[ovs-dev] [PATCH 07/12] conntrack: Implement dumping to ct_entry.

Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/conntrack-private.h | 3 ++ lib/conntrack-tcp.c | 34 + lib/conntrack.c | 125 lib/conntrack.h | 16 +++ 4 files changed, 178 inse

[ovs-dev] [PATCH 09/12] dpif-netdev: Implement conntrack dump functions.

Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpif-netdev.c | 60 --- 1 file changed, 57 insertions(+), 3 deletions(-) diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c index 1061ee4..b976925 100644 --- a/li

[ovs-dev] [PATCH 08/12] dpif-netdev: Execute conntrack action.

Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpif-netdev.c | 65 ++- tests/dpif-netdev.at | 14 +-- tests/ofproto-dpif.at | 20 3 files changed, 71 insertions(+), 28 deletions(-) diff --git

Re: [ovs-dev] [PATCH v2] INSTALL.DPDK: Mention issue with QEMU v2.4.0 & dpdkvhostuser

I applied this to master, thanks. We should remember to remove this when we move to DPDK 2.2 On 05/11/2015 03:14, "Ciara Loftus" wrote: >Currently when using QEMU v2.4.0+, two (or more) dpdkvhostuser ports >cannot >be unbound from the kernel driver in the guest without

[ovs-dev] [PATCH v2 00/11] Conntrack debugging appctl/dpctl

TCP protocol info. Now we use spaces instead of commas, to be consistent with the rest of the entry formatting code. * Use dpctl/dump-conntrack in an IPv6 system testcase. Daniele Di Proietto (11): ct-dpif: New module. netlink-conntrack: New module. ct-dpif: Add ct_dpif_dump_{start,next,d

[ovs-dev] [PATCH v2 05/11] dpif-netlink: Implement ct_dump_{start, next, done}.

. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpif-netlink.c | 58 +++--- 1 file changed, 55 insertions(+), 3 deletions(-) diff --git a/lib/dpif-netlink.c b/lib/dpif-netlink.c index fa995c1..189506c 100644 --- a/li

[ovs-dev] [PATCH v2 10/11] system-traffic: use `dpctl/*conntrack` instead of `conntrack` tool.

state mapping done in tcp_state_coalesce(), SYN_RECV is replaced by ESTABLISHED in four places in the testsuite. The rest of the changes are just done to match the formatting style. Also, check the conntrack entries for the IPv6 HTTP test. Signed-off-by: Daniele Di Proietto <dipro

[ovs-dev] [PATCH v2 04/11] ct-dpif: Add ct_dpif_flush().

This function will flush the connection tracking tables of a specific datapath. It simply calls a function pointer in the dpif_class. No dpif currently implements the required interface. The next commits will provide an implementation in dpif-netlink. Signed-off-by: Daniele Di Proietto

[ovs-dev] [PATCH v2 08/11] dpctl: Add new 'flush-conntrack' command.

Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpctl.c | 30 ++ lib/dpctl.man | 6 ++ 2 files changed, 36 insertions(+) diff --git a/lib/dpctl.c b/lib/dpctl.c index 2990026..73204e2 100644 --- a/lib/dpctl.c +++ b/lib/dpctl.c @@ -

[ovs-dev] [PATCH v2 07/11] dpif-netlink: Implement ct_flush.

. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpif-netlink.c | 12 +++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/lib/dpif-netlink.c b/lib/dpif-netlink.c index 189506c..99457b9 100644 --- a/lib/dpif-netlink.c +++ b/lib/dpif-netlink.c @@ -2331,6 +2

[ovs-dev] [PATCH v2 11/11] system-kmod-macros: Do not require the 'conntrack' tool.

We can use 'test-ovs test-netlink-conntrack' instead. Now that it is not required anymore, we can remove the HAVE_CONNTRACK macro in the build system. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- tests/atlocal.in| 7 --- tests/system-kmod-macros.

[ovs-dev] [PATCH v2 01/11] ct-dpif: New module.

This defines some structures (and their related formatting functions) to manipulate entries in connection tracking tables. It will be used by next commits. Based on original work by Jarno Rajahalme Signed-off-by: Jarno Rajahalme <jrajaha...@nicira.com> Signed-off-by: Daniele Di Pr

[ovs-dev] [PATCH v2 03/11] ct-dpif: Add ct_dpif_dump_{start, next, done}().

These function can be used to dump conntrack entries from a datapath. They simply call a function pointer in the dpif_class. No dpif currently implements the interface. The next commits will provide an implementation in dpif-netlink. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.

[ovs-dev] [PATCH v2 09/11] ovs-test: Add test-netlink-conntrack command.

on the connection table, until killed with Ctrl-C * `ovstest test-netlink-conntrack flush [zone=zone]` empties connection (and therefore expectations table). Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- tests/automake.mk | 5 ++ tests/test-netlink-connt

[ovs-dev] [PATCH v2 02/11] netlink-conntrack: New module.

all the connections. * Listen for updates by registering a netlink notifier. It will be used by dpif-netlink to implement the interface required by the ct-dpif module. Based on original work by Jarno Rajahalme Signed-off-by: Jarno Rajahalme <jrajaha...@nicira.com> Signed-off-by: Dani

[ovs-dev] [PATCH v2 06/11] dpctl: Add 'conntrack-dump' command.

It can be used to inspect the connection tracking entries in the datapath. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpctl.c | 45 + lib/dpctl.man | 24 2 files changed, 69 insertions(+) diff

[ovs-dev] [PATCH 03/11] ct-dpif: Add ct_dpif_dump_{start, next, done}().

These function can be used to dump conntrack entries from a datapath. They simply call a function pointer in the dpif_class. No dpif currently implements the interface. The next commits will provide an implementation in dpif-netlink. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.

[ovs-dev] [PATCH 11/11] system-kmod-macros: Do not require the 'conntrack' tool.

We can use 'test-ovs test-netlink-conntrack' instead. Now that it is not required anymore, we can remove the HAVE_CONNTRACK macro in the build system. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- tests/atlocal.in| 7 --- tests/system-kmod-macros.

[ovs-dev] [PATCH 07/11] dpif-netlink: Implement ct_flush.

. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpif-netlink.c | 12 +++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/lib/dpif-netlink.c b/lib/dpif-netlink.c index 189506c..99457b9 100644 --- a/lib/dpif-netlink.c +++ b/lib/dpif-netlink.c @@ -2331,6 +2

[ovs-dev] [PATCH 00/11] Conntrack debugging appctl/dpctl

to implement dumping and flushing. The dpctl commands are finally added to the dpctl module, and they're used by the system testsuite. Finally, a test module (test-netlink-conntrack) is added to allow the use of the netlink-conntrack API without a datapath. Daniele Di Proietto (11): ct-dpif: New

[ovs-dev] [PATCH 04/11] ct-dpif: Add ct_dpif_flush().

This function will flush the connection tracking tables of a specific datapath. It simply calls a function pointer in the dpif_class. No dpif currently implements the required interface. The next commits will provide an implementation in dpif-netlink. Signed-off-by: Daniele Di Proietto

[ovs-dev] [PATCH 02/11] netlink-conntrack: New module.

all the connections. * Listen for updates by registering a netlink notifier. It will be used by dpif-netlink to implement the interface required by the ct-dpif module. Based on original work by Jarno Rajahalme Signed-off-by: Jarno Rajahalme <jrajaha...@nicira.com> Signed-off-by: Dani

[ovs-dev] [PATCH 08/11] dpctl: Add new 'flush-conntrack' command.

Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpctl.c | 30 ++ lib/dpctl.man | 6 ++ 2 files changed, 36 insertions(+) diff --git a/lib/dpctl.c b/lib/dpctl.c index aadfd68..a87e71e 100644 --- a/lib/dpctl.c +++ b/lib/dpctl.c @@ -

[ovs-dev] [PATCH 09/11] ovs-test: Add test-netlink-conntrack command.

on the connection table, until killed with Ctrl-C * `ovstest test-netlink-conntrack flush [zone=zone]` empties connection (and therefore expectations table). Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- tests/automake.mk | 5 ++ tests/test-netlink-connt

[ovs-dev] [PATCH 01/11] ct-dpif: New module.

This defines some structures (and their related formatting functions) to manipulate entries in connection tracking tables. It will be used by next commits. Based on original work by Jarno Rajahalme Signed-off-by: Jarno Rajahalme <jrajaha...@nicira.com> Signed-off-by: Daniele Di Pr

[ovs-dev] [PATCH 06/11] dpctl: Add 'conntrack-dump' command.

It can be used to inspect the connection tracking entries in the datapath. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpctl.c | 45 + lib/dpctl.man | 24 2 files changed, 69 insertions(+) diff

[ovs-dev] [PATCH 10/11] system-traffic: use `dpctl/*conntrack` instead of `conntrack` tool.

state mapping done in tcp_state_coalesce(), SYN_RECV is replaced by ESTABLISHED in four places in the testsuite. The rest of the changes are just done to match the formatting style. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- tests/system-common-macros.at | 10 ++--

[ovs-dev] [PATCH 05/11] dpif-netlink: Implement ct_dump_{start, next, done}.

. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dpif-netlink.c | 58 +++--- 1 file changed, 55 insertions(+), 3 deletions(-) diff --git a/lib/dpif-netlink.c b/lib/dpif-netlink.c index fa995c1..189506c 100644 --- a/li

Re: [ovs-dev] [PATCH] INSTALL.DPDK.md: Fix small documentation error in ovs with DPDK installation

On 29/10/2015 04:44, "Mauricio Vásquez" wrote: >The openvswitch directory does not exist anymore, boot.sh and configure >are >located at $(OVS_DIR). > >Signed-off-by: Mauricio Vasquez B >

Re: [ovs-dev] [PATCH] INSTALL.DPDK: Mention issue with QEMU v2.4.0 & dpdkvhostuser

Hi, Is this a bug in OVS code? In this case I think we can work on a fix, rather than suggesting to downgrade QEMU. If this is a bug in DPDK librte_vhost, is there a fix available (on master, or on the mailing list)? Thanks On 29/10/2015 04:50, "Ciara Loftus" wrote:

Re: [ovs-dev] [PATCH v2] netdev-dpdk: Clean-up after vHost User port delete

I applied this to master, thanks On 21/10/2015 06:50, "Ciara Loftus" wrote: >Unregister and delete the socket associated with a vhost-user >port when the port is deleted and/or the switch is brought down. >Do not delete the socket if the vhost-user device is still

Re: [ovs-dev] [PATCH] netdev-dpdk: Fix comment about vhost cuse/user vswitchd arguments

Thanks for the fix, I applied this to master On 21/10/2015 02:41, "Ciara Loftus" wrote: >Signed-off-by: Ciara Loftus >--- > lib/netdev-dpdk.c | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > >diff --git a/lib/netdev-dpdk.c

[ovs-dev] [PATCH] vtep-ctl: Exit if database connection fails.

tl and ovn-sbctl. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> CC: Ansis Atteka <aatt...@nicira.com> CC: Gurucharan Shetty <shet...@nicira.com> --- vtep/vtep-ctl.c | 5 + 1 file changed, 5 insertions(+) diff --git a/vtep/vtep-ctl.c b/vtep/vtep-ctl.c i

Re: [ovs-dev] [PATCH] vtep-ctl: Exit if database connection fails.

On 22/10/2015 16:11, "Justin Pettit" <jpet...@nicira.com> wrote: >> >> On Oct 22, 2015, at 2:37 PM, Daniele Di Proietto >><diproiet...@vmware.com> wrote: >> >> Before this commit vtep-ctl hung forever if it didn't manage to reach >> t

Re: [ovs-dev] [PATCH] Detailed documentation for configuring native userspace-tunneling in OVS with/without DPDK.

Thanks for writing this up, it will definitely help many users. I'm not sure the appropriate place for this is the OVS source tree (given that's similar to README-native-tunneling.md), but this seems a perfect candidate for a configuration cookbook

Re: [ovs-dev] [PATCH] dpctl: Fix jump through wild pointer in "dpctl/help".

d-at: >https://urldefense.proofpoint.com/v2/url?u=http-3A__openvswitch.org_piperm >ail_discuss_2015-2DOctober_019135.html=BQIGaQ=Sqcl0Ez6M0X8aeM67LKIiDJA >XVeAw-YihVMNtXt-uEs=SmB5nZacmXNq0gKCC1s_Cw5yUNjxgD4v5kJqZ2uWLlE=OrWGS3 >tQ3PzCvpaif3pjUIuOxAY8nQCTY_8Q_Qs_Wj8=TeEaw1_lnbTmgin2fd7Sjw0dEf__XAROJU >z7KORhS

Re: [ovs-dev] [PATCH v5] dpif-netdev: proper tx queue id

Hi Ben, I apologize for the delay, I can definitely review this. Thanks, Daniele On 12/10/2015 19:09, "Ben Pfaff" wrote: >Daniele, are you the right person to review this? If not, do you know >who should review it? ___ dev

Re: [ovs-dev] [PATCH v5] dpif-netdev: proper tx queue id

Hi Ilya, Sorry for the delay, One question inline On 11/09/2015 12:38, "Ilya Maximets" wrote: >Currently tx_qid is equal to pmd->core_id. This leads to unexpected >behavior if pmd-cpu-mask different from '/(0*)(1|3|7)?(f*)/', >e.g. if core_ids are not sequential, or

Re: [ovs-dev] [PATCH] netdev_dpdk.c: Add QoS functionality.

On 12/10/2015 18:02, "Stokes, Ian" <ian.sto...@intel.com> wrote: >Hi Daniele, > >Thanks for providing feedback, answers inline. > >> -----Original Message- >> From: Daniele Di Proietto [mailto:diproiet...@vmware.com] >> Sent: Friday, October

Re: [ovs-dev] [PATCH] netdev_dpdk.c: Add QoS functionality.

Hi, Thanks for the patch, the implementation looks simpler than I expected. General questions: * It appears that we're using the srCTM, but * We're only sending the green packets and dropping the rest. * The `input_color` is always green. Therefore * `other-config:ebs` is ignored

Re: [ovs-dev] [PATCHv4 06/11] Add support for connection tracking.

Hi Joe, I have a couple of minor comments inline On 02/10/2015 22:16, "Joe Stringer" wrote: >This patch adds a new action and fields to OVS that allow connection >tracking to be performed. This support works in conjunction with the >Linux kernel support merged into the

Re: [ovs-dev] [PATCHv3 11/11] system-traffic: Add ct tests using local stack.

On 30/09/2015 17:59, "Joe Stringer" wrote: >On 30 September 2015 at 09:03, Ben Pfaff wrote: >> On Tue, Sep 29, 2015 at 01:40:34PM -0700, Joe Stringer wrote: >>> When interacting with the local stack, the kernel may provide packets >>> with existing ct

Re: [ovs-dev] [RFC] travis: Use container infrastructure.

On 29/09/2015 04:27, "Ben Pfaff" <b...@nicira.com> wrote: >On Mon, Sep 28, 2015 at 07:36:37PM +0100, Daniele Di Proietto wrote: >> Recently some testcases have been failing in travis because of a warning >> related to the use of an L3 device (OpenVZ specific) in

Re: [ovs-dev] [RFC] travis: Use container infrastructure.

On 29/09/2015 18:51, "Ben Pfaff" <b...@nicira.com> wrote: >On Tue, Sep 29, 2015 at 10:47:56AM -0700, Joe Stringer wrote: >> On 28 September 2015 at 20:27, Ben Pfaff <b...@nicira.com> wrote: >> > On Mon, Sep 28, 2015 at 07:36:37PM +0100, Daniele Di Proie

[ovs-dev] [PATCH] travis: Install `bc` utility for kernel compilation

Newer kernels appear to require `bc` to build all the headers Also, alphabetize the package list Tested-at: https://travis-ci.org/ddiproietto/ovs/builds/82757574 Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- .travis.yml | 3 ++- 1 file changed, 2 insertions(+), 1 de

Re: [ovs-dev] [PATCH] travis: Install `bc` utility for kernel compilation

On 29/09/2015 18:56, "Ben Pfaff" <b...@nicira.com> wrote: >On Tue, Sep 29, 2015 at 06:55:26PM +0100, Daniele Di Proietto wrote: >> Newer kernels appear to require `bc` to build all the headers >> >> Also, alphabetize the package list >> >> Teste

[ovs-dev] [RFC] travis: Use container infrastructure.

access anymore, but we can install packages with the apt plugin, and we shouldn't use root for anything else Tested-at: https://travis-ci.org/ddiproietto/ovs/builds/81764972 Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> CC: Joe Stringer <joestrin...@nicira.com> ---

Re: [ovs-dev] [PATCH] dpif-netdev: move header prefetch earlier into the receive function

I tested the patch, but I wasn't able to reproduce your measurements. On my test setup I noticed no difference in throughput for different packet sizes/flow tables. Could you describe your setup in more details? I'd be happy to improve prefetching if it a simple change like the this. Thanks,

Re: [ovs-dev] [PATCHv2 1/6] Add support for connection tracking.

Hi Joe, thanks for sending this! While doing some testing with my userspace connection tracker on top of your series I encountered some small issues that I was hoping you could squash in before pushing it to master. None of the comments is supposed to be a blocker, we can address them after

Re: [ovs-dev] [PATCH] docs: Expand performance tuning section in INSTALL.DPDK.md.

Thanks for taking the time to write this up, it is really detailed! I think some of the information is more for developers than end users, but I don't think this means it shouldn't be in INSTALL.DPDK.md. I've fixed a couple of typos with a spell checker and applied this to master. Thanks On

Re: [ovs-dev] [PATCH v3] dpif-netdev: Check for PKT_RX_RSS_HASH flag.

On 10/09/2015 20:16, "Pravin Shelar" <pshe...@nicira.com> wrote: >On Thu, Sep 10, 2015 at 10:02 AM, Daniele Di Proietto ><diproiet...@vmware.com> wrote: >> DPDK mbufs contain a valid RSS hash only if PKT_RX_RSS_HASH is >> set in 'ol_flags'. Otherwise t

Re: [ovs-dev] [PATCH v2] dpif-netdev: Check for PKT_RX_RSS_HASH flag.

On 09/09/2015 18:56, "Pravin Shelar" <pshe...@nicira.com> wrote: >On Wed, Sep 9, 2015 at 8:45 AM, Daniele Di Proietto ><diproiet...@vmware.com> wrote: >> DPDK mbufs contain a valid RSS hash only if PKT_RX_RSS_HASH is >> set in 'ol_flags'. Otherwise t

[ovs-dev] [PATCH v3] dpif-netdev: Check for PKT_RX_RSS_HASH flag.

Flavio Leitner <f...@sysclose.org> Acked-by: Kevin Traynor <kevin.tray...@intel.com> Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- lib/dp-packet.h| 25 + lib/dpif-netdev.c | 5 +++-- lib/netdev-bsd.c | 2 +- lib/netdev-dpdk.c |

Re: [ovs-dev] [PATCH v4] dpif-netdev: proper tx queue id

Sorry for the delay. There's still one problem with this patch: when a non-DPDK port is added to the datapath, its txqs are not added to the pmd threads. Can you confirm the issue? Thanks On 10/09/2015 07:52, "Ilya Maximets" wrote: >Ping. > >On 02.09.2015 14:44, Ilya

[ovs-dev] [PATCH v2] dpif-netdev: Check for PKT_RX_RSS_HASH flag.

Flavio Leitner <f...@sysclose.org> Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- v1 -> v2: * Added a comment above dp_packet_get_rss_hash() * Added an OVS_UNUSED attribute on dp_packet_rss_valid() --- lib/dp-packet.h | 13 + lib/dpif-netdev.c | 2 +-

Re: [ovs-dev] [PATCH] dpif-netdev: Check for PKT_RX_RSS_HASH flag.

On 08/09/2015 18:12, "Traynor, Kevin" <kevin.tray...@intel.com> wrote: > > >> -Original Message- > >> From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Daniele Di > >> Proietto > >> Sent: Tuesday, June 16, 2015 7:39

Re: [ovs-dev] travis build failures--dpdk 2.1

On 09/09/2015 17:38, "Ben Pfaff" wrote: >We're starting to get build failures in travis starting from "dpdk: add >support for v2.1.0", see >https://urldefense.proofpoint.com/v2/url?u=https-3A__travis-2Dci.org_openv

[ovs-dev] [PATCH] travis: Fix build with --enable-shared and DPDK 2.1.

of the file. Furthermore, since vhost support is enabled by default in DPDK 2.1 and vhost-user is OVS primary target, there's no need to customize the vhost related option anymore. Signed-off-by: Daniele Di Proietto <diproiet...@vmware.com> --- .travis/build.sh | 4 +--- 1 file chan

Re: [ovs-dev] [PATCH] travis: Fix build with --enable-shared and DPDK 2.1.

On 09/09/2015 17:56, "Ben Pfaff" <b...@nicira.com> wrote: >On Wed, Sep 09, 2015 at 05:44:04PM +0100, Daniele Di Proietto wrote: >> When building OVS with --enable-shared, -fPIC should be used in DPDK >> CFLAGS. We used to add a custom option for this (CONFIG

Re: [ovs-dev] [PATCH v3] dpdk: add support for v2.1.0

The patch looks good, I added you and Michal in AUTHORS and pushed it to master. Thanks On 08/09/2015 07:56, "Puha, TimoX" wrote: >Hi, > >> From: Puha, TimoX >> Subject: [PATCH v3] dpdk: add support for v2.1.0 >> >> Update relevant artifacts to add support for DPDK

Re: [ovs-dev] [PATCH V2 2/2] dpif-netdev: Purge all ukeys when reconfigure pmd.

I've tested it and it appears to correctly keep all the stats. Two comments inline, otherwise: Acked-by: Daniele Di Proietto diproiet...@vmware.com Thanks for fixing this Alex! On 28/08/2015 06:25, Alex Wang ee07b...@gmail.com wrote: When dpdk configuration changes, all pmd threads

Re: [ovs-dev] [PATCH V2 1/2] ofproto-dpif-upcall: Do not attribute stats when flow_del returns error.

With the older version of this series I was able to reproduce the problem and this patch appears to fix it. Acked-by: Daniele Di Proietto diproiet...@vmware.com Thanks! On 28/08/2015 06:25, Alex Wang ee07b...@gmail.com wrote: In the push_ukey_ops__(), when flow_del operation returns error

Re: [ovs-dev] [PATCH V2 2/2] dpif-netdev: Purge all ukeys when reconfigure pmd.

On 28/08/2015 18:51, Joe Stringer joestrin...@nicira.com wrote: On 28 August 2015 at 09:41, Daniele Di Proietto diproiet...@vmware.com wrote: I've tested it and it appears to correctly keep all the stats. Two comments inline, otherwise: Acked-by: Daniele Di Proietto diproiet...@vmware.com

Re: [ovs-dev] [PATCH] dpdk: add support for v2.1.0

The patch looks good, thanks. Two comments below On 26/08/2015 13:44, Timo Puha timox.p...@intel.com wrote: Update relevant artifacts to add support for DPDK v2.1.0 - INSTALL.DPDK.md - acinclude.m4: Change DPDK library name - netdev-dpdk: Add 16 bytes extra padding to mbuf size to adapt to

Re: [ovs-dev] [PATCH] coverage: Add coverage_try_clear() for performance-critical threads.

Hi Alex, sorry for the delay and thanks for taking care of this. I couldn't experience any noticeable performance drop. Acked-by: Daniele Di Proietto diproiet...@vmware.com On 22/08/2015 16:44, Alex Wang al...@nicira.com wrote: Sorry for the delay of pushing this and related dpdk patches

Re: [ovs-dev] [PATCHv2 1/5] system-common-macros: Allow quotes in NS_EXEC().

Acked-by: Daniele Di Proietto diproiet...@vmware.com On 12/08/2015 22:01, Joe Stringer joestrin...@nicira.com wrote: This allows arbitrary commands to be passed into the NS_EXEC macro to be executed within a namespace, including commands that have quotes and commands chained together. Signed

Re: [ovs-dev] [PATCHv2 5/5] kmod-traffic: Add basic vxlan tunnel sanity test.

It works both for userspace and kernel datapath, thanks! Acked-by: Daniele Di Proietto diproiet...@vmware.com On 12/08/2015 22:01, Joe Stringer joestrin...@nicira.com wrote: This test is skipped if the 'ip' command cannot interpret the vxlan 'dstport' option; this is used as a proxy

Re: [ovs-dev] [PATCHv2 2/5] system-traffic: Check ping-by-ping output.

Acked-by: Daniele Di Proietto diproiet...@vmware.com On 12/08/2015 22:01, Joe Stringer joestrin...@nicira.com wrote: Rather than saving all of the ping output to a file then checking at the end, check each ping and fail as soon as there is a connectivity failure. Signed-off-by: Joe Stringer

Re: [ovs-dev] [PATCHv2 4/5] system-macros: Don't explicitly remove bridge.

Acked-by: Daniele Di Proietto diproiet...@vmware.com On 12/08/2015 22:01, Joe Stringer joestrin...@nicira.com wrote: Depending on the kernel in use, manually removing a bridge during OVS_VSWITCHD_STOP can cause the kernel to send a route update that refers to the bridge device which is being

Re: [ovs-dev] [PATCH v2] dpif-netdev: proper tx queue id

Sorry about the long wait. I think this is the right direction, I like the idea of having a thread local map of the txqs. It will allow us to assign the txqs in a more sophisticated way. I see some unit tests failing with this patch applied. Could you try running the testsuite with 'make

Re: [ovs-dev] [PATCH 1/2] dpif-netdev: Purge all ukeys when reconfigure pmd.

The patch looks good to me. I think that losing some packets when the thread are reconfigured is unavoidable, considering that often the NIC must be stopped to change the number of rxqs. Does this make sense? Related to this, I've had an offline discussion with Ethan and we realized that ukeys

[ovs-dev] Status of Open vSwitch with DPDK

There has been some discussion lately about the status of the Open vSwitch port to DPDK. While part of the code has been tested for quite some time, I think we can agree that there are a few rough spots that prevent it from being easily deployed and used. I was hoping to get some feedback from

Re: [ovs-dev] [PATCH 2/5] system-common-macros: Don't use bash to exec in ns.

() and NS_CHECK_EXEC_UNQUOTED(). I've seen this other places in OVS testsuite. On 10 August 2015 at 11:40, Daniele Di Proietto diproiet...@vmware.com wrote: I guess you need this to use quotes() inside 'command'. One effect of this change is that if 'command' contains a pipe (or , or ||) just the first command

Re: [ovs-dev] [PATCH 1/5] system-kmod-macros: Fix VSWITCHD_STOP.

I'm surprised as well that the tests were passing. Sorry about this and thanks for finding out Acked-by: Daniele Di Proietto diproiet...@vmware.com On 08/08/2015 00:28, Joe Stringer joestrin...@nicira.com wrote: This was renamed. Surprisingly, the tests still pass without this, however

Re: [ovs-dev] [PATCH 4/5] system-macros: Create ADD_BR variant.

My idea was to use ADD_BR inside the OVS_TRAFFIC_VSWITCHD_START() parameters, but I'm fine with this approach too. Acked-by: Daniele Di Proietto diproiet...@vmware.com On 08/08/2015 00:28, Joe Stringer joestrin...@nicira.com wrote: This patch splits ADD_BR into two commands, so they can be used

Re: [ovs-dev] [PATCH 2/5] system-common-macros: Don't use bash to exec in ns.

I guess you need this to use quotes() inside 'command'. One effect of this change is that if 'command' contains a pipe (or , or ||) just the first command will be executed inside the namespace. I'm not sure if it's a big problem. What do you think? On 08/08/2015 00:28, Joe Stringer

[ovs-dev] [PATCH v2 2/4] tests: Introduce NS_EXEC and NS_CHECK_EXEC for system tests.

Instead of repeating every time ip netns exec ... it is better to introduce some macros. Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- tests/system-common-macros.at | 27 +-- tests/system-traffic.at | 24 2 files changed, 33

[ovs-dev] [PATCH v2 4/4] Vagrantfile: Add test_ovs_system_userspace provision.

with system networking. Suggested-by: Joe Stringer joestrin...@nicira.com Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- INSTALL.md | 7 +++ NEWS| 3 +++ Vagrantfile | 6 ++ 3 files changed, 16 insertions(+) diff --git a/INSTALL.md b/INSTALL.md index 3dc16aa..9dac430

Re: [ovs-dev] [PATCH 0/3] Vagrant userspace testsuite

On 07/08/2015 19:15, Joe Stringer joestrin...@nicira.com wrote: On 4 August 2015 at 11:00, Daniele Di Proietto diproiet...@vmware.com wrote: This series adds a new testsuite for the userspace datapath that runs the already written kmod-sanity tests. The reason for this are explained

[ovs-dev] [PATCH v2 3/4] tests: Add system-userspace-testsuite.

) The userspace datapath is able to use system network interfaces via an AF_PACKET socket. Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- tests/.gitignore| 1 + tests/automake.mk | 22 ++-- tests/system-common-macros.at

[ovs-dev] [PATCH v2 1/4] tests: Rename kmod-testsuite to system-kmod-testsuite.

The name makes more sense, especially with the addition of a userspace system testsuite. No functional change in this commit. Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- tests/.gitignore | 2 +- tests/automake.mk | 24 - tests/kmod

[ovs-dev] [PATCH v2 0/4] Vagrant userspace testsuite

to remove port in ADD_VETH. * Introduced NS_EXEC and NS_CHECK_EXEC to abstract the namespace commands. * Added mention in NEWS. Daniele Di Proietto (4): tests: Rename kmod-testsuite to system-kmod-testsuite. tests: Introduce NS_EXEC and NS_CHECK_EXEC for system tests. tests: Add system

Re: [ovs-dev] [PATCH] dpif-netdev: proper tx queue id

On 05/08/2015 13:28, Ilya Maximets i.maxim...@samsung.com wrote: Currently tx_qid is equal to pmd-core_id. This leads to wrong behavior if pmd-cpu-mask different from '/(0*)(1|3|7)?(f*)/', e.g. if core_ids are not sequential, or doesn't start from 0, or both. Example(just one of possible wrong

Re: [ovs-dev] [PATCH] dpif-netdev: proper tx queue id

* ) pmd2 will call netdev_send(netdev=dpdk0, tx_qid= *pmd2-core_id* ) I agree, on current master they can't. I meant with this patch applied. On 05.08.2015 17:54, Daniele Di Proietto wrote: On 05/08/2015 13:28, Ilya Maximets i.maxim...@samsung.com wrote: Currently tx_qid is equal

Re: [ovs-dev] [PATCH] dpif-netdev: proper tx queue id

On 05/08/2015 17:47, Ilya Maximets i.maxim...@samsung.com wrote: On 05.08.2015 19:26, Daniele Di Proietto wrote: On 05/08/2015 16:42, Ilya Maximets i.maxim...@samsung.com wrote: Sorry, I agree that example is incorrect. It is really not true, because of using ovs_numa_get_n_cores

Re: [ovs-dev] [PATCH 3/3] tests: Add userspace-testsuite.

to test the userspace datapath as well as the kernel module. On 4 August 2015 at 11:00, Daniele Di Proietto diproiet...@vmware.com wrote: @@ -32,10 +32,11 @@ m4_define([ADD_NAMESPACES], # The existing 'port' or 'ovs-port' will be removed before new ones are added. # m4_define([ADD_VETH

[ovs-dev] [PATCH 0/3] Vagrant userspace testsuite

. The testsuite is called `userspace-testsuite` and can be launched with `make check-userspace`. Daniele Di Proietto (3): tests: Rename kmod-traffic.at to traffic.at. kmod-macros: Move some code to traffic-common-macros. tests: Add userspace-testsuite. tests/.gitignore | 1 + tests

[ovs-dev] [PATCH 2/3] kmod-macros: Move some code to traffic-common-macros.

These macros will also be used by userspace datapath testing in following commits. No functional change in this commit. Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- tests/automake.mk | 1 + tests/kmod-macros.at | 54

[ovs-dev] [PATCH 3/3] tests: Add userspace-testsuite.

datapath is able to use system network interfaces via an AF_PACKET socket. Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- tests/.gitignore | 1 + tests/automake.mk | 21 +++-- tests/kmod-macros.at | 19 --- tests

Re: [ovs-dev] [PATCH 1/3] tests: Expand kernel sanity tests.

On 04/08/2015 02:38, Joe Stringer joestrin...@nicira.com wrote: On 30 July 2015 at 11:21, Daniele Di Proietto diproiet...@vmware.com wrote: Acked-by: Daniele Di Proietto diproiet...@vmware.com On 30/07/2015 00:52, Joe Stringer joestrin...@nicira.com wrote: The initial sanity test only

[ovs-dev] [PATCH 1/3] tests: Rename kmod-traffic.at to traffic.at.

The file will be part of two different testsuites: one for the kernel datapath and another for the userspace datapath. No functional change in this commit. Signed-off-by: Daniele Di Proietto diproiet...@vmware.com --- tests/automake.mk | 2 +- tests/kmod-testsuite.at | 2 +- tests

Re: [ovs-dev] [PATCH 3/3] tests: Add basic vxlan tunnel sanity test.

On 31/07/2015 01:30, Joe Stringer joestrin...@nicira.com wrote: On 30 July 2015 at 11:37, Daniele Di Proietto diproiet...@vmware.com wrote: I get a warning in the OVS log that causes this test to fail. It appears that when br0 is removed (in OVS_KMOD_VSWITCHD_STOP) OVS gets a rtnetlink

Re: [ovs-dev] [PATCH 1/3] tests: Expand kernel sanity tests.

Acked-by: Daniele Di Proietto diproiet...@vmware.com On 30/07/2015 00:52, Joe Stringer joestrin...@nicira.com wrote: The initial sanity test only checked IPv4 without IP fragments. This patch adds additional tests using IPv6 and VLANs with IP fragments and expands the existing test to be more

Re: [ovs-dev] [PATCH 2/3] kmod-macros: Don't unload kmod in VSWITCHD_STOP.

Acked-by: Daniele Di Proietto diproiet...@vmware.com On 30/07/2015 00:52, Joe Stringer joestrin...@nicira.com wrote: We already queue the removal of the kernel module in OVS_VSWITCHD_START, via an ON_EXIT() call. This redundant removal also doesn't interact very well with usage of vports

Re: [ovs-dev] [PATCH 3/3] tests: Add basic vxlan tunnel sanity test.

, 0% packet loss, time 0ms ]) +AT_CHECK([ip addr del dev br0 10.1.1.100/24]) +AT_CHECK([ip addr del dev br-ovs-p0 172.31.1.100/24]) + OVS_KMOD_VSWITCHD_STOP AT_CLEANUP I'll leave it up to you, I can also make this change in my next series. Acked-by: Daniele Di Proietto diproiet...@vmware.com

Re: [ovs-dev] [PATCH] netdev-dpdk: add support for rings in secondary processes in IVSHMEM setups

This is interesting, thanks for the patch. I'm definitely not a IVSHMEM expert, but I have a concern: what happens if the secondary OVS process allocates or frees some mbufs? (e.g because a packet is sent to multiple destinations or is dropped) I found this in the DPDK documentation:

Re: [ovs-dev] [PATCH] dpif-netdev: fix race for queues between pmd threads

= ovs_thread_create(pmd, pmd_thread_main, pmd[i]); } VLOG_INFO(Created %d pmd threads on numa node %d, can_have, numa_id); +dp_netdev_reload_pmds(dp); } } On 24.07.2015 19:42, Daniele Di Proietto wrote: That's a bad race condition, thanks for reporting it! Regarding

Re: [ovs-dev] [PATCH v2] dpif-netdev: fix race for queues between pmd threads

all of them have been configured. Cc: Daniele Di Proietto diproiet...@vmware.com Cc: Dyasly Sergey s.dya...@samsung.com Signed-off-by: Ilya Maximets i.maxim...@samsung.com --- lib/dpif-netdev.c | 21 ++--- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/lib/dpif

Re: [ovs-dev] [PATCH] dpif-netdev: fix race for queues between pmd threads

That's a bad race condition, thanks for reporting it! Regarding the fix, I agree that reloading the threads would restore the correct mapping, but it would still allow the threads to run with the incorrect mapping for a brief interval. How about postponing the actual threads creation until all

Re: [ovs-dev] [PATCH 1/2] netdev-dpdk: Restore txq/rxq number if initialization fails.

AM, Traynor, Kevin kevin.tray...@intel.commailto:kevin.tray...@intel.com wrote: -Original Message- From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Daniele Di Proietto Sent: Thursday, July 16, 2015 7:48 PM To: dev@openvswitch.orgmailto:dev@openvswitch.org Subject: [ovs-dev

<    5   6   7   8   9   10   11   12   13   14   >