Currently mempool name size limited to 25 characters by
RTE_MEMPOOL_NAMESIZE. netdev-dpdk tries to create mempool with the
following name pattern: "ovs_%{hash}_%{socket}_%{mtu}_%{n_mbuf}".
We have 3 chars for "ovs" + 4 chars for delimiters + 8 chars for
hash (because it's the 32 bit integer printe
New appctl 'netdev-dpdk/get-mempool-info' implemented to get result
of 'rte_mempool_list_dump()' function if no arguments passed and
'rte_mempool_dump()' if DPDK netdev passed as argument.
Could be used for debugging mbuf leaks and other mempool related
issues. Most useful in pair with `grep -v "c
Signed-off-by: Ilya Maximets
Acked-by: Antonio Fischetti
---
NEWS| 2 ++
lib/automake.mk | 1 +
lib/netdev-dpdk-unixctl.man | 9 +
manpages.mk | 2 ++
vswitchd/ovs-vswitchd.8.in | 1 +
5 files changed, 15 insertions(+)
create mode 100
This series implemented on top of my previous patch-set:
* [PATCH v2 0/4] netdev-dpdk: mempool management: Leaks & Refactoring.
https://mail.openvswitch.org/pipermail/ovs-dev/2017-November/340657.html
I can rebase it on top of current master easily if needed.
First 2 patches are independent f
On 09.11.2017 17:02, Flavio Leitner wrote:
>
> Hi Ilya,
>
> This patch is doing two things. If we need to revert the
> mempool stuff, it will impact on everything on top of the
> documentation refactoring.
>
> I think the refactoring looks easier for Ian to get in.
>
> I could ack just the ref
Adding a OVS configuration option to whitelist DPDK physical ports. By default
running multiple instances of DPDK on a single platform cannot use physical
ports at the same time even though they are distinct.
The eal init scans all the ports that are bound to DPDK and initialize the
drivers accord
DPDK allocate memory regions at the time of vswitchd init. To run multiple
primary instance of DPDK including OVS on a single platform, the memory map
regions in the filesystem should be distinct.
The new configuration option let user to enable the memory isolation in need.
By default, OVS uses de
The current OVS-DPDK implementation doesnt allow users to run another DPDK
application simultaneously on the same platform.
To avoid this limitation, the patch series offers two configuration options
to isolate the OVS-DPDK process completely on a platform.
1) The configuration option is added to
En línea y en Vivo / Para todo su Equipo con una sola Conexión
Gastos de Viaje, Viáticos y su Régimen Fiscal
17 de noviembre - Online en Vivo - 10:00 a 13:00 y de 15:00 a 18:00 Hrs
Asista a esta completa capacitación y aprenda cuáles son los requisitos
fiscales que deben cumplirse para que los
Looks good by me!
On Thu, Nov 9, 2017 at 4:03 PM Ben Pfaff wrote:
> This is adapted from a talk I gave at OpenStack Summit Sydney on Nov. 6.
>
> Signed-off-by: Ben Pfaff
>
Acked-by: Mark Michelson
> ---
> v1->v2: Replace overview of OVN with reference to ovn-architecture(7).
> (Thanks Mark!
On Fri, Nov 10, 2017 at 06:02:17AM +0900, Gregory Rose wrote:
>
> On 11/9/2017 9:34 PM, Ilya Maximets wrote:
> >Since 57eebbb4c315, the caller must make sure that 'netdev' supports
> >sending. This mentioned at the start of the comment.
> >
> >Fixes: 57eebbb4c315 ("dpif-netdev: Don't try to output
Oops, this is v3, not v2, sorry about that.
On Thu, Nov 09, 2017 at 02:02:29PM -0800, Ben Pfaff wrote:
> This is adapted from a talk I gave at OpenStack Summit Sydney on Nov. 6.
>
> Signed-off-by: Ben Pfaff
> ---
> v1->v2: Replace overview of OVN with reference to ovn-architecture(7).
> (Thank
On Wed, Nov 08, 2017 at 09:44:53PM +, Mark Michelson wrote:
> Hi Ben, I gave this another read and found a couple of small issues. I
> think once those are cleared up, I'll be ready to ack this.
>
> On Tue, Nov 7, 2017 at 8:50 PM Ben Pfaff wrote:
>
> > This is adapted from a talk I gave at O
This is adapted from a talk I gave at OpenStack Summit Sydney on Nov. 6.
Signed-off-by: Ben Pfaff
---
v1->v2: Replace overview of OVN with reference to ovn-architecture(7).
(Thanks Mark!)
v2->v3: Additional improvements from Mark Michelson.
Documentation/automake.mk | 1 +
Docum
Actualice sus conocimientos en materia fiscal y cumpla con las disposiciones
del SAT
CFDI de Nóminas
17 de noviembre - Mtro. David Lozada Martínez9am-8pm
La Reforma Fiscal del año 2014 trajo consigo la modificación del artículo 99 en
su fracción III de la Ley del Impuesto sobre la Renta, señala
Hallo, ein SPÄTERER KUNDE, DER DEN GLEICHEN LETZTEN NAMEN MIT IHNEN TEILT,
starb Intestate mit einem nicht beanspruchten Vermögenswert. Wir möchten Sie
für den Anspruch präsentieren.Antwort für Details
___
dev mailing list
d...@openvswitch.org
https://
On 11/9/2017 9:34 PM, Ilya Maximets wrote:
Since 57eebbb4c315, the caller must make sure that 'netdev' supports
sending. This mentioned at the start of the comment.
Fixes: 57eebbb4c315 ("dpif-netdev: Don't try to output on a device without
txqs.")
Signed-off-by: Ilya Maximets
---
lib/netdev
When the netdev is in another namespace and the operation doesn't
support network namespaces, return the correct error.
Signed-off-by: Flavio Leitner
---
lib/netdev-linux.c | 134 +++--
1 file changed, 120 insertions(+), 14 deletions(-)
diff --git
Signed-off-by: Flavio Leitner
---
utilities/nlmon.c | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/utilities/nlmon.c b/utilities/nlmon.c
index d38a70b6f..8d9d20f97 100644
--- a/utilities/nlmon.c
+++ b/utilities/nlmon.c
@@ -41,6 +41,7 @@ main(int argc OVS_UNUSED, char
Internal ports may be moved to another network namespace
and when that happens, the vswitch stops receiving netlink
notifications.
This patch enables the vswitch to listen to all network
namespaces that have a nsid assigned into the network
namespace where the socket has been opened.
It requires
The ioctl interface doesn't support network namespaces, so
try updating the netdev using netlink message instead.
To provide backwards compatibility, fall back to the previous
method if netlink isn't supported or fails.
Signed-off-by: Flavio Leitner
---
lib/netdev-linux.c | 107
Recent kernels provide the network namespace ID of a port,
so use that to discover where the port currently is.
Signed-off-by: Flavio Leitner
---
datapath/linux/compat/include/linux/openvswitch.h | 2 ++
lib/dpif-netlink.c| 6 ++
lib/dpif-netlink.h
A network device in another network namespace could have the
same name, so once the socket starts listening to other network
namespaces, it is necessary to confirm the netns id.
Signed-off-by: Flavio Leitner
---
lib/netdev-linux.c | 50 +++---
1 file c
A port might be already in another netns, so initialize it
as invalid to force a state update.
Signed-off-by: Flavio Leitner
---
lib/netdev-linux.c | 4
1 file changed, 4 insertions(+)
diff --git a/lib/netdev-linux.c b/lib/netdev-linux.c
index 184822816..c31334ce1 100644
--- a/lib/netdev-l
The netlink notification's ancillary data contains the network
namespace id (netnsid) needed to identify the device correctly.
(ifindex and netnsid).
Signed-off-by: Flavio Leitner
---
ChangeLog:
* V2
- report and close unexpected file descriptors.
configure.ac | 3 +-
lib/automa
Today Open vSwitch doesn't know about network namespaces (netns), but
users are moving internal ports to other namespaces. Although packets
are still flowing, the daemon fails to find out basic port information,
like if it is UP or DOWN, for instance.
This patchset rely on a new kernel vport API
I feel much better about this approach.
On Wed, Nov 8, 2017 at 3:00 AM wrote:
> From: Numan Siddique
>
> Presently, logrotate script, searches for the pid files in
> /var/log/openvswitch
> and passes the pid file name (without .pid) as target to ovs-appctl. This
> approach
> doesn't work for OV
Greetings in the name of the lord.Sorry to say if i intruded into
your privacy, l'm Mrs Maria Davidson, a born again christian,
also .God Fearing Woman, With due respect to you my dear in
Christ. Am here for a message from the Lord to you which will
change the life of people round you. Am hopel
Aaron Conole writes:
> Hi Bhanu,
>
> "Bodireddy, Bhanuprakash" writes:
>
>> Hi,
>>
>>
>>
>> ovs-tcpdump throws the below error when trying to capture packets on one of
>> the
>> vhostuserports.
>>
>>
>>
>> $ ovs-tcpdump -i dpdkvhostuser0
>>
>>ERROR: Please create an interface called `mi
On Thu, Nov 9, 2017 at 7:29 PM, Colin King wrote:
> From: Colin Ian King
>
> upcall may be assigned a NULL pointer as genlmsg_put can potentially
> return a NULL. Add a null check to avoid a null pointer dereference
> on upcall.
>
> Detected by CoverityScan, CID#728404 ("Dereference null return
Hi Ilya,
This patch is doing two things. If we need to revert the
mempool stuff, it will impact on everything on top of the
documentation refactoring.
I think the refactoring looks easier for Ian to get in.
I could ack just the refactoring because I haven't reviewed
the mempool change.
fbl
From: Colin Ian King
upcall may be assigned a NULL pointer as genlmsg_put can potentially
return a NULL. Add a null check to avoid a null pointer dereference
on upcall.
Detected by CoverityScan, CID#728404 ("Dereference null return value")
Fixes: commit ccb1352e76cf ("net: Add Open vSwitch ker
Since 57eebbb4c315, the caller must make sure that 'netdev' supports
sending. This mentioned at the start of the comment.
Fixes: 57eebbb4c315 ("dpif-netdev: Don't try to output on a device without
txqs.")
Signed-off-by: Ilya Maximets
---
lib/netdev.c | 5 +
1 file changed, 1 insertion(+), 4
Adding the break statement for CLONE action case.
Signed-off-by: Vishal Deep Ajmera
---
lib/odp-execute.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/odp-execute.c b/lib/odp-execute.c
index 3011479..2d20cd5 100644
--- a/lib/odp-execute.c
+++ b/lib/odp-execute.c
@@ -800,6 +800,7 @@ odp_
Hi all,
I'm using ovs-dpdk with vhost-user port and 10 VM started by qemu, topology
is:
VM1 ~ VM10
| |
-OVS
|
dpdk-bond
the start command of ovs-dpdk is:
root 8969 200 0.1 107748696 231284 ?S ovs-vswitchd --dpdk -c 0x40004 -n 4 --socket-mem 10240 --proc
35 matches
Mail list logo