If RTE_LIBRTE_AF_XDP is enabled in the DPDK build, OVS must link
the libbpf library, otherwise build failures will occur.
Signed-off-by: Ciara Loftus
---
acinclude.m4 | 4
1 file changed, 4 insertions(+)
diff --git a/acinclude.m4 b/acinclude.m4
index 6f284eaf9..366324778 100644
If RTE_LIBRTE_PMD_PCAP is enabled in the DPDK build, OVS must link
the pcap library, otherwise build failures will occur.
Signed-off-by: Ciara Loftus
---
acinclude.m4 | 4
1 file changed, 4 insertions(+)
diff --git a/acinclude.m4 b/acinclude.m4
index 1212a463e..6f284eaf9 100644
for performance tuning when
testing TSO with the tool iperf.
Fixes: 29cf9c1b3b9c ("userspace: Add TCP Segmentation Offload support")
Signed-off-by: Ciara Loftus
Acked-by: Flavio Leitner
---
v3:
- Added Fixes tag
- Removed unwanted manpages.mk change
v2:
- rebased to master
- changed p
for performance tuning when
testing TSO with the tool iperf.
Signed-off-by: Ciara Loftus
Acked-by: Flavio Leitner
---
v2:
- rebased to master
- changed patch links from net-next tree to patchwork
---
Documentation/topics/userspace-tso.rst | 27 ++
manpages.mk
is supported by OVS.
Also, document best known methods for performance tuning when
testing TSO with the tool iperf.
Signed-off-by: Ciara Loftus
---
Documentation/topics/dpdk/tso.rst | 27 +++
1 file changed, 27 insertions(+)
diff --git a/Documentation/topics/dpdk/tso.rst
b
' and 'dpdkr' ports, but now applies to all
DPDK port types including vHost User.
Performance (pps) of the different topologies p2p, pvp, pvvp and vv has
been measured to remain within a +/- 5% margin of existing performance.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
To function cor
-by: Ciara Loftus <ciara.lof...@intel.com>
Acked-by: Ilya Maximets <i.maxim...@samsung.com>
---
v13:
* Rebase
* Update commit message with recent performance measurement
Documentation/intro/install/dpdk.rst | 2 +
Documentation/topics/dpdk/vhost-user.rst | 73 ++
-by: Ciara Loftus <ciara.lof...@intel.com>
---
v11:
* Move assignment of zc_enabled
Documentation/intro/install/dpdk.rst | 2 +
Documentation/topics/dpdk/vhost-user.rst | 73
NEWS | 1 +
lib/netdev-
-by: Ciara Loftus <ciara.lof...@intel.com>
---
v11:
* Rebase
* Fix mutex
Documentation/intro/install/dpdk.rst | 2 +
Documentation/topics/dpdk/vhost-user.rst | 73
NEWS | 1 +
lib/netdev-dpdk.c
-by: Ciara Loftus <ciara.lof...@intel.com>
---
v10:
* Rebase
* Fix vhost flags
Documentation/intro/install/dpdk.rst | 2 +
Documentation/topics/dpdk/vhost-user.rst | 73
NEWS | 1 +
lib/netdev-dpdk.c
-by: Ciara Loftus <ciara.lof...@intel.com>
---
v9:
* Rebase
* Fix docs issue
* Move variable asignment inside mutex
* Reset dq-zero-copy value if vhost_driver_register fails
Documentation/intro/install/dpdk.rst | 2 +
Documentation/topics/dpdk/vhost-user.rs
-by: Ciara Loftus <ciara.lof...@intel.com>
---
v8:
* Disallow configurability after vHost device has been registered &
update docs accordingly.
* Give performance datapoint in commit message.
Documentation/intro/install/dpdk.rst | 2 +
Documentation/topics/dpdk/vhost-use
: The sum of the tx descriptors of all 'dpdk' ports the VM will send
to should not exceed 128. Due to this requirement, the feature is
considered 'experimental'.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v7:
* Remove support for zc for dpdkvhostuser ports & patch 1 in the series
descriptors on that 'dpdk' port must be
set to a smaller value. 128 is recommended. This can be achieved like
so:
ovs-vsctl set Interface dpdkport options:n_txq_desc=128
Due to the requirement above, the feature is considered 'experimental'.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.
e new feature, so when the VM
starts again it doesn't pick up the new device as it hasn't been
re-registered in time.
Ciara Loftus (2):
netdev-dpdk: Helper function for vHost device setup
netdev-dpdk: Enable optional dequeue zero copy for vHost User
Documentation/howto/dpdk.rst |
descriptors on that 'dpdk' port must be
set to a smaller value. 128 is recommended. This can be achieved like
so:
ovs-vsctl set Interface dpdkport options:n_txq_desc=128
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v5:
* Rebase
* Update docs with warning of potential packe
dpdkvhostuser and dpdkvhostuserclient ports share a lot of the same
setup & configuration code. Create a common function they can share in
order to remove some duplication of code.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-dp
ough to allow a vhost
device unregister & re-register with the new feature, so when the VM
starts again it doesn't pick up the new device as it hasn't been
re-registered in time.
Ciara Loftus (2):
netdev-dpdk: Helper function for vHost device setup
netdev-dpdk: Enable optional
descriptors on that 'dpdk' port must be
set to a smaller value. 128 is recommended. This can be achieved like
so:
ovs-vsctl set Interface dpdkport options:n_txq_desc=128
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v4:
* Rebase
Documentation/howto/dpdk.rst
dpdkvhostuser and dpdkvhostuserclient ports share a lot of the same
setup & configuration code. Create a common function they can share in
order to remove some duplication of code.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-dp
han a reboot. The reason why this doesn't work is probably
because the total downtime during reboot isn't enough to allow a vhost
device unregister & re-register with the new feature, so when the VM
starts again it doesn't pick up the new device as it hasn't been
re-registered in time.
Cia
-devargs option:
ovs-vsctl set Interface myport options:dpdk-devargs=:06:00.0,X
Where X is an unsigned integer representing one of multiple ports
associated with the PCI address provided.
This patch has not been tested.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v2:
* Si
descriptors on that 'dpdk' port must be
set to a smaller value. 128 is recommended. This can be achieved like
so:
ovs-vsctl set Interface dpdkport options:n_txq_desc=128
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v3:
* Documentation updates:
** Style fixes
** Elaborate on ex
ature, so when the VM
starts again it doesn't pick up the new device as it hasn't been
re-registered in time.
Ciara Loftus (2):
netdev-dpdk: Helper function for vHost device setup
netdev-dpdk: Enable optional dequeue zero copy for vHost User
Documentation/howto/dpdk.rst | 33
dpdkvhostuser and dpdkvhostuserclient ports share a lot of the same
setup & configuration code. Create a common function they can share in
order to remove some duplication of code.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-dp
descriptors on that 'dpdk' port must be
set to a smaller value. 128 is recommended. This can be achieved like
so:
ovs-vsctl set Interface dpdkport options:n_txq_desc=128
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
Documentation/howto/dpdk.rst
dpdkvhostuser and dpdkvhostuserclient ports share a lot of the same
setup & configuration code. Create a common function they can share in
order to remove some duplication of code.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-dp
egister with the new feature, so when the VM
starts again it doesn't pick up the new device as it hasn't been
re-registered in time.
Ciara Loftus (2):
netdev-dpdk: Helper function for vHost device setup
netdev-dpdk: Enable optional dequeue zero copy for vHost User
Documentation/howt
-devargs option:
ovs-vsctl set Interface myport options:dpdk-devargs=:06:00.0,X
Where X is an unsigned integer representing one of multiple ports
associated with the PCI address provided.
This patch has not been tested.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-
stpmd to source (txonly) and sink in the NIC
1C1Q 64B packets: 6.81Mpps -> 7.76Mpps = 13.9% improvement
phy -> vhost -> phy
No improvement measured
Ciara Loftus (2):
netdev-dpdk: Helper function for vHost device setup
netdev-dpdk: Enable optional dequeue zero copy for vHost User
D
the behavior of the
emc_insert_inv_prob setting for high-throughput (large bursts)
single-flow cases.
Fixes: 4c30b24602c3 ("dpif-netdev: Conditional EMC insert")
Reported-by: Kevin Traynor <ktray...@redhat.com>
Acked-by: Darrell Ball <dlu...@gmail.com>
Signed-off-by: Ciara Loft
the behavior of the
emc_insert_inv_prob setting for high-throughput (large bursts)
single-flow cases.
Fixes: 4c30b24602c3 ("dpif-netdev: Conditional EMC insert")
Reported-by: Kevin Traynor <ktray...@redhat.com>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v2:
- Remove
The vHost PMD allows vHost User ports to be controlled by the DPDK
librte_ether API, like 'dpdk' ports and 'dpdkr' ports. This commit
integrates this PMD into OVS and removes direct calls to the
librte_vhost DPDK library.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/
This patch is to be applied on top of the DPDK 17.05 patch:
https://mail.openvswitch.org/pipermail/ovs-dev/2017-May/333105.html
Previous:
https://mail.openvswitch.org/pipermail/ovs-dev/2016-November/325492.html
Ciara Loftus (1):
netdev-dpdk: Add vHost User PMD
lib/dpdk.c| 10 +
lib
Instead of counting all polling cycles as processing cycles, only count
the cycles where packets were received from the polling.
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Co-authored-by: Georg Schmuecking <
Instead of counting all polling cycles as processing cycles, only count
the cycles where packets were received from the polling.
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Co-authored-by: Georg Schmuecking <
option. This value sets the average
probability of insertion to 1/emc-insert-inv-prob.
For example the following command changes the insertion probability to
(on average) 1 in every 20 packets ie. 1/20 ie. 5%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-inv-prob=20
Signed-off-by: Ciara
option. This value sets the average
probability of insertion to 1/emc-insert-inv-prob.
For example the following command changes the insertion proability to
(on average) 1 in every 20 packets ie. 1/20 ie. 5%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-inv-prob=20
Signed-off-by: Ciara
option. For example the following command
increases the insertion probability to 10%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-prob=10
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Co-authored-by: Georg
option. For example the following command
increases the insertion probability to 10%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-prob=10
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Co-authored-by: Georg
option. For example the following command
increases the insertion probability to 10%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-prob=10
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Co-authored-by: Georg
option. For example the following command
increases the insertion probability to 1/10 ie. 10%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-prob=10
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Co-author
option. For example the following command
increases the insertion probability to 1/10 ie. 10%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-prob=10
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Co-author
option. For example the following command
increases the insertion probability to 1/10 ie. 10%.
ovs-vsctl set Open_vSwitch . other_config:emc-insert-prob=10
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Co-author
Instead of counting all polling cycles as processing cycles, only count
the cycles where packets were received from the polling.
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Co-authored-by: Ciara Loftu
This patch is part of the OVS-DPDK performance optimizations presented
on the OVS fall conference
(http://openvswitch.org/support/ovscon2016/8/1400-gray.pdf)
The Exact Match Cache does not perform well in use cases with a high
numbers of parallel packet flows. When the flow count exceeds 8k,
'pmd-stats-show' now reports the number of entries in the EMC as well as
the percentage full it is.
Eg. For 2048 entries the EMC is reported as 25% full as the maximum
capacity is 8192 entries.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Georg Schmuecking <georg
Instead of counting all polling cycles as processing cycles, only count
the cycles where packets were received from the polling.
Signed-off-by: Georg Schmuecking <georg.schmueck...@ericsson.com>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Co-authored-by: Ciara Loftu
now must specify the relevant PCI address
as input instead of the port name.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
Co-authored-by: Daniele Di Proietto <diproiet...@vmware.com>
Signed-off-by: Kevin Traynor &l
-by: Ciara Loftus <ciara.lof...@intel.com>
---
Changelog:
* Updated process_vdevargs to work with Daniele's incremental in the
previous patch.
* Allow vdev detach
* Update docs to show af_packet example
* Fix af_packet docs example
* Fix style issues in docs
Documentation/howto/dpdk.rs
quez B <mauricio.vasquezber...@studenti.polito.it>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Co-authored-by: Ciara Loftus <ciara.lof...@intel.com>
---
Changelog:
* Use xasprintf instead of snprintf when reporting attach/detach errors.
* Updated format of link in docs to comply with ne
now must specify the relevant PCI address
as input instead of the port name.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
Co-authored-by: Daniele Di Proietto <diproiet...@vmware.com>
Signed-off-by: Kevin Traynor &l
-by: Ciara Loftus <ciara.lof...@intel.com>
---
Changelog:
* Updated process_vdevargs to work with Daniele's incremental in the
previous patch.
* Allow vdev detach
* Update docs to show af_packet example
Documentation/intro/install/dpdk-advanced.rst | 27
the user attaches a new device, it has to be added to a bridge
using the add-port command, similarly, before detaching a device,
it has to be removed using the del-port command.
Signed-off-by: Mauricio Vasquez B <mauricio.vasquezber...@studenti.polito.it>
Signed-off-by: Ciara Loftus <
has changed in that the user now must specify the relevant PCI address
as input instead of the port name.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
Co-authored-by: Daniele Di Proietto <diproiet...@vmware.com
-by: Ciara Loftus <ciara.lof...@intel.com>
---
Changelog:
* Updated process_vdevargs to work with Daniele's incremental in the
previous patch.
* Allow vdev detach
* Update docs to show af_packet example
Documentation/intro/install/dpdk-advanced.rst | 27 ++
the user attaches a new device, it has to be added to a bridge
using the add-port command, similarly, before detaching a device,
it has to be removed using the del-port command.
Signed-off-by: Mauricio Vasquez B <mauricio.vasquezber...@studenti.polito.it>
Signed-off-by: Ciara Loftus <
-by: Ciara Loftus <ciara.lof...@intel.com>
---
Documentation/intro/install/dpdk-advanced.rst | 22 ++
NEWS | 1 +
lib/netdev-dpdk.c | 21 +
vswitchd/vswitch.xml
-detach command
has changed in that the user now must specify the relevant PCI address
as input instead of the port name.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
Changelog:
* Keep port-detach appctl function - use PCI as input arg
* Add requires_mutex to devargs processing fun
In order to use dpdk ports in ovs they have to be bound to a DPDK
compatible driver before ovs is started.
This patch adds the possibility to hotplug (or hot-unplug) a device
after ovs has been started. The implementation adds two appctl commands:
netdev-dpdk/port-attach and
:
ovs-vsctl set Interface null0 options:dpdk-devargs=eth_null0
All virtual DPDK PMDs haven't been tested so this port type can be
considered experimental.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTALL.DPDK-ADVANCED.md | 23 ++
NEWS
In order to use dpdk ports in ovs they have to be bound to a DPDK
compatible driver before ovs is started.
This patch adds the possibility to hotplug (or hot-unplug) a device
after ovs has been started. The implementation adds two appctl commands:
netdev-dpdk/port-attach and
This RFC series consists of 3 patches.
1. Port Hotplug (Mauricio Vasquez) (v8)
Previous: http://openvswitch.org/pipermail/dev/2016-July/075350.html
2. Arbitrary Port Naming (Ciara Loftus) (v4)
Previous: http://openvswitch.org/pipermail/dev/2016-July/075385.html
3. Experimental vDev PMD (Ciara
-port options:dpdk-devargs=:06:00.3
The user must no longer hotplug DPDK ports by issuing specific
ovs-appctl commands. The hotplug is now automatically invoked when a
valid PCI address is set in the dpdk-devargs.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTAL
This commit announces support for DPDK 16.11. Compaitibilty with DPDK
v16.07 is not broken yet thanks to no code changes being needed for the
upgrade. This may change soon however with the addition of subsequent
commits that integrate 16.11-only features.
Signed-off-by: Ciara Loftus <ciara.
Host & update commit message
Ciara Loftus (2):
netdev-dpdk: Add support for DPDK 16.11
netdev-dpdk: Add vHost User PMD
.travis/linux-build.sh | 2 +-
INSTALL.DPDK-ADVANCED.md | 6 +-
INSTALL.DPDK.rst | 18 +-
NEWS | 3 +
lib/dpdk.c
available in
previous releases, and thus breaks compatibility with such releases.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v6:
* Unregister callbacks before detach
v5:
* change vhost_pmd_id to signed int and use -1 value to indicate an
ID from the pool hasn't been alloced for
This commit announces support for DPDK 16.11. Compaitibilty with DPDK
v16.07 is not broken yet thanks to only minor code changes being needed
for the upgrade. This may change soon however with the addition of
subsequent commits that integrate 16.11-only features.
Signed-off-by: Ciara Loftus
available in
previous releases, and thus breaks compatibility with such releases.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v5:
* change vhost_pmd_id to signed int and use -1 value to indicate an
ID from the pool hasn't been alloced for it yet.
* free pool ID if rte_eth_dev_attach
tdev_dpdk_init fails
* Introduce "out" in client_reconfigure for when txq alloc fails
* Remove set_tx_multiq fn for vHost ports
v2:
* Disable indirect desc for vHost & update commit message
Ciara Loftus (2):
netdev-dpdk: Add support for DPDK 16.11
netdev-dpdk: Add vHost User PMD
.t
available in
previous releases, and thus breaks compatibility with such releases.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v4:
* Use id-pool implementation for allocating vHost PMD IDs
v3:
* Added DPDK_DEV_VHOST_CLIENT netdev_dpdk "type"
* Reintroduced socket-id logic
tdev_dpdk_init fails
* Introduce "out" in client_reconfigure for when txq alloc fails
* Remove set_tx_multiq fn for vHost ports
v2:
* Disable indirect desc for vHost & update commit message
Ciara Loftus (2):
netdev-dpdk: Add support for DPDK 16.11
netdev-dpdk: Add vHost User
This commit announces support for DPDK 16.11. Compaitibilty with DPDK
v16.07 is not broken yet thanks to only minor code changes being needed
for the upgrade. This may change soon however with the addition of
subsequent commits that integrate 16.11-only features.
Signed-off-by: Ciara Loftus
reconfigure for when txq alloc fails
* Remove set_tx_multiq fn for vHost ports
v2:
* Disable indirect desc for vHost & update commit message
Ciara Loftus (2):
netdev-dpdk: Add support for DPDK 16.11
netdev-dpdk: Add vHost User PMD
.travis/linux-build.sh |2 +-
INSTALL.DPDK-ADVANCED.md
available in
previous releases, and thus breaks compatibility with such releases.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v3:
* Added DPDK_DEV_VHOST_CLIENT netdev_dpdk "type"
* Reintroduced socket-id logic to correctly set client type sid
* Removed magic number &a
This commit announces support for DPDK 16.11. Compaitibilty with DPDK
v16.07 is not broken yet thanks to only minor code changes being needed
for the upgrade. This may change soon however with the addition of
subsequent commits that integrate 16.11-only features.
Signed-off-by: Ciara Loftus
available in
previous releases, and thus breaks compatibility with such releases.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTALL.DPDK.md | 10 +
NEWS |2 +
lib/netdev-dpdk.c | 1103 +
3 files change
This commit announces support for DPDK 16.11. Compaitibilty with DPDK
v16.07 is not broken yet thanks to only minor code changes being needed
for the upgrade. This may change soon however with the addition of
subsequent commits that integrate 16.11-only features.
Signed-off-by: Ciara Loftus
:
http://dpdk.org/ml/archives/dev/2016-September/046631.html
Early feedback on this patchset is important in case we need to submit
changes to DPDK (eg. see above) before the release is made in November.
v2:
* Disable indirect desc for vHost & update commit message
Ciara Loftus (2):
netdev-
available in
previous releases, and thus breaks compatibility with such releases.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTALL.DPDK.md | 10 +
NEWS |2 +
lib/netdev-dpdk.c | 1101 +
3 files change
This commit announces support for DPDK 16.11. No code changes are
required, so compaitibilty with DPDK v16.07 is not broken yet. This may
change soon however with the addition of subsequent commits that
integrate 16.11-only features.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.
/ml/archives/dev/2016-September/046631.html
Early feedback on this patchset is important in case we need to submit
changes to DPDK (eg. see above) before the release is made in November.
Ciara Loftus (2):
netdev-dpdk: Add support for DPDK 16.11
netdev-dpdk: Add vHost User PMD
.travis/linux
The rte_pdump header file was not included in the file that requires it.
Fix this.
Fixes: 01961bbdd34a ("dpdk: New module with some code from netdev-dpdk.")
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/dpdk.c| 4
lib/netdev-dpdk.c | 3 ---
2
Configurable queue sizing for DPDK ports did not make the 2.6 release
however the NEWS entry suggests it did. Fix this.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
NEWS | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/NEWS b/NEWS
index 725754a..04943d4
the NIC to restart when changed.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Acked-by: Yunhong Jiang <yunhong.ji...@linux.intel.com>
Acked-by: Ilya Maximets <i.maxim...@samsung.com>
---
v6:
* Reintroduce check for queue_size >= 0
v5:
* Rebase
* If invalid value is specifi
the NIC to restart when changed.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Acked-by: Yunhong Jiang <yunhong.ji...@linux.intel.com>
Acked-by: Ilya Maximets <i.maxim...@samsung.com>
---
v5:
* Rebase
* If invalid value is specified, request a default value rather than th
the NIC to restart when changed.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Acked-by: Yunhong Jiang <yunhong.ji...@linux.intel.com>
---
v4:
* Fix typos in vswitchd.xml
* Use internal OVS function is_pow2 rather than DPDK function
* Additional documentation
v3:
* Make queue si
the NIC to restart when changed.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v3:
* Make queue sizes per-port rather than global
* Check if queue size is power of 2 - fail if so.
v2:
* Rebase
INSTALL.DPDK-ADVANCED.md | 16 ++--
NEWS | 2 ++
lib/
as changing the queue size requires the NIC to restart.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
v2
* Rebase
INSTALL.DPDK-ADVANCED.md | 16 ++--
NEWS | 3 +++
lib/netdev-dpdk.c| 35 +++
vswitchd/vswitch.xml
as changing the queue size requires the NIC to restart.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTALL.DPDK-ADVANCED.md | 16 ++--
NEWS | 3 +++
lib/netdev-dpdk.c| 35 +++
vswitchd/vswitch.xml
The 'dpdkvhostuser' port type no longer supports both server and client
mode. Instead, 'dpdkvhostuser' ports are always 'server' mode and
'dpdkvhostuserclient' ports are always 'client' mode.
Suggested-by: Daniele Di Proietto <diproiet...@vmware.com>
Signed-off-by: Ciara Loftus <
The 'dpdkvhostuser' port type no longer supports both server and client
mode. Instead, 'dpdkvhostuser' ports are always 'server' mode and
'dpdkvhostuserclient' ports are always 'client' mode.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTALL.DPDK-ADVANCED.md
Fixes: 419876444357 ("netdev-dpdk: Remove dpdkvhostcuse ports")
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
INSTALL.DPDK-ADVANCED.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/INSTALL.DPDK-ADVANCED.md b/INSTALL.DPDK-ADVANCED.md
index 9694003
function is called but happen to be zero. Provide
an explicit flag instead for better practice.
Fixes: ("c1ff66ac80b5: netdev-dpdk: vHost client mode and reconnect")
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-dpdk.c | 2 +-
1 file changed, 1 insertio
If NUMA information can't be derived from a vHost User device, only
print an error if the VHOST_NUMA option is enabled in DPDK. Otherwise
'fail' silently.
Fixes: 0a0f39df1d5a ("netdev-dpdk: Add support for DPDK 16.07")
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Reporte
of its lifetime.
QEMU v2.7.0+ is required when using OVS in vHost client mode and QEMU in
vHost server mode.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
v5:
- Added Daniele's incremental change to fix const id
- R
old
this should however be a low impact change.
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
Acked-by: Flavio Leitner <f...@sysclose.org>
Acked-by: Daniele Di Proietto <diproiet...@vmware.com>
Acked-by: Ilya Maximets <i.maxim...@samsung.com>
---
ner <f...@sysclose.org>
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/netdev-dpdk.c | 25 -
1 file changed, 8 insertions(+), 17 deletions(-)
diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 6998452..9866c85 100644
--- a/lib/netdev-dpdk.c
+++ b
Only 'dpdk' ports support flow control. This patch stops 'dpdkr' ports
from attempting to initialise this feature as this port type does not
support it.
Fixes: 9fd39370c12c ("netdev-dpdk: Add Flow Control support.")
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
---
lib/ne
Only devices of type "DPDK_DEV_ETH" use the netdev_dpdk_set_config
function, so no need to check for the device type within the function.
Fixes: 9fd39370c12c ("netdev-dpdk: Add Flow Control support.")
Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
-
1 - 100 of 207 matches
Mail list logo