[ovs-dev] Organizaciones sin fines de Lucro

Temario e Inscripciones: Respondiendo por este medio "Fondos"+TELÉFONO + NOMBRE+ COMPAÑÍA o marcando al: 045 + 5515546630 FONDOS PARA ORGANIZACIONES SIN FINES DE LUCRO Enero 30 - webinar Interactivo Temas a tratar: Como lograr reconocimiento y prestigio en la comunidad. Como conseguir

[ovs-dev] [PATCH v9 3/3] nsh: add dec_nsh_ttl action

NSH ttl is a 6-bit field ranged from 0 to 63, it should be decremented by 1 every hop, if it is 0 or it is so after decremented, the packet should be dropped and a packet-in message is sent to main controller. Signed-off-by: Yi Yang --- NEWS |

Re: [ovs-dev] [no-slow v2 4/8] ofproto-dpif: Modify process_upcall() to remove some redundant code.

> On Jan 10, 2018, at 4:18 PM, Ben Pfaff wrote: > > On Wed, Jan 10, 2018 at 02:27:22PM -0800, Justin Pettit wrote: >> Signed-off-by: Justin Pettit >> --- >> v1->v2: New to the series. > > Acked-by: Ben Pfaff Great. Thanks for the reviews! I

[ovs-dev] [PATCH v9 1/3] nsh: add new flow key 'ttl'

IETF NSH draft added a new filed ttl in NSH header, this patch is to add new nsh key 'ttl' for it. Signed-off-by: Yi Yang --- NEWS | 1 + datapath/linux/compat/include/linux/openvswitch.h | 2 +- include/openvswitch/flow.h

[ovs-dev] [PATCH v9 2/3] nsh: fix nested mask for OVS_KEY_ATTR_NSH

NSH kernel implementation used nested mask for OVS_KEY_ATTR_NSH, so NSH userspace must adapt to it, OVS hasn't used nested mask for any key attribute so far, OVS_KEY_ATTR_NSH is the first use case. Signed-off-by: Yi Yang --- lib/odp-execute.c | 56 +--

[ovs-dev] [PATCH v9 0/3] nsh: add new nsh key ttl and action dec_nsh_ttl

v8->v9 - Add ttl and dec_nsh_ttl information to NEWS - Fix several unit tests failures - Add NSH introduction in ovs-fields.7 v7->v8 - Ths first patch in v7 series has been merged - Use assignment instead of memcpy - Fix sparse warnings - Keep nsh fields number in meta-flow.inc to

Re: [ovs-dev] [no-slow v2 1/8] ofproto-dpif: Use a fixed size userspace cookie.

> On Jan 10, 2018, at 7:06 PM, Gregory Rose wrote: > > On 1/10/2018 2:27 PM, Justin Pettit wrote: >> This simplifies the cookie handling a bit. >> >> Signed-off-by: Justin Pettit > > All previous failures ares now passing. > > ## - ## > ##

Re: [ovs-dev] [PATCH v8 1/3] nsh: add new flow key 'ttl'

On Thu, Jan 11, 2018 at 06:50:35AM +0800, Ben Pfaff wrote: > On Tue, Jan 09, 2018 at 09:56:16PM +0800, Yi Yang wrote: > > IETF NSH draft added a new filed ttl in NSH header, this patch > > is to add new nsh key 'ttl' for it. > > > > Signed-off-by: Yi Yang > > Thanks for the

[ovs-dev] Subject=Re: Re: [PATCH v5 1/5] dpif-netdev: associate flow with a mark id

+static void +try_netdev_flow_put(struct dp_netdev_pmd_thread *pmd, odp_port_t in_port, +struct dp_netdev_flow *flow, struct match *match, +const struct nlattr *actions, size_t actions_len) +{ +struct offload_info info; +struct dp_netdev_port

Re: [ovs-dev] [PATCH] netdev-dummy: Lock mutex when retrieving custom stats.

Hi Ben, You are right, I totally forgot about this mutex. - Michal. > -Original Message- > From: Ben Pfaff [mailto:b...@ovn.org] > Sent: Thursday, January 11, 2018 12:47 AM > To: d...@openvswitch.org > Cc: Ben Pfaff ; Weglicki, MichalX >

[ovs-dev] Block Egress traffic using flows

Hi, Is there a way to block/drop the egress traffic on a port by configuring a flow? -- Regards Kapil ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH v8 3/3] nsh: add dec_nsh_ttl action

On Thu, Jan 11, 2018 at 06:52:00AM +0800, Ben Pfaff wrote: > On Tue, Jan 09, 2018 at 09:56:18PM +0800, Yi Yang wrote: > > NSH ttl is a 6-bit field ranged from 0 to 63, it should be > > decremented by 1 every hop, if it is 0 or it is so after > > decremented, the packet should be dropped and a

Re: [ovs-dev] [PATCH v5 2/3] dpif-netdev: Detailed performance stats for PMDs

Hi Billy, Thanks for the review. Please find some responses inline. I'll fix the issues in the next version. Regards, Jan > -Original Message- > From: O Mahony, Billy [mailto:billy.o.mah...@intel.com] > Sent: Tuesday, 09 January, 2018 17:25 > To: Jan Scheurich

Re: [ovs-dev] [no-slow v2 1/8] ofproto-dpif: Use a fixed size userspace cookie.

On 1/10/2018 2:27 PM, Justin Pettit wrote: This simplifies the cookie handling a bit. Signed-off-by: Justin Pettit All previous failures ares now passing. ## - ## ## Test results. ## ## - ## 97 tests were successful. 2 tests were skipped. make[1]:

Re: [ovs-dev] [PATCH v8 3/3] nsh: add dec_nsh_ttl action

On Thu, Jan 11, 2018 at 07:02:29AM +0800, Ben Pfaff wrote: > On Wed, Jan 10, 2018 at 02:52:00PM -0800, Ben Pfaff wrote: > > On Tue, Jan 09, 2018 at 09:56:18PM +0800, Yi Yang wrote: > > > NSH ttl is a 6-bit field ranged from 0 to 63, it should be > > > decremented by 1 every hop, if it is 0 or it

[ovs-dev] [PATCH v3 3/4] ovs-bugtool: Enhancement of bugtool plugins.

Bugtool extended with NUMA related, QoS related and RHEL specific information. Signed-off-by: David Patrik Pinter Signed-off-by: Miklos Pelyva Co-authored-by: Miklos Pelyva ---

[ovs-dev] [PATCH v3 2/4] ovs-bugtool: Refactorize bugtool plugin xml files.

Introducing new query calling practice: - single line query called directly from plugin xml - multiple line query saved as script and the script is called from plugin xml Signed-off-by: David Patrik Pinter --- utilities/bugtool/automake.mk

[ovs-dev] [PATCH v3 1/4] ovs-bugtool: Bugfix for bugtool plugin queries.

Introducing 'ovs-bugtool-ovs-ofctl-loop-over-bridges' bash script. It calls ovs-ofctl commands given as first parameter for each bridge with the corresponding open flow protocol option. Usage: ovs-bugtool-ovs-ofctl-loop-over-bridges "param1" "param2" - param1: ovs-ofctl command to call (show,

[ovs-dev] [PATCH v3 0/4] ovs-bugtool: Enahncing and refactoring the OVS-Bugtool.

The development and maintenance of the OVS-Bugtool is long due. It completely ignores DPDK datapath-related logs and information, which are essential by troubleshooting OVS with DPDK datapath. There is also a wide set of none DPDK-related files and commands already used by the community but not

[ovs-dev] ovs+dpdk vhost-user performance.

hi, I tested the vhost-user, but i dont get a better performance. The test case is VM2VM which are in the same host. if we use the vhost-net in kernel, we get a 20 Gbits/sec throughput, but vhost-user is only 5Gits/sec. vhost-net: qemu-system-x86_64 -enable-kvm -m 1G -smp 4 \ -cpu host \ -netdev

[ovs-dev] [PATCH v3 4/4] ovs-bugtool: Extend bugtool with query repeat feature.

Devs can configure bugtool plugin queries to be repeated using repeat counters. The value of a repeat counter is an integer greater than 1. The outputs of a repeated query are saved in the same output file with date headers. Queries without repeat counter will run only once. Users can set the

Re: [ovs-dev] [PATCH v6 1/2] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

Comments inline. Best regards, Ilya Maximets. On 09.01.2018 12:26, Jan Scheurich wrote: > Add module dpif-netdev-perf to host all PMD performance-related > data structures and functions in dpif-netdev. Refactor the PMD > stats handling in dpif-netdev and delegate whatever possible into > the new

Re: [ovs-dev] [PATCH v5 0/5] OVS-DPDK flow offload with rte_flow

Hi Yuanhan, Thank you for your reply!..and for the wishes too :) At very high level, my comments are on the approach taken for enabling hardware acceleration in OVS-DPDK. In general, the proposal works very well for the specific partial offload use case. i.e alleviate the miniflow extract and

Re: [ovs-dev] [PATCH v5 0/5] OVS-DPDK flow offload with rte_flow

Hi All, Based on the comments below, I wanted to call out for a meeting to decide what further needs to be done to handle different kinds of hardware acceleration in OVS-DPDK. We have some POC implementation that partially handles some of the cases , But it only work with some of Intel

[ovs-dev] [PATCH v7 0/2] Refactor PMD stats and cycle counting

This series contains the two refactoring patches of the earlier series * [PATCH v5 0/3] dpif-netdev: Detailed PMD performance metrics and supervision * [RFC PATCH 0/8] dpif-netdev: Refactor cycle count and rebased patches They are intended to serve as common base for the following contibutions: *

[ovs-dev] [PATCH v7 1/2] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

Add module dpif-netdev-perf to host all PMD performance-related data structures and functions in dpif-netdev. Refactor the PMD stats handling in dpif-netdev and delegate whatever possible into the new module, using clean interfaces to shield dpif-netdev from the implementation details.

Re: [ovs-dev] [PATCH v6 1/2] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

On 10.01.2018 18:51, Jan Scheurich wrote: > Hi Ilya, > Thanks for comments. Answers below. > BR, Jan > >> -Original Message- >> From: Ilya Maximets [mailto:i.maxim...@samsung.com] >> Sent: Wednesday, 10 January, 2018 12:24 >> To: Jan Scheurich ;

[ovs-dev] [PATCH v7 2/2] dpif-netdev: Refactor cycle counting

Simplify the historically grown TSC cycle counting in PMD threads. Cycles are currently counted for the following purposes: 1. Measure PMD ustilization PMD utilization is defined as ratio of cycles spent in busy iterations (at least one packet received or sent) over the total number of cycles.

Re: [ovs-dev] [PATCH] windows: Fix x64 build

> -Original Message- > From: Ben Pfaff [mailto:b...@ovn.org] > Sent: Wednesday, January 10, 2018 7:30 PM > To: Alin Gabriel Serdean > Cc: d...@openvswitch.org > Subject: Re: [ovs-dev] [PATCH] windows: Fix x64 build > > On Wed, Jan 10, 2018 at 07:27:52PM +0200, Alin

Re: [ovs-dev] [PATCH v2] tests: Add system-dpdk-testsuite

Hi Marcin, Thanks for the v2 of this patch and thank you for addressing my comments. I have tested again with the latest master and can confirm that this works like in the v1 with ixgbe and i40e devices. I can also confirm that the 3rd test (Add vhost-user-client port) is no longer skipped

[ovs-dev] [RFC 1/3] OVN: add icmp4{} action support

icmp4 action is used to replace the IPv4 packet been processed with an ICMPv4 packet initialized based on incoming IPv4 one. Ethernet and IPv4 fields not listed are not changed: - ip.proto = 1 - ip.frag = 0 - icmp4.type = 3 - icmp4.code = 1 Prerequisite: ip4 Signed-off-by: Lorenzo Bianconi

[ovs-dev] [RFC 0/3] add acl reject rule support introducing icmp4 action

Lorenzo Bianconi (3): OVN: add icmp4{} action support OVN: add ovn-trace support to icmp4 action OVN: add acl reject support using icmp4 action include/ovn/actions.h | 7 + ovn/controller/pinctrl.c | 51 +++ ovn/lib/actions.c | 22

[ovs-dev] [RFC 2/3] OVN: add ovn-trace support to icmp4 action

Signed-off-by: Lorenzo Bianconi --- ovn/utilities/ovn-trace.c | 28 1 file changed, 28 insertions(+) diff --git a/ovn/utilities/ovn-trace.c b/ovn/utilities/ovn-trace.c index 7ff4a2682..8f44a852d 100644 --- a/ovn/utilities/ovn-trace.c +++

[ovs-dev] [RFC 3/3] OVN: add acl reject rule support using icmp4 action

Whenever the acl reject rule is hit send back an ICMPv4 destination unreachable packet and do not handle reject rule as drop one Signed-off-by: Lorenzo Bianconi --- ovn/northd/ovn-northd.c | 76 - 1 file changed, 50

[ovs-dev] [PATCH] tunnel: fix tunnel flags set/clear.

Existing code only set these tunnel flags (df, csum, and key) when the flag is set in the output tunnel port, but did not clear when the flag is unset. The patch fixes it by setting and clearing it accordingly. Two existing testcases need to fix: 'tunnel - Geneve option present' has no key set

[ovs-dev] Auditoria Interna - webinar Interactivo

Solicite AHORA MISMO el temario con toda la información de este EXCLUSIVO EVENTO PRESIONE AQUI o responda "Auditoría"+TELÉFONO + NOMBRE+ COMPAÑÍA 045 + 5515546630 Buenas prácticas para la conducción de un departamento de Auditoria Interna Enero 23 - webinar Interactivo Temas a tratar:

Re: [ovs-dev] [PATCH 0/3] Initial support for new SIP Alg.

On 1/9/18, 12:44 PM, "ovs-dev-boun...@openvswitch.org on behalf of Darrell Ball" wrote: On 1/9/18, 11:33 AM, "ovs-dev-boun...@openvswitch.org on behalf of Mark Michelson"

[ovs-dev] [PATCH] appveyor: Bump OpenSSL version

The URL https://slproweb.com/download/Win32OpenSSL-1_0_2L.exe is no longer valid. Bump the version of OpenSSL to 1_0_2m. Signed-off-by: Alin Gabriel Serdean --- appveyor.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/appveyor.yml b/appveyor.yml

Re: [ovs-dev] [PATCH v6 2/2] dpif-netdev: Refactor cycle counting

PMD_CYCLES_UPCALL PMD_CYCLES_POLL_IDLE PMD_CYCLES_POLL_BUSY are not used in current series and should be removed. PMD_CYCLES_OVERHEAD implemented in patch #1 and removed in patch #2. Should be removed from patch #1 to simplify it. Other comments inline. Best regards, Ilya Maximets. On

Re: [ovs-dev] [PATCH 0/3] Initial support for new SIP Alg.

Hi Mark, Your email strikes me as if you haven't read the previous email exchange at: https://mail.openvswitch.org/pipermail/ovs-dev/2017-November/341089.html (TL;DR I've asked similar questions there) Having said that, and knowing this is happening, my intention is exactly

Re: [ovs-dev] [PATCH v2 0/4] ovs-bugtool: Enahncing and refactoring the OVS-Bugtool.

Hi Ben, Sorry, there was some mix up with tabs and spaces in the atomake.mk file. Here you can find the corrected versions: https://patchwork.ozlabs.org/patch/858195/ https://patchwork.ozlabs.org/patch/858201/ https://patchwork.ozlabs.org/patch/858198/ https://patchwork.ozlabs.org/patch/858200/

Re: [ovs-dev] [no-slow 4/6] ofproto: Add 'ofproto_uuid' and 'ofp_in_port' to user action cookie.

> On Dec 28, 2017, at 4:13 PM, Gregory Rose wrote: > >> diff --git a/ofproto/ofproto-dpif-xlate.c b/ofproto/ofproto-dpif-xlate.c >> index 3bdd64d4d552..ec92c6a730bf 100644 >> --- a/ofproto/ofproto-dpif-xlate.c >> +++ b/ofproto/ofproto-dpif-xlate.c >> @@ -2927,7 +2927,13

[ovs-dev] [PATCH] ovn-northd.at: Fix MSYS IPv6 interpretation

Similar to commit 847dc1c22c0b4af2ba33d15c311be32d34257429, MSYS mangles the IPv6 address: 'ovn-nbctl: ro-sw: invalid network address: aef0;1\64' This patch uses the full form of the IPv6 address instead of its shorter notation. Signed-off-by: Alin Gabriel Serdean ---

Re: [ovs-dev] [PATCH] ofproto-dpif: Issue clear error messages for unsupported CT features.

Thanks for doing this; I have debugged the associated kinds of problems and the new more granular errors for mask and action will help. I did not test it yet, but I have one comment inline. On 1/10/18, 8:35 AM, "ovs-dev-boun...@openvswitch.org on behalf of Ben Pfaff"

Re: [ovs-dev] [PATCH v2] tests: add-del-add sequence for interface

On Fri, Jan 5, 2018 at 7:30 AM, Ben Pfaff wrote: > Yi-Hung, are you planning to review this version/ > > On Fri, Dec 15, 2017 at 07:09:50AM -0800, Ashish Varma wrote: >> Added a unit test case for testing the condition when a veth interface >> is added to br0 and then the veth

[ovs-dev] [PATCH v7] ofproto-dpif-ipfix: add interface Information Elements to flow key

Extend flow key part of data record to include following Information Elements: - ingressInterface - ingressInterfaceType - egressInterface - egressInterfaceType - interfaceName - interfaceDescription In case of input sampling we don't have information about egress port. Define templates depending

Re: [ovs-dev] [ovs-dev, v5, 2/3] dpif-netdev: Detailed performance stats for PMDs

On 10.01.2018 11:56, Jan Scheurich wrote: > Hi Ilya, > > This patch collecting comprehensive and fine grained run-time metrics of PMDs > (histograms as well as time series) is essentially different from the all > other existing functions in OVS or patch sets in progress dealing with >

Re: [ovs-dev] [PATCH v5 1/3] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

> > > > ds_put_format(reply, > > - "\temc hits:%llu\n\tmegaflow hits:%llu\n" > > - "\tavg. subtable lookups per hit:%.2f\n" > > - "\tmiss:%llu\n\tlost:%llu\n" > > + "\tpackets received:%"PRIu64"\n" > > +

Re: [ovs-dev] [PATCH V4] ofproto-dpif-xlate: Incorrect handling of errors in group action processing

On Wed, Jan 10, 2018 at 08:56:32AM +, Vishal Deep Ajmera wrote: > As per OpenFlow v1.3 specification, when an action list contains a group > action a copy of the packet is passed to the group for processing by the > group. This means that if there is an error encountered during group >

Re: [ovs-dev] [PATCH 0/3] Initial support for new SIP Alg.

Hi Tiago, Apologies if my message came across as dismissive or offensive (and to you as well, Darrell). I realize after re-reading it that I could have stated my intentions better. I never intended to discourage you in what you are contributing. Thanks for the mailing list link. I had

Re: [ovs-dev] [PATCH v3 0/4] ovs-bugtool: Enahncing and refactoring the OVS-Bugtool.

On Wed, Jan 10, 2018 at 10:36:49AM +, Dávid Patrik Pintér wrote: > The development and maintenance of the OVS-Bugtool is long due. It > completely ignores DPDK datapath-related logs and information, which > are essential by troubleshooting OVS with DPDK datapath. There is also > a wide set of

Re: [ovs-dev] [PATCH v6 1/2] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

Hi Ilya, Thanks for comments. Answers below. BR, Jan > -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Wednesday, 10 January, 2018 12:24 > To: Jan Scheurich ; d...@openvswitch.org > Cc: ktray...@redhat.com; ian.sto...@intel.com;

[ovs-dev] [PATCH] netdev-linux: do not send packets to down tap ifaces.

Today OVS pushes packets to the TAP interface ignoring its current state. That works because the kernel will return -EIO when it's not UP and OVS will just ignore that as it is not an OVS issue. However, it causes a huge impact when broadcasts happen when using userspace datapath accelerated with

Re: [ovs-dev] [PATCH] appveyor: Bump OpenSSL version

On Wed, Jan 10, 2018 at 09:06:16PM +0200, Alin Gabriel Serdean wrote: > The URL https://slproweb.com/download/Win32OpenSSL-1_0_2L.exe is > no longer valid. > > Bump the version of OpenSSL to 1_0_2m. > > Signed-off-by: Alin Gabriel Serdean I wonder whether there's a stable URL

Re: [ovs-dev] [PATCH] tunnel: fix tunnel flags set/clear.

On Wed, Jan 10, 2018 at 10:04:48AM -0800, William Tu wrote: > Existing code only set these tunnel flags (df, csum, and key) when the > flag is set in the output tunnel port, but did not clear when the flag > is unset. The patch fixes it by setting and clearing it accordingly. > > Two existing

Re: [ovs-dev] [PATCH] tunnel: fix tunnel flags set/clear.

On Wed, Jan 10, 2018 at 1:27 PM, Ben Pfaff wrote: > On Wed, Jan 10, 2018 at 10:04:48AM -0800, William Tu wrote: >> Existing code only set these tunnel flags (df, csum, and key) when the >> flag is set in the output tunnel port, but did not clear when the flag >> is unset. The patch

[ovs-dev] [PATCHv2] tunnel: fix tunnel flags set/clear.

Existing code only set these tunnel flags (df, csum, and key) when the flag is set in the output tunnel port, but did not clear when the flag is unset. The patch fixes it by setting and clearing it accordingly. Two existing testcases need to fix: 'tunnel - Geneve option present' has no key set

Re: [ovs-dev] [PATCHv2] tunnel: fix tunnel flags set/clear.

On Wed, Jan 10, 2018 at 01:13:11PM -0800, William Tu wrote: > Existing code only set these tunnel flags (df, csum, and key) when the > flag is set in the output tunnel port, but did not clear when the flag > is unset. The patch fixes it by setting and clearing it accordingly. > > Two existing

Re: [ovs-dev] [PATCH] ovn-northd.at: Fix MSYS IPv6 interpretation

On Wed, Jan 10, 2018 at 09:34:11PM +0200, Alin Gabriel Serdean wrote: > Similar to commit 847dc1c22c0b4af2ba33d15c311be32d34257429, MSYS mangles the > IPv6 address: > 'ovn-nbctl: ro-sw: invalid network address: aef0;1\64' > > This patch uses the full form of the IPv6 address instead of its

Re: [ovs-dev] [PATCH] ofproto-dpif: Issue clear error messages for unsupported CT features.

On 1/10/18, 1:05 PM, "Ben Pfaff" wrote: On Wed, Jan 10, 2018 at 08:49:15PM +, Darrell Ball wrote: > Thanks for doing this; I have debugged the associated kinds of problems and the new more granular errors for mask and action will help. > > I did not test it

[ovs-dev] [no-slow v2 1/8] ofproto-dpif: Use a fixed size userspace cookie.

This simplifies the cookie handling a bit. Signed-off-by: Justin Pettit --- v1->v2: New to the series. --- lib/odp-util.c| 35 -- lib/odp-util.h| 58 ++- ofproto/ofproto-dpif-ipfix.c

Re: [ovs-dev] [PATCH] ofproto-dpif: Issue clear error messages for unsupported CT features.

On Wed, Jan 10, 2018 at 08:49:15PM +, Darrell Ball wrote: > Thanks for doing this; I have debugged the associated kinds of problems and > the new more granular errors for mask and action will help. > > I did not test it yet, but I have one comment inline. Thanks for the comments and the

Re: [ovs-dev] [PATCH v2] tests: add-del-add sequence for interface

On Thu, Jan 11, 2018 at 03:32:18AM +0800, Yi-Hung Wei wrote: > On Fri, Jan 5, 2018 at 7:30 AM, Ben Pfaff wrote: > > Yi-Hung, are you planning to review this version/ > > > > On Fri, Dec 15, 2017 at 07:09:50AM -0800, Ashish Varma wrote: > >> Added a unit test case for testing the

Re: [ovs-dev] [no-slow 5/6] ofproto-dpif: Don't slow-path controller actions.

> On Jan 3, 2018, at 4:57 PM, Ben Pfaff wrote: > > On Thu, Dec 21, 2017 at 02:25:14PM -0800, Justin Pettit wrote: >> Controller actions have become more commonly used for purposes other >> than just making forwarding decisions (e.g., packet logging). A packet >> that needs to be

Re: [ovs-dev] [no-slow v2 1/8] ofproto-dpif: Use a fixed size userspace cookie.

On Wed, Jan 10, 2018 at 02:27:19PM -0800, Justin Pettit wrote: > This simplifies the cookie handling a bit. > > Signed-off-by: Justin Pettit > --- > v1->v2: New to the series. Acked-by: Ben Pfaff ___ dev mailing list

[ovs-dev] [PATCH] netdev-dummy: Lock mutex when retrieving custom stats.

Found by Clang. CC: Michal Weglicki Fixes: 971f4b394c6e ("netdev: Custom statistics.") Signed-off-by: Ben Pfaff --- Somehow I didn't notice this before I applied the previous patch. Oops, sorry. lib/netdev-dummy.c | 2 ++ 1 file changed, 2

Re: [ovs-dev] [PATCH] netdev-dummy: Lock mutex when retrieving custom stats.

Looks good to me, thanks. Reviewed-by: Yifeng Sun On Wed, Jan 10, 2018 at 3:47 PM, Ben Pfaff wrote: > Found by Clang. > > CC: Michal Weglicki > Fixes: 971f4b394c6e ("netdev: Custom statistics.") > Signed-off-by: Ben Pfaff

Re: [ovs-dev] [PATCH 01/15] log: Add async commit support.

I read through lib/seq.c to learn how this patch works. Looks good to me, but I feel not very confident. Reviewed-by: Yifeng Sun On Sun, Dec 31, 2017 at 9:16 PM, Ben Pfaff wrote: > The OVSDB log code has always had the ability to commit the log to disk

Re: [ovs-dev] [PATCH v3 0/6] Add minimum network namespace support.

Thanks for the series. I actually think that it's pretty close. For me, this series falls into the category of "obviously the right direction but impossible to fully validate before applying it". It builds fine and I was about to push it when I realized that it breaks most of the unit tests

Re: [ovs-dev] [PATCH] netdev-dummy: Lock mutex when retrieving custom stats.

Thanks a lot! I applied this to master. On Wed, Jan 10, 2018 at 04:02:24PM -0800, Yifeng Sun wrote: > Looks good to me, thanks. > > > Reviewed-by: Yifeng Sun > > On Wed, Jan 10, 2018 at 3:47 PM, Ben Pfaff wrote: > > > Found by Clang. > > > > CC: Michal

Re: [ovs-dev] [no-slow v2 4/8] ofproto-dpif: Modify process_upcall() to remove some redundant code.

On Wed, Jan 10, 2018 at 02:27:22PM -0800, Justin Pettit wrote: > Signed-off-by: Justin Pettit > --- > v1->v2: New to the series. Acked-by: Ben Pfaff ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [PATCH 01/15] log: Add async commit support.

Thanks for the review. The "seq" code introduces kind of a weird concept. I might have invented it, not sure, but it's probably some kind of distortion of a more standard idea. I'd like it to be easy for people to understand. Are there any questions that I could help to answer? Maybe I could

[ovs-dev] [no-slow v2 3/8] ofproto-dpif: Reorganize upcall handling.

- This reduces the number of times upcall cookies are processed. - It separate true miss calls from slow-path actions. The reorganization will also be useful for a future commit. Signed-off-by: Justin Pettit --- v1->v2: Changes suggested by Ben. ---

[ovs-dev] [no-slow v2 2/8] ofproto-dpif: Add ability to look up an ofproto by UUID.

This will have callers in the future. Signed-off-by: Justin Pettit Acked-by: Ben Pfaff --- v1->v2: Changes suggested by Ben. --- ofproto/ofproto-dpif-trace.c | 2 +- ofproto/ofproto-dpif.c | 92 +++-

[ovs-dev] [no-slow v2 7/8] ofproto-dpif: Don't slow-path controller actions.

Controller actions have become more commonly used for purposes other than just making forwarding decisions (e.g., packet logging). A packet that needs to be copied to the controller and forwarded would always be sent to ovs-vswitchd to be handled, which could negatively affect performance and

[ovs-dev] [no-slow v2 8/8] ofproto-dpif: Don't slow-path controller actions with pause.

A previous patch removed slow-pathing for controller actions with the exception of ones that specified "pause". This commit removes that restriction so that no controller actions are slow-pathed. Signed-off-by: Justin Pettit --- v1->v2: Changes suggested by Ben. ---

Re: [ovs-dev] [PATCH] ofproto-dpif: Issue clear error messages for unsupported CT features.

On Wed, Jan 10, 2018 at 09:37:42PM +, Darrell Ball wrote: > > > On 1/10/18, 1:05 PM, "Ben Pfaff" wrote: > > On Wed, Jan 10, 2018 at 08:49:15PM +, Darrell Ball wrote: > > Thanks for doing this; I have debugged the associated kinds of problems > and the new more

Re: [ovs-dev] [PATCH v6 1/2] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

> > > > > > -unixctl_command_register("dpif-netdev/pmd-stats-show", "[dp]", > > > - 0, 1, dpif_netdev_pmd_info, > > > +unixctl_command_register("dpif-netdev/pmd-stats-show", "[-pmd core | > > > dp]", > > > > It should be "[-pmd core] [dp]". > > Current version

[ovs-dev] Declaración anual de personas morales

Cumpla con las obligaciones fiscales de su empresa en tiempo y forma Declaración anual de personas morales 25 de enero- Mtro. David Lozada Martínez - 9am-8pm Existen dos posibles situaciones en las que se puede ampliar la fecha límite para el envío de la Declaración Anual como Personas

Re: [ovs-dev] [PATCH v8 3/3] nsh: add dec_nsh_ttl action

On Tue, Jan 09, 2018 at 09:56:18PM +0800, Yi Yang wrote: > NSH ttl is a 6-bit field ranged from 0 to 63, it should be > decremented by 1 every hop, if it is 0 or it is so after > decremented, the packet should be dropped and a packet-in > message is sent to main controller. > > Signed-off-by: Yi

Re: [ovs-dev] [PATCH v6 2/2] dpif-netdev: Refactor cycle counting

Hi Ilya, Please find answers inline. Regards, Jan > -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Wednesday, 10 January, 2018 12:53 > To: Jan Scheurich ; d...@openvswitch.org > Cc: ktray...@redhat.com; ian.sto...@intel.com

[ovs-dev] [no-slow v2 5/8] ofp-actions: Add action "debug_slow" for testing slow-path.

It isn't otherwise useful and in fact hurts performance so it's disabled without --enable-dummy. An upcoming commit will make use of this. Signed-off-by: Justin Pettit Acked-by: Ben Pfaff --- v1->v2: Unchanged. --- include/openvswitch/ofp-actions.h | 1 +

[ovs-dev] [no-slow v2 6/8] ofproto: Add 'ofproto_uuid' and 'ofp_in_port' to user action cookie.

Previously, the ofproto instance and OpenFlow port have been derived based on the datapath port number. This change explicitly declares them both, which will be helpful in future commits that no longer can depend on having a unique datapath port (e.g., a source port that represents the

[ovs-dev] [no-slow v2 4/8] ofproto-dpif: Modify process_upcall() to remove some redundant code.

Signed-off-by: Justin Pettit --- v1->v2: New to the series. --- ofproto/ofproto-dpif-upcall.c | 45 --- 1 file changed, 17 insertions(+), 28 deletions(-) diff --git a/ofproto/ofproto-dpif-upcall.c b/ofproto/ofproto-dpif-upcall.c index

Re: [ovs-dev] [PATCH v8 1/3] nsh: add new flow key 'ttl'

On Tue, Jan 09, 2018 at 09:56:16PM +0800, Yi Yang wrote: > IETF NSH draft added a new filed ttl in NSH header, this patch > is to add new nsh key 'ttl' for it. > > Signed-off-by: Yi Yang Thanks for the revision! This breaks a test: 939: ofproto - table features (OpenFlow

Re: [ovs-dev] [PATCH v8 1/3] nsh: add new flow key 'ttl'

On Wed, Jan 10, 2018 at 02:50:35PM -0800, Ben Pfaff wrote: > On Tue, Jan 09, 2018 at 09:56:16PM +0800, Yi Yang wrote: > > IETF NSH draft added a new filed ttl in NSH header, this patch > > is to add new nsh key 'ttl' for it. > > > > Signed-off-by: Yi Yang > > Thanks for the

Re: [ovs-dev] [PATCH v8 3/3] nsh: add dec_nsh_ttl action

On Wed, Jan 10, 2018 at 02:52:00PM -0800, Ben Pfaff wrote: > On Tue, Jan 09, 2018 at 09:56:18PM +0800, Yi Yang wrote: > > NSH ttl is a 6-bit field ranged from 0 to 63, it should be > > decremented by 1 every hop, if it is 0 or it is so after > > decremented, the packet should be dropped and a

Re: [ovs-dev] [PATCH] netdev-linux: do not send packets to down tap ifaces.

On Wed, Jan 10, 2018 at 02:06:43PM -0200, Flavio Leitner wrote: > Today OVS pushes packets to the TAP interface ignoring its > current state. That works because the kernel will return -EIO > when it's not UP and OVS will just ignore that as it is not > an OVS issue. > > However, it causes a huge

Re: [ovs-dev] [PATCH v7] ofproto-dpif-ipfix: add interface Information Elements to flow key

On Wed, Jan 10, 2018 at 01:06:03PM +, Michal Weglicki wrote: > Extend flow key part of data record to include following Information Elements: > - ingressInterface > - ingressInterfaceType > - egressInterface > - egressInterfaceType > - interfaceName > - interfaceDescription > > In case of

Re: [ovs-dev] [PATCH v4] netdev: Custom statistics.

On Tue, Jan 09, 2018 at 07:55:37AM +, Michal Weglicki wrote: > - New get_custom_stats interface function is added to netdev. It > allows particular netdev implementation to expose custom > counters in dictionary format (counter name/counter value). > - New statistics are retrieved using

[ovs-dev] Si todo falla…cómo terminar la relación laboral

En línea y en Vivo / Para todo su Equipo con una sola Conexión Cómo Trabajar con Empleados Difíciles y Conflictivos 26 de enero - Online en Vivo - 10:00 a 13:00 y de 15:00 a 18:00Hrs Mientras que la mayoría de los trabajadores no dan en absoluto problemas, se llevan bien con los demás

Re: [ovs-dev] [ovs-dev, v5, 2/3] dpif-netdev: Detailed performance stats for PMDs

Hi Ilya, This patch collecting comprehensive and fine grained run-time metrics of PMDs (histograms as well as time series) is essentially different from the all other existing functions in OVS or patch sets in progress dealing with statistics I am aware of. I don't think this lends itself to

[ovs-dev] [PATCH V4] ofproto-dpif-xlate: Incorrect handling of errors in group action processing

As per OpenFlow v1.3 specification, when an action list contains a group action a copy of the packet is passed to the group for processing by the group. This means that if there is an error encountered during group processing, only the copy of packet should be dropped, but subsequent actions in

Re: [ovs-dev] [RFC PATCH 0/8] dpif-netdev: Refactor cycle count and rebased patches

Hi, I have just sent out a series with patches #1 and #2 as agreed. They address comments by Ilya on #1 and the draft for nestable cycle counters. I haven't done extensive tests yet as I wanted to share as early as possible. I will continue to test and prepare a rebased v6 of the remainder of

[ovs-dev] [PATCH v6 2/2] dpif-netdev: Refactor cycle counting

Simplify the historically grown TSC cycle counting in PMD threads. Cycles are currently counted for the following purposes: 1. Measure PMD ustilization PMD utilization is defined as ratio of cycles spent in busy iterations (at least one packet received or sent) over the total number of cycles.

[ovs-dev] [PATCH v6 1/2] dpif-netdev: Refactor PMD performance into dpif-netdev-perf

Add module dpif-netdev-perf to host all PMD performance-related data structures and functions in dpif-netdev. Refactor the PMD stats handling in dpif-netdev and delegate whatever possible into the new module, using clean interfaces to shield dpif-netdev from the implementation details.

[ovs-dev] [PATCH v6 0/2] Refactor PMD stats and cycle counting

This series contains the two refactoring patches of the earlier series * [PATCH v5 0/3] dpif-netdev: Detailed PMD performance metrics and supervision * [RFC PATCH 0/8] dpif-netdev: Refactor cycle count and rebased patches They are intended to serve as common base for the following contibutions: *

Re: [ovs-dev] [PATCH V3] ofproto-dpif-xlate: Incorrect handling of errors in group action processing

Hi Ben, The whitespace issue with the patch seems to be triggered by my MS Outlook. I compose mail in HTML format which is causing the issue. V4 version of patch in plain-text format is sent. In case it still has issues, I have committed changes in my repo on git-hub with details below.