This seems to be related to netdev-afxdp's batch size bigger than
kernel's xdp batch size.
I created a patch to fix it.
https://patchwork.ozlabs.org/patch/1214397/
Could anyone take a look at this patch?
Thanks,
Yifeng
On Fri, Nov 22, 2019 at 9:52 AM William Tu wrote:
>
> Hi Ilya and Eelco,
>
William reported that there is iperf TCP issue between two afxdp ports:
[ 3] local 10.1.1.2 port 40384 connected with 10.1.1.1 port 5001
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 17.0 MBytes 143 Mbits/sec
[ 3] 1.0- 2.0 sec 9.62 MBytes 80.7 Mbits/sec
[ 3] 2.0- 3.0
On Wed, Dec 18, 2019 at 10:44:21AM +0800, yang_y_yi wrote:
> Hi, William
>
>
> I used OVS DPDK to test it, you shouldn't add tap interface to ovs DPDK
> bridge if you use vdev to add tap, virtio_user is just for it, but that won't
> use this receive function to receive packets.
Right.
I mean
On Fri, Dec 20, 2019 at 01:14:37PM -0800, Ben Pfaff wrote:
> On Fri, Dec 20, 2019 at 09:49:44AM -0800, William Tu wrote:
> > On Thu, Dec 19, 2019 at 08:44:30PM -0800, Ben Pfaff wrote:
> > > On Thu, Dec 19, 2019 at 04:41:25PM -0800, William Tu wrote:
> > > > Currently the performance of sending
Thanks, Numan! Please let me know what I should be monitoring to check for
issues, if any,resulting from this change.
thanks,
-venu
On Friday, December 20, 2019, 11:36:30 AM PST, Numan Siddique
wrote:
On Fri, Dec 20, 2019 at 12:15 AM wrote:
>
> From: venu iyer
>
> If one creates a
On Fri, Dec 20, 2019 at 09:51:08AM -0800, Yi-Hung Wei wrote:
> In connection tracking system, a connection is established if we
> see packets from both directions. However, in userspace datapath's
> conntrack, if we send a connection setup packet in one direction
> twice, it will make the
On Fri, Dec 20, 2019 at 09:49:44AM -0800, William Tu wrote:
> On Thu, Dec 19, 2019 at 08:44:30PM -0800, Ben Pfaff wrote:
> > On Thu, Dec 19, 2019 at 04:41:25PM -0800, William Tu wrote:
> > > Currently the performance of sending packets from userspace
> > > ovs to kernel veth device is pretty bad
On 12/20/2019 11:53 AM, David Ahern wrote:
On 12/20/19 11:14 AM, Gregory Rose wrote:
On 12/19/2019 7:20 PM, Gregory Rose wrote:
Bisecting is hard when you're doing it across 10s of thousands of
Linux revisions but after a few fitsand starts I think it's this
patch:
commit
On Fri, Dec 6, 2019 at 11:29 PM Han Zhou wrote:
>
> A meter/group can be used by multiple logical flows. However, current
> code didn't handle this properly. Each table_info item has a lflow_uuid
> field, which can keep track of only a single lflow.
>
> In most cases this doesn't create problems
On Tue, Dec 03, 2019 at 05:57:20PM -0800, Han Zhou wrote:
> Cluster doesn't work after all nodes restarted after DB compaction,
> unless there is any transaction after DB compaction before the restart.
>
> Error log is like:
> raft|ERR|internal error: deferred vote_request message completed but
On Fri, Dec 6, 2019 at 11:29 PM Han Zhou wrote:
>
> These commands are supposed to print existing items of the tables,
> but they actually print only items that is in existing table but not
> in desired table, which is useless because this would print nothing
> in normal conditions. The patch
On Fri, Dec 6, 2019 at 11:29 PM Han Zhou wrote:
>
> Reuse xxx_clear() function in xxx_destroy() and remove redundant code.
>
> Signed-off-by: Han Zhou
Looks good to me.
Acked-by: Dumitru Ceara
> ---
> lib/extend-table.c | 31 ++-
> 1 file changed, 10
On Fri, Dec 6, 2019 at 11:29 PM Han Zhou wrote:
>
> Remove redundant code.
>
> Signed-off-by: Han Zhou
Looks good to me.
Acked-by: Dumitru Ceara
> ---
> controller/ovn-controller.c | 54
> +++--
> 1 file changed, 13 insertions(+), 41 deletions(-)
>
>
On Thu, Dec 19, 2019 at 04:50:47PM -0800, amgin...@gmail.com wrote:
> From: Aliasgar Ginwala
>
> --with-linux can be made configurable while building containers
> for leveraging kernel modules installed on host.
> KERNEL_VERSION=host should be used in env variable for the same.
>
>
On Fri, Dec 20, 2019 at 01:25:29AM +, Yi Yang (杨�D)-云服务集团 wrote:
> Current ovs matser has included sendmmsg declaration in
> include/sparse/sys/socket.h
I believe you are mistaken.
> int sendmmsg(int, struct mmsghdr *, unsigned int, unsigned int);
>
> I saw "+^L" in your patch.
Yes, OVS
On Fri, Dec 20, 2019 at 06:35:07PM +0100, Timothy Redaelli wrote:
> Since Python 2 support was removed in 1ca0323e7c29 ("Require Python 3 and
> remove support for Python 2."), python3-six is not needed anymore.
>
> Moreover python3-six is not available on RHEL/CentOS7 without using EPEL
> and so
On 12/20/19 11:14 AM, Gregory Rose wrote:
>
> On 12/19/2019 7:20 PM, Gregory Rose wrote:
>>
>> Bisecting is hard when you're doing it across 10s of thousands of
>> Linux revisions but after a few fitsand starts I think it's this
>> patch:
>>
>> commit 9b9a3f20cbe0ba9269cde6fff9f9c69907e150cf
>>
On Fri, Dec 20, 2019 at 12:15 AM wrote:
>
> From: venu iyer
>
> If one creates a port group and a MAC address set, and an
> ACL that prevents packets being output to a port in that Port Group from
> any MAC address in that address set, the outcome is not consistent.
>
> The outcome depends on
On Wed, Dec 18, 2019 at 12:31:06PM -0800, Yi-Hung Wei wrote:
> Currently, the AF_XDP socket (XSK) related memory are allocated by main
> thread in the main thread's NUMA domain. With the patch that detects
> netdev-linux's NUMA node id, the PMD thread of AF_XDP port will be run on
> the AF_XDP
On 12/19/2019 7:20 PM, Gregory Rose wrote:
Bisecting is hard when you're doing it across 10s of thousands of
Linux revisions but after a few fitsand starts I think it's this
patch:
commit 9b9a3f20cbe0ba9269cde6fff9f9c69907e150cf
Author: Masahiro Yamada
Date: Thu Aug 15 01:06:23 2019 +0900
On 12/16/19 2:42 PM, Aaron Conole wrote:
> Can you try the following and see if your scalability issue is
> addressed? I think it could be better integrated, but this is a
> different quick 'n dirty.
your patch reduces the number of threads awakened, but it is still
really high - 43 out of 71
In connection tracking system, a connection is established if we
see packets from both directions. However, in userspace datapath's
conntrack, if we send a connection setup packet in one direction
twice, it will make the connection to be in established state.
This patch fixes the aforementioned
On Thu, Dec 19, 2019 at 08:44:30PM -0800, Ben Pfaff wrote:
> On Thu, Dec 19, 2019 at 04:41:25PM -0800, William Tu wrote:
> > Currently the performance of sending packets from userspace
> > ovs to kernel veth device is pretty bad as reported from YiYang[1].
> > The patch adds AF_PACKET v3, tpacket
On Fri, Dec 20, 2019 at 06:09:08AM +, Yi Yang (杨燚)-云服务集团 wrote:
> Hi, William
>
> What kernel version can support AF_PACKET v3? I can try it with your patch.
Hi Yiyang,
Kernel +4.0 should have v3 support.
I'm also reading this doc:
Since Python 2 support was removed in 1ca0323e7c29 ("Require Python 3 and
remove support for Python 2."), python3-six is not needed anymore.
Moreover python3-six is not available on RHEL/CentOS7 without using EPEL
and so this patch is needed in order to release OVS 2.13 on RHEL7.
Signed-off-by:
This reverts commit 9e334d91b3ea95e2b96f7b3edcb2ba9c3353288a.
This commit is not needed since OVS doesn't use six anymore.
Signed-off-by: Timothy Redaelli
---
Documentation/intro/install/fedora.rst | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git
Since Python 2 support was removed in 1ca0323e7c29 ("Require Python 3 and
remove support for Python 2."), python3-six is not needed anymore.
Moreover python3-six is not available on RHEL/CentOS7 without using EPEL
and so this patch is needed in order to release OVS 2.13 on RHEL7.
Changes in v2:
Bleep bloop. Greetings Timothy Redaelli, I am a robot and I have tried out
your patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
ERROR: Author Timothy Redaelli needs to sign off.
Lines checked: 34, Warnings: 0, Errors:
Since Python 2 support was removed in 1ca0323e7c29 ("Require Python 3 and
remove support for Python 2."), python3-six is not needed anymore.
Moveover python3-six is not available on RHEL/CentOS7 without using EPEL
and so this patch is needed in order to release OVS 2.13 on RHEL7.
Signed-off-by:
This reverts commit 9e334d91b3ea95e2b96f7b3edcb2ba9c3353288a.
This commit is not needed since OVS doesn't use six anymore.
---
Documentation/intro/install/fedora.rst | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/Documentation/intro/install/fedora.rst
Since Python 2 support was removed in 1ca0323e7c29 ("Require Python 3 and
remove support for Python 2."), python3-six is not needed anymore.
Moveover python3-six is not available on RHEL/CentOS7 without using EPEL
and so this patch is needed in order to release OVS 2.13 on RHEL7.
Tested locally
Add an ovs-appctl command to iterate through the dpcls
and for each subtable output the miniflow bits for any
existing table.
$ ovs-appctl dpif-netdev/subtable-show
pmd thread numa_id 0
dpcls port 2:
subtable:
unit_0: 2 (0x5)
unit_1: 1 (0x1)
pmd thread numa_id 1
dpcls port 3:
Hi,
I don't know whether you are the right person, so I am hoping you can point me
in the right direction.
I see on the internet that you have some open positions within your company,
and I have some candidates that may interest you.
It doesn't cost anything to look at resumes, so please
On Fri, Dec 20, 2019 at 1:39 PM taoyunxi...@cmss.chinamobile.com
wrote:
>
> Hi, Could you review this patch。It is an important QoS feature for plugin of
> OVN.
Hi Taoyunxiang,
I am sorry for the delay. Looks like I missed these patches.
The patch doesn't apply to the present master. Can you
On Fri, Dec 20, 2019 at 12:28 AM Ben Pfaff wrote:
>
> On Fri, Dec 13, 2019 at 03:15:36PM -0500, num...@ovn.org wrote:
> > From: Numan Siddique
> >
> > When ovsdb-server is in backup mode and connects to the active
> > ovsdb-server for replication, and if takes more than 5 seconds to
> > get the
From: Numan Siddique
When ovsdb-server is in backup mode and connects to the active
ovsdb-server for replication, and if takes more than 5 seconds to
get the dump of the whole database, it will drop the connection
soon after as the default probe interval is 5 seconds. This
results in a snowball
On Tue, Dec 17, 2019 at 5:30 PM Nikolay Aleksandrov
wrote:
>
> On 17/12/2019 17:51, Matteo Croce wrote:
> > New action to decrement TTL instead of setting it to a fixed value.
> > This action will decrement the TTL and, in case of expired TTL, drop it
> > or execute an action passed via a nested
Introduce logical flows in ovn router pipeline in order to parse dhcpv6
advertise/reply from IPv6 prefix delegation router.
Do not overwrite ipv6_ra_pd_list info in options column of SB port_binding
table written by ovn-controller
Signed-off-by: Lorenzo Bianconi
---
northd/ovn-northd.c | 69
Introduce IPv6 Prefix delegation state machine according to RFC 3633
https://tools.ietf.org/html/rfc3633.
Add handle_dhcpv6_reply controller action to parse advertise/reply from
IPv6 delegation server.
Introduce logical flows in ovn router pipeline in order to parse dhcpv6
advertise/reply from
Dobry den,
Do dnesniho dne jste nesplnili Vasi zakonnou povinnost a nevratili mi
zaplacenou financni castku, kterou jste byli povinni mi vratit.
V opacnem pripade budu nucen obratit se se svym narokem na soud s navrhem na
vydani platebniho rozkazu. Verim vsak, ze to nebude nutne.
Stahnout
Hi, Could you review this patch。It is an important QoS feature for plugin of
OVN.
Thanks,
Yun
From: taoyunxi...@cmss.chinamobile.com
Date: 2019-11-26 15:57
To: ovs-dev
Subject: [ovs-dev,ovn,1/2] ovn-nbctl.c: Add "name" column of QoS table.
Add "name" column of QoS table
Add "name"
Hi, Could you review this patch。It is an important QoS feature for plugin of
OVN.
Thanks,
Yun
From: taoyunxi...@cmss.chinamobile.com
Date: 2019-11-26 15:57
To: ovs-dev
Subject: [ovs-dev,ovn,2/2] ovn-nbctl.c: Add a way to delete QoS by its name or
uuid.
Add a way to delete QoS by its name
42 matches
Mail list logo