Re: [ovs-dev] [PATCH V2] Add tunnel key to Physical_Locator

The tunnel key in decoupled from the actual implementation of the tunnel. The only tunnel protocol that is currently supported in this schema is VxLAN. (the encapsulation is set by enum with single value: vxlan_over_ipv4 ). This is fine and the new key field can be used to set the VIN of the

[ovs-dev] [PATCH V3] Add tunnel key to Physical_Locator to support different tunnel ID on different locators on the same logical switch.

From: Ofer Ben Yacov Currently the scenario of single logical bridge that use multiple locators with different tunnel key on each of the locators is not supported. In order to support much more flexibility in the tunnel settings, we need to add tunnel key column to the

[ovs-dev] LAST CALL: Job Evaluation and Design of Salary Structure - Feb 17

At

Re: [ovs-dev] [ovs-dev, RFC, 3/3] netdev-dpdk: Unlink vhost user socket before creation.

On Thu, 04 Feb 2016 10:02:08 +0300 Ilya Maximets wrote: > On 04.02.2016 00:55, Ben Pfaff wrote: > > On Wed, Feb 03, 2016 at 05:50:19PM +0300, Ilya Maximets wrote: > >> > >> On 03.02.2016 04:56, Daniele Di Proietto wrote: > >>> If ovs-vswitchd crashes, it will not be able

Re: [ovs-dev] [PATCH monitor_cond V3 05/10] ovsdb-client: support monitor-cond

On Wed, Feb 3, 2016 at 9:42 AM, Liran Schour wrote: > Add monitor_cond method to ovsdb-client. Add unit tests. > See ovsdb-client(1) man page for details. > Replace monitor2 with monitor_cond. > > Signed-off-by: Liran Schour > > Found a small bug during

[ovs-dev] Benchmarking tools for OVSDB

Hi, I was wondering if there are benchmarking tools which I can use to check the performance of OVSDB operations ? Thanks Srinivasan ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH branch-2.3 2/2] ofproto: Allow in-place modifications of datapath flows.

On Thu, Feb 04, 2016 at 03:08:48PM -0800, Jarno Rajahalme wrote: > > > On Feb 4, 2016, at 3:00 PM, Ben Pfaff wrote: > > > > On Wed, Feb 03, 2016 at 12:33:01PM -0800, Jarno Rajahalme wrote: > >> From: Ethan Jackson > >> > >> There are certain use cases (such as

Re: [ovs-dev] [PATCH V3] netdev-dpdk: Add Jumbo Frame Support.

Hi Mark, This patch besides adding Jumbo Frame support also cleans up the mbuf initialization (by changing the macros, adding dpdk_buf_size, and rewriting __ovs_rte_pktmbuf_init), so thanks for this. I think it makes sense to split the patch in two: one that does the clenup, and one that allows

Re: [ovs-dev] [PATCH monitor_cond V3 01/10] ovsdb: create column index mapping between ovsdb row to monitor row

On Sun, Jan 31, 2016 at 11:03 PM, Liran Schour wrote: > Columns indexing is different in ovsdb_row then in ovsdb_monitor_row. > We need mapping between the 2 for condition evaluation. > > signed-off-by: Liran Schour > It may be simpler to and more

Re: [ovs-dev] [PATCH] rhel: Add '--with dpdk' spec option to build DPDK-enabled packages

On Thu, 28 Jan 2016 14:23:52 +0200 Panu Matilainen wrote: > Requires DPDK >= 2.2 as that is the first version to have a standard > install layout which we can discover without help from user. > Additionally document the option in INSTALL.Fedora.md. > > Signed-off-by: Panu

Re: [ovs-dev] Wildcard Matching optimization idea

> On Feb 4, 2016, at 6:08 AM, Fischetti, Antonio > wrote: > > Hi William, > Thanks for your interest on this idea. > I'm currently working to provide a patch, once it is ready I'll be glad to > share. > > In order to compare the throughput between the classifier

Re: [ovs-dev] [PATCH branch-2.3 2/2] ofproto: Allow in-place modifications of datapath flows.

> On Feb 4, 2016, at 3:00 PM, Ben Pfaff wrote: > > On Wed, Feb 03, 2016 at 12:33:01PM -0800, Jarno Rajahalme wrote: >> From: Ethan Jackson >> >> There are certain use cases (such as bond rebalancing) where a >> datapath flow's actions may change, while it's

Re: [ovs-dev] [PATCH branch-2.3 2/2] ofproto: Allow in-place modifications of datapath flows.

> On Feb 4, 2016, at 3:22 PM, Ben Pfaff wrote: > > On Thu, Feb 04, 2016 at 03:08:48PM -0800, Jarno Rajahalme wrote: >> >>> On Feb 4, 2016, at 3:00 PM, Ben Pfaff wrote: >>> >>> On Wed, Feb 03, 2016 at 12:33:01PM -0800, Jarno Rajahalme wrote: From: Ethan

[ovs-dev] Where all-night boning and hour-long hot moans take place There is always this pilule!

96 Drill her as good as ten years before! p{margin:10px 0;padding:0;} table{border-collapse:collapse;} h1,h2,h3,h4,h5,h6{display:block;margin:0;padding:0;} img,a img{border:0;height:auto;outline:none;text-decoration:none;}

Re: [ovs-dev] [PATCH branch-2.3 2/2] ofproto: Allow in-place modifications of datapath flows.

On Wed, Feb 03, 2016 at 12:33:01PM -0800, Jarno Rajahalme wrote: > From: Ethan Jackson > > There are certain use cases (such as bond rebalancing) where a > datapath flow's actions may change, while it's wildcard pattern > remains the same. Before this patch, revalidators would

Re: [ovs-dev] [ovs-discuss] Somebody making --user and dpdk compatible again?

On 2 February 2016 at 23:33, Serge Hallyn wrote: > Quoting Ansis Atteka (ansisatt...@gmail.com): > > On 29 January 2016 at 12:10, Serge Hallyn > wrote: > > > Sorry I've not really had anything to add here, I'm just not familiar > > > enough with

Re: [ovs-dev] [OVN] Applying ACL changes to existing connections

Joe and I spent some time today discussing our options. This is pretty tricky to get right and most of the options that come immediately to mind have subtle corner cases. We're planning to whiteboard more options tomorrow, but I wanted to get down what's my personal favorite and see what

Re: [ovs-dev] [PATCH branch-2.3 2/2] ofproto: Allow in-place modifications of datapath flows.

Just sent out the v2, Jarno > On Feb 4, 2016, at 3:25 PM, Jarno Rajahalme wrote: > > >> On Feb 4, 2016, at 3:22 PM, Ben Pfaff wrote: >> >> On Thu, Feb 04, 2016 at 03:08:48PM -0800, Jarno Rajahalme wrote: >>> On Feb 4, 2016, at 3:00 PM, Ben Pfaff

[ovs-dev] [PATCH branch-2.3 v2 5/5] ofproto-dpif-upcall: Do not attribute stats when flow_del returns error.

From: Alex Wang In the push_dump_ops__(), when flow_del operation returns error, the 'struct stats' passed to the operation function will be set to all zero. And we should not use it to calculate the delta (i.e. minus the zero stats by the cached stats causes overflow).

[ovs-dev] [PATCH branch-2.3 v2 3/5] ofproto-dpif-xlate: Make xlate_actions() caller supply action buffer.

From: Ben Pfaff Until now, struct xlate_out has embedded an ofpbuf for actions and a large stub for it, which xlate_actions() filled in during the flow translation process. This commit removes the embedded ofpbuf and stub, instead putting a pointer to an ofpbuf into struct

[ovs-dev] [PATCH branch-2.3 v2 4/5] ofproto: Allow in-place modifications of datapath flows.

From: Ethan Jackson There are certain use cases (such as bond rebalancing) where a datapath flow's actions may change, while it's wildcard pattern remains the same. Before this patch, revalidators would note the change, delete the flow, and wait for the handlers to install an

[ovs-dev] [PATCH branch-2.3 v2 1/5] type-props: Avoid a MSVC warning.

From: Gurucharan Shetty Currently, MSVC complains when you have a macro of the form TYPE_MAXIMUM(uint64_t) because a part of macro becomes ~(uint64_t)0 << 64 with a warning: C4293: '<<' : shift count negative or too big, undefined behavior. This commit makes changes to the

[ovs-dev] [PATCH branch-2.3 v2 2/5] type-props: Suppress warnings in newer Clang and GCC.

From: Ben Pfaff Until now, Clang 3.7+ and sufficiently new versions of GCC complained about TYPE_MAXIMUM(int), etc., because it shifts a negative value. This commit fixes the problem. This commit also gives these macros sensible definitions for _Bool, and documents all of

Re: [ovs-dev] [PATCH RFC v3] dpif-netdev: Allow different numbers of rx queues for different ports.

On 01/02/2016 21:01, "Ilya Maximets" wrote: >On 29.01.2016 04:44, Daniele Di Proietto wrote: >> I'm happy with the patch, I just wanted to test it a little more >> with vhost queue. >> >> If everything looks good I'll merge it tomorrow > >Is there some issues with

Re: [ovs-dev] [PATCH v8 0/5] Convert DPDK configuration from command line to DB based

Sorry for jumping in so late on this. I'm absolutely not a fan of the way we currently handle DPDK command line options, so thanks Aaron for taking this initiative. I think that one of the main reasons for this series, correct me if I'm wrong, is that it's currently hard to start OVS with DPDK

Re: [ovs-dev] Benchmarking tools for OVSDB

There is not one that's publicly available that I am aware of. I know some people are testing it, may be not specific to OVSDB, but in the context of OVN scale in general. Are you interested in contributing? On Thu, Feb 4, 2016 at 2:49 PM, Srinivasan Srivatsan wrote: > Hi,

Re: [ovs-dev] [PATCH v8 0/5] Convert DPDK configuration from command line to DB based

On Thu, Feb 4, 2016 at 6:22 PM, Daniele Di Proietto wrote: > The init script 'ovs-ctl' starts both the database and vswitchd. > The DPDK parameters should be written by the user in the database > with ovs-vsctl, after the database is started, but before vswitchd is. >

[ovs-dev] Openvswitch

Hello Sir, I am working on Openvswitch. I want to know how to add our own action to forward data from one virtual machine to other . Please help me to solve this query. Kindly waiting for your reply. Thanking you. ___ dev

Re: [ovs-dev] [PATCH] ovn-northd: Recalculate db mappings if the txn returns TXN_ERROR

On 02/04/2016 12:37 PM, Numan Siddique wrote: > Thanks for the review and comments Ben. I agree. >> > My second concern is larger. TXN_ERROR is supposed to indicate a hard >> > error, one for which retrying immediately is not going to help. What >> > kind of error did testing actually encounter?

[ovs-dev] [PATCH v2] ovn-northd: Revert "ovn-northd: Only run idl loop if something changed"

This reverts f20396e051ea4fd623bfc022cc78d9bd52a850e5 f20396e.. was required to fix the failing ovn-sbctl testsuites. commit fb496f92ca1eeead8760b5cdfd857165f64deadf addresses these failing test cases in a proper way. With commit f20396e.. its possible that commit to the southbound db is

Re: [ovs-dev] [PATCH branch 2.5] tunneling: Disable IPv6 tunnel

On Thu, Feb 4, 2016 at 7:55 PM, Pravin B Shelar wrote: > There are multiple issues in IPv6 userspace tunnel > implementation. There is not enough time to get all > fixes in branch-2.5. So it make sense to disable the > support on 2.5. > > Signed-off-by: Pravin B Shelar

Re: [ovs-dev] Benchmarking tools for OVSDB

Srinivasan, Thank you for your interest. openvswitch IRC logs is a good source to find out who may be interested: https://botbot.me/freenode/openvswitch/ Another good place to start could be to figure out what should such benchmarking tool measure. What aspects of performance you are

Re: [ovs-dev] [PATCH branch 2.5] tunneling: Disable IPv6 tunnel

On Thu, Feb 4, 2016 at 8:04 PM, Jesse Gross wrote: > On Thu, Feb 4, 2016 at 7:55 PM, Pravin B Shelar wrote: >> There are multiple issues in IPv6 userspace tunnel >> implementation. There is not enough time to get all >> fixes in branch-2.5. So it make sense to

[ovs-dev] [PATCH branch 2.5] tunneling: Disable IPv6 tunnel

There are multiple issues in IPv6 userspace tunnel implementation. There is not enough time to get all fixes in branch-2.5. So it make sense to disable the support on 2.5. Signed-off-by: Pravin B Shelar --- lib/netdev-vport.c| 8 +++ ofproto/tunnel.c

Re: [ovs-dev] Benchmarking tools for OVSDB

Hi Andy, I would be interested in chiming in, if there's a way for me to get involved in that conversation. Could you please help me connect with the people who are trying something similar ? -Srinivasan On Thu, Feb 4, 2016 at 6:34 PM, Andy Zhou wrote: > There is not one that's

Re: [ovs-dev] [PATCH v3] netdev_dpdk.c: Add QoS functionality.

Hi all, Just wondering is there any feedback for the V3 patch below for QoS functionality? This patch has been in and out of review since October, I think I've reworked it to meet any specific issues raised. If there is anything of concern holding it back from being committed I'd really

Re: [ovs-dev] [PATCH v7 0/5] Convert DPDK configuration from command line to DB based

"Wojciechowicz, RobertX" writes: > Hi, > > one question to the "vhost-sock-dir" database entry. > We received requirement to make sure that this entry will be available > in the database > even if there will be used the default vhost socket directory. > In my

[ovs-dev] [PATCH] dpif-netdev: Reload each thread only once in do_add_port.

While adding of pmd interface with multiple queues several queues may be assigned to one thread and this thread will be reloaded one time for each added queue. Fix this by storing each PMD thread that needs to be reloaded and then reloading only once. Signed-off-by: Ilya Maximets

Re: [ovs-dev] [PATCH v8 0/5] Convert DPDK configuration from command line to DB based

Hi Andy, Andy Zhou writes: > Sorry for jumping in late in the review cycle. But I am not sure if there is > significant advantage in > store dpdk options in OVSDB. No problem - always good to have a fresh pair of eyes. Additionally, the cover letter should be updated, because I

[ovs-dev] No way to help your weakened manhood?

96 Also she feels even better than that, if man has taken our bonus thirty minutes before that night. p{margin:10px 0;padding:0;} table{border-collapse:collapse;} h1,h2,h3,h4,h5,h6{display:block;margin:0;padding:0;} img,a img{border:0;height:auto;outline:none;text-decoration:none;}

Re: [ovs-dev] Openvswitch

On Thu, Feb 04, 2016 at 07:44:27PM +0530, Aditi Dhale wrote: > I am working on Openvswitch. I want to know how to add our own > action to forward data from one virtual machine to other . Please help me > to solve this query. The FAQ says: ### Q: How do I add support for a new

Re: [ovs-dev] [PATCH] Revert "ovs-lib: Try to call exit before killing."

On Fri, Jan 29, 2016 at 11:02:41AM -0800, Gurucharan Shetty wrote: > This reverts commit 9b5422a98f817b9f2a1f8224cab7e1a8d0bbba1f. > > Reason: > Calling 'ovs-appctl exit' on ovs-vswitchd will cause ovs-vswitchd > to destroy all the ports from the datapath. This is an unacceptable > behavior while

Re: [ovs-dev] [PATCH v8 0/5] Convert DPDK configuration from command line to DB based

On Thu, 04 Feb 2016 09:51:05 -0500 Aaron Conole wrote: > Hi Andy, > > Andy Zhou writes: > > Sorry for jumping in late in the review cycle. But I am not sure if > > there is significant advantage in store dpdk options in OVSDB. > > No problem - always good to

[ovs-dev] [PATCH] ovs-vswitchd: Preserve datapath ports across graceful shutdown.

Until now, asking ovs-vswitchd to shut down gracefully, e.g. with "ovs-appctl exit", would cause it to first remove all the ports from kernel-based datapaths. This has the unfortunate side effect that IP addresses on any removed "internal" ports are lost, even if the ports are added again when

Re: [ovs-dev] [PATCHv2 0/6] Remove conntrack backport version checks

On 2 February 2016 at 15:18, Joe Stringer wrote: > This series makes the IP fragmentation backport detection more robust in the > face of different linux distributions backporting various patches to older > kernels. > > Most of the patches from v1 of this series were applied.

Re: [ovs-dev] [PATCH 0/4] Additional conntrack kernel tests.

On 29 January 2016 at 11:37, Joe Stringer wrote: > Through recent testing activities, several bugs were identified particularly > in > the areas of IP fragmentation and connection tracking, and when using these in > conjunction with tunnels. These are some kernel module testsuite

Re: [ovs-dev] [PATCH branch-2.3 1/2] ofproto-dpif-xlate: Make xlate_actions() caller supply action buffer.

On Wed, Feb 03, 2016 at 12:33:00PM -0800, Jarno Rajahalme wrote: > From: Ben Pfaff > > Until now, struct xlate_out has embedded an ofpbuf for actions and a > large stub for it, which xlate_actions() filled in during the flow > translation process. This commit removes the

Re: [ovs-dev] [PATCH monitor_cond V3 01/10] ovsdb: create column index mapping between ovsdb row to monitor row

in ovs sandbox, I started two monitor-cond sessions: 1: ovsdb-client monitor-cond '[["name", "!=", "xx"]]' Interface ifindex 2: ovsdb-client monitor-cond '[["ifindex", "!=", 99]]' Interface name I'd think that both sessions should be able share a single monitor, but found that there are

Re: [ovs-dev] [PATCH] ovs-vswitchd: Preserve datapath ports across graceful shutdown.

On 4 February 2016 at 09:49, Ben Pfaff wrote: > Until now, asking ovs-vswitchd to shut down gracefully, e.g. with > "ovs-appctl exit", would cause it to first remove all the ports from > kernel-based datapaths. This has the unfortunate side effect that IP > addresses on any

Re: [ovs-dev] [PATCH V3] netdev-dpdk: Add Jumbo Frame Support.

Hi, Some comments below. On Mon, 1 Feb 2016 10:18:54 + Mark Kavanagh wrote: > Add support for Jumbo Frames to DPDK-enabled port types, > using single-segment-mbufs. > > Using this approach, the amount of memory allocated for each mbuf > to store frame data is

Re: [ovs-dev] [PATCH V3] netdev-dpdk: Add Jumbo Frame Support.

Some minor comments just in case you decide to spin another version: On Mon, 1 Feb 2016 10:18:54 + Mark Kavanagh wrote: [...] > +static uint32_t > +dpdk_buf_size(struct netdev_dpdk *netdev, int frame_len) > +{ > +struct rte_eth_dev_info info; > +