[ovs-dev] Few observations on low performance of 64 byte packet size

Hi All, While sending 2G traffic of 64bytes size, I see a low performance for Phy-Phy setup using OVS with DPDK. I get around 1500/1500 throughput. Following are the Platform and setup details: NOTE: Used OVS 2.4 and DPDK2.0.0 1. Intel(R) Atom(TM) 2. I assigned 1core to vswitchd process 3. Bound

Re: [ovs-dev] [ovs-discuss] Deletion of Indirect Groups on Ovs2.5

Hi, I for one would be happy to see your fix posted. On Tue, Mar 22, 2016 at 10:17:04AM +, Balazs Nemeth wrote: > Hi, > > We have a solution for enabling group deletion with type=indirect. Is there > anybody working on the fix? We can send our patch to the dev mail list. > > Best regards,

Re: [ovs-dev] [PATCH v2 5/5] byte-order: use system ntohll() and htonll() for OS X

On Tue, Mar 15, 2016 at 11:52:59AM -0400, Lance Richardson wrote: > Avoid collision with system headers when building under OS X. > > Signed-off-by: Lance Richardson Applied, thanks! ___ dev mailing list dev@openvswitch.org

Re: [ovs-dev] [PATCH v2 4/5] osx: handle differences between OS X and other BSDs

On Tue, Mar 15, 2016 at 11:52:58AM -0400, Lance Richardson wrote: > Conditional compilation to account for: > - OS X does not implement RTM_IFANNOUNCE. > - OS X does not implement tap netdeivces. > - OS X does not implement RT_ROUNDUP(). > > Signed-off-by: Lance Richardson

Re: [ovs-dev] [PATCH v2 3/5] utilities: OS X compatibility

On Tue, Mar 15, 2016 at 11:52:57AM -0400, Lance Richardson wrote: > Handle OS X like other BSDs (date -r is not supported, use sha1 > instead of sha1sum). > > Signed-off-by: Lance Richardson Applied, thanks! ___ dev mailing list

Re: [ovs-dev] [PATCH v2 2/5] timeval: Add clock_gettime() for OS X

On Tue, Mar 15, 2016 at 11:52:56AM -0400, Lance Richardson wrote: > OS X does not implement clock_gettime(), implement replacement. > > Signed-off-by: Lance Richardson Applied, thanks! ___ dev mailing list dev@openvswitch.org

Re: [ovs-dev] [PATCH v2 1/5] ofproto-dpif: rename wait() to avoid collision with system wait(2)

On Tue, Mar 15, 2016 at 11:52:55AM -0400, Lance Richardson wrote: > Rename ofproto-dpif wait() to avoid collision with wait(2) under OS X. > > Signed-off-by: Lance Richardson > --- > Changes from v1: None Applied, thanks! ___ dev

Re: [ovs-dev] [PATCH 07/10] netdev-dummy: Queue packets only to one rx queue.

On Wed, Mar 23, 2016 at 01:13:06AM +, Daniele Di Proietto wrote: > > On 22/03/2016 17:57, "Ben Pfaff" wrote: > > >On Mon, Mar 14, 2016 at 06:18:17PM +0300, Ilya Maximets wrote: > >> This is unused functionality and it will harm to > >> multiqueue implementation. > >> > >>

Re: [ovs-dev] [PATCH] netdev-dpdk: Fix crash when changing the vhost-user port.

Thanks for the patch and the review! Pushed to master, branch-2.5 and branch-2.4 On 22/03/2016 16:27, "Traynor, Kevin" wrote: >> -Original Message- >> From: Ilya Maximets [mailto:i.maxim...@samsung.com] >> Sent: Tuesday, March 22, 2016 12:42 PM >> To:

Re: [ovs-dev] [PATCH] bond: don't re-zero recirc_id when creating bond

On Tue, Mar 22, 2016 at 10:48:29AM -0700, Ben Pfaff wrote: > On Tue, Mar 08, 2016 at 03:08:23PM +0900, Simon Horman wrote: > > The bond structure is already zeroed as it is allocated > > using xzalloc so there is no need to re-zero the recirc_id field. > > > > Signed-off-by: Simon Horman

Re: [ovs-dev] [PATCH v9 06/10] Add incremental proessing to lflow_run

On Fri, Mar 11, 2016 at 1:06 PM, Ryan Moats wrote: > > From: RYAN D. MOATS > > This code changes lflow_run to do incremental process of the > logical flow table rather than processing the full table each run. > > Signed-off-by: RYAN D. MOATS

Re: [ovs-dev] [PATCH 07/10] netdev-dummy: Queue packets only to one rx queue.

On 22/03/2016 17:57, "Ben Pfaff" wrote: >On Mon, Mar 14, 2016 at 06:18:17PM +0300, Ilya Maximets wrote: >> This is unused functionality and it will harm to >> multiqueue implementation. >> >> Signed-off-by: Ilya Maximets > >This change doesn't make any

Re: [ovs-dev] [PATCH] Change TCP connections to support DNS names

On Mon, Mar 14, 2016 at 02:25:33PM -0500, Ryan Moats wrote: > From: RYAN D. MOATS > > Allow TCP connection strings to also use DNS names in > addition to IPv4 and IPv6 addresses. Updated test case > "ovsdb-client get-schema-version - tcp socket" to > verify. > >

Re: [ovs-dev] [PATCH 07/10] netdev-dummy: Queue packets only to one rx queue.

On Mon, Mar 14, 2016 at 06:18:17PM +0300, Ilya Maximets wrote: > This is unused functionality and it will harm to > multiqueue implementation. > > Signed-off-by: Ilya Maximets This change doesn't make any sense to me. An equivalent change to the Linux kernel would mean

Re: [ovs-dev] [PATCH 04/10] ofproto-dpif.at: Ignore port type while checking result of dpctl/dump-flows.

On Mon, Mar 14, 2016 at 06:18:14PM +0300, Ilya Maximets wrote: > Many ofproto-dpif tests works only with non-pmd interfaces because > of hard coded output of 'dpctl/dump-flows'. > > Fix that by clearing out port types. > > Signed-off-by: Ilya Maximets Acked-by: Ben

Re: [ovs-dev] [PATCH 05/10] ofproto-dpif.at: Allow output from all threads in 'patch ports - stack'.

On Mon, Mar 14, 2016 at 06:18:15PM +0300, Ilya Maximets wrote: > Ignore thread_name suffix. > > Signed-off-by: Ilya Maximets Acked-by: Ben Pfaff ___ dev mailing list dev@openvswitch.org

Re: [ovs-dev] [PATCH 02/10] dummy: Add dummy_pmd class.

On Mon, Mar 14, 2016 at 06:18:12PM +0300, Ilya Maximets wrote: > 'dummy_pmd' class is a replacement for 'dummy' class. > Created in purposes of testing of PMD interfaces. > > May be activated instead of usual 'dummy' by additional > parameter 'pmd' to --enable-dummy. > > Ex.: >

[ovs-dev] [PATCH v4 13/22] Move a couple of bitmap macros to exportable header

From: Ben Warren This allows lib/meta-flow.h to become exportable Signed-off-by: Ben Warren --- include/openvswitch/util.h | 4 lib/bitmap.h | 4 2 files changed, 4 insertions(+), 4 deletions(-) diff --git

[ovs-dev] [PATCH v4 18/22] Assorted #include additions

From: Ben Warren Necessary in preparation for making ofp-util.h public Signed-off-by: Ben Warren --- ofproto/ofproto-dpif-ipfix.c | 1 + ovn/controller/ofctrl.c | 3 +++ ovn/controller/physical.c| 2 ++ ovn/controller/pinctrl.c |

Re: [ovs-dev] [PATCH] netdev-dpdk: Fix crash when changing the vhost-user port.

> -Original Message- > From: Ilya Maximets [mailto:i.maxim...@samsung.com] > Sent: Tuesday, March 22, 2016 12:42 PM > To: dev@openvswitch.org; Daniele Di Proietto > Cc: Dyasly Sergey ; Ben Pfaff ; Flavio > Leitner

Re: [ovs-dev] [PATCH] ovn-controller: add restart test

> This adds a test for this invariant for a specific test case, which is > useful. However, I believe that this should be a universal invariant > for ovn-controller, so that at any time if ovn-controller is restarted > gracefully after it has converged, it should preserve these flows. Is > that

[ovs-dev] [PATCH v4 06/22] Move BLDASSERT macros to compiler header file

From: Ben Warren Signed-off-by: Ben Warren --- include/openvswitch/compiler.h | 30 ++ lib/util.h | 28 2 files changed, 30 insertions(+), 28 deletions(-) diff --git

[ovs-dev] [PATCH v4 11/22] Move lib/match.h to include/openvswitch directory

From: Ben Warren Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/match.h | 214 lib/automake.mk | 1 - lib/classifier.h|

[ovs-dev] [PATCH v4 21/22] Debian: add libopenvswitch-dev build target

From: Ben Warren Add shared objects and header files Signed-off-by: Ben Warren --- debian/automake.mk| 1 + debian/control| 15 +++ debian/libopenvswitch-dev.install | 5 + 3 files changed,

[ovs-dev] [PATCH v4 12/22] Remove inter-header dependencies in OVN files

From: Ben Warren These includes were needed when "meta-flow.h" was refactored, even though neither of affected files included that header file directly. Signed-off-by: Ben Warren --- ovn/controller/ovn-controller.c | 2 ++

[ovs-dev] [PATCH v4 09/22] Break packets.h into private and public parts

From: Ben Warren Public (struct definitions and some prototypes) go in include/openvswitch Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/packets.h | 64 +

[ovs-dev] [PATCH v4 02/22] Remove lib/list.h completely

From: Ben Warren All code is now in include/openvswitch/list.h Signed-off-by: Ben Warren Acked-by: Ryan Moats --- lib/automake.mk | 1 - lib/bfd.c | 2 +- lib/dp-packet.h |

[ovs-dev] [PATCH v4 16/22] Move lib/type-props.h to include/openvswitch directory

From: Ben Warren Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/type-props.h | 55 lib/automake.mk | 1 - lib/classifier.h |

[ovs-dev] [PATCH v4 07/22] Break tun-metadata.h into private and public parts

From: Ben Warren Public (struct definitions and some prototypes) go in include/openvswitch Signed-off-by: Ben Warren --- include/openvswitch/automake.mk| 1 + include/openvswitch/tun-metadata.h | 101 +

[ovs-dev] [PATCH v4 17/22] Break netdev.h into private and public parts

From: Ben Warren Public (struct definitions and some prototypes) go in include/openvswitch Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/netdev.h| 87 +

[ovs-dev] [PATCH v4 05/22] Move lib/ofpbuf.h to include/openvswitch directory

From: Ben Warren Signed-off-by: Ben Warren Acked-by: Ryan Moats --- include/openvswitch/automake.mk | 1 + include/openvswitch/ofpbuf.h| 277 lib/automake.mk |

[ovs-dev] [PATCH v4 10/22] Break flow.h into private and public parts

From: Ben Warren Public (struct definitions and some prototypes) go in include/openvswitch Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/flow.h | 197

[ovs-dev] [PATCH v4 01/22] Move contents of lib/list.h to include/openvswitch directory

From: Ben Warren Most of the list code is properly namespaced, so is OK to move to the global export directory. Some "lib/util.h" code had to move to the other directory as well, but I've tried to make that as small as possible Signed-off-by: Ben Warren

[ovs-dev] [PATCH v4 04/22] Move ofp-parse.h to include/openvswitch directory

From: Ben Warren Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/ofp-parse.h | 106 lib/automake.mk | 1 - lib/dpctl.c |

[ovs-dev] [PATCH v4 15/22] Break uuid.h into private and public parts

From: Ben Warren Public (struct definitions and some prototypes) go in include/openvswitch Signed-off-by: Ben Warren --- include/openvswitch/automake.mk | 1 + include/openvswitch/uuid.h | 35 +++

[ovs-dev] [PATCH v4 20/22] Debian: build openvswitch as shared libraries

From: Ben Warren Signed-off-by: Ben Warren --- debian/openvswitch-common.install | 3 +++ debian/rules | 5 - 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/debian/openvswitch-common.install

[ovs-dev] [PATCH v4 08/22] Misc cleanup with "util.h" header files

From: Ben Warren Removed from redundant #includes and moved some macros to different file scope Signed-off-by: Ben Warren Acked-by: Ryan Moats --- include/openvswitch/compiler.h | 3 +++ include/openvswitch/util.h | 50

[ovs-dev] [PATCH v4 00/22] rework code base for third-party linking

From: Ben Warren This patch set is an attempt at making a 'dev' distribution for OpenVswitch The goal is to provide shared libraries and header files so that third party applications can link in OVS rather than always using the command line utilities. Changes in V4: -

Re: [ovs-dev] [ovs-dev, v9, 02/10] Present tracked changes in increasing change number order

On Tue, Mar 22, 2016 at 02:37:50PM -0700, Ben Pfaff wrote: > On Fri, Mar 11, 2016 at 03:06:17PM -0600, Ryan Moats wrote: > > From: RYAN D. MOATS > > > > Currently changes are added to the front of the track list, so > > they are looped through in LIFO order. Incremental

Re: [ovs-dev] [ovs-dev,v9,05/10] Persist local_datapaths

On Fri, Mar 11, 2016 at 03:06:20PM -0600, Ryan Moats wrote: > From: RYAN D. MOATS > > Persist local_datapaths across runs so that a change can be used > as a trigger to reset incremental flow processing. > > Signed-off-by: RYAN D. MOATS This patch makes

Re: [ovs-dev] [ovs-dev,v9,05/10] Persist local_datapaths

On Fri, Mar 11, 2016 at 03:06:20PM -0600, Ryan Moats wrote: > From: RYAN D. MOATS > > Persist local_datapaths across runs so that a change can be used > as a trigger to reset incremental flow processing. > > Signed-off-by: RYAN D. MOATS One thing I'm

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

> > >> >> So with the LB series, I need to store the value of ct_label and ct_mark >> in a register and then load it from there when I finally do ct_commit. >> ct_label is 32 bits or one register and ct_mark is 128 bits or 4 registers >> for a total of 5 registers. We do not have that many

Re: [ovs-dev] [ovs-dev, v9, 04/10] Persist ports simap in logical_datapath

On Fri, Mar 11, 2016 at 03:06:19PM -0600, Ryan Moats wrote: > From: RYAN D. MOATS > > Persist across runs so that a change to this simap can be used > as a trigger for resetting incremental processing. This makes a lot of sense but it will have to be ported to the new

Re: [ovs-dev] [ovs-dev, v9, 03/10] Make flow table persistent in ovn controller

On Fri, Mar 11, 2016 at 03:06:18PM -0600, Ryan Moats wrote: > From: RYAN D. MOATS > > This is a prerequisite for incremental processing. > > Side effects: > > 1. Table rows are now tracked so that removed rows are correctly >handled. > 2. Hash by table id+priority+action

Re: [ovs-dev] [ovs-dev, v9, 02/10] Present tracked changes in increasing change number order

On Fri, Mar 11, 2016 at 03:06:17PM -0600, Ryan Moats wrote: > From: RYAN D. MOATS > > Currently changes are added to the front of the track list, so > they are looped through in LIFO order. Incremental processing > is more efficient with a FIFO presentation, so > (1) add new

Re: [ovs-dev] [ovs-dev, v9, 01/10] Add useful information to ovn E2E tests

On Fri, Mar 11, 2016 at 03:06:16PM -0600, Ryan Moats wrote: > From: RYAN D. MOATS > > Modify E2E test to output the OF flows from all three > hypervisors to help debug when something goes wrong. > > Signed-off-by: RYAN D. MOATS Applied, thanks. By the

Re: [ovs-dev] [PATCH monitor_cond V5 04/18] ovsdb: generate update notifications for monitor_cond session

Ben Pfaff wrote on 22/03/2016 07:23:33 PM: > On Fri, Mar 04, 2016 at 08:08:59AM +, Liran Schour wrote: > > Hold session's conditions in ovsdb_monitor_session_condition. Pass it > > to ovsdb_monitor for generating "update2" notifications. > > Add functions that can generate

[ovs-dev] [PATCH RFC] OVN: Openstack floating ip support

This patch adds distributed floating ip support for ovn. The assumption made here is that the external network is a single L2 broadcast domain and all the chassis have connectivity to the external network. 2 new tables are added in the LROUTER pipeline IN_IP_DNAT & IP_IN_SNAT. IN_IP_DNAT will

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

On Tue, Mar 22, 2016 at 4:10 PM, Guru Shetty wrote: > > > On 22 March 2016 at 12:55, Russell Bryant wrote: > >> >> >> On Tue, Mar 22, 2016 at 11:49 AM, Guru Shetty wrote: >>> >>> Macro was probably wrong use of word. I mean to say, something like

Re: [ovs-dev] [PATCH v2] ovn: Add hostname to Chassis.

> On Mar 22, 2016, at 12:20 PM, Russell Bryant wrote: > > @@ -89,7 +91,16 @@ chassis_run(struct controller_ctx *ctx, const char > *chassis_id) > } > free(tokstr); > > +char hostname[HOST_NAME_MAX + 1]; > +if (gethostname(hostname, sizeof hostname)) { > +

Re: [ovs-dev] [PATCH] FAQ: Document that new fields need to be added to nx_put_raw() also.

On Tue, Mar 22, 2016 at 12:40:26PM -0700, Justin Pettit wrote: > > > On Mar 22, 2016, at 8:39 AM, Ben Pfaff wrote: > > > > Reported-by: Enas Ahmad > > Signed-off-by: Ben Pfaff > > Acked-by: Justin Pettit Thanks, applied

Re: [ovs-dev] [PATCH 5/5] tests:ovsdb-idl: Add testing for compound index feature

On Wed, Mar 09, 2016 at 12:05:46AM +, Rodriguez Betancourt, Esteban wrote: > This commit includes the tests to verify compound index behavior. > Tests are divide in single and double column indexes and skiplist. > > Signed-off-by: Arnoldo Lutz Guevara >

Re: [ovs-dev] [PATCH 4/5] ovsdb-idl: Autogenerated functions for compound indexes

On Wed, Mar 09, 2016 at 12:04:54AM +, Rodriguez Betancourt, Esteban wrote: > From: Arnoldo Lutz Guevara > > Generates and fill the default comparators for columns with > type int, real, string. Also creates the macros that allow > to iterate over the contents of

Re: [ovs-dev] [PATCH 3/5] ovsdb-idl: IDL Compound Indexes Implementation

On Wed, Mar 09, 2016 at 12:03:54AM +, Rodriguez Betancourt, Esteban wrote: > In the C IDL, allows to create multicolumn indexes in the > tables, that are keep synched with the data in the replica. > > Signed-off-by: Esteban Rodriguez Betancourt Until now, ovsdb-idl.h has

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

On 22 March 2016 at 12:55, Russell Bryant wrote: > > > On Tue, Mar 22, 2016 at 11:49 AM, Guru Shetty wrote: >> >> Macro was probably wrong use of word. I mean to say, something like (very >> crude): ct_commit(ct_label=MARK_FOR_DELETION) >> >> And you are only

[ovs-dev] [PATCH v6 3/3] ovn: Add doc for zone-id external-id on iface record

Update documentation for the new external-id in the interface record of ovsdb. The key consists if the string "ovn-zone-id" concatenated with the logical port id, and the value is the zone-id. Signed-off-by: Ramu Ramamurthy --- ovn/controller/ovn-controller.8.xml |

[ovs-dev] [PATCH v6 2/3] ovn: Add a restart test

Add a test to validate that a restart of the ovn-controller will program zoneids consistently on ports. Flows before restart are compared against flows after restart to detect problems with ofports or zone-ids. Signed-off-by: Ramu Ramamurthy ---

[ovs-dev] [PATCH v6 1/3] ovn: Assign zone-id consistently

Currently, ovn-controller does not record the zoneid assigned to logical port. Tests indicate that zoneids can be different on the same logical port after ovn-controller restart. The fix sets the zone-id as an external-id of the interface record, and recovers the zone-id from that record.

[ovs-dev] [PATCH v6 0/3] ovn: Assign zoneid consistently

Changes v5 to v6 * updates per code-review * handle child-ports and localnet ports * add a test * update docs ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] Subject: [PATCH 2/5] lib:Data structures: Skiplist implementation

On Wed, Mar 09, 2016 at 12:02:38AM +, Rodriguez Betancourt, Esteban wrote: > Skiplist implementation intended for the IDL compound indexes > feature. > > Signed-off-by: Esteban Rodriguez Betancourt Thanks for the patch. This is a new and nontrivial data structure, but the

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

On Tue, Mar 22, 2016 at 11:49 AM, Guru Shetty wrote: > > Macro was probably wrong use of word. I mean to say, something like (very > crude): ct_commit(ct_label=MARK_FOR_DELETION) > > And you are only allowed to set certain values to ct_label and those > values only set certain

Re: [ovs-dev] [PATCH] FAQ: Document that new fields need to be added to nx_put_raw() also.

> On Mar 22, 2016, at 8:39 AM, Ben Pfaff wrote: > > Reported-by: Enas Ahmad > Signed-off-by: Ben Pfaff Acked-by: Justin Pettit --Justin ___ dev mailing list

Re: [ovs-dev] [RFC] OVN northbound address sets

Great, thanks for the feedback! I'm working on the implementation of address sets for OVN now. It's still incomplete, but I'd like to post something by the end of the week. https://github.com/russellb/ovs/commits/ovn-address-sets -- Russell Bryant On Tue, Mar 22, 2016 at 3:26 PM, Salvatore

Re: [ovs-dev] [RFC] OVN northbound address sets

As I am doing some integration between OVN and Kubernetes, there is a similar problem there where the introduction of this concept can be very beneficial. To provide some context a Kubernetes network policy [1] might have several "from" clauses which might translate into a great number of IP

[ovs-dev] [PATCH v2] ovn: Add hostname to Chassis.

We currently use the system-id from the Open_vSwitch schema on each host to populate the unique name field of a Chassis in OVN_Southbound. On most systems, this is a UUID. It would be very convenient to also have the hostname available as that will allow people to more quickly identify which

Re: [ovs-dev] [PATCH 1/5] ovsdb-idl: Compound Indexes Design Document

On Wed, Mar 09, 2016 at 12:01:53AM +, Rodriguez Betancourt, Esteban wrote: > This is the pull request of the complete change: > https://github.com/openvswitch/ovs/pull/111 > > --- > From d7d82c305a610fdb9a81427aa5483e8c6a071687 Mon Sep 17 00:00:00 2001 > From: Esteban Rodriguez Betancourt

Re: [ovs-dev] [RFC PATCH] tunneling: Improving vxlan performance using DPDK flow director feature.

Hi William, All the NICs with flow director cannot benefit from the patch due to the flow matching limitation in the NIC. The offload patch programs the NIC to match on tunnel + header fields (L2 + L3 + L4 + Tunnel header). The XL710 supports filtering on any flexible 16 byte field after the L4

Re: [ovs-dev] [PATCH v1] bridge: Dump configurable QoS types.

On Fri, Mar 18, 2016 at 05:14:16PM +, Ian Stokes wrote: > This commit adds a new command 'qos/show-types' for use with appctl. > This allows a user to query the types of QoS which are configurable via > Open vSwitch on a given interface. > > Signed-off-by: Ian Stokes

Re: [ovs-dev] [PATCH v1] bridge: Fix qos_unixctl_show bug.

On Tue, Mar 08, 2016 at 11:10:31PM +, Ian Stokes wrote: > netdev_get_qos returns a value to indicate if an error has occurred while > attempting to query the QoS configuration of an interface. If an error does > occur the pointer argument passed to it will be set to null before returning. >

Re: [ovs-dev] [PATCH] bond: don't re-zero recirc_id when creating bond

On Tue, Mar 08, 2016 at 03:08:23PM +0900, Simon Horman wrote: > The bond structure is already zeroed as it is allocated > using xzalloc so there is no need to re-zero the recirc_id field. > > Signed-off-by: Simon Horman > --- > Found by inspection. Acked-by: Ben

Re: [ovs-dev] [PATCH] ovn-controller: add restart test

On Mon, Mar 07, 2016 at 04:03:56PM -0500, Ramu Ramamurthy wrote: > Add a test to validate that a restart of the ovn-controller > will program flows in table 0 consistently. Flows before > restart are compared against flows after restart to detect > problems with ofports or zone-ids. > >

Re: [ovs-dev] [PATCH] nx-match: Fix use-after-free parsing matches.

On Mon, Mar 07, 2016 at 11:31:02AM -0800, Joe Stringer wrote: > Address pointed by header_ptr might be free'd due to realloc > happened in ofpbuf_put_hex(). Reported by valgrind in the test > 379: check TCP flags expression in OXM and NXM. > > Invalid write of size 4 >

Re: [ovs-dev] [PATCH monitor_cond V5 04/18] ovsdb: generate update notifications for monitor_cond session

On Fri, Mar 04, 2016 at 08:08:59AM +, Liran Schour wrote: > Hold session's conditions in ovsdb_monitor_session_condition. Pass it > to ovsdb_monitor for generating "update2" notifications. > Add functions that can generate "update2" notification for a > "monitor_cond" session. > JSON cache is

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

On 22 March 2016 at 08:33, Russell Bryant wrote: > On Tue, Mar 22, 2016 at 11:22 AM, Guru Shetty wrote: > > > > > > > On 21 March 2016 at 16:40, Russell Bryant wrote: > > > >> On Mon, Mar 21, 2016 at 11:23 AM, Russell Bryant >

Re: [ovs-dev] Few observations on low performance of 64 byte packet size

On Tue, Mar 22, 2016 at 04:36:20AM +, ravali.bu...@wipro.com wrote: > Hi All, > > While sending 2G traffic of 64bytes size, I see a low performance for Phy-Phy > setup using OVS with DPDK. I get around 1500/1500 throughput. > > Following are the Platform and setup details: > NOTE: Used OVS

[ovs-dev] [PATCH] FAQ: Document that new fields need to be added to nx_put_raw() also.

Reported-by: Enas Ahmad Signed-off-by: Ben Pfaff --- AUTHORS | 1 + FAQ.md | 11 ++- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/AUTHORS b/AUTHORS index 96bdc4f..13b19ca 100644 --- a/AUTHORS +++ b/AUTHORS @@ -282,6 +282,7 @@

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

On Tue, Mar 22, 2016 at 11:22 AM, Guru Shetty wrote: > > > On 21 March 2016 at 16:40, Russell Bryant wrote: > >> On Mon, Mar 21, 2016 at 11:23 AM, Russell Bryant wrote: >> >>> >>> >>> On Mon, Mar 21, 2016 at 11:16 AM, Guru Shetty

Re: [ovs-dev] [PATCH v3 2/3] ovn: Add ct_commit(ct_mark=INT, ct_label=INT); action.

On 21 March 2016 at 16:40, Russell Bryant wrote: > On Mon, Mar 21, 2016 at 11:23 AM, Russell Bryant wrote: > >> >> >> On Mon, Mar 21, 2016 at 11:16 AM, Guru Shetty wrote: >> >>> >>> >>> On 21 March 2016 at 07:54, Russell Bryant

Re: [ovs-dev] [PATCH monitor_cond V5 00/18] Implement conditional monitoring

Ben Pfaff wrote on 21/03/2016 10:53:15 PM: > On Fri, Mar 04, 2016 at 08:08:55AM +, Liran Schour wrote: > > This patch series implements conditional monitoring by introducing an OVSDB > > RFC extension with 2 new JSON-RPC methods: "monitor_cond" and > > "monitor_cond_update".

Re: [ovs-dev] [PATCH monitor_cond V4 02/17] ovsdb: add conditions utilities to support monitor_cond

Ben Pfaff wrote on 21/03/2016 06:36:37 PM: > On Thu, Feb 25, 2016 at 09:26:42AM +0200, Liran Schour wrote: > > Ben Pfaff wrote on 25/02/2016 02:25:32 AM: > > > On Thu, Feb 18, 2016 at 11:46:40AM +, Liran Schour wrote: > > > > Change ovsdb_condition to be a

Re: [ovs-dev] [PATCH] ovn: Add hostname to Chassis.

On Mon, Mar 21, 2016 at 10:36 PM, Russell Bryant wrote: > > @@ -125,8 +127,12 @@ chassis_run(struct controller_ctx *ctx, const char > *chassis_id) >chassis_id); > > if (!chassis_rec) { > +char hostname[HOST_NAME_MAX + 1]; >

[ovs-dev] [PATCH] netdev-dpdk: Fix crash when changing the vhost-user port.

According to netdev-provider API: 'The "destruct" function is not allowed to fail.' netdev-dpdk breaks this restriction for vhost-user ports. This leads to SIGABRT or SIGSEGV in dpdk_watchdog thread because 'dealloc' will be called anyway indifferently to result of 'destruct'. For

[ovs-dev] Document 2

___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

[ovs-dev] FW: Statement S#942535

Dear dev, Please find attached the statement (S#942535) that matches back to your invoices. Can you please sign and return. Best regards, Lizzie Hardin Public Affairs/Public Relations Manager ___ dev mailing list dev@openvswitch.org

[ovs-dev] Document 2

___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [ovs-discuss] Deletion of Indirect Groups on Ovs2.5

Hi, We have a solution for enabling group deletion with type=indirect. Is there anybody working on the fix? We can send our patch to the dev mail list. Best regards, Balazs -Original Message- From: discuss [mailto:discuss-boun...@openvswitch.org] On Behalf Of Simon Horman Sent: 22

Re: [ovs-dev] [PATCH v2] openvswitch: call only into reachable nf-nat code

On Fri, Mar 18, 2016 at 02:33:45PM +0100, Arnd Bergmann wrote: > The openvswitch code has gained support for calling into the > nf-nat-ipv4/ipv6 modules, however those can be loadable modules > in a configuration in which openvswitch is built-in, leading > to link errors: > > net/built-in.o: In

Re: [ovs-dev] [PATCH] openvswitch: Fix checking for new expected connections.

On Mon, Mar 21, 2016 at 11:15:19AM -0700, Jarno Rajahalme wrote: > OVS should call into CT NAT for packets of new expected connections only > when the conntrack state is persisted with the 'commit' option to the > OVS CT action. The test for this condition is doubly wrong, as the CT > status

Re: [ovs-dev] [PATCH v6 6/6] datapath-windows: Updated FAQ regarding Hyper-V recirculation.

Acked-by: Nithin Raju Dependent on previous patches in the series getting checked in. -Original Message- From: dev on behalf of Sorin Vinturis Date: Friday, March 18, 2016 at 7:58 AM To:

Re: [ovs-dev] [PATCH v6 5/6] datapath-windows: Extract flow metadata in execute cmd handler.

Acked-by: Nithin Raju I was wondering if this should be part of the recirc patch itself. -Original Message- From: dev on behalf of Sorin Vinturis Date: Friday, March 18, 2016 at 7:58 AM To:

Re: [ovs-dev] [PATCH v6 4/6] datapath-windows: Support for OVS_ACTION_ATTR_HASH attribute

How is key->dphash being used after it gets stored as part of the key. Shouldn¹t it be used for flow lookup? Is it purely for reporting purposes? Thanks, -- Nithin -Original Message- From: dev on behalf of Sorin Vinturis

Re: [ovs-dev] [PATCH v6 3/6] datapath-windows: Allow recirculation feature probe.

Acked-by: Nithin Raju This patch is part of a series though and cannot be committed till the previous ones in the series get committed. -Original Message- From: dev on behalf of Sorin Vinturis Date: