Re: [ovs-dev] [PATCH v4 3/3] ofp-util: Fix memory leaks when parsing OF1.5 group properties.

That's great! Thank you for running these tests. --Justin > On Sep 22, 2017, at 7:32 PM, Bhargava Shastry > wrote: > > If I may, the v4 series of patches are holding up quite well to > medium-term fuzzing (roughly 50 million iterations). > > On 09/23/2017

Re: [ovs-dev] [ovs-security] RFC: Adding OvS to fuzzer test suite

Hi, Any thoughts on the proposal I made? The bugs libFuzzer has helped find recently makes a compelling case to integrate OvS with oss-fuzz. Regards, Bhargava On 09/01/2017 05:31 PM, Bhargava Shastry wrote: > Dear all, > > I suppose the following are the agenda points for adding OvS to

Re: [ovs-dev] [PATCH v4 3/3] ofp-util: Fix memory leaks when parsing OF1.5 group properties.

If I may, the v4 series of patches are holding up quite well to medium-term fuzzing (roughly 50 million iterations). On 09/23/2017 12:01 AM, Ben Pfaff wrote: > On Fri, Sep 22, 2017 at 02:28:16PM -0700, Justin Pettit wrote: >> >>> On Sep 21, 2017, at 9:59 AM, Ben Pfaff wrote: >>>

Re: [ovs-dev] 答复: [PATCH v1 1/3] Add multipath static router in OVN northd and north-db

Sorry for misleading, in my other testing, I ping the IP(is a router port's IP) and saw packets go into a chassis(router are pined on this ovn-chassis by using option:chassis=x). So in that time I though the router should be only on a specific ovn-node if route was pinned. Miguel had told

[ovs-dev] Calendario del mes de Octubre

Buenos días Le hacemos llegar la programación de Octubre para que elija los temas que necesita usted y su equipo de trabajo. -Reclutamiento, Entrevistas y Selección de Personal – 05 octubre – 6 horas -Cómo Proveer Servicio al Cliente que Impacte y Sorprenda – 06 octubre – 3 horas -Sistemas

Re: [ovs-dev] [PATCH] ovs-save: Use --bundle to restore flows (on OpenFlow 1.4+)

On Fri, 8 Sep 2017 13:03:48 +0200 Timothy Redaelli wrote: > If possible, use OpenFlow 1.4 atomic bundle transaction to restore flows. > The patch uses also the enabled OpenFlow version to do the queries. > > With the actual implementation if you have the default openflow

Re: [ovs-dev] [PATCH v4 0/2] Add system service to delete transient ports on boot.

On Wed, 13 Sep 2017 09:35:32 +0200 Timothy Redaelli wrote: > Add a systemd service file that is only executed the first time > ovsdb-server starts after boot and that removes all transient ports > (--delete-transient-ports). > > This is important on certain environments

Re: [ovs-dev] [PATCH] rhel: fix log directory permissions

On Fri, 22 Sep 2017 09:44:18 -0400 Aaron Conole wrote: > When the logrotate script runs, and Open vSwitch is running as a non-root > user, the /var/log/openvswitch directory doesn't have other rx bits set. > This means the reopen attempt will fail with "permission denied",

Re: [ovs-dev] [PATCH v4 2/3] ofp-util: Fix memory leaks on error cases in ofputil_decode_group_mod().

On Fri, Sep 22, 2017 at 02:26:36PM -0700, Justin Pettit wrote: > > > On Sep 21, 2017, at 9:59 AM, Ben Pfaff wrote: > > > > Found by libFuzzer. > > > > Reported-by: Bhargava Shastry > > Signed-off-by: Ben Pfaff > > Acked-by:

Re: [ovs-dev] [PATCH v4 1/3] ofp-util: Fix buffer overread in ofputil_decode_bundle_add().

On Fri, Sep 22, 2017 at 02:06:01PM -0700, Justin Pettit wrote: > > > On Sep 21, 2017, at 9:59 AM, Ben Pfaff wrote: > > > > A buffer overread of up to 4 bytes was possible given a malformed > > message. The message was discarded following the overread. > > > > Found by libFuzzer.

Re: [ovs-dev] [PATCH] datapath-windows: Fix bugs in cleaner threads

Good catch. Thanks for fixing it. Acked-by: Anand Kumar Thanks, Anand Kumar On 9/22/17, 2:24 PM, "ovs-dev-boun...@openvswitch.org on behalf of Shashank Ram" wrote: Conntrack, Conntrack-related, Stt,

Re: [ovs-dev] [PATCH v4 3/3] ofp-util: Fix memory leaks when parsing OF1.5 group properties.

> On Sep 21, 2017, at 9:59 AM, Ben Pfaff wrote: > > Found by libFuzzer. > > Reported-by: Bhargava Shastry > Signed-off-by: Ben Pfaff Acked-by: Justin Pettit --Justin

Re: [ovs-dev] [PATCH v4 2/3] ofp-util: Fix memory leaks on error cases in ofputil_decode_group_mod().

> On Sep 21, 2017, at 9:59 AM, Ben Pfaff wrote: > > Found by libFuzzer. > > Reported-by: Bhargava Shastry > Signed-off-by: Ben Pfaff Acked-by: Justin Pettit --Justin

[ovs-dev] [PATCH] datapath-windows: Fix bugs in cleaner threads

Conntrack, Conntrack-related, Stt, and IP fragmentation have cleaner threads that run periodically to clean up their respective tables. During driver unload, OvsExtDetach() calls into routines that are meant for explicitly cleaning these tables up and freeing the resources associated with these

Re: [ovs-dev] [PATCH 01/15] acinclude: Check for SKB_GSO_UDP

On 09/22/2017 12:43 PM, Andy Zhou wrote: On Mon, Sep 11, 2017 at 10:55 AM, Greg Rose wrote: Removed in kernel 4.13 Signed-off-by: Greg Rose Pushed the series to master with some minor edits. Patch 2 and 3 of the series are dropped in favor of

Re: [ovs-dev] [PATCH 14/15] Documentation: Update NEWS and FAQ.

On 09/22/2017 11:23 AM, Andy Zhou wrote: On Fri, Sep 22, 2017 at 8:02 AM, Greg Rose wrote: On 09/20/2017 03:18 PM, Andy Zhou wrote: On Mon, Sep 11, 2017 at 10:56 AM, Greg Rose wrote: Document Open vSwitch Linux kernel support for the 4.13 kernel

Re: [ovs-dev] [PATCH RFC 39/52] ovn-sbctl: Allow retries by default.

Thank you for the review. There isn't currently a way to control the number of retries. If that is a valuable feature, then it could be added. You can control the timeout for these utilities with the --timeout option (or use the "timeout" program from GNU coreutils). On Thu, Sep 21, 2017 at

Re: [ovs-dev] [PATCH 1/2] datapath: Optimize updating for OvS flow_stats.

On Sun, Sep 10, 2017 at 6:00 PM, Tonghao Zhang wrote: > Upstream commit: > commit c57c054eb5b1ccf230c49f736f7a018fcbc3e952 > Author: Tonghao Zhang > Date: Mon Jul 17 23:28:05 2017 -0700 > > openvswitch:

Re: [ovs-dev] [PATCH 01/15] acinclude: Check for SKB_GSO_UDP

On Mon, Sep 11, 2017 at 10:55 AM, Greg Rose wrote: > Removed in kernel 4.13 > > Signed-off-by: Greg Rose Pushed the series to master with some minor edits. Patch 2 and 3 of the series are dropped in favor of Tonghao's patch as per mailing list

Re: [ovs-dev] [PATCH 1/3] dpif-netdev: Rename rxq_interval.

Are there any other comments? On 8/30/17, 10:49 AM, "Darrell Ball" wrote: Thanks Kevin Naming is hard. The name looks a bit more intuitive and matches closely with the description previously added. Darrell On 8/30/17, 10:45 AM, "Kevin

Re: [ovs-dev] [PATCH 3/3] dpif-netdev: Calculate rxq cycles prior to rxq_cycle_sort calls.

Are there any other comments for this patch? On 8/30/17, 11:01 AM, "Darrell Ball" wrote: Thanks for the patch Kevin On 8/30/17, 10:45 AM, "Kevin Traynor" wrote: rxq_cycle_sort summed the latest cycles from each queue for

Re: [ovs-dev] OVS-DPDK public meeting

20th September 2017 ATTENDEES: Aaron, Ben, Flavio, Darrell, Ian, Georg, Sammeh, Yippeng, Frikkie, Kevin, Billy, Thomas M, Bhanu, Ciara, Eelco, Johan, Simon, Jan, Michael, Zoltan, Sugesh, Eelco, Jan, Ciara (Missed a couple?) === GENERAL === - Testing: Intel to share current test plan.

Re: [ovs-dev] [PATCH 14/15] Documentation: Update NEWS and FAQ.

On Fri, Sep 22, 2017 at 8:02 AM, Greg Rose wrote: > On 09/20/2017 03:18 PM, Andy Zhou wrote: >> >> On Mon, Sep 11, 2017 at 10:56 AM, Greg Rose wrote: >>> >>> Document Open vSwitch Linux kernel support for the 4.13 kernel >>> release. >>> >>>

Re: [ovs-dev] [RFC 0/2] EMC load-shedding

Thanks for working on this Billy One comment inline. On 9/22/17, 6:47 AM, "Billy O'Mahony" wrote: Hi All, Please find attached RFC patch for EMC load-shedding [1] as promised [2]. This applies clean on 5ff834 "Increment ct packet counters..." It

Re: [ovs-dev] [RFC 1/2] dpif-netdev: Fix per packet cycles statistics.

Hi Billy Maybe you need to rebase your branch; this patch was applied a couple weeks ago. Thanks Darrell On 9/22/17, 6:47 AM, "Billy O'Mahony" wrote: From: Ilya Maximets DP_STAT_LOOKUP_HIT statistics used mistakenly for

[ovs-dev] RE

Hallo ik ben de heer William Mason, de wettige eigenaar van een legitieme en betrouwbare bedrijf, ik geef geld op duidelijke en begrijpelijke voorwaarden uit en voorwaarden Mijn waarden En zakelijke filosofie zijn passievolle inzet klantenservice, zeer hoge ethische normen en integriteit en Open

[ovs-dev] locks for clustered OVSDB

We've had a couple of brief discussions during the OVN meeting about locks in OVSDB. As I understand it, a few services use OVSDB locks to avoid duplicating work. The question is whether and how to extend OVSDB locks to a distributed context. First, I think it's worth reviewing how OVSDB locks

Re: [ovs-dev] [PATCH 0/4] prioritizing latency sensitive traffic

Hi Jan, > -Original Message- > From: Jan Scheurich [mailto:jan.scheur...@ericsson.com] > Sent: Friday, September 22, 2017 12:37 PM > To: O Mahony, Billy ; Kevin Traynor > ; d...@openvswitch.org > Cc: Mechthild Buescher

Re: [ovs-dev] [PATCH 14/15] Documentation: Update NEWS and FAQ.

On 09/20/2017 03:18 PM, Andy Zhou wrote: On Mon, Sep 11, 2017 at 10:56 AM, Greg Rose wrote: Document Open vSwitch Linux kernel support for the 4.13 kernel release. Signed-off-by: Greg Rose --- Documentation/faq/releases.rst | 2 +- NEWS

[ovs-dev] [PATCH v3] dpif-netdev: Set MAX_RECIRC_DEPTH to 6.

In an ovn gateway node with DPDK, the RECIRC_DEPTH may be greater than 5. Scenes: VM ping self floating IP, or VM ping Floating IP of VMs with the same network. It need process UNDNAT SNAT in LRouter egress and UNSNAT DNAT in LRouter ingress, and output to geneve tunnel also need recirc. This

[ovs-dev] [PATCH 2/2] lib/netlink: Use correct netlink max message size

The maximum message size for recent Linux kernels is 32Kb and in older kernels it is 16KB. See http://www.spinics.net/lists/netdev/msg431592.html Adjust the size checked and update a comment. Signed-off-by: Greg Rose --- lib/netlink-socket.c | 2 +- lib/netlink.c

[ovs-dev] [PATCH 1/2] datapath: Check maximum netlink message size

In kernels < 4.9 the maximum netlink message size is 16KB. See http://www.spinics.net/lists/netdev/msg431592.html Signed-off-by: Greg Rose --- datapath/flow_netlink.c | 4 1 file changed, 4 insertions(+) diff --git a/datapath/flow_netlink.c b/datapath/flow_netlink.c

[ovs-dev] [RFC 1/2] dpif-netdev: Fix per packet cycles statistics.

From: Ilya Maximets DP_STAT_LOOKUP_HIT statistics used mistakenly for calculation of total number of packets. This leads to completely wrong per packet cycles statistics. For example: emc hits:0 megaflow hits:253702308 avg. subtable lookups per

[ovs-dev] [RFC 2/2] dpif-netdev: RFC EMC load-shedding

When EMC hit rate goes down start start shedding load from the EMC. --- lib/dpif-netdev.c | 107 -- 1 file changed, 103 insertions(+), 4 deletions(-) diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c index e3a5590..f77e79a 100644 ---

[ovs-dev] [RFC 0/2] EMC load-shedding

Hi All, Please find attached RFC patch for EMC load-shedding [1] as promised [2]. This applies clean on 5ff834 "Increment ct packet counters..." It also uses Ilya's patch "Fix per packet cycles statistics." [3] so I've included that in the patch set as it wasn't merged when I started the RFC.

[ovs-dev] [PATCH] rhel: fix log directory permissions

When the logrotate script runs, and Open vSwitch is running as a non-root user, the /var/log/openvswitch directory doesn't have other rx bits set. This means the reopen attempt will fail with "permission denied", even though the default logrotate configuration creates a new log file with the

Re: [ovs-dev] 答复: [PATCH v1 1/3] Add multipath static router in OVN northd and north-db

On Thu, Sep 21, 2017 at 10:56 AM, Miguel Angel Ajo Pelayo wrote: > On Thu, Sep 21, 2017 at 2:21 PM, Gao Zhenyu wrote: > >> I think the S/N or E/W are not the matter we should considering now. >> >> The multipath implementation is based on the

Re: [ovs-dev] [PATCH 0/4] prioritizing latency sensitive traffic

Hi Billy, > -Original Message- > From: O Mahony, Billy [mailto:billy.o.mah...@intel.com] > Sent: Friday, 22 September, 2017 10:52 > > The next question is how to classify the ingress traffic on the NIC and > > insert it > > into rx queues with different priority. Any scheme implemented

[ovs-dev] [PATCH] vhost: Expose virtio interrupt requirement on rte_vhos API

Performance tests with the OVS DPDK datapath have shown that the achievable tx throughput over a vhostuser port into a VM with an interrupt-based virtio driver is limited by the overhead incurred by virtio interrupts. The OVS PMD spends up to 30% of its cycles in system calls kicking the

Re: [ovs-dev] [PATCH v5] netdev-dpdk: reset packet_type for reused dp_packets

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/11/17, 12:56

Re: [ovs-dev] [PATCH v2 11/12] dpif-netdev: Remove 'cnt' in dp_netdev_input__().

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:31

Re: [ovs-dev] [PATCH v2 09/12] netdev-dpdk: Minor cleanup of netdev_dpdk_send__.

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:29

Re: [ovs-dev] [PATCH v2 08/12] netdev-dpdk: Cleanup dpdk_do_tx_copy.

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:28

Re: [ovs-dev] [PATCH v2 06/12] dpif-netdev: Use DP_PACKET_BATCH_FOR_EACH in fast_path_processing.

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:27

Re: [ovs-dev] [PATCH v2 05/12] dpif-netdev: Use DP_PACKET_BATCH_FOR_EACH in dp_netdev_run_meter.

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:26

Re: [ovs-dev] [PATCH v2 03/12] netdev-dpdk: Use DP_PACKET_BATCH_FOR_EACH in netdev_dpdk_ring_send

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:25

Re: [ovs-dev] [PATCH v2 01/12] conntrack: Use DP_PACKET_BATCH_FOR_EACH macro.

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/20/17, 6:23

Re: [ovs-dev] [PATCH] docs: Use DPDK 17.05.2 release.

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/13/17, 7:00

Re: [ovs-dev] [PATCH v5] dpif-netdev: Avoid reading RSS hash when EMC is disabled

I applied the patch to dpdk_merge here https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_darball_ovs_commits_dpdk-5Fmerge=DwIGaQ=uilaK90D4TOVoH58JNXRgQ=BVhFA09CGX7JQ5Ih-uZnsw=A2_FCacqbp2moAo3HGFlTuxsjONUGhlN42OBcAuQQ6w=b6btPKhgvOFr2GOUYvktND6kaC6jc3fXI-mXfvNgXOU= On 9/19/17, 2:46

Re: [ovs-dev] [PATCH 0/4] prioritizing latency sensitive traffic

Hi Jan, Kevin, > -Original Message- > From: Jan Scheurich [mailto:jan.scheur...@ericsson.com] > Sent: Thursday, September 21, 2017 4:12 PM > To: Kevin Traynor ; O Mahony, Billy > ; d...@openvswitch.org > Cc: Mechthild Buescher

Re: [ovs-dev] [PATCH 2/2] dpctl: init CT entry variable.

On 9/13/17, 5:37 AM, "ovs-dev-boun...@openvswitch.org on behalf of antonio.fische...@intel.com" wrote: ct_dpif_entry_uninit could potentially be called even if ct_dpif_dump_next failed. As ct_dpif_entry_uninit

[ovs-dev] CPU freqency is not max when running ovs_DPDK

Hi All, I am using OVS_DPDK, and the target CPU has running 100%. However, I notice the cpu frequency is NOT exceeding the max value, so the performance may not reach the best value. I have 2 pmd only for now, each is hyper-thread core in one physical core. I am not sure the reason, and do