[ovs-dev] [PATCH 0/4] system-traffic: Add basic IPv6 underlay tunnel tests

Currently there is no system-traffic coverage for tunnels with IPv6 underlays. This series adds very basic ping tests for VXLANv6 and GENEVEv6. Note: GREv6 is not added by this series due to some incompatibilities between OVS and Linux native ip6gretap. More info available in bugzilla [0]. [0]

Re: [ovs-dev] [PATCH] dpdk: announce deprecation of vhost-user server ports

On 6/7/17, 3:46 PM, "Aaron Conole" wrote: Since vhost-user server mode ports are the preferred mechanism for interconnecting Open vSwitch with VMs when using DPDK, and since there are currently no known use cases for vhost-user server mode ports apart from

[ovs-dev] Request to tag 2.7 branch with v2.7.1

Hello Ben, Justin, Is it possible to tag the 2.7 branch with v2.7.1. Recently there were many back ports to 2.7 branch. OVS 2.7 is required for RDO [1] and the RDO community is expecting a new tag to build the latest OVS 2.7 branch. [1] -

Re: [ovs-dev] [PATCH] checkpatch: Also allow .at files to have leading tabs.

Ben Pfaff writes: > Autotest .at files often have lines with samples of expected output from > various programs, which fairly often includes leading tabs, so this warning > causes false positives there. > > Signed-off-by: Ben Pfaff > --- I'm assuming the list is

[ovs-dev] [PATCH] dpdk: announce deprecation of vhost-user server ports

Since vhost-user server mode ports are the preferred mechanism for interconnecting Open vSwitch with VMs when using DPDK, and since there are currently no known use cases for vhost-user server mode ports apart from version incompatibilities with QEMU, announce that server mode ports are considered

Re: [ovs-dev] [PATCH 2/6] redhat: replace python3 with python package macro

On Wed, Jun 07, 2017 at 05:39:28PM -0300, Flavio Leitner wrote: > On Sat, Jun 03, 2017 at 11:09:57AM -0400, Aaron Conole wrote: > > diff --git a/rhel/openvswitch-fedora.spec.in > > b/rhel/openvswitch-fedora.spec.in > > index 9fc5f27..95533aa 100644 > > --- a/rhel/openvswitch-fedora.spec.in > >

Re: [ovs-dev] [PATCH 2/6] redhat: replace python3 with python package macro

Flavio Leitner writes: > On Sat, Jun 03, 2017 at 11:09:57AM -0400, Aaron Conole wrote: >> According to the packaging guidelines found at >> https://fedoraproject.org/wiki/PackagingDrafts:Python3EPEL, when >> specifying a python3 package, use the %{python3_pkgversion} macro to

Re: [ovs-dev] [PATCH] docs: Update dpdk vdev naming instructions

On Wed, Jun 07, 2017 at 03:33:49PM +0100, Stephen Finucane wrote: > On Tue, 2017-06-06 at 16:26 +0100, Ciara Loftus wrote: > > Signed-off-by: Ciara Loftus > > I couldn't find where this changed (the only related commit was 69876ed, but > that references the > previous

Re: [ovs-dev] [PATCH v2 0/6] Add OVS DPDK keep-alive functionality

"Bodireddy, Bhanuprakash" writes: > Hi Darrel, Aaron Hi Bhanu, >>There two ways to go with the design. >> >>1) Make it generic, so that it is not so PMD specific, as it is now. >>2) If it stays PMD specific, make it stronger; right now, the health check is

Re: [ovs-dev] [patch_v1 0/4] dpdk: Add ALG infra and support FTP V4.

On 6/7/17, 1:00 PM, "ovs-dev-boun...@openvswitch.org on behalf of Joe Stringer" wrote: On 30 May 2017 at 14:21, Darrell Ball wrote: > ALG infra and FTP v4 support is added to the userspace > datapath.

Re: [ovs-dev] [PATCH] ovn-sb.xml: Update and improve documentation.

On Wed, Jun 07, 2017 at 03:31:39PM -0400, Russell Bryant wrote: > On Tue, Jun 6, 2017 at 6:32 PM, Ben Pfaff wrote: > > Some of the abbreviations at the head of this document, like LN and PN, > > turn out to not be very useful, so expand them for clarity. > > > > Some of the

Re: [ovs-dev] [patch_v1 0/4] dpdk: Add ALG infra and support FTP V4.

On 30 May 2017 at 14:21, Darrell Ball wrote: > ALG infra and FTP v4 support is added to the userspace > datapath. FTP v6 support is a small incremental needing > some additional message parsing support, but very similar > to v4 and will be added soon. TFTP support is another

[ovs-dev] Finanzas para no Financieros + 11 Temas

Buenas Tardes: Este mes de Junio le invitamos a adquirir una de nuestras pólizas de Capacitación online, los cuáles constan de 12 Temas que son utilizables durante 3 meses, las 24 hrs del día, las veces que usted así lo requiera. En Específico le ofrecemos el plan de Contabilidad y Finanzas

Re: [ovs-dev] [PATCH] ovn-sb.xml: Update and improve documentation.

On Tue, Jun 6, 2017 at 6:32 PM, Ben Pfaff wrote: > Some of the abbreviations at the head of this document, like LN and PN, > turn out to not be very useful, so expand them for clarity. > > Some of the statements in this document are more about planning the design > than the current

Re: [ovs-dev] 答复: Re: [PATCH 2/2] ovn-northd: Fix ping failure of vlan networks.

Is the router bound to a chassis by specifying a "redirect-chassis" ? Dumping the northbound db might make it easier for me to understand and reproduce the issue ... On Mon, Jun 5, 2017 at 8:58 PM, wrote: > router is not external to OVN > > > *Russell Bryant

Re: [ovs-dev] [patch_v1 2/4] dpdk: Add ALG infra and support FTP V4.

Hi Ben I intend to fold in a V6 incremental for FTP anyways; I am trying to get that done this week. Let me repost with the V6 additions for FTP. Darrell On 6/7/17, 11:44 AM, "ovs-dev-boun...@openvswitch.org on behalf of Ben Pfaff"

Re: [ovs-dev] [PATCH v3] Copy external_ids from Logical_Switch_Port to SB database

On Tue, Jun 6, 2017 at 6:08 AM, Daniel Alvarez wrote: > This patch makes ovn-northd copy all string-string pairs in > external_ids column of the Logical_Switch_Port table in Northbound > database to the equivalent column of the Port_Binding table in > Southbound database. > >

Re: [ovs-dev] [PATCH] ovn-sb-xml: remove redundant spaces for aligning

On Tue, Jun 06, 2017 at 04:00:17PM +0800, Dong Jun wrote: > Signed-off-by: Dong Jun Thanks, I folded in a few more similar fixes and applied this to master. ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [patch_v1 2/4] dpdk: Add ALG infra and support FTP V4.

Hi Darrell, I'm unfortunately getting a lot of rejects on this patch. Can you rebase and repost the series? Thanks a lot. ___ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [PATCH 1/2] xlate: Add datapath clone generation API

On Wed, Jun 07, 2017 at 11:26:56AM -0700, Andy Zhou wrote: > On Tue, Jun 6, 2017 at 4:55 PM, Ben Pfaff wrote: > > On Fri, May 26, 2017 at 08:47:44PM -0700, Andy Zhou wrote: > >> There are three methods of translating openflow layer clone action. > >> Using datapath clone action,

Re: [ovs-dev] [PATCH] ovn: ssl proto/cipher configuration in nb/sb db

On Wed, Jun 07, 2017 at 01:35:20PM -0400, Lance Richardson wrote: > Add SSL protocol and cipher columns to SSL tables in northbound > and southbound databases. Start nb/sb ovsdb-server with command- > line options to use these columns. Add support to ovn-nbctl > and ovn-sbctl "set-ssl" commands

Re: [ovs-dev] [PATCH 2/2] xlate: Use datapath clone action for patch port translation

On Tue, Jun 6, 2017 at 5:01 PM, Ben Pfaff wrote: > On Fri, May 26, 2017 at 08:47:45PM -0700, Andy Zhou wrote: >> When available, use datapath 'clone' for patch port translation. >> Clone provides a stronger guarantee that packet will be restored >> after going through a patch port,

Re: [ovs-dev] [PATCH 1/2] xlate: Add datapath clone generation API

On Tue, Jun 6, 2017 at 4:55 PM, Ben Pfaff wrote: > On Fri, May 26, 2017 at 08:47:44PM -0700, Andy Zhou wrote: >> There are three methods of translating openflow layer clone action. >> Using datapath clone action, datapath sample action or using actions >> to negating the any changes

[ovs-dev] [PATCH] ovn: ssl proto/cipher configuration in nb/sb db

Add SSL protocol and cipher columns to SSL tables in northbound and southbound databases. Start nb/sb ovsdb-server with command- line options to use these columns. Add support to ovn-nbctl and ovn-sbctl "set-ssl" commands for user-friendly management of these settings. Signed-off-by: Lance

Re: [ovs-dev] [patch_v1] dpdk: Recover hash input for nat_range_hash.

Thanks Ben I had a quick look; I will test out today and get back. Darrell On 6/7/17, 9:37 AM, "ovs-dev-boun...@openvswitch.org on behalf of Ben Pfaff" wrote: On Sat, Jun 03, 2017 at 01:38:14PM -0700, Darrell Ball wrote: >

Re: [ovs-dev] [patch_v2] flow.c: Refactor ct_orig_tuple check in miniflow_extract.

On Mon, Jun 05, 2017 at 06:34:33AM -0700, Darrell Ball wrote: > The checks to populate ct_orig_tuple in miniflow_extract > include recirc_id being non-zero. Now, ct_orig_tuple > is only populated if the packet has passed through the > connection tracker, which is a prerequisite for having > valid

[ovs-dev] [PATCH 1/2] hash: New helper functions for adding words in a buffer to a hash.

These will receive their first user (outside of hash.h) in the following commit. Signed-off-by: Ben Pfaff --- lib/hash.h | 66 +- 1 file changed, 48 insertions(+), 18 deletions(-) diff --git a/lib/hash.h b/lib/hash.h

[ovs-dev] [PATCH v2 2/2] ovn-controller: Use separate thread for packet-in processing.

This patch introduces multi-threading for ovn-controller and use dedicated thread for packet-in processing as a start. It decouples packet-in processing and ovs flow computing, so that packet-in inputs won't trigger flow recomputing, and flow computing won't block packet-in processing. In large

[ovs-dev] [PATCH v2 2/3] ovn-controller: readonly mode binding_run and get_br_int

This change is to prepare for the future change for multi-threading. Both binding_run() and get_br_int() are needed by pinctrl thread, but we don't want to update SB DB or create bridges in that scenario, so need "readonly" mode for these functions. Signed-off-by: Han Zhou ---

[ovs-dev] [PATCH v2 0/3] ovn-controller: Separate thread for pinctrl

This patch series is the first attempt of ovn-controller multi-threading. The intention is to avoid flow re-computing being triggered by unrelated input. An obvious example is that packet-in message from vswitchd to ovn-controller will trigger full round of flow computing before processing the

Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.

Some serious formatting issue with the results table in my last mail - hopefully this time will be better... ++-+--+-+-+ | vhost function | vhost user mode | log printed? |

[ovs-dev] [RFC PATCH 20/21] keepalive: Display extended Keepalive status.

This commit adds support to display the extended keepalive statistics stored in SHM block. The status can be displayed as follows. $ ovs-appctl keepalive/pmd-xstats-show keepAlive Status : Enabled keepAlive Interval: 1000 ms CORE: 0 PMD thread id : 1269 [ACTIVE] PMD

[ovs-dev] [RFC PATCH 21/21] Documentation: Update DPDK doc with Keepalive feature.

Keepalive feature is aimed at achieving Fastpath Service Assurance in OVS-DPDK deployments. It adds support for monitoring the packet processing cores(PMD thread cores) by dispatching heartbeats at regular intervals. Incase of heartbeat misses additional health checks are enabled on the PMD thread

[ovs-dev] [RFC PATCH 19/21] netdev-dpdk: Enable PMD health checks on heartbeat failure.

The keepalive thread sends heartbeats to PMD thread and when PMD fails to respond to successive heartbeats the PMD is potentially stalled. The PMD state transition is as below: ALIVE -> MISSING -> DEAD -> GONE This commit enables PMD healthchecks when PMD doesn't respond to heartbeats. This is

[ovs-dev] [RFC PATCH 18/21] keepalive: Check the PMD cycle stats as part of PMD health checks.

This commit adds the support to check the PMD cycle stats. If the cycles aren't changing for a duration of time this can be flagged as possible PMD stall. Signed-off-by: Bhanuprakash Bodireddy --- lib/dpif-netdev.c | 17 ++--- lib/dpif-netdev.h | 6

[ovs-dev] [RFC PATCH 16/21] keepalive: Check the link status as part of PMD health checks.

This commit adds the initial support in to performing PMD health checks. The ports handled by the PMD threads are checked for the link status and the same is updated in to SHM block. Signed-off-by: Bhanuprakash Bodireddy --- lib/dpif-netdev.c | 41

[ovs-dev] [RFC PATCH 15/21] dpif-netdev: Add additional datapath health checks.

This commit enables additional datapath health checks. The checks are enabled only on a PMD heartbeat failure. On missing three successive heartbeats additional health checks needs to be performed on each PMD to confirm and flag the failure. The datapath health is monitored periodically from

[ovs-dev] [RFC PATCH 13/21] keepalive: Add support to query keepalive status.

This commit adds support to query if keepalive status is enabled/disabled. $ ovs-appctl keepalive/status keepAlive Status: Enabled Signed-off-by: Bhanuprakash Bodireddy --- lib/keepalive.c | 17 + 1 file changed, 17 insertions(+) diff

[ovs-dev] [RFC PATCH 14/21] dpif-netdev: Add helper function to check false positives.

This commit adds an API to store the PMD thread id in SHM block. The tid later shall be retrieved by callback function that gets invoked to check for false positives. Signed-off-by: Bhanuprakash Bodireddy --- lib/dpif-netdev.c | 1 + lib/keepalive.c | 13

[ovs-dev] [RFC PATCH 12/21] keepalive: Add support to query keepalive statistics.

This commit adds support to query keepalive statistics stored in posix shared memory block. Datapath health status can be retrieved as follows: $ ovs-appctl keepalive/pmd-health-show Keepalive status keepalive status : Enabled keepalive interval: 1000 ms CORESTATE

[ovs-dev] [RFC PATCH 11/21] bridge: Update keepalive status in ovsdb

This commit allows vswitchd thread to update the ovsdb with the datapath status along with the status for all registered PMD threads. The status can be monitored using ovsdb-client. $ ovsdb-client monitor Open_vSwitch Open_vSwitch keepalive rowaction keepalive

[ovs-dev] [RFC PATCH 10/21] keepalive: Retrieve PMD status periodically.

This commit implements APIs to retrieve the PMD thread status and return the status in the below format for each PMD thread. Format: CORE_="STATUS, last_seen_timestamp" eg: CORE_1="ALIVE,9220698256784207" CORE_2="GONE,9220698256786231" The status is periodically retrieved by

[ovs-dev] [RFC PATCH 09/21] dpif-netdev: Dispatch heartbeats for DPDK datapath.

This commit adds heartbeat mechanism support for DPDK datapath. Heartbeats are sent to registered PMD threads at predefined intervals, as set in ovsdb using 'keepalive-interval'. The heartbeats are only enabled when there is atleast one port added to the bridge and with active PMD thread polling

[ovs-dev] [RFC PATCH 08/21] dpif-netdev: Register packet processing cores to KA framework.

This commit registers the packet processing PMD cores to keepalive framework. Only PMDs that have rxqs mapped will be registered and actively monitored by KA framework. This commit spawns a keepalive thread that will dispatch heartbeats to PMD cores. The pmd threads respond to heartbeats by

[ovs-dev] [RFC PATCH 07/21] keepalive: Add more helper functions to KA framework.

This commit introduces helper functions in 'keepalive' module that are needed to register/unregister PMD threads to KA framework. Also introduce APIs to mark the PMD core states. Signed-off-by: Bhanuprakash Bodireddy --- lib/keepalive.c | 56

[ovs-dev] [RFC PATCH 06/21] bridge: Invoke keepalive framework.

With this commit the keepalive framework is invoked when enable-keepalive is set to 'true' in ovsdb. As part of initialization the shared memory block is created and initialized. Also the keepalive data structure is initialized and the callback functions are registered if DPDK datapath is enabled.

[ovs-dev] [RFC PATCH 05/21] Keepalive: Add initial keepalive support.

This commit introduces the initial keepalive support by adding 'keepalive' module and also helper and initialization functions that will be invoked by later commits. Signed-off-by: Bhanuprakash Bodireddy --- lib/automake.mk | 2 + lib/dpdk.c| 23

[ovs-dev] [RFC PATCH 04/21] process: Retrieve process status.

Implement helper function to retrieve the process status. This will be used by keepalive monitoring thread to detect false alarms and to show PMD thread state in future commits. Signed-off-by: Bhanuprakash Bodireddy --- lib/process.c | 60

[ovs-dev] [RFC PATCH 03/21] dpdk: Add helper functions for DPDK datapath keepalive.

Introduce helper functions in 'dpdk' module that are needed for DPDK keepalive functionality. Also add dummy functions in 'dpdk-stub' module that are needed when DPDK datapath is not available. Signed-off-by: Bhanuprakash Bodireddy --- lib/dpdk-stub.c | 24

[ovs-dev] [RFC PATCH 02/21] ovsschema: Introduce 'keepalive' column in Open_vSwitch.

This commit adds new ovsdb column "keepalive". It shows the overall datapath status and the health of the cores running datapath threads. Signed-off-by: Bhanuprakash Bodireddy --- vswitchd/vswitch.ovsschema | 7 +-- vswitchd/vswitch.xml | 20

[ovs-dev] [RFC PATCH 01/21] vswitch.xml: Add keepalive support.

Add support for keepalive functionality. By default, the keepalive is off and can be enabled/disabled only at init time. For eg: To enable keepalive feature. 'ovs-vsctl --no-wait set Open_vSwitch . other_config:enable-keepalive=true' To set timer interval of 500ms for monitoring packet

[ovs-dev] Sync on PTAP, EXT-382 and NSH - Minutes of meeting Tue 2017-06-07 17:00 CET

Participants * Zoltan, Jan, Jiri, Ben P, Georg, Ben M Review/Discussion of current patch sets * RTNETLINK tunnel configuration (RedHat) Done: Merged my Joe on May 18th * L3 Tunneling (Ericsson) Done: remaining 3 patches merged by Ben on June 2nd * L3 tunnel config

Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.

Hi Michal, I've conducted some testing on v4 of the patch: specifically, wrt how OvS reacts in the event of an error condition in the vhost construct/configure functions. For these tests I hardcoded the listed (DPDK) function to return an error value, and observed how the following functions

Re: [ovs-dev] [patch_v1 1/4] dpdk: Move tcp_payload_length to include file.

On Tue, May 30, 2017 at 02:21:33PM -0700, Darrell Ball wrote: > The function tcp_payload_length is moved to a private > include file to be used by other conntrack files. A > sanity check is added for general use, although > previous usage was safe in that filtering is already > done by the time

Re: [ovs-dev] [PATCH] tests: Export PYTHONCOERCECLOCALE=0 for python3 tests

On Mon, Jun 05, 2017 at 03:28:38PM +0200, Timothy Redaelli wrote: > This patch exports PYTHONCOERCECLOCALE=0 when you have Python3 tests > enabled. > This is needed since testsuite forces LC_ALL=C and Python 3, with PEP 538, > prints the following warning on stderr: > > "Python runtime

Re: [ovs-dev] [PATCH] stream: include ssl protocol/cipher options in run-time help

On Wed, Jun 07, 2017 at 10:54:52AM -0400, Lance Richardson wrote: > Include --ssl-protocols and --ssl-ciphers options in run-time > help output. > > Sample output with this change: > > PKI configuration (required to use SSL): > -p, --private-key=FILE file with private key > -c,

Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.

William Townsend writes: > Hi Aaron, > > On Wed, Jun 7, 2017 at 9:51 AM, Aaron Conole wrote: > > Hi Michal, > > mweglicx writes: > > > Following changes are applied: > > - netdev-dpdk: Changes required by DPDK API

Re: [ovs-dev] Why do port numbers continue to change when I configure ovs with openstack?

Please don't drop the mailing list. A port number for an existing port wouldn't normally change. What's in your database log? Run "ovsdb-tool -mm show-log" on conf.db. On Thu, Jun 08, 2017 at 12:20:52AM +0900, Nam Bong Ha wrote: > Thanks for your reply. > > No. A port whose port number

Re: [ovs-dev] Why do port numbers continue to change when I configure ovs with openstack?

On Wed, Jun 07, 2017 at 11:45:50PM +0900, Nam Bong Ha wrote: > Why do port numbers continue to change when I configure ovs with openstack? > > > > I want to fix the port number of the int-br-wan of br-int(bridge) > > > > However, the port number of int-br-wan continues to increase (55 ... 58

Re: [ovs-dev] [PATCH 2/3] netdev-linux: make tap devices persistent.

On Wed, Jun 07, 2017 at 09:39:16AM +, Vishal Deep Ajmera wrote: > Hi Flavio, > > If the tap-device is persistent but the 'netdev' datapath is not yet > started then will it create any issues in the system ? What happens > if we start sending packets on this interface whereas data-path is >

Re: [ovs-dev] [PATCH 2/2] ipfix: Update Timestamp when flow updated

On 06/07/2017 12:23 AM, Felix Konstantin Maurer wrote: In case you know a little Go, here is my script to test my IPFIX setup. I also use Wireshark which works quite well. I'll look into it too, today. Regards Felix Yes, I'm just capturing the traffic to a pcap file and will try wireshark.

Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.

Hi Aaron, On Wed, Jun 7, 2017 at 9:51 AM, Aaron Conole wrote: > Hi Michal, > > mweglicx writes: > > > Following changes are applied: > > - netdev-dpdk: Changes required by DPDK API modifications. > > - doc: Because of DPDK API changes, backward

[ovs-dev] [PATCH] stream: include ssl protocol/cipher options in run-time help

Include --ssl-protocols and --ssl-ciphers options in run-time help output. Sample output with this change: PKI configuration (required to use SSL): -p, --private-key=FILE file with private key -c, --certificate=FILE file with certificate for private key -C, --ca-cert=FILE file with

Re: [ovs-dev] [PATCH 1/3] ovs-router: fix refcnt leak when program terminates.

On Tue, Jun 06, 2017 at 05:10:10PM -0700, Ben Pfaff wrote: > On Mon, May 29, 2017 at 04:40:21PM -0300, Flavio Leitner wrote: > > Install a handler to flush routes and release devices when > > the program is terminating. > > > > Signed-off-by: Flavio Leitner > > Thank you! I

[ovs-dev] Why do port numbers continue to change when I configure ovs with openstack?

Hi, all :) Why do port numbers continue to change when I configure ovs with openstack? I want to fix the port number of the int-br-wan of br-int(bridge) However, the port number of int-br-wan continues to increase (55 ... 58 ... 60 ... 62 ... 1070) I tried the following command but it

Re: [ovs-dev] [PATCH] docs: Update dpdk vdev naming instructions

On Wed, 2017-06-07 at 15:33 +0100, Stephen Finucane wrote: > On Tue, 2017-06-06 at 16:26 +0100, Ciara Loftus wrote: > > Signed-off-by: Ciara Loftus > > I couldn't find where this changed (the only related commit was 69876ed, but > that references the > previous naming

Re: [ovs-dev] [PATCH] docs: Update dpdk vdev naming instructions

On Tue, 2017-06-06 at 16:26 +0100, Ciara Loftus wrote: > Signed-off-by: Ciara Loftus I couldn't find where this changed (the only related commit was 69876ed, but that references the previous naming format) but I trust you know what you're talking about. From the docs

Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.

Hi Michal, mweglicx writes: > Following changes are applied: > - netdev-dpdk: Changes required by DPDK API modifications. > - doc: Because of DPDK API changes, backward compatibility > with previous DPDK releases will be broken, thus all > relevant documentation

Re: [ovs-dev] [PATCH] netdev-dpdk: round up mbuf_size to cache_line_size

Hi, On Monday 05 June 2017 10:31 AM, santosh wrote: > On Wednesday 31 May 2017 06:38 PM, Santosh Shukla wrote: > >> Some pmd driver(e.g: vNIC thunderx PMD) want mbuf_size to be multiple of >> cache_line_size. With out this fix, Netdev-dpdk initialization would >> simply fail for those drivers.

Re: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for DPDK 17.05.

>From: ovs-dev-boun...@openvswitch.org [mailto:ovs-dev-boun...@openvswitch.org] >On Behalf Of >mweglicx >Sent: Wednesday, June 7, 2017 10:57 AM >To: d...@openvswitch.org >Subject: [ovs-dev] [PATCH v4] Update relevant artifacts to add support for >DPDK 17.05. > >Following changes are applied: >-

Re: [ovs-dev] What's different between ovs bond port and switch lag port?

ovs's bonding supports LAG, Active Backup, SLB. http://docs.openvswitch.org/en/latest/topics/bonding/ 2017-06-07 16:49 GMT+08:00 Sam : > Hi all, > > For switch lag, there are some RFCs to define its behivour. > For ovs bond port, is there some standard to define this? > > I

Re: [ovs-dev] [PATCH 2/3] netdev-linux: make tap devices persistent.

Hi Flavio, If the tap-device is persistent but the 'netdev' datapath is not yet started then will it create any issues in the system ? What happens if we start sending packets on this interface whereas data-path is not present ? Regards, Vishal -Original Message- From:

[ovs-dev] [PATCH 7/8] netdev-dpdk: Configurable retries while enqueuing to vHost User ports.

This commit adds "vhost-enque-retry" where in the number of retries performed while enqueuing packets to vHostUser ports can be configured in ovsdb. Currently number of retries are set to '8' and a retry is performed when atleast some packets have been successfully sent on previous attempt. While

[ovs-dev] [PATCH 6/8] netdev-dpdk: Enable intermediate queue for vHost User port.

This commit refactors the __netdev_dpdk_vhost_send() and enables intermediate queue where in the packets are buffered till the threshold 'INTERIM_QUEUE_BURST_THRESHOLD[32] is hit and eventually gets transmitted. This commit improves the throughput as reported below in simple Physical to virtual

[ovs-dev] [PATCH 5/8] netdev-dpdk: Add netdev_dpdk_vhost_txq_drain function.

Add netdev_dpdk_vhost_txq_drain(), that flushes packets on vHost User port queues. Also add netdev_dpdk_vhost_tx_burst() function that uses rte_vhost_enqueue_burst() to enqueue burst of packets on vHost User ports. Signed-off-by: Bhanuprakash Bodireddy

[ovs-dev] [PATCH 4/8] dpif-netdev: Drain the packets in intermediate queue.

Under low rate traffic conditions, there can be 2 issues. (1) Packets potentially can get stuck in the intermediate queue. (2) Latency of the packets can increase significantly due to buffering in intermediate queue. This commit handles the (1) issue by draining the tx port queues from

[ovs-dev] [PATCH 2/8] netdev-dpdk: Add netdev_dpdk_txq_drain function.

This commit adds netdev_dpdk_txq_drain() function. If there are any packets waiting in the queue, they are transmitted instantly using the rte_eth_tx_burst function. In XPS enabled case, lock is taken on the tx queue before draining the queue. Signed-off-by: Bhanuprakash Bodireddy

Re: [ovs-dev] [PATCH 2/2] ipfix: Update Timestamp when flow updated

In case you know a little Go, here is my script to test my IPFIX setup. I also use Wireshark which works quite well. I'll look into it too, today. Regards Felix On 06/06/2017 10:42 PM, Greg Rose wrote: > On 06/06/2017 08:22 AM, Ben Pfaff wrote: >> On Mon, Jun 05, 2017 at 08:34:32PM -0700, Greg