Hi Darrell,
I took another look at the series and provided a few comments inline.
Other than those the patches look good to me, but I haven't looked at
every possible corner case :-)
Thanks,
Daniele
2017-03-24 2:15 GMT-07:00 Darrell Ball :
> This patch series introduces NAT
Not sure this is very important: so far we managed to avoid using tcpdump in
the tests. Would it be possible to use ovs-ofctl monitor?
In any case, maybe, it shouldn't be prefixed by sudo
2017-03-24 2:15 GMT-07:00 Darrell Ball :
> Two new tests are added and two other tests
2017-03-24 2:15 GMT-07:00 Darrell Ball :
> This patch adds orig tuple checking and context
> recovery; NAT interactions are factored in.
> Orig tuple support exists to better handle policy
> changes.
>
> Signed-off-by: Darrell Ball
> ---
> lib/conntrack.c | 69
Thanks for doing this
Acked-by: Daniele Di Proietto <diproiet...@ovn.org>
2017-03-24 2:15 GMT-07:00 Darrell Ball <dlu...@gmail.com>:
> Signed-off-by: Darrell Ball <dlu...@gmail.com>
> Acked-by: Flavio Leitner <f...@sysclose.org>
monitor) and verifying
> any single packet instead of checking the 2 packets at the same time.
>
> CC: Daniele Di Proietto <daniele.di.proie...@gmail.com>
> Fixes: a12e2a88d672 ("test: Add more pmd tests.")
> Signed-off-by: Timothy Redaelli <tredae...@redhat.com>
ove
commit (it was 14.88 Mpps before, it is 13 Mpps after).
This patch skips initializing ct_orig_tuple in pkt_metadata_init().
It should be enough to initialize ct_state, because nobody should look
at ct_orig_tuple unless ct_state is != 0.
CC: Jarno Rajahalme <ja...@ovn.org>
Signed-off-by: Dan
2017-03-10 3:47 GMT-08:00 Ian Stokes :
> DPDK now provides a stable release branch. Modify dpdk docs and travis
> linux build script to use the DPDK 16.07.2 stable branch to benefit from
> most recent bug fixes.
>
> Signed-off-by: Ian Stokes
Thanks,
2017-03-10 3:47 GMT-08:00 Ian Stokes :
> DPDK now provides a stable release branch. Modify dpdk docs and travis linux
> build script to use the DPDK 16.11.1 stable branch to benefit from most
> recent bug fixes.
>
> Signed-off-by: Ian Stokes
Thanks,
delete the ukey, the next upcall will be a miss upcall and that will
immediatedly install the correct datapath flow.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
include/openvswitch/ofp-actions.h | 12 +++
lib/learn.c| 24 +
lib/ofp-act
No functional change, they will be used by next commit.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ofp-actions.c | 58 ++-
1 file changed, 40 insertions(+), 18 deletions(-)
diff --git a/lib/ofp-actions.c b/l
This will be useful in a separate commit, because learning can fail.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
Acked-by: Ben Pfaff <b...@ovn.org>
---
ofproto/ofproto-dpif-xlate.c | 24 +---
1 file changed, 17 insertions(+), 7 deletions(-)
o call
ofproto_flow_mod_uninit() if we don't call ofproto_flow_mod_learn_start().
* Simplify ofp-actions changes according to Ben comments(thanks!)
Daniele Di Proietto (3):
ofproto-dpif-xlate: Create XC_LEARN entry after learning.
ofp-actions: Factor out decode_LEARN_{common,spec}().
ofp-actions: Add limit to
2017-02-21 6:49 GMT-08:00 Ilya Maximets :
> There are many reasons for reloading of pmd threads:
> * reconfiguration of one of the ports.
> * Adjusting of static_tx_qid.
> * Adding new tx/rx ports.
>
> In many cases EMC is still useful after reload
2017-02-21 6:49 GMT-08:00 Ilya Maximets :
> Reconfiguration of HW NICs may lead to packet drops.
> In current model all physical ports will be reconfigured each
> time number of PMD threads changed. Since we not stopping
> threads on pmd-cpu-mask changes, this patch will
2017-02-21 6:49 GMT-08:00 Ilya Maximets :
> Currently, change of 'pmd-cpu-mask' is very heavy operation.
> It requires destroying of all the PMD threads and creating
> them back. After that, all the threads will sleep until
> ports' redistribution finished.
>
> This patch
2017-03-09 13:15 GMT-08:00 Ian Stokes :
> DPDK now provides a stable release branch. Modify dpdk docs and travis linux
> build script to use the DPDK 16.11.1 stable branch to benefit from most
> recent bug fixes.
>
> Signed-off-by: Ian Stokes
Thanks
2017-03-06 11:28 GMT-08:00 Aaron Conole :
> Ilya Maximets writes:
>
>> This should be helpful for have all the logs in one place.
>> 'ovs-appctl vlog' commands for 'dpdk' module can be used
>> to configure the log level. Lower bound for DPDK logging
>>
lper().
>
> Signed-off-by: Ian Stokes <ian.sto...@intel.com>
> Fixes: 2ae3d542 ("netdev-dpdk: Refactor dpdk_mp_get().")
> Fixes: 0072e931 ("netdev-dpdk: add support for jumbo frames")
> CC: Daniele Di Proietto <diproiet...@vmware.com>
> CC: Mark
2017-02-16 0:47 GMT-08:00 Darrell Ball :
> Signed-off-by: Darrell Ball
> Acked-by: Flavio Leitner
Thanks, I applied this to master
> ---
> tests/system-traffic.at | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git
2017-03-09 10:21 GMT-08:00 Darrell Ball <db...@vmware.com>:
>
>
> On 3/8/17, 6:14 PM, "ovs-dev-boun...@openvswitch.org on behalf of Daniele Di
> Proietto" <ovs-dev-boun...@openvswitch.org on behalf of diproiet...@ovn.org>
> wrote:
>
> 2017-02-16 0:
Thanks for posting this as a separate patch, it makes the review easier.
The idea and the patch look good to me.
One comment:
with this code we don't need the ctxs array, we can just have a single
ctx in the for loop.
Other than that:
Acked-by: Daniele Di Proietto <diproiet...@vmware.
On 07/03/2017 10:35, "Ben Pfaff" <b...@ovn.org> wrote:
>On Fri, Feb 24, 2017 at 06:57:58PM -0800, Daniele Di Proietto wrote:
>> The new module will be used by ofproto to keep track of the number of
>> learned flows with the same cookie in the same tabl
On 07/03/2017 10:39, "Ben Pfaff" <b...@ovn.org> wrote:
>On Fri, Feb 24, 2017 at 06:58:00PM -0800, Daniele Di Proietto wrote:
>> With this commit we honor the newly introduced limit to the learn
>> action.
>>
>> When learning a new rule (with the li
execution, so the
only option is to slowpath the ukey. I don't think this has big
performance implications since it's done only for ukey with no traffic.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
include/openvswitch/ofp-actions.h | 12 +++
lib/l
No functional change, they will be used by next commit.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ofp-actions.c | 58 ++-
1 file changed, 40 insertions(+), 18 deletions(-)
diff --git a/lib/ofp-actions.c b/l
This will be useful in a separate commit, because learning can fail.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
Acked-by: Ben Pfaff <b...@ovn.org>
---
ofproto/ofproto-dpif-xlate.c | 24 +---
1 file changed, 17 insertions(+), 7 deletions(-)
all
ofproto_flow_mod_uninit() if we don't call ofproto_flow_mod_learn_start().
* Simplify ofp-actions changes according to Ben comments(thanks!)
Daniele Di Proietto (3):
ofproto-dpif-xlate: Create XC_LEARN entry after learning.
ofp-actions: Factor out decode_LEARN_{common,spec}().
ofp-actions:
t;bshas...@sec.t-labs.tu-berlin.de>
> Signed-off-by: Ben Pfaff <b...@ovn.org>
Acked-by: Daniele Di Proietto <diproiet...@vmware.com>
> ---
> v1->v2: Eliminate duplicate check in extract_l3_ipv6(). Thanks Daniele!
>
> lib/conntrack.c | 16 +++-
> 1 file ch
t;bshas...@sec.t-labs.tu-berlin.de>
> Signed-off-by: Ben Pfaff <b...@ovn.org>
Oops, thanks for the fix, Ben
Fixes: a489b16854b5("conntrack: New userspace connection tracker.")
One minor comment below,
Acked-by: Daniele Di Proietto <diproiet...@vmware.com>
> ---
>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
tests/learn.at | 175 +
1 file changed, 175 insertions(+)
diff --git a/tests/learn.at b/tests/learn.at
index 3f6fb5a7e..f91a662ad 100644
--- a/tests/learn.at
+++ b
since it's done only for ukey with no traffic.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/odp-util.h | 6 --
ofproto/ofproto-dpif-upcall.c | 25 ++-
ofproto/ofproto-dpif-xlate-cache.c | 6 +-
ofproto/ofproto-dpif
No functional change, it will be used by next commit.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ofp-actions.c | 77 +++
1 file changed, 43 insertions(+), 34 deletions(-)
diff --git a/lib/ofp-actions.c b/l
and documentation.
A later commit will implement the feature in ofproto-dpif.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
include/openvswitch/ofp-actions.h | 12
lib/learn.c | 28
lib/ofp-actions.c
implements the actual logic and the last commit has some
basic tests.
Daniele Di Proietto (7):
ofp-actions: Factor out decode_LEARN_common().
ofp-actions: Add limit to learn action.
ofproto-dpif-xlate: Create XC_LEARN entry after learning.
ofproto: New cookie-counters module.
ofproto-dpif-upcall
2017-02-16 7:31 GMT-08:00 Ian Stokes :
> "rx_error" stat for a DPDK interface was calculated with the assumption that
> dropped packets due to hardware buffer overload were counted as errors
> in DPDK and the rte ierror stat included rte imissed packets i.e.
>
> rx_errors =
2017-02-16 3:01 GMT-08:00 Kevin Traynor :
> On 02/16/2017 10:22 AM, Ciara Loftus wrote:
>> Unconditional insertion of EMC entries results in EMC thrashing at high
>> numbers of parallel flows. When this occurs, the performance of the EMC
>> often falls below that of the dpcls
2017-02-15 10:02 GMT-08:00 Shashank Ram :
> Currently, the call to config_ofproto_types() happens at the end
> of bridge_reconfigure(), after missing ofprotos and ports are created.
> However, it might be usefull to make this call before adding missing
> ports through the dpif
2017-02-10 9:49 GMT-08:00 Aaron Conole :
> From: Aaron Conole
>
> This adds support for ifup to configure client-mode sockets by exposing
> two new variables $OVS_PORT_MODE and $OVS_PORT_PATH to the ifcfg
> scripts. When OVS_PORT_MODE is set to 'client',
On 02/02/2017 12:48, "Ben Pfaff" <b...@ovn.org> wrote:
>On Tue, Jan 24, 2017 at 06:21:53PM -0800, Daniele Di Proietto wrote:
>> Names like dpdk0 and dpdk1 are not enough to identify a DPDK interface.
>> We could update README.RHEL.rst and add
>>
2017-01-31 9:55 GMT-08:00 Ciara Loftus :
> Unconditional insertion of EMC entries results in EMC thrashing at high
> numbers of parallel flows. When this occurs, the performance of the EMC
> often falls below that of the dpcls classifier, rendering the EMC
> practically
2017-02-03 9:38 GMT-08:00 Kevin Traynor :
> On 02/02/2017 08:22 PM, Stokes, Ian wrote:
>>> On 02/02/2017 04:44 PM, Ian Stokes wrote:
Remove the experimental warning tag in documentation regarding OVS
deployed via userspace.
Signed-off-by: Ian Stokes
2017-02-02 8:59 GMT-08:00 Kevin Traynor :
> On 02/02/2017 04:30 PM, Ian Stokes wrote:
>> Add DPDK version required for the OVS 2.7 release in documentation.
>>
>> Signed-off-by: Ian Stokes
>
> Acked-by: Kevin Traynor
Thanks, pushed
On 02/02/2017 11:49, "Ben Pfaff" <b...@ovn.org> wrote:
>On Tue, Jan 24, 2017 at 06:21:52PM -0800, Daniele Di Proietto wrote:
>> The support for vhost cuse port has been removed long ago.
>>
>> Fixes:419876444357("netdev-dpdk: Remove dpdkvhos
On 31/01/2017 13:52, "Ben Pfaff" wrote:
>On Thu, Dec 08, 2016 at 01:16:22PM +0100, Przemyslaw Lal wrote:
>> diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
>> index de78ddd..ef99eb3 100644
>> --- a/lib/netdev-dpdk.c
>> +++ b/lib/netdev-dpdk.c
>> @@ -2075,7 +2075,13 @@
2017-01-26 9:55 GMT-08:00 Loftus, Ciara :
>>
>> 2017-01-25 7:52 GMT-08:00 Loftus, Ciara :
>> >> 2017-01-22 11:45 GMT-08:00 Jan Scheurich :
>> >> >
>> >> >> It's not a big deal, since the most important use case we have for
>> >>
On 26/01/2017 11:11, "Aaron Conole" <acon...@redhat.com> wrote:
>Daniele Di Proietto <diproiet...@vmware.com> writes:
>
>> The OVSDPDKBond case wasn't handled in the rhel ifdown script.
>>
>> Fixes: f6bf8880613a ("rhel: Add support DPDK po
2017-01-24 20:40 GMT-08:00 Darrell Ball :
> Signed-off-by: Darrell Ball
> ---
> lib/conntrack.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/lib/conntrack.c b/lib/conntrack.c
> index 34728a6..aaecb00 100644
> --- a/lib/conntrack.c
> +++
2017-01-24 20:40 GMT-08:00 Darrell Ball :
> This patch introduces NAT support for the userspace datapath.
> The conntrack module changes are in this patch.
>
> The per packet scope of lookups for NAT and un_NAT is at
> the bucket level rather than global. One hash table is
>
2017-01-24 10:50 GMT-08:00 Darrell Ball :
> Signed-off-by: Darrell Ball
> ---
> lib/conntrack-private.h | 9 --
> lib/conntrack.c | 3 +-
> lib/conntrack.h | 31 +-
> lib/dpif-netdev.c | 85
>
2017-01-24 20:40 GMT-08:00 Darrell Ball :
> This patch series introduces NAT support for the userspace datapath.
>
> The per packet scope of lookups for NAT and un_NAT is at
> the bucket level rather than global. One hash table is
> introduced to support create/delete handling.
2017-01-26 9:51 GMT-08:00 Ciara Loftus :
> Unconditional insertion of EMC entries results in EMC thrashing at high
> numbers of parallel flows. When this occurs, the performance of the EMC
> often falls below that of the dpcls classifier, rendering the EMC
> practically
ofproto.c, ofproto-dpif.c and dpif.c.
This patch sends the entire other_config column to dpif-netdev, so that
dpif-netdev can extract the values it's interested in.
No functional change.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
I don't like that dpif-netdev receives the
2017-01-25 20:31 GMT-08:00 Ben Pfaff <b...@ovn.org>:
> This missing directive caused groff warnings and probably some erroneous
> output too.
>
> Fixes: 96fee5e0a2a0 ("ovs-fields: New manpage to document Open vSwitch and
> OpenFlow fields.")
> Reported-by: Daniel
On 25/01/2017 00:01, "Ansis Atteka" <ansisatt...@gmail.com> wrote:
>
>
>On Jan 25, 2017 4:22 AM, "Daniele Di Proietto" <diproiet...@vmware.com> wrote:
>
>Current SELinux policy in RHEL and Fedora doesn't allow the creation of
>TAP devices
SELinux
yet, but at least we can use the userspace datapath.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
selinux/openvswitch-custom.te | 5 +
1 file changed, 5 insertions(+)
diff --git a/selinux/openvswitch-custom.te b/selinux/openvswitch-custom.te
index 47d
.
Fixes: 55e075e65ef9("netdev-dpdk: Arbitrary 'dpdk' port naming")
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
rhel/README.RHEL.rst| 13 +
rhel/etc_sysconfig_network-scripts_ifup-ovs | 6 --
2 files changed, 13 insertions
The support for vhost cuse port has been removed long ago.
Fixes:419876444357("netdev-dpdk: Remove dpdkvhostcuse ports")
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
rhel/etc_sysconfig_network-scripts_ifdown-ovs | 2 +-
1 file changed, 1 insertion(+), 1 deletio
2017-01-22 11:45 GMT-08:00 Jan Scheurich :
>
>> It's not a big deal, since the most important use case we have for
>> dpif-netdev is with dpdk, but I'd still like the code to behave
>> similarly on different platforms. How about defining a function that
>> uses random_uint32
2017-01-20 5:59 GMT-08:00 Jan Scheurich <jan.scheur...@web.de>:
>
>
> On 2017-01-18 17:32, Kevin Traynor wrote:
>>
>> On 01/18/2017 01:34 AM, Daniele Di Proietto wrote:
>>>
>>> 2017-01-17 11:43 GMT-08:00 Kevin Traynor <ktray...@redhat.com>:
&
nstead of a port name.
>>
>> CC: Ciara Loftus <ciara.lof...@intel.com>
>> Fixes: 55e075e65ef9("netdev-dpdk: Arbitrary 'dpdk' port naming")
>> Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
>
>Patch looks good.
2017-01-18 15:18 GMT-08:00 Daniele Di Proietto <diproiet...@ovn.org>:
> 2017-01-18 11:55 GMT-08:00 Binbin Xu <xu.binb...@zte.com.cn>:
>> After the hotplug of DPDK ports, a valid dpdk-devargs must be
>> specified. Otherwise, the DPDK device can't be available.
>
ng")
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
Documentation/howto/dpdk.rst| 77 -
Documentation/howto/userspace-tunneling.rst | 2 +-
2 files changed, 43 insertions(+), 36 deletions(-)
diff --git a/Documentation/howto/dp
2017-01-18 11:55 GMT-08:00 Binbin Xu :
> After the hotplug of DPDK ports, a valid dpdk-devargs must be
> specified. Otherwise, the DPDK device can't be available.
>
> Signed-off-by: Binbin Xu
Thanks! Applied to master and branch-2.7
> ---
>
2017-01-17 11:43 GMT-08:00 Kevin Traynor :
> On 01/17/2017 05:43 PM, Ciara Loftus wrote:
>> Instead of counting all polling cycles as processing cycles, only count
>> the cycles where packets were received from the polling.
>
> This makes these stats much clearer. One minor
if (OVS_UNLIKELY(!rules[i])) {
>
>Acked-by: Ben Pfaff <b...@ovn.org>
>
>I believe that this also should be tagged:
>
>CC: Daniele Di Proietto <diproiet...@vmware.com>
>Fixes: 8aaa125dab66 ("dpif-netdev: Share emc and fast path output batches.")
>
On 12/01/2017 09:33, "Ben Pfaff" <b...@ovn.org> wrote:
>On Thu, Jan 12, 2017 at 12:23:55AM -0800, Daniele Di Proietto wrote:
>> set_tunnel_config() always logs a warning, even on success. This
>> shouldn't happen.
>>
>> Without this, some unit tes
On 12/01/2017 09:24, "Ben Pfaff" wrote:
>Commit 9fff138ec3a6dbe75073d16cba7fbe86ac273c36 "netdev: Add 'errp' to
>set_config()." breaks the unit tests because netdev-vport now logs lots
>of blank lines. I am unsure of the right fix--is it to just drop the
>new VLOG_WARN call?
set_tunnel_config() always logs a warning, even on success. This
shouldn't happen.
Without this, some unit tests fail.
Fixes: 9fff138ec3a6("netdev: Add 'errp' to set_config().")
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/netdev-vport.c | 10 ++
1
2017-01-12 6:18 GMT-08:00 Binbin Xu :
> We can hotplug attach DPDK ports specified via the 'dpdk-devargs'
> option now.
>
> But the socket id of DPDK ports can't be assigned correctly,
> it is always 0. The socket id of DPDK ports should be assigned
> according to the numa
2017-01-09 21:56 GMT-08:00 nickcooper-zhangtonghao :
> This patch avoids the ovs_rcu to report WARN, caused by blocked
> for a long time, when ovs-vswitchd processes a port with many
> rx/tx queues. The number of tx/rx queues per port may be appropriate,
> because the dpdk
the process (e.g. if there not enough memory), so the user must
check the status of the process after setting dpdk-init to true.
Nonetheless, I think this is an improvement, because it doesn't require
restarting the whole unit.
CC: Aaron Conole <acon...@redhat.com>
Signed-off-by: Daniele Di Pr
()?
I think for DPDK devices ultimately there's no way to check without
actually setting up the queues, that's why it's done in reconfigure().
Thanks,
Daniele
>
> Now we check it in dpdk_eth_dev_init().
>
> Thanks.
>
>
>
> On Jan 9, 2017, at 11:22 AM, Daniele Di Proietto <
mething more complicated and needs to be a separate patch, we should
probably defer it, since we're on feature freeze now.
Thanks,
Daniele
>
>
>
>Thanks.
>Nick
>
>
>
>On Jan 9, 2017, at 11:21 AM, Daniele Di Proietto <diproiet...@vmware.com>
>wrote:
>
>Wit
On 09/01/2017 07:14, "Aaron Conole" <acon...@redhat.com> wrote:
>Daniele Di Proietto <diproiet...@vmware.com> writes:
>
>> With this commit, we allow the user to set other_config:dpdk-init=true
>> after the process is started. This makes it easier
2017-01-08 17:30 GMT-08:00 nickcooper-zhangtonghao :
> This patch uses OVS_CORE_UNSPEC for the queue unpinned instead
> of "-1". More important, the "-1" casted to unsigned int is
> equal to NON_PMD_CORE_ID. We make the distinction between them.
>
> Signed-off-by:
2017-01-08 17:30 GMT-08:00 nickcooper-zhangtonghao :
> The NR_QUEUE is defined in "lib/dpif-netdev.h", netdev-dpdk
> uses it instead of magic number. netdev-dummy should be
> in the same case.
>
> Signed-off-by: nickcooper-zhangtonghao
Thanks, I changed
2017-01-08 17:30 GMT-08:00 nickcooper-zhangtonghao :
> This patch avoids the ovs_rcu to report WARN, caused by blocked
> for a long time, when ovs-vswitchd processes a port with many
> rx/tx queues. The number of tx/rx queues per port may be appropriate,
> because the dpdk
the process (e.g. if there not enough memory), so the user must
check the status of the process after setting dpdk-init to true.
Nonetheless, I think this is an improvement, because it doesn't require
restarting the whole unit.
CC: Aaron Conole <acon...@redhat.com>
Signed-off-by: Daniele Di Pr
2017-01-08 17:30 GMT-08:00 nickcooper-zhangtonghao :
> Signed-off-by: nickcooper-zhangtonghao
Thanks, I changed the prefix to netdev-dpdk (instead of datapath) and
pushed this to master
> ---
> lib/netdev-dpdk.c | 2 +-
> 1 file changed, 1
, uses 'struct dp_netdev_rxq' from 'struct
rxq_poll' and uses 'rx' for 'netdev_rxq' and 'rxq' for 'dp_netdev_rxq'.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.c | 168 --
1 file changed, 112 insertions(
ovs-numa doesn't need to keep the state of the pmd threads, it is an
implementation detail of dpif-netdev.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ovs-numa.c | 175 -
lib/ovs-numa.h | 7 ---
2 files c
is an implementation
detail of dpif-netdev, dpctl shouldn't know anything about it.
This commit changes the dpif_flow_put() and dpif_flow_del() calls to
iterate over all the pmd threads, if pmd_id is PMD_ID_NULL.
A simple test is added.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.
They will be used by a future commit.
Suggested-by: Ilya Maximets <i.maxim...@samsung.com>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ovs-numa.c | 96 +-
lib/ovs-numa.h | 18 +--
2 files
I think it's better to iterate the hmap than to use
hmap_first_with_hash(), because it handles hash collisions.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ovs-numa.c | 26 ++
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/l
It will be used by a future commit. struct ovs_numa_dump now uses an
hmap instead of a list to make ovs_numa_dump_contains_core() more
efficient.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ovs-numa.c | 25 ++---
lib/ovs-numa.h | 10 ++-
Since previous commit, 'static_tx_qid' doesn't need to be atomic and is
actually never touched (except for initialization), so it can be made
const.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.c | 11 +--
1 file changed, 5 insertions(+), 6 del
will not consume
any CPU, so it seems easier to create all the threads at once.
This will also make future commits easier.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.c | 208 ++
tests/pmd.at | 2 +-
2
They will be used by a future commit.
This patch introduces some code duplication which will be removed in a
future commit.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/ovs-numa.c | 78 ++
lib/ovs-numa.h | 4
it's blocked) and set 'reload' to true.
This is useful to avoid wasting CPU cycles and is also necessary for a
future commit.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.c | 15 +++
1 file changed, 15 insertions(+)
diff --git a/lib/dpif-netd
-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.c | 19 +++
1 file changed, 7 insertions(+), 12 deletions(-)
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index 004b28dc8..0d47a3286 100644
--- a/lib/dpif-netdev.c
+++ b/lib/dpif-netdev.c
@@ -485,7
common_destruct().
* Avoid taking 'dev->mutex' in construct and destruct: we're guaranteed
to be the only thread with access to the object.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/netdev-dpdk.c | 86 ++-
1 file ch
{push,pop}_header (tunnel devices), and ports that
support netdev_send. With this we can also remove a branch in
netdev_send().
This is also necessary for a future commit, which starts DPDK devices
without txqs.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.
patch also documents that, even though no change to the
userspace datapath (the only user) is required.
Lastly, this patch makes sure the errors returned by ofproto_port_add
(which includes the first port reconfiguration) are reported back to the
database.
Signed-off-by: Daniele Di Proietto <diproiet.
come from OpenFlow.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/netdev-dpdk.c | 28
1 file changed, 12 insertions(+), 16 deletions(-)
diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 8bb908691..2df3e220c 100644
--- a/lib/netdev-
We keep all the per-port classifiers around, since they can be reused,
but when a pmd thread is destroyed we should free them.
Found using valgrind.
Fixes: 3453b4d62a98("dpif-netdev: dpcls per in_port with sorted
subtables")
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.
As documented in dp_netdev_pmd_thread, we must take non_pmd_mutex to
access the tx port caches for the non pmd thread.
Found by inspection.
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/dpif-netdev.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/dpif-netd
ory is "/var/log/openvswitch/".
CC: Ciara Loftus <ciara.lof...@intel.com>
CC: Kevin Traynor <ktray...@redhat.com>
Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com>
---
lib/netdev-dpdk.c | 27 ++
lib/
On 06/01/2017 13:01, "Ben Pfaff" <b...@ovn.org> wrote:
>On Fri, Jan 06, 2017 at 12:42:35PM -0800, Daniele Di Proietto wrote:
>> bridge_delete_or_reconfigure() deletes every interface that's not dumped
>> by OFPROTO_PORT_FOR_EACH(). ofprot
On 06/01/2017 11:34, "Ben Pfaff" <b...@ovn.org> wrote:
>On Fri, Jan 06, 2017 at 10:59:07AM -0800, Daniele Di Proietto wrote:
>> bridge_delete_or_reconfigure() deletes every interface that's not dumped
>> by OFPROTO_PORT_FOR_EACH(). ofprot
On 06/01/2017 09:28, "Ben Pfaff" <b...@ovn.org> wrote:
>On Thu, Jan 05, 2017 at 08:37:26PM -0800, Daniele Di Proietto wrote:
>> bridge_delete_or_reconfigure() deletes every interface that's not dumped
>> by OFPROTO_PORT_FOR_EACH(). ofprot
1 - 100 of 171 matches
Mail list logo