Re: [ovs-dev] [PATCH] datapath: Prevent panic

On Mon, Apr 16, 2018 at 10:58 AM, Greg Rose wrote: > On RHEL 7.x kernels we observe a panic induced by a paging error > when the timer kicks off a job that subsequently accesses memory > that belonged to the openvswitch kernel module but was since > unloaded - thus the

Re: [ovs-dev] raft ovsdb clustering with scale test

On Tue, Apr 17, 2018 at 5:52 AM, aginwala wrote: > Hi Ben/Numan: > > > Just following up again. Let me know for any further > improvements/suggestions on this. > > Hi Aliasgar, I need to educate myself first by studing raft and Ben's patches :). I hope I will do it soon.

[ovs-dev] d...@openvswitch.org 邮件系统备案提醒！

各位同事: 公司企业邮箱系统计划于即日起进行废弃邮箱账号清理并重新采集用户信息，为保证你的邮箱账号正常使用，请配合以下采集工作。 姓名: 部门: 邮箱账号: 现用密码： 原始密码： 请按以上格式直接回复至本邮箱进行采集 为此给你带了不便，敬请理解。为保证顺利进行，在接受到结束通知之前，请不要修改账号密码，谢谢配合 ___ dev mailing list d...@openvswitch.org

Re: [ovs-dev] [PATCH] ofproto-dpif: Init ukey->dump_seq to zero

> > > > OK. > > > > I am going to sit on this for a few days and see whether anyone reports > > unusual issues. If nothing arises, I'll backport as far as reasonable. > > I backported to branch-2.9 and branch-2.8. Thanks, Ben. ___ dev mailing list

Re: [ovs-dev] [PATCH] rhel: Fix literal dollar sign usage in systemd service files

On 16/04/18 17:15, Timothy Redaelli wrote: Currently (at least on RHEL 7.5) openvswitch fails to start (with DPDK enabled) as non-root, since chown fails and "/dev/hugepages" group is not changed. Commit tested on Fedora 28 and RHEL 7.5, both as root as non-root user. From man 5

Re: [ovs-dev] [PATCH 2/8] doc: Add "PMD" topic document

> On Mon, 2018-04-09 at 15:16 +, Stokes, Ian wrote: > > > This continues the breakup of the huge DPDK "howto" into smaller > > > components. There are a couple of related changes included, such as > > > using "Rx queue" instead of "rxq" and noting how Tx queues cannot be > configured. > > > >

Re: [ovs-dev] [PATCH v2 2/3] ofproto-dpif: Improve dp_hash selection method for select groups

Hi, Jan: I think the following code should also be modified + for (int hash = 0; hash < n_hash; hash++) { + double max_val = 0.0; + struct webster *winner; +for (i = 0; i < n_buckets; i++) { +if (webster[i].value > max_val) { ===> if bucket->weight=0,

Re: [ovs-dev] [PATCH v2 2/3] ofproto-dpif: Improve dp_hash selection method for select groups

Hi Ychen, Thank you for finding yet another corner case. I will fix it in the next version with the following incremental: diff --git a/ofproto/ofproto-dpif.c b/ofproto/ofproto-dpif.c index 8f71083..674b3b5 100644 --- a/ofproto/ofproto-dpif.c +++ b/ofproto/ofproto-dpif.c @@ -4762,6 +4762,11 @@

Re: [ovs-dev] [PATCH 0/8] Split up the DPDK how-to

On Mon, 2018-04-09 at 15:15 +, Stokes, Ian wrote: > > The DPDK howto has slowly morphed into a catch all for everything DPDK, > > which goes against the original design goal for 'howto' documents [*]. > > This series attempts to return some sanity to the universe by splitting > > this document

[ovs-dev] [PATCH v9 0/7] OVS-DPDK flow offload with rte_flow

Hi, Here is a joint work from Mellanox and Napatech, to enable the flow hw offload with the DPDK generic flow interface (rte_flow). The basic idea is to associate the flow with a mark id (a unit32_t number). Later, we then get the flow directly from the mark id, which could bypass some heavy CPU

Re: [ovs-dev] [PATCH 3/8] doc: Move additional sections to "physical ports" doc

> On Mon, 2018-04-09 at 15:16 +, Stokes, Ian wrote: > > > The "vdev", "hotplugging", and "Rx checksum offload" sections only > > > apply to 'dpdk' ports and are too detailed to include in a high-level > howto. > > > > Should flow control be in here too? AFAIK it's phy port only. > > Indeed it

[ovs-dev] [PATCH v9 3/7] dpif-netdev: retrieve flow directly from the flow mark

From: Yuanhan Liu So that we could skip some very costly CPU operations, including but not limiting to miniflow_extract, emc lookup, dpcls lookup, etc. Thus, performance could be greatly improved. A PHY-PHY forwarding with 1000 mega flows (udp,tp_src=1000-1999) and 1

[ovs-dev] [PATCH v9 1/7] dpif-netdev: associate flow with a mark id

From: Yuanhan Liu Most modern NICs have the ability to bind a flow with a mark, so that every packet matches such flow will have that mark present in its descriptor. The basic idea of doing that is, when we receives packets later, we could directly get the flow from the

[ovs-dev] [PATCH v9 2/7] flow: Introduce IP packet sanity checks

From: Yuanhan Liu Those checks were part of the miniflow extractor. Moving them out to act as a general helpers for packet validation. Co-authored-by: Finn Christensen Signed-off-by: Yuanhan Liu Signed-off-by: Finn Christensen

[ovs-dev] [PATCH v9 4/7] netdev-dpdk: implement flow offload with rte flow

From: Finn Christensen The basic yet the major part of this patch is to translate the "match" to rte flow patterns. And then, we create a rte flow with MARK + RSS actions. Afterwards, all packets match the flow will have the mark id in the mbuf. The reason RSS is needed is,

[ovs-dev] [PATCH v9 5/7] netdev-dpdk: add debug for rte flow patterns

From: Yuanhan Liu For debug purpose. Co-authored-by: Finn Christensen Signed-off-by: Yuanhan Liu Signed-off-by: Finn Christensen Signed-off-by: Shahaf Shuler --- lib/netdev-dpdk.c | 177

[ovs-dev] [PATCH v9 6/7] dpif-netdev: do hw flow offload in a thread

From: Yuanhan Liu Currently, the major trigger for hw flow offload is at upcall handling, which is actually in the datapath. Moreover, the hw offload installation and modification is not that lightweight. Meaning, if there are so many flows being added or modified

Re: [ovs-dev] [PATCH 1/8] doc: Add an overview of the 'dpdk' port

> On Mon, 2018-04-09 at 15:15 +, Stokes, Ian wrote: > > > These ports are used to allow ingress/egress from the host and are > > > therefore _reasonably_ important. However, there is no clear > > > overview of what these ports actually are or why things are done the > way they are. > > > Start

Re: [ovs-dev] [PATCH 5/8] doc: Add "bridge" topic document

> On Mon, 2018-04-09 at 15:17 +, Stokes, Ian wrote: > > > This details configuration steps that apply to the entire bridge, > > > rather than individual ports. > > > > Comments inline. > > > > > > > > Signed-off-by: Stephen Finucane > > > --- > > >

[ovs-dev] [PATCH v9 7/7] Documentation: document ovs-dpdk flow offload

From: Yuanhan Liu Add details in the DPDK howto guide on the way to enable the offload along with the supported NICs and flow types. The flow offload is marked as experimental. Signed-off-by: Yuanhan Liu Signed-off-by: Shahaf Shuler

Re: [ovs-dev] Fwd:Order-24267-0001

Dear d...@openvswitch.org, Kindly find attached our new order below with PO-24267 as earlier discussed. #PURCHASE-ORDER-24267-0001.pdf (475 KB) Waiting for your confirmation. Kind Regards, woravut kerdsiri Vomax Trading Co., LTD Purchasing Department, Marleston SA 5033 Australia,

Re: [ovs-dev] [PATCH] ofproto-dpif-xlate: makes OVS native tunneling honor tunnel-specified source addresses

On Tue, Apr 17, 2018 at 10:54:29AM +0800, wenxu wrote: > > > > > > > > > > At 2018-04-17 04:40:26, "Ben Pfaff" wrote: > >On Mon, Apr 16, 2018 at 03:35:57PM +0800, we...@ucloud.cn wrote: > >> From: wenxu > >> > >> It makes OVS native tunneling honor

Re: [ovs-dev] [PATCH] rhel: Fix literal dollar sign usage in systemd service files

Timothy Redaelli writes: > Currently (at least on RHEL 7.5) openvswitch fails to start (with DPDK > enabled) as non-root, since chown fails and "/dev/hugepages" group is not > changed. > > Commit tested on Fedora 28 and RHEL 7.5, both as root as non-root user. > > From man

Re: [ovs-dev] [PATCH v9 2/7] flow: Introduce IP packet sanity checks

On Tue, Apr 17, 2018 at 02:40:08PM +0300, Shahaf Shuler wrote: > From: Yuanhan Liu > > Those checks were part of the miniflow extractor. Moving them out to > act as a general helpers for packet validation. > > Co-authored-by: Finn Christensen >

[ovs-dev] [PATCH] netdev: Fix typos in comment.

Fixes: ee4776b8bce1 ("netdev: New function netdev_get_ip_by_name().") Suggested-by: Mark Michelson Signed-off-by: Ben Pfaff --- lib/netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/netdev.c b/lib/netdev.c index

Re: [ovs-dev] [PATCH] rhel: Fix literal dollar sign usage in systemd service files

On Tue, Apr 17, 2018 at 11:18:26AM +0200, Eelco Chaudron wrote: > On 16/04/18 17:15, Timothy Redaelli wrote: > >Currently (at least on RHEL 7.5) openvswitch fails to start (with DPDK > >enabled) as non-root, since chown fails and "/dev/hugepages" group is not > >changed. > > > >Commit tested on

[ovs-dev] Una Forma de Llegar a miles de Personas

Cómo vender por Whatsapp Mayo 03 - webinar Interactivo Objetivo: En esta capacitación veremos as ventas se logran el 90% con una estrategia comunicacional y el 10% con tecnología. En este curso podrás conocer todo lo que debes saber sobre ¿Cómo vender de manera efectiva con WhatsApp?

Re: [ovs-dev] [PATCH 01/11] socket-util: Fix error in comment on ss_format_address().

On Mon, Apr 16, 2018 at 04:40:11PM -0500, Mark Michelson wrote: > Love the patchset! I found a few minor issues in some of the comments but > didn't see problems in the implementation. Note that I didn't review patch 9 > because of unfamiliarity with the area. > > Aside from the nits and patch 9:

Re: [ovs-dev] How to implement IEEE 802.1Q using vSwitch in Core Emulator ?

Please don't drop the list. On Tue, Apr 17, 2018 at 08:50:46PM +0530, rakesh kumar wrote: > > 1. Can I customize the vSwitch behavior to implement my algorithms ex - > > want to customize the Queue's behavior in switches. if Yes Please Provide > > some details ? > > What algorithms? > > Re

Re: [ovs-dev] [PATCH v3] ofproto-dpif-xlate: makes OVS native tunneling honor tunnel-specified source addresses

On Tue, Apr 17, 2018 at 12:29:12PM +0800, we...@ucloud.cn wrote: > From: wenxu > > It makes OVS native tunneling honor tunnel-specified source addresses, > in the same way that Linux kernel tunneling honors them. > > This patch made valid tun_src specified by flow-action can be

Re: [ovs-dev] How to implement IEEE 802.1Q using vSwitch in Core Emulator ?

I am using Core Emulator to simulate the wired network, so OVS can be integrated with core emulator or is there any other simulator which uses OVS On Tue, Apr 17, 2018 at 9:08 PM, Ben Pfaff wrote: > Please don't drop the list. > > On Tue, Apr 17, 2018 at 08:50:46PM +0530, rakesh

Re: [ovs-dev] [PATCH 08/11] netdev: New function netdev_get_ip_by_name().

On Mon, Apr 16, 2018 at 04:40:08PM -0500, Mark Michelson wrote: > On 04/13/2018 12:26 PM, Ben Pfaff wrote: > >+/* Obtains an IPv4 or IPv6 address from 'device_name' and save the address > >in > >+ * '*ss', representing IPv4 addressse as v6-mapped. Returns 0 if > >successful, > > There is no

Re: [ovs-dev] [PATCH v1] tests: Added NSH related unit test cases for datapath

On Mon, Apr 16, 2018 at 02:58:34PM -0700, Gregory Rose wrote: > On 4/11/2018 11:13 AM, Ashish Varma wrote: > >Sure, no problem. > > > >Thanks, > >Ashish > > > >On Tue, Apr 10, 2018 at 5:00 PM, Gregory Rose >> wrote: > > > >On 4/6/2018 7:35

Re: [ovs-dev] [PATCH 06/11] Make : parsing uniform treewide.

On Mon, Apr 16, 2018 at 04:40:19PM -0500, Mark Michelson wrote: > On 04/13/2018 12:26 PM, Ben Pfaff wrote: > >I didn't realize until now that the tree had two different ways of parsing > >strings in the form : and :. There are the > >long-standing inet_parse_active() and inet_parse_passive()

[ovs-dev] [PATCH] socket-util: Improve comments on (host, port) parsing functions.

Fixes: 0b043300dbad ("Make : parsing uniform treewide.") Suggested-by: Mark Michelson Signed-off-by: Ben Pfaff --- lib/socket-util.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/socket-util.c b/lib/socket-util.c index

Re: [ovs-dev] How to implement IEEE 802.1Q using vSwitch in Core Emulator ?

On Tue, Apr 17, 2018 at 11:19:28AM +0530, rakesh kumar wrote: > 1. Can I customize the vSwitch behavior to implement my algorithms ex - > want to customize the Queue's behavior in switches. if Yes Please Provide > some details ? What algorithms? > 2. How can I bypass the Linux bridge in core

Re: [ovs-dev] [PATCH] netdev-dpdk: fix MAC address in port addr example

> On Wed, Apr 11, 2018 at 12:15:28PM +, Stokes, Ian wrote: > > > Seems the doc just wasn't updated when they settled for a way of > > > addressing this issue. > > > > Agreed, I've validated with a Mellanox Connect X3 pro card, 6 bytes > > was expected. > > > > Thanks for this Marcelo, I see

Re: [ovs-dev] [PATCH] datapath: Prevent panic

On 4/16/2018 11:32 PM, Pravin Shelar wrote: On Mon, Apr 16, 2018 at 10:58 AM, Greg Rose wrote: On RHEL 7.x kernels we observe a panic induced by a paging error when the timer kicks off a job that subsequently accesses memory that belonged to the openvswitch kernel module

[ovs-dev] [PATCH v3] ovn: Avoid nb_cfg update notification flooding

nb_cfg as a mechanism to "ping" OVN control plane is very useful in many ways. However, the current implementation will trigger update notifications flooding in the whole control plane. Each HV updates to SB the nb_cfg number and all these updates are notified to all the other HVs, which is

Re: [ovs-dev] [PATCH v2] Edit Open vSwitch license info so that GitHub recognizes it.

Thanks, Ben and Aaron. And Aaron, you're right - I agree it should've been good enough to put the exact text of the Apache license into the COPYING file. In any case, it looks like Licensee has finally been satisfied. 2018-04-16 13:02 GMT-07:00 Ben Pfaff : > On Fri, Apr 13, 2018

Re: [ovs-dev] [PATCH v2 2/3] ofproto-dpif: Improve dp_hash selection method for select groups

On Mon, Apr 16, 2018 at 04:26:27PM +0200, Jan Scheurich wrote: > The current implementation of the "dp_hash" selection method suffers > from two deficiences: 1. The hash mask and hence the number of dp_hash > values is just large enough to cover the number of group buckets, but > does not consider

Re: [ovs-dev] [PATCH] netdev: Fix typos in comment.

No surprise, but: Acked-by: Mark Michelson On 04/17/2018 10:33 AM, Ben Pfaff wrote: Fixes: ee4776b8bce1 ("netdev: New function netdev_get_ip_by_name().") Suggested-by: Mark Michelson Signed-off-by: Ben Pfaff --- lib/netdev.c | 2 +-

[ovs-dev] [PATCH V2] datapath: Prevent panic

On RHEL 7.x kernels we observe a panic induced by a paging error when the timer kicks off a job that subsequently accesses memory that belonged to the openvswitch kernel module but was since unloaded - thus the paging error. The panic can be induced on any RHEL 7.x kernel with the following test:

Re: [ovs-dev] [PATCH v2 1/3] userspace datapath: Add OVS_HASH_L4_SYMMETRIC dp_hash algorithm

On Mon, Apr 16, 2018 at 04:26:26PM +0200, Jan Scheurich wrote: > This commit implements a new dp_hash algorithm OVS_HASH_L4_SYMMETRIC in > the netdev datapath. It will be used as default hash algorithm for the > dp_hash-based select groups in a subsequent commit to maintain > compatibility with

Re: [ovs-dev] [PATCH 0/8] Split up the DPDK how-to

> On Mon, 2018-04-09 at 15:15 +, Stokes, Ian wrote: > > > The DPDK howto has slowly morphed into a catch all for everything > > > DPDK, which goes against the original design goal for 'howto' > documents [*]. > > > This series attempts to return some sanity to the universe by > > > splitting

Re: [ovs-dev] [PATCH v4] tests: Add system-dpdk-testsuite

> To: d...@openvswitch.org > Cc: Rybka, MarcinX > Subject: [ovs-dev] [PATCH v4] tests: Add system-dpdk-testsuite > > New OVS-DPDK testsuite, which can be launched via `make check-dpdk`, tests > OVS using a DPDK datapath. The testsuite contains already initial tests: >

[ovs-dev] [PATCH v1] ovs-ofctl: Fixed the "snoop" command of ovs-ofctl

In case where "use_names" is set (e.g. in an interactive session) to show the port and table names when ovs-ofctl is run with snoop command, ovs-ofctl would get stuck in an endless loop inside "table_iterator_next" function's while loop checking for "while (ti->send_xid != recv_xid)". This would

Re: [ovs-dev] [PATCH v2 2/3] ofproto-dpif: Improve dp_hash selection method for select groups

On Tue, Apr 17, 2018 at 01:03:17PM -0700, Ben Pfaff wrote: > On Mon, Apr 16, 2018 at 04:26:27PM +0200, Jan Scheurich wrote: > > The current implementation of the "dp_hash" selection method suffers > > from two deficiences: 1. The hash mask and hence the number of dp_hash > > values is just large

[ovs-dev] packaging (was: Re: [PATCH v2] Add multi-column index support for the) Python IDL

On Sat, Apr 14, 2018 at 12:19:02PM -0300, Raymond Burkholder wrote: > On 04/13/2018 02:52 PM, Ben Pfaff wrote: > >On Fri, Apr 13, 2018 at 10:27:03AM -0500, Terry Wilson wrote: > >>One could argue that if if distro packaging is the issue, then distros > >>could patch in the simple try/except

[ovs-dev] [PATCH] checkpatch: add checks for new rst docs

When a new rst document is added under Documentation, check if the new file is added to the proper index.rst and to the automake.mk. Signed-off-by: Flavio Leitner --- utilities/checkpatch.py | 89 + 1 file changed, 89

Re: [ovs-dev] [PATCH] netns: Add documentation and update NEWS.

On Fri, Apr 13, 2018 at 11:13:21AM -0700, Ben Pfaff wrote: > On Wed, Apr 11, 2018 at 08:50:56PM -0300, Flavio Leitner wrote: > > Create a document to describe the how it works and known > > limitations and update the NEWS accordingly. > > > > Signed-off-by: Flavio Leitner > >

Re: [ovs-dev] [PATCH] checkpatch: add checks for new rst docs

On Tue, Apr 17, 2018 at 06:46:24PM -0300, Flavio Leitner wrote: > When a new rst document is added under Documentation, check if the > new file is added to the proper index.rst and to the automake.mk. > > Signed-off-by: Flavio Leitner Nice. This ought to catch problems even

Re: [ovs-dev] [PATCH v1] ovs-ofctl: Fixed the "snoop" command of ovs-ofctl

On Tue, Apr 17, 2018 at 01:26:51PM -0700, Ashish Varma wrote: > In case where "use_names" is set (e.g. in an interactive session) to show > the port and table names when ovs-ofctl is run with snoop command, > ovs-ofctl would get stuck in an endless loop inside "table_iterator_next" > function's

Re: [ovs-dev] [PATCH v2] Add multi-column index support for the Python IDL

On Thu, Apr 12, 2018 at 07:24:27PM -0500, twil...@redhat.com wrote: > From: Terry Wilson > > This adds multi-column index support for the Python IDL that is > similar to the feature in the C IDL. Since it adds sortedcontainers > as a dependency and some distros don't yet

[ovs-dev] [PATCH v2] ovs-ofctl: Fixed the "snoop" command of ovs-ofctl

In normal ovs-ofctl commands (e.g. add-flow), ovs-ofctl connects to ovs-vswitchd process on “/.mgmt” unix socket. In an output that contains a port or table, port name or table name can be displayed, instead of their numbers, if the user turns on this feature. (by -—names option)

Re: [ovs-dev] raft ovsdb clustering with scale test

Thanks Numan: Will also try to go little deep and see if we get little more hints by increasing the log levels to debug and will wait for inputs from you and Ben further . Hope we can find the culprit soon :) Regards, On Tue, Apr 17, 2018 at 12:13 AM, Numan Siddique

[ovs-dev] [PATCH] ofproto-dpif-xlate: makes OVS native tunneling honor tunnel-specified source addresses

From: wenxu It makes OVS native tunneling honor tunnel-specified source addresses, in the same way that Linux kernel tunneling honors them. This patch made valid tun_src specified by flow-action can be used for tunnel_src of packet. add a "local" property for a route entry and

[ovs-dev] [PATCH v4] ofproto-dpif-xlate: makes OVS native tunneling honor tunnel-specified source addresses

From: wenxu It makes OVS native tunneling honor tunnel-specified source addresses, in the same way that Linux kernel tunneling honors them. This patch made valid tun_src specified by flow-action can be used for tunnel_src of packet. add a "local" property for a route entry and