximets Date: Friday, July 28, 2017 at 7:00 AM To: Darrell Ball , "d...@openvswitch.org" Subject: Re: [ovs-dev] [patch_v1] dpdk: Fix device

Re: [ovs-dev] [PATCH] ofproto-dpif-rid: Don't include action_set_len as part of hash.

> On Jul 28, 2017, at 9:29 AM, Ben Pfaff wrote: > > On Thu, Jul 27, 2017 at 07:15:33PM -0700, Justin Pettit wrote: >> It doesn't improve the hashing, since the number of bytes hashed is >> included in hash_bytes64() hash calculation. >> >> Signed-off-by: Justin Pettit

Re: [ovs-dev] [PATCH] ofproto-dpif-rid: Don't include action_set_len as part of hash.

On Thu, Jul 27, 2017 at 07:15:33PM -0700, Justin Pettit wrote: > It doesn't improve the hashing, since the number of bytes hashed is > included in hash_bytes64() hash calculation. > > Signed-off-by: Justin Pettit Acked-by: Ben Pfaff

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

-Original Message- From: on behalf of "Fischetti, Antonio" Date: Friday, July 28, 2017 at 8:43 AM To: Darrell Ball , "d...@openvswitch.org" Cc: Ilya Maximets

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_v1] dpdk: Fix device cleanup.

In general, I have no objections to return 'detach' appctl command. Comments inline. On 26.07.2017 08:09, Darrell Ball wrote: > Commit 5dcde09c80a8 was introduced to make detaching more > automatic without using an additional command. > > Sometimes, since commit 5dcde09c80a8, dpdk devices are >

Re: [ovs-dev] [PATCH] tc: Correct convert ticks to msecs on parsing tc TM

On Thu, Jul 27, 2017 at 01:20:07PM +0300, Or Gerlitz wrote: > On 7/27/2017 1:14 PM, Roi Dayan wrote: > >the system call is done only once. > > good to know, would be worth to mention that on the change-log, so it's > clear we're good w.r.t performance. Roi, could you respin this patch with an

Re: [ovs-dev] [PATCH 3/3] netdev-tc-offloads: Parse ip related fields only if eth type is ip

On Thu, Jul 27, 2017 at 01:20:00PM +0300, Roi Dayan wrote: > From: Paul Blakey > > No need to parse ip related fields otherwise. I would prefer if the changelog could be read without reference to the subject. As you are planning to respin anyway perhaps you could fix this

Re: [ovs-dev] [PATCH 1/3] tc: Refactor nl_msg_put_flower_options

On Thu, Jul 27, 2017 at 01:19:58PM +0300, Roi Dayan wrote: > From: Paul Blakey > > Refactor nl_msg_put_flower_options to be more readable. > This commit doesn't change functionality. > > Signed-off-by: Paul Blakey > Reviewed-by: Roi Dayan

Re: [ovs-dev] [PATCH 2/3] tc: Split IPs and transport layer ports unions in flower struct

On Thu, Jul 27, 2017 at 01:19:59PM +0300, Roi Dayan wrote: > From: Paul Blakey > > Split dst/src_port and ipv4/ipv6 union so we can > distingush them easily for later features. The implications of this change on the size of struct tc_flower_key seem somewhat undesirable to

Re: [ovs-dev] [PATCH] dpif-netlink-rtnl: Fix false errors on interfaces without tunnel config

On Thu, Jul 27, 2017 at 02:40:02PM +0300, Roi Dayan wrote: > When we skip adding a port using rtnetlink and not because of an error we > need to return EOPNOTSUPP to avoid logging an error message. > > Fixes: 2fd3d5eda508 ("dpif-netlink-rtnl: Support layer3 GRE") > Signed-off-by: Roi Dayan

[ovs-dev] [PATCH] dpif-netdev: Simplify emc replacement policy.

Current EMC replacement policy allows to replace active EMC entry even if there are dead (empty) entries available. This leads to EMC trashing even on few hundreds of flows. In some cases PMD threads starts to execute classifier lookups even in tests with 50 - 100 active flows. Fix this by

[ovs-dev] Financial Provider

We offer loan and Financing services to all seekers, not considering their Country, credit scores and nature of collateral. contact i...@springtrustfinance.com to apply now. ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [PATCH 0/4] prioritizing latency sensitive traffic

Hi Billy, >Hi All, > >This patch set provides a method to request ingress scheduling on interfaces. >It also provides an implemtation of same for DPDK physical ports. > >This allows specific packet types to be: >* forwarded to their destination port ahead of other packets. >and/or >* be less

[ovs-dev] [Fwd: I request your partnership]

Hello, I request your partnership in a venture with good return on investment. Get in touch, Send me your Name and telephone No. for further details. Sincerely, Hui-Wen Huang ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [PATCH RFC v2 4/4] dpif-netdev: Time based output batching.

I have not tested yet However, I would have expected something max latency config. to be specific to netdev-dpdk port types This type of code also seems to intersect with present and future QoS considerations in netdev-dpdk -Original Message- From: Ilya Maximets

[ovs-dev] [PATCH] dpif-netdev: Optimize the exact match lookup.

When inserting or updating (e.g. emc_insert) a flow to EMC, we compare (e.g the hash and miniflow ) the netdev_flow_key. If the key is matched, we will update it. If we didn’t find the miniflow in the cache, the new flow will be stored. But when looking up the flow, we compare the hash and

[ovs-dev] [PATCH v3] ofproto-dpif-ipfix: add support for per-flow drop counters

Patch based on RFC 5102, section 5.10. It implements per-flow drop counters: - droppedPacketDeltaCount - droppedPacketTotalCount - droppedOctetDeltaCount - droppedOctetTotalCount In order to determine if packet is going to be dropped, flow actions associated with packet are read. If at least one