Re: [ovs-dev] [PATCH v7 09/16] hmap: Use struct for hmap_at_position().

> >Hi Mark, > >On 14/04/2016 05:36, "Kavanagh, Mark B" wrote: > >>Hi Daniele, >> >>One minor comment inline. >> >>Cheers, >>Mark >> >>> >>>The interface will be more similar to the cm

Re: [ovs-dev] [PATCH v7 16/16] netdev-dpdk: Use ->reconfigure() call to change rx/tx queues.

> > > >On 14/04/2016 05:37, "Kavanagh, Mark B" wrote: > >>Hi Daniele, >> >>One comment inline. >> >>Thanks, >>Mark >> >>> >>>This introduces in dpif-netdev and netdev-dpdk the first use for the >>>newly

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

Hi Przemek, A few review comments inline. Also, the patch/commit name suggests that sFlow support is only added for vhost-user ports, but it's also added for dpdk_eth ports, right? Cheers, Mark > >This patch adds sFlow support for DPDK vHost-user interfaces by assigning >ifindex value. Values

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

ould I change the subject before >resubmitting the >patch with changes suggested by you to a more generic one, for instance >"netdev-dpdk: add >sflow support for dpdk ports"? > >Thanks, >Przemek > >-Original Message- >From: Kavanagh, Mark B >Sent:

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

Hi Przemek, Apologies for the churn, but some additional points occurred to me - please refer to comments in netdev_dpdk_get_ifindex. Thanks, Mark > >This patch adds sFlow support for DPDK vHost-user interfaces by assigning >ifindex value. Values of ifindexes for vHost-user interfaces start wit

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

Hi Przemek, Some additional comments/queries inline. Thanks again, Mark > >This patch adds sFlow support for DPDK vHost-user interfaces by assigning >ifindex value. Values of ifindexes for vHost-user interfaces start with 2000 >to avoid overlapping with kernel datapath interfaces. > >Patch also

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

> >On Thu, May 05, 2016 at 12:18:52PM +, Kavanagh, Mark B wrote: >> >+if ((ret = netdev_dpdk_lookup_vhost_id(dev)) >= 0) { >> >+ifindex = VHOST_ID_TO_IFINDEX(ret); >> >+} else { >> >+ifindex = 0; >>

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

> >Hi Mark, > >Replies inline prefixed with [PL]. > >Thanks, >Przemek > >-Original Message----- >From: Kavanagh, Mark B >Sent: Thursday, May 5, 2016 2:19 PM >To: Lal, PrzemyslawX ; dev@openvswitch.org >Subject: RE: [PATCH] netdev-dpdk: add sflow sup

Re: [ovs-dev] ovs+dpdk hang? (was: Re: c)

> >>Hi Mark, >> >>I observed the same issue using Ubuntu 16.04 server with 4.4.0-28-generic >>kernel. >> >>Thanks for looking into this. >> >>Charlie >> >>On Tue, Jul 5, 2016 at 5:04 PM, Kavanagh, Mark B >>wrote: >>Hi

Re: [ovs-dev] [PATCH v3] netdev-dpdk: Set pmd thread priority

> Hi Bhanu, Thanks for the patch - some comments inline. Cheers, Mark >Set the DPDK pmd thread scheduling policy to SCHED_RR and static >priority to highest priority value of the policy. This is to deal with >pmd thread starvation case where another cpu hogging process can get >scheduled/affini

Re: [ovs-dev] [PATCH v4] netdev-dpdk: Set pmd thread priority

> >Set the DPDK pmd thread scheduling policy to SCHED_RR and static >priority to highest priority value of the policy. This is to deal with >pmd thread starvation case where another cpu hogging process can get >scheduled/affinitized on to the same core the pmd thread is running >there by significa

Re: [ovs-dev] [PATCH v5] netdev-dpdk: Set pmd thread priority

> >Set the DPDK pmd thread scheduling policy to SCHED_RR and static >priority to highest priority value of the policy. This is to deal with >pmd thread starvation case where another cpu hogging process can get >scheduled/affinitized on to the same core the pmd thread is running >there by significan

Re: [ovs-dev] [ovs-discuss] OVS+DPDK: pci_map_resource(): cannot mmap error

> >Hello, > >i am getting "EAL: pci_map_resource(): cannot mmap(18, 0x7f504000, >0x8, 0x0): Invalid >argument (0x)" when i start ovs-vswitchd. > Hi Kapil, This is a known DPDK issue, which has been resolved in DPDK v16.07. To fix the issue in your setup, you could patch

Re: [ovs-dev] [ovs-dev, 7/7] netdev-dpdk: add support for Jumbo Frames

> >Hi Daniele. Thanks for posting this. Hi Ilya, I actually implemented this patch as part of Daniele's MTU patchset, based on my earlier patch - Daniele mainly rebased it to head of master :) Thanks for your feedback - I've responded inline. Cheers, Mark >I have almost same patch in my local

Re: [ovs-dev] [ovs-dev,V2] netdev-dpdk: fix memory leak

> >Thanks for the report, I didn't realize that the callback could come in the >same thread. > Likewise - thanks for the catch, Ilya. >I sent a patch that I believe should fix the deadlock here: Thanks for resolving the issue, Daniele. > >http://openvswitch.org/pipermail/dev/2016-August/077315

Re: [ovs-dev] netdev-dpdk: Fix deadlock in destroy_device().

> >Minor comment inline. > >Acked-by: Ilya Maximets > Other than the comment mentioned by Ilya, this LGTM also - thanks again for resolving, Daniele. Acked-by: mark.b.kavan...@intel.com >On 05.08.2016 23:57, Daniele Di Proietto wrote: >> netdev_dpdk_vhost_destruct() calls rte_vhost_driver_unre

Re: [ovs-dev] [PATCH 2/2] ovs-appctl: Fix potential crash with timeout argument

> >ovs-appctl can crash with missing timeout argument. > # ovs-appctl --timeout= dpif-netdev/pmd-stats-show > >Fix by using strtol and validating the timeout value. > >Signed-off-by: Bhanuprakash Bodireddy >--- > utilities/ovs-appctl.c | 9 - > 1 file changed, 8 insertions(+), 1 deletion(-

Re: [ovs-dev] [PATCH 7/7] netdev-dpdk: add support for Jumbo Frames

On 08.08.2016 11:32, Ilya Maximets wrote: > On 05.08.2016 17:34, 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 to each mbuf >> to store frame data is increased to a value gre

Re: [ovs-dev] [PATCH V3 7/7] netdev-dpdk: add support for Jumbo Frames

>On 08.08.2016 18:50, 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 to each mbuf >> to store frame data is increased to a value greater than 1518B >> (typical Ethernet maximu

Re: [ovs-dev] [PATCH V5 7/7] netdev-dpdk: add support for Jumbo Frames

>Few minor comments inline. Thanks Ilya - responses inline. > >On 09.08.2016 15:03, 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 to each mbuf >> to store frame data is incr

Re: [ovs-dev] [PATCH V6 7/7] netdev-dpdk: add support for jumbo frames

> >On 09.08.2016 18:02, 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 to each mbuf >> to store frame data is increased to a value greater than 1518B >> (typical Ethernet maxim

Re: [ovs-dev] [PATCH V7 1/7] ofproto: Consider datapath_type when looking for internal ports.

> >On 09/08/2016 09:08, "Thadeu Lima de Souza Cascardo" >wrote: > >>On Tue, Aug 09, 2016 at 05:01:14PM +0100, Mark Kavanagh wrote: >>> From: Daniele Di Proietto >>> >>> Interfaces with type "internal" end up having a netdev with type "tap" >>> in the dpif-netdev datapath, so a strcmp will fail t

Re: [ovs-dev] [PATCH] netdev-dpdk: add sflow support for vhost-user ports

re your thoughts. > >Thanks, >Przemek > >-Original Message- >From: Kavanagh, Mark B >Sent: Wednesday, May 11, 2016 11:56 AM >To: Lal, PrzemyslawX ; dev@openvswitch.org >Subject: RE: [PATCH] netdev-dpdk: add sflow support for vhost-user ports > >> >>Hi

Re: [ovs-dev] [PATCH RFC 1/1] netdev-dpdk: add jumbo frame support

> >"dev" wrote on 05/12/2016 04:38:21 AM: > >> From: Mark Kavanagh >> To: dev@openvswitch.org, jim.lozanov...@ericsson.com >> Date: 05/12/2016 04:38 AM >> Subject: [ovs-dev] [PATCH RFC 1/1] netdev-dpdk: add jumbo frame support >> Sent by: "dev" >> >> Add support for Jumbo Frames to DPDK-enabled

Re: [ovs-dev] ovs+dpdk hang? (was: Re: c)

> >The logs show that ovs-vswitchd failing to log anything after it >receives the initial configuration from the database. This is probably >a bug in the DPDK portion of OVS. OVS-DPDK folks, have you noticed >anything like this before? Can you take over the investigation? > I can take this Ben

Re: [ovs-dev] ovs+dpdk hang? (was: Re: c)

.5.7-200.fc23.x86_64) > >Charlie > >On Tue, Jul 5, 2016 at 5:37 AM, Kavanagh, Mark B >wrote: > >> >>The logs show that ovs-vswitchd failing to log anything after it >>receives the initial configuration from the database.  This is probably >>a bug in the

Re: [ovs-dev] ovs+dpdk hang? (was: Re: c)

[mailto:charlie...@gmail.com] Sent: Tuesday, July 5, 2016 5:16 PM To: Kavanagh, Mark B Cc: Ben Pfaff ; dev@openvswitch.org; disc...@openvswitch.org Subject: Re: [ovs-dev] ovs+dpdk hang? (was: Re: c) The attachment (Fedora_server_23.sh) was rejected. Renamed it to Fedora_server_23.sh_txt and try it again

Re: [ovs-dev] ovs+dpdk hang? (was: Re: c)

>Hi Mark, > >I observed the same issue using Ubuntu 16.04 server with 4.4.0-28-generic >kernel. > >Thanks for looking into this. > >Charlie > >On Tue, Jul 5, 2016 at 5:04 PM, Kavanagh, Mark B >wrote: >Hi Charlie, > >Thanks for providing the setu

Re: [ovs-dev] [PATCH V5 2/2] netdev-dpdk: add jumbo frame support

> >On Fri, 19 Feb 2016 11:25:12 + >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 increased to a value greater than 1518B >> (typ

Re: [ovs-dev] [PATCH 01/11] dpif-netdev: Proper error handling in do_add_port().

Hi Daniele, One trivial comment below, but other than that, LGTM. Cheers, Mark > >This fixes multiple error path mistakes in do_add_port, none of which >has been a problem in practice so far. This change will make it easier >for a following commit to return in case of error. > >Also, this remove

Re: [ovs-dev] [PATCH 00/11] Reconfigure netdev at runtime

Hi Daniele, Thanks for this patchset! I like the approach you've taken - it really lends itself to maintainability and extensibility, and the implementation that you've provided is quite elegant. I've reviewed the entire patchset, but have only found the need to comment on three of the patche

Re: [ovs-dev] [PATCH 07/11] dpif-netdev: Change pmd thread configuration in dpif_netdev_run().

Hi Daniele, One minor comment below. Thanks, Mark >--- > lib/dpif-netdev.c | 137 ++-- > lib/dpif-provider.h | 3 +- > 2 files changed, 82 insertions(+), 58 deletions(-) > >diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c >index c9c7d16..2c11bd

Re: [ovs-dev] [PATCH 11/11] netdev-dpdk: Use ->reconfigure() call to change rx/tx queues.

Hi Daniele, Some comments inline - thanks again for the patchset! Cheers, Mark > >This introduces in dpif-netdev and netdev-dpdk the first use for the >newly introduce reconfigure netdev call. > >When a request to change the number of queues comes, netdev-dpdk will >remember this and notify the

Re: [ovs-dev] [PATCH 11/11] netdev-dpdk: Use ->reconfigure() call to change rx/tx queues.

Hi Daniele, Comments inline, as usual. Cheers, Mark > >On 01/03/2016 09:12, "Kavanagh, Mark B" wrote: > >>Hi Daniele, >> >>Some comments inline - thanks again for the patchset! >> >>Cheers, >>Mark >> >>> >>>This int

Re: [ovs-dev] [PATCH v2 11/11] netdev-dpdk: Use ->reconfigure() call to change rx/tx queues.

Hi Daniele, Thanks for making the changes to this patch and also 1/11 and 7/11. Apart from one minor comment below, all LGTM. Thanks, Mark > >This introduces in dpif-netdev and netdev-dpdk the first use for the >newly introduce reconfigure netdev call. > >When a request to change the number of

Re: [ovs-dev] [PATCH v5 10/12] dpif-netdev: Fix reconfigure_pmd_threads().

Hi Daniele, One minor comment below. Cheers, Mark > >This commit changes reconfigure_pmd_threads() to interact with the ports >cmap using RCU semantics (the content of the port structure is not >altered while concurrent readers might access it) and to fail more >gracefully in case of a set_multi

Re: [ovs-dev] [PATCH v5 08/12] dpif-netdev: Change pmd thread configuration in dpif_netdev_run().

Hi Daniele, One comment inline. Cheers, Mark >-Original Message- >From: Daniele Di Proietto [mailto:diproiet...@vmware.com] >Sent: Wednesday, March 23, 2016 6:37 PM >To: dev@openvswitch.org >Cc: Ben Pfaff; Kavanagh, Mark B; Ilya Maximets; Daniele Di Proietto >Subjec

Re: [ovs-dev] [PATCH v5 08/12] dpif-netdev: Change pmd thread configuration in dpif_netdev_run().

> >Hi Mark, > >thanks for your comment, I replied inline > >On 24/03/2016 10:17, "Kavanagh, Mark B" wrote: > >>Hi Daniele, >> >>One comment inline. >> >>Cheers, >>Mark >> >>>-Original Message- >>>F

Re: [ovs-dev] [PATCH v6 00/12] Reconfigure netdev at runtime

Hi Daniele, Thanks for addressing my comments; all LGTM now. => Acked-by: Mark Kavanagh BTW, any idea if Ben is planning to review this patchset soon? Thanks, Mark > >Currently we treat set_multiq() calls specially in netdev and dpif-netdev: >every pmd thread must be stopped and set_mult

Re: [ovs-dev] [PATCH v6 00/12] Reconfigure netdev at runtime

Hi Ben - np, thanks for clarifying. > >On Wed, Mar 30, 2016 at 02:41:55PM +, Kavanagh, Mark B wrote: >> BTW, any idea if Ben is planning to review this patchset soon? > >I'm not planning to review the whole series. Daniele asked me to look >at patch 6 so I pr

Re: [ovs-dev] [PATCH v7 11/16] ovs-thread: Do not quiesce in ovs_mutex_cond_wait().

Hi Daniele, One comment inline. Cheers, Mark > >ovs_mutex_cond_wait() is used in many functions in dpif-netdev to >synchronize with pmd threads, but we can't guarantee that the callers do >not hold RCU references, so it's better to avoid quiescing. You'll need to update the following comment in

Re: [ovs-dev] [PATCH v7 16/16] netdev-dpdk: Use ->reconfigure() call to change rx/tx queues.

Hi Daniele, One comment inline. Thanks, Mark > >This introduces in dpif-netdev and netdev-dpdk the first use for the >newly introduce reconfigure netdev call. > >When a request to change the number of queues comes, netdev-dpdk will >remember this and notify the upper layer via >netdev_request_re

Re: [ovs-dev] [PATCH v7 09/16] hmap: Use struct for hmap_at_position().

Hi Daniele, One minor comment inline. Cheers, Mark > >The interface will be more similar to the cmap. > >Signed-off-by: Daniele Di Proietto >--- > lib/hmap.c | 26 -- > lib/hmap.h | 7 ++- > lib/sset.c | 12 +--- > lib/sset.h

Re: [ovs-dev] Cant `make install` ovs

> >Hi, >If you could have a look at this > problem >it would be very helpful. > >or here is the detail. > >I am following this > guide to >install OVS with DPDK. >I man

Re: [ovs-dev] [ovs-discuss] Configuring MTU for dpdk and vhost ports

> >Hi, > >Is there a way to configure MTU for dpdk and vhost ports from its default 1500 >? >I read, "with OVS, Normally the MTU should be changed using operating system >specific >interfaces (e.g. ifconfig).", but as they are dpdk ports, how can i configure >them ? > Hi Kapil, Depending on th

Re: [ovs-dev] [PATCH 2/2] netdev-dpdk: Fix issues introduced by recent style fix.

> >Double word removed. Error message rewritten to avoid breaking of the >user-visible string. > >CC: Mark Kavanagh >Fixes: 58be5c0eecf3 ("netdev-dpdk: Fix coding style") >Signed-off-by: Ilya Maximets >--- > lib/netdev-dpdk.c | 7 --- > 1 file changed, 4 insertions(+), 3 deletions(-) > >diff -

Re: [ovs-dev] [PATCH 1/2] CodingStyle.md: Clarify limit for line length.

> >People in OVS again and again tries to break log messages in parts. >This breaks ability to find this lines in code while debugging. should be 'these lines', or 'this line' Other than that, LGTM - thanks for making this explicit. Acked-by: Mark Kavanagh >It's required to document this t

Re: [ovs-dev] [PATCH 1/2] CodingStyle.md: Clarify limit for line length.

> >On 30.09.2016 11:49, Kavanagh, Mark B wrote: >>> >>> People in OVS again and again tries to break log messages in parts. >>> This breaks ability to find this lines in code while debugging. >> >> should be 'these lines', or 'this l

Re: [ovs-dev] [PATCH] netdev-dpdk: Optimise the initialization of "port_conf"

> >The member "max_rx_pkt_len" of "port_conf" is only used if >jumbo_frame enabled, so it can be initialized with value '0'. > >Signed-off-by: Binbin Xu >--- > lib/netdev-dpdk.c | 4 +--- > 1 file changed, 1 insertion(+), 3 deletions(-) > >diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c >index 3

Re: [ovs-dev] The Patch netdev-dpdk: add TSO support for vhost-user ports

> >Hi, all > > >This patch is very important for users want to improve the performance >of the large packets. > > >But you know, in data center, lots of networks using vxlan, so if it >supports vxlan, then it will be very useful. > > >Would you guys has a plan to support it? I would like to help t

Re: [ovs-dev] [PATCH] netdev-dpdk: Optimise the initialization of "port_conf"

nks Yes, you're right. In one of my earlier implementations 'port_conf' itself was changed, which is why the 'else' statement was included - apologies for the confusion. Thanks, Mark > > >"Kavanagh, Mark B" 写于 2016/10/11 21:46:00: > >> 发件人:

Re: [ovs-dev] The Patch netdev-dpdk: add TSO support for vhost-user ports

t's what it was. Commits have recently been introduced to DPDK that introduce additional flags for tunnel offloading, but I haven't had a chance to test them with in my TSO+VxLAN codebase. Thanks, Mark > > >2016/10/11 22:34, Kavanagh, Mark B : >>> Hi, all >>&

Re: [ovs-dev] The Patch netdev-dpdk: add TSO support for vhost-user ports

len - b->mbuf.data_off)) > b->mbuf.data_len = (uint16_t)(b->mbuf.buf_len - b->mbuf.data_off); Yes, you’re right - I have the same code in my local repo :) > > >Thanks, >Michael > >在 2016/10/11 22:34, Kavanagh, Mark B 写道: >>> Hi, all >>> &

Re: [ovs-dev] The Patch netdev-dpdk: add TSO support for vhost-user ports

port out on it. Thanks, Mark > >Thanks, >Michael > >2016年10月14日，下午5:15，Kavanagh, Mark B ： > >>> >>> >>> Hi, Mark >>> >>> >>> OK, once it's ready， pls let me know and I'm glade to help to test it. >>> >>

Re: [ovs-dev] [ovs-discuss] Vhostports drop issue - related to MTU - Qemu version

> >Hi, > >Issue Setup:  DPDK 16.07 + OVS 2.6.0 + qemu 2.4.1 : PHY-VM-PHY > >I am trying to upgrade from (DPDK16.04 + OVS2.5.9), to (DPDK16.07 + OVS2.6.0) >for jumbo frame >support. After the upgrade, all packets are getting dropped on the vhostuser >port. >The dpdk/vhost user ports used here has

Re: [ovs-dev] [ovs-discuss] Vhostports drop issue - related to MTU - Qemu version

200 vhost-user: start/stop all rings We are currently only sending VRING_ENABLE message for the first ring, that's wrong: we must start/stop them all. Thanks, Mark > >Regards >Kapil. > >On Wed, Oct 26, 2016 at 7:42 PM, Kavanagh, Mark B

Re: [ovs-dev] [PATCH 1/5] lib/dp-packet: init the mbuf to zero when build with DPDK

> >When building with DPDK, and using xmalloc() to get a new packet, >field mbuf of the packet will not be initialized, but it's very important for >DPDK port when copying the data to DPDK mbuf, because if ol_flags >and other info are random values, DPDK driver may hang. > >Signed-off-by: Michael Q

Re: [ovs-dev] [PATCH 2/5] lib/dp-packet: copy additional packet info when do packet copy

> >Currently, when doing packet copy, lots of DPDK mbuf's info >will be missed, like packet type, ol_flags, etc. >Those information is very important for DPDK to do >packets processing. > >Signed-off-by: Michael Qiu >Signed-off-by: Jijiang Liu >--- > lib/dp-packet.c | 3 +++ > lib/netdev-dpdk.c

Re: [ovs-dev] [PATCH 3/5] lib/dp-packet: Fix data_len issue with multi-segments

> This patch didn't apply cleanly either; 'apply -3' resolved the issue, but I recommend rebasing to HEAD of master for next version. Other than that, just some minor cosmetic comments inline. >When a packet is from DPDK source, and it contains >multipule segments, data_len is not equal to the

Re: [ovs-dev] [PATCH 4/5] lib/dp-packet: copy multi-segments data from DPDK mbuf

>When doing packet clone, if packet source is from DPDK driver, >multi-segment must be considered, and copy the segment's >data one by one. > >Signed-off-by: Michael Qiu >Signed-off-by: Jijiang Liu >--- > lib/dp-packet.c | 25 ++--- > 1 file changed, 22 insertions(+), 3 deletio

Re: [ovs-dev] [PATCH 5/5] lib/netdev-dpdk: copy large packet to multi-segment mbufs

> >Currently, one packet is only copied to one segment >in function dpdk_do_tx_copy(), this could be an issue >when a jumboframe comes, especially for multipile segments. Typos - 'jumboframe', 'multipile' This patch doesn't apply cleanly - change 'mbufs' to 'pkts' as previously described to addr

Re: [ovs-dev] [PATCH] dpif-netdev: log port/core affinity

>When using multiple PMDs and numerous ports, a performance gain >may be achieved in some use cases by pinning a PMD/port to a >particular (set of) core(s). > >This patch provides a summary of the switch's port/core affinities >each time that the status of the switch's ports is modified. >Based on

Re: [ovs-dev] [PATCH 3/3] The netdev-dpdk uses the struct ether_addr rather than struct eth_addr internal ovs datatype.

Hi Ben, I pushed a patch that addresses that same issue early last week (September 2 - http://openvswitch.org/pipermail/dev/2015-September/059541.html) - just curious if there was any particular reason why this patch (which seems to have been submitted on September 4th) was selected over mine?

Re: [ovs-dev] [PATCH 3/3] The netdev-dpdk uses the struct ether_addr rather than struct eth_addr internal ovs datatype.

No worries - thanks for the update. >-Original Message- >From: Ben Pfaff [mailto:b...@nicira.com] >Sent: Monday, September 7, 2015 6:04 PM >To: Kavanagh, Mark B >Cc: Pravin Shelar; Daniele di Proietto; d...@openvswitch.com >Subject: Re: [ovs-dev] [PATCH 3/3] The ne

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

>Hi Mark, > >Thanks for the patch! I've not done a very thorough review of this, but >my first-blush comments are inline. Thanks for the review Aaron! Any additional comments are welcome - my initial responses are inline, below. Thanks, Mark > >Mark Kavanagh writes: >> Add support for Jumbo Fr

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

One addendum below, Aaron. > >>Hi Mark, >> >>Thanks for the patch! I've not done a very thorough review of this, but >>my first-blush comments are inline. > >Thanks for the review Aaron! > >Any additional comments are welcome - my initial responses are inline, below. > >Thanks, >Mark > >> >>Mark K

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

Further clarifications below Aaron - please let me know if you have any additional comments. Thanks, Mark > >One addendum below, Aaron. > >> >>>Hi Mark, >>> >>>Thanks for the patch! I've not done a very thorough review of this, but >>>my first-blush comments are inline. >> >>Thanks for the revie

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

> >"Kavanagh, Mark B" writes: >> Further clarifications below Aaron - please let me know if you have >> any additional comments. >> >> Thanks, >> Mark > >Thanks again for this work, Mark! > >>> >>>One addendum below, Aaron

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

>"Kavanagh, Mark B" writes: > >>> >>>"Kavanagh, Mark B" writes: >>>> Further clarifications below Aaron - please let me know if you have >>>> any additional comments. >>>> >>>> Thanks,

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

Hi Zoltan. Thanks for your mail - responses inline below. Cheers, Mark > >Hi, > >I have a related question: is it a possible alternative with the current >codebase to use KNI for configuring the MTU? This would (as far as I'm aware) require the implementation of a new KNI netdev class, along wi

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

> >Hi, > >Some comments below. > Hi Flavio, Thanks for your review! I've responded to your comments inline - I've also addressed the cosmetic changes that you suggested in V3 of the patch. Thanks again, Mark > >On Mon, 1 Feb 2016 10:18:54 + >Mark Kavanagh wrote: > >> Add support for Ju

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

> >Hi Mark, > Hi Daniele, Thanks for the review! Responses inline below. Cheers, 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 ma

Re: [ovs-dev] [PATCH] CONTRIBUTING: Strengthen testing guidelines

> >On Mon, Jan 25, 2016 at 03:15:23PM +, Mark Kavanagh wrote: >> Current testing guidelines do not take account of two distinct >> OVS builds: >>a) 'standard' OVS >>b) OVS with DPDK integration >> >> It is critical that all patches are tested against both builds; if not, >> there is a s

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

> > >On 08/02/2016 03:23, "Kavanagh, Mark B" wrote: > >>> >>>Hi Mark, >>> >> >>Hi Daniele, >> >>Thanks for the review! Responses inline below. >> >>Cheers, >>Mark >> >>>This patch be

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

>> > >> >Hi, >> > >> >Some comments below. >> > >> >> Hi Flavio, >> >> Thanks for your review! >> >> I've responded to your comments inline - I've also addressed the >> cosmetic changes that you suggested in V3 of the patch. >> >> Thanks again, >> Mark >> >> > >> >On Mon, 1 Feb 2016 10:18:54 +

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

> >> >> > >> >> >Hi, >> >> > >> >> >Some comments below. >> >> > >> >> >> >> Hi Flavio, >> >> >> >> Thanks for your review! >> >> >> >> I've responded to your comments inline - I've also addressed the >> >> cosmetic changes that you suggested in V3 of the patch. >> >> >> >> Thanks again, >> >> Mark

Re: [ovs-dev] [PATCH V4 4/4] NEWS: Jumbo Frames supported by DPDK ports

Please disregard these patches, as they were sent erroneously - the proper patchset has since been posted here: http://openvswitch.org/pipermail/dev/2016-February/066191.html. Cheers, Mark > NEWS | 2 ++ > 1 file changed, 2 insertions(+) > >diff --git a/NEWS b/NEWS >index 3e33871..2942ae0 10064

Re: [ovs-dev] [PATCH V4 3/4] INSTALL.DPDK.md: add Jumbo Frames section

Please disregard this patch, as it was sent erroneously - the proper patchset has since been posted here: http://openvswitch.org/pipermail/dev/2016-February/066191.html. Cheers, Mark >--- > INSTALL.DPDK.md | 59 + > 1 file changed, 59 inser

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

> >"Kavanagh, Mark B" writes: > >>> >>>"Kavanagh, Mark B" writes: >>>> Further clarifications below Aaron - please let me know if you have >>>> any additional comments. >>>> >>>> Than

Re: [ovs-dev] [PATCH V4 1/4] netdev-dpdk: clean up mbuf initialization

Hey Daniele, If you're happy with this patch, could you add your 'signed-off-by', seeing as you contributed code towards it? Thanks in advance, Mark >Current mbuf initialization relies on magic numbers and does not >accomodate mbufs of different sizes. > >Resolve this issue by ensuring that mbu

Re: [ovs-dev] [PATCH V2] netdev-dpdk: Add Jumbo Frame Support.

> >"Kavanagh, Mark B" writes: > >>> >>>"Kavanagh, Mark B" writes: >>> >>>>> >>>>>"Kavanagh, Mark B" writes: >>>>>> Further clarifications below Aaron - please let me know if you

Re: [ovs-dev] [PATCH V4 1/4] netdev-dpdk: clean up mbuf initialization

> >Hi Mark, > >Thanks for splitting the clean up, this looks better. >comment below. > > >On Tue, 16 Feb 2016 11:31:48 + >Mark Kavanagh wrote: > >> Current mbuf initialization relies on magic numbers and does not >> accomodate mbufs of different sizes. >> >> Resolve this issue by ensuring that

Re: [ovs-dev] [PATCH V4 3/4] INSTALL.DPDK.md: add Jumbo Frames section

> >On Tue, 16 Feb 2016 11:31:50 + >Mark Kavanagh wrote: > >> Signed-off-by: Mark Kavanagh >> --- >> INSTALL.DPDK.md | 59 >> + >> 1 file changed, 59 insertions(+) >> >> diff --git a/INSTALL.DPDK.md b/INSTALL.DPDK.md >> index 722fb9e..4

Re: [ovs-dev] [PATCH V4 4/4] NEWS: Jumbo Frames supported by DPDK ports

>On Tue, 16 Feb 2016 11:31:51 + >Mark Kavanagh wrote: > >> Signed-off-by: Mark Kavanagh >> --- >> NEWS | 2 ++ >> 1 file changed, 2 insertions(+) >> >> diff --git a/NEWS b/NEWS >> index 3e33871..2942ae0 100644 >> --- a/NEWS >> +++ b/NEWS >> @@ -12,6 +12,8 @@ Post-v2.5.0 >> Old 'other

Re: [ovs-dev] [PATCH V4 2/4] netdev-dpdk: Add Jumbo Frame Support

> >On Tue, 16 Feb 2016 11:31:49 + >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 increased to a value greater than 1518B >> (typ

Re: [ovs-dev] [PATCH RFC] automake: fix rte_memcopy for gcc versions <=4.8.2

>On Tue, Mar 31, 2015 at 11:23:32PM +0100, Mark Kavanagh wrote: >> DPDK 2.0 contains an updated implementation of rte_memcopy, which >> leverages SSE and AVX instrinsics. In versions of GCC <= 4.8.2, it >> has been observed that the relevant instrinsics are not defined in >> gcc headers, resulting

Re: [ovs-dev] [PATCH RFC] automake: fix rte_memcopy for gcc versions <=4.8.2

>On 04/01/15 at 07:45am, Kavanagh, Mark B wrote: >> >> >What's wrong with setting CFLAGS on the "configure" or "make" command >> >line? This is the standard way to do this with Automake and Autoconf. >> > >> >> Sure. How

Re: [ovs-dev] [PATCH RFC] automake: fix rte_memcopy for gcc versions <=4.8.2

>On Thu, Apr 02, 2015 at 04:38:13PM +0000, Kavanagh, Mark B wrote: >> >> >On 04/01/15 at 07:45am, Kavanagh, Mark B wrote: >> >> >> >> >What's wrong with setting CFLAGS on the "configure" or "make" command >&g

Re: [ovs-dev] [PATCH] DPDK: add support for v2.0.0

>Thanks for the patch, I’m looking forward to use new >DPDK 2.0 features! > Hi Daniele - sure, no problem :) >I have some doubts about the required -mssse3 option. >The main point is: does DPDK always requires a CPU >with SSSE3? > >I believe the answer is yes (Please correct me if I’m wrong). >If

Re: [ovs-dev] [PATCH] DPDK: add support for v2.0.0

>-Original Message- >From: Panu Matilainen [mailto:pmati...@redhat.com] >Sent: Thursday, April 9, 2015 8:23 AM >To: Kavanagh, Mark B; dev@openvswitch.org >Subject: Re: [PATCH] DPDK: add support for v2.0.0 > >On 04/08/2015 06:34 PM, Mark Kavanagh wrote: >> Updat

Re: [ovs-dev] [PATCH] DPDK: add support for v2.0.0

>-Original Message- >From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Kavanagh, Mark B >Sent: Wednesday, April 8, 2015 10:26 PM >To: Daniele Di Proietto >Cc: dev@openvswitch.org; Butler, Siobhan A >Subject: Re: [ovs-dev] [PATCH] DPDK: add support for v2.0.0

Re: [ovs-dev] [PATCHv3] DPDK: add support for v2.0.0

Hi all, Just a quick poll: are the resolutions to review comments in this patch acceptable to everyone? If I've missed anything, or are there any additional opens that need to be addressed before it can be merged, just let me know. Thanks in advance, Mark > >Update relevant artifacts to add s

Re: [ovs-dev] [PATCHv3] DPDK: add support for v2.0.0

> >On 04/23/2015 11:58 PM, Kavanagh, Mark B wrote: >> Hi all, >> >> Just a quick poll: are the resolutions to review comments in this patch >> acceptable to >everyone? >> >> If I've missed anything, or are there any additional opens that need

Re: [ovs-dev] [PATCHv3] DPDK: add support for v2.0.0

>On Fri, 24 Apr 2015 10:32:32 + >"Kavanagh, Mark B" wrote: > >> >> > >> >On 04/23/2015 11:58 PM, Kavanagh, Mark B wrote: >> >> Hi all, >> >> >> >> Just a quick poll: are the resolutions to review comments in this

Re: [ovs-dev] [PATCHv3] DPDK: add support for v2.0.0

> >>On Fri, 24 Apr 2015 10:32:32 + >>"Kavanagh, Mark B" wrote: >> >>> >>> > >>> >On 04/23/2015 11:58 PM, Kavanagh, Mark B wrote: >>> >> Hi all, >>> >> >>> >> Just a quick poll: a

Re: [ovs-dev] [PATCHv3] DPDK: add support for v2.0.0

>On Fri, 24 Apr 2015 14:04:05 + >"Kavanagh, Mark B" wrote: > >> > >> >>On Fri, 24 Apr 2015 10:32:32 + >> >>"Kavanagh, Mark B" wrote: >> >> >> >>> >> >>> > >> >>> >

Re: [ovs-dev] [PATCH] travis: Fix clang build for DPDK-2.0.

>-Wno-cast-align is a CFLAG, not a configure option. > >Signed-off-by: Joe Stringer >--- > .travis/build.sh | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > >diff --git a/.travis/build.sh b/.travis/build.sh >index c7796e1..6dfc9fe 100755 >--- a/.travis/build.sh >+++ b/.travis/build.sh >@@

Re: [ovs-dev] [PATCHv2] lib: upgrade to DPDK 1.8

Hi Ben, I don't think so - jsonrpc_run() empties the rpc output queue, freeing the ofpbufs, after their contents are sent to the stream. Thanks, Mark > -Original Message- > From: Ben Pfaff [mailto:b...@nicira.com] > Sent: Friday, February 6, 2015 8:41 PM > To: Kava

Re: [ovs-dev] [PATCHv2] lib: upgrade to DPDK 1.8

nday, February 9, 2015 4:33 PM > To: Kavanagh, Mark B > Cc: dev@openvswitch.org; Rory Sexton > Subject: Re: [ovs-dev] [PATCHv2] lib: upgrade to DPDK 1.8 > > I keep getting a bounce on rory.sex...@intel.com ("550 #5.1.0 Address > rejected."). Is that email address correct

Re: [ovs-dev] [PATCHv2] lib: upgrade to DPDK 1.8

ctions (in particular ofpbuf_resize__), but it's not clear at this time if this is a viable option. Thanks, Mark > -Original Message- > From: Kavanagh, Mark B > Sent: Monday, February 9, 2015 4:15 PM > To: Pravin Shelar > Cc: dev@openvswitch.org; Rory Sexton > Sub

  1   2   >