[dpdk-dev] [PATCH v12 2/2] vhost: Add VHOST PMD

2016/03/18 ??9:27 "Bruce Richardson" : > > On Tue, Mar 15, 2016 at 05:31:41PM +0900, Tetsuya Mukawa wrote: > > The patch introduces a new PMD. This PMD is implemented as thin wrapper > > of librte_vhost. It means librte_vhost is also needed to compile the PMD. > > The vhost messages will be

[dpdk-dev] [PATCH v4] vhost: use SMP barriers instead of compiler ones.

On Fri, Mar 18, 2016 at 03:23:53PM +0300, Ilya Maximets wrote: > Since commit 4c02e453cc62 ("eal: introduce SMP memory barriers") virtio > uses architecture dependent SMP barriers. vHost should use them too. > > Fixes: 4c02e453cc62 ("eal: introduce SMP memory barriers") > > Signed-off-by: Ilya

[dpdk-dev] DPDK and HW offloads

2016-03-18 10:16, Stephen Hemminger: > As I look at how the ethernet device interface in DPDK has exploded in > complexity; Yes I would like to start addressing this complexity in 16.07. > it makes life very hard for end users. The goal has been to enable all the > cool hardware > features,

[dpdk-dev] [PATCH v2] enic: update enic PMD maintainer and pointer to the guide.

> --- a/MAINTAINERS > +++ b/MAINTAINERS > @@ -268,8 +268,8 @@ F: doc/guides/nics/cxgbe.rst > > Cisco enic > M: John Daley > -M: Sujith Sankar > -F: drivers/net/enic/ mistake here > +M: Nelson Escobar > +F: doc/guides/nics/enic.rst

[dpdk-dev] [PATCH v8 0/4] DPDK polling-mode driver for Amazon Elastic Network Adapters (ENA)

Great news! We are going to extend functionality of the ENA PMD, so from now I will send patches based on v8 version. Thanks, Jan 2016-03-18 18:04 GMT+01:00 Bruce Richardson : > On Thu, Mar 17, 2016 at 03:31:14PM +0100, Jan Medala wrote: > > v3: > > Additional features for Amazon ENA: > > *

[dpdk-dev] [PATCH v3 10/10] qede: Enable PMD build

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- config/common_base| 14 ++ drivers/net/Makefile |1 + mk/rte.app.mk |2 ++ scripts/test-build.sh |1 + 4 files changed, 18 insertions(+) diff --git a/config/common_base

[dpdk-dev] [PATCH v3 09/10] qede: Add DCBX support

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/Makefile |1 + drivers/net/qede/base/bcm_osal.h | 100 ++-- drivers/net/qede/base/ecore.h |2 + drivers/net/qede/base/ecore_dcbx.c| 887

[dpdk-dev] [PATCH v3 08/10] qede: Add attention support

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/base/ecore_attn_values.h |13287 + drivers/net/qede/base/ecore_dev.c | 51 + drivers/net/qede/base/ecore_int.c | 1131 +++ 3 files changed, 14469

[dpdk-dev] [PATCH v3 07/10] qede: Add SRIOV support

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/Makefile |2 + drivers/net/qede/base/bcm_osal.c | 57 +- drivers/net/qede/base/ecore.h |1 + drivers/net/qede/base/ecore_dev.c | 116 +-

[dpdk-dev] [PATCH v3 06/10] qede: Add L2 support

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/Makefile|2 + drivers/net/qede/base/ecore_chain.h |6 + drivers/net/qede/base/ecore_l2.c | 1608 ++ drivers/net/qede/base/ecore_l2.h

[dpdk-dev] [PATCH v3 05/10] qede: Add core driver

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/Makefile | 90 +++ drivers/net/qede/qede_eth_if.h| 176 + drivers/net/qede/qede_ethdev.c| 957 +++

[dpdk-dev] [PATCH v3 04/10] qede: Add base driver

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/base/bcm_osal.c| 129 + drivers/net/qede/base/bcm_osal.h| 407 drivers/net/qede/base/common_hsi.h | 714 ++ drivers/net/qede/base/ecore.h

[dpdk-dev] [PATCH v3 03/10] qede: Add license file

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- drivers/net/qede/LICENSE.qede_pmd | 28 1 file changed, 28 insertions(+) create mode 100644 drivers/net/qede/LICENSE.qede_pmd diff --git a/drivers/net/qede/LICENSE.qede_pmd

[dpdk-dev] [PATCH v3 02/10] qede: Add documentation

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- doc/guides/nics/index.rst|1 + doc/guides/nics/overview.rst | 78 +- doc/guides/nics/qede.rst | 340 ++ 3 files changed, 380 insertions(+), 39

[dpdk-dev] [PATCH v3 01/10] qede: Add maintainers

Signed-off-by: Harish Patil Signed-off-by: Rasesh Mody Signed-off-by: Sony Chacko --- MAINTAINERS |7 +++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8b21979..815df37 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -357,6 +357,13 @@ M: Declan Doherty

[dpdk-dev] [PATCH v3 00/10] qede: Add qede PMD

Submitting v3 patch series for QEDE PMD. There is no code change from v2 series except PMD version change. Earlier we had generated and tested the v2 series against dpdk tree then latest. The v3 series includes: - Patches generated and tested against latest dpdk-next-net - Reworked MAINTAINERS

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

On Fri, Mar 18, 2016 at 10:34:56AM +0100, Thomas Monjalon wrote: > 2016-03-18 17:16, Yuanhan Liu: > > On Fri, Mar 18, 2016 at 09:09:04AM +0100, Thomas Monjalon wrote: > > > 2016-03-18 16:00, Yuanhan Liu: > > > > On Thu, Mar 17, 2016 at 04:29:32PM +0100, Thomas Monjalon wrote: > > > > > 2016-02-24

[dpdk-dev] [PATCH 2/2] mlx5: fix handling of NULL RSS key

On Fri, Mar 18, 2016 at 01:54:43PM +0100, Nelio Laranjeiro wrote: > Update function can be called with no key to enable or disable a RSS > protocol, or with a key to be applied to the desired protocols. > > Fixes: 2f97422e7759 ("mlx5: support RSS hash update and get") > > Signed-off-by: Nelio

[dpdk-dev] [PATCH 1/2] mlx5: fix overwritten RSS configuration

On Fri, Mar 18, 2016 at 01:54:42PM +0100, Nelio Laranjeiro wrote: > RSS configuration provided by the application should not be used as storage > by the PMD. > > Fixes: 2f97422e7759 ("mlx5: support RSS hash update and get") > > Signed-off-by: Nelio Laranjeiro > --- > drivers/net/mlx5/mlx5.h

[dpdk-dev] [PATCH v8 0/4] DPDK polling-mode driver for Amazon Elastic Network Adapters (ENA)

On Fri, Mar 18, 2016 at 06:11:29PM +0100, Jan M?dala wrote: > Great news! > We are going to extend functionality of the ENA PMD, so from now I will > send patches based on v8 version. > More specifically, please base any further patches on the code on dpdk-next-net/rel_16_04 branch. At this stage

[dpdk-dev] [PATCH v8 4/4] ena: DPDK polling-mode driver for Amazon Elastic Network Adapters (ENA)

On Thu, Mar 17, 2016 at 03:31:18PM +0100, Jan Medala wrote: > This is a PMD for the Amazon ethernet ENA family. > The driver operates variety of ENA adapters through feature negotiation > with the adapter and upgradable commands set. > ENA driver handles PCI Physical and Virtual ENA functions. >

[dpdk-dev] [PATCH v9 01/11] ethdev: add API to query supported packet types

Hi Thomas, On 3/15/2016 4:50 AM, Jianfeng Tan wrote: > Add a new API rte_eth_dev_get_supported_ptypes to query what packet types > can be filled by given already started device (or its pmd rx burst function > has already been decided). > > Signed-off-by: Jianfeng Tan > Acked-by: Konstantin

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

On Fri, Mar 18, 2016 at 09:09:04AM +0100, Thomas Monjalon wrote: > 2016-03-18 16:00, Yuanhan Liu: > > On Thu, Mar 17, 2016 at 04:29:32PM +0100, Thomas Monjalon wrote: > > > 2016-02-24 14:47, Ilya Maximets: > > > > Implementation of rte_vhost_enqueue_burst() based on lockless > > > > ring-buffer >

[dpdk-dev] [PATCH v8 0/4] DPDK polling-mode driver for Amazon Elastic Network Adapters (ENA)

On Thu, Mar 17, 2016 at 03:31:14PM +0100, Jan Medala wrote: > v3: > Additional features for Amazon ENA: > * Low Latenycy Queue (LLQ) for Tx > * RSS > v4: > * Improved doc > * Improved style according to checkpatch script > * Fixed build problems on: i686, clang, +shared, +debug > v5: > * Removed

[dpdk-dev] [PATCH 1/2] mbuf: Add rte_pktmbuf_copy

Hi, > > >-Original Message- > > >From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen > > >Hemminger > > >Sent: Friday, July 10, 2015 1:38 AM > > >To: dev at dpdk.org > > >Cc: Mike Davison ; Stephen Hemminger > > > > > >Subject: [dpdk-dev] [PATCH 1/2] mbuf: Add rte_pktmbuf_copy

[dpdk-dev] Performance issue with uio_pci_generic driver

If it?s of any use for debugging I would be willing to setup teamviewer or something like that for a person to remote desktop in a VM and have an SSH access to both servers (all of this is being firewalls that are out of my control so I can?t give direct SSH access). The two servers are for

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

On Fri, Mar 18, 2016 at 11:04:49AM +0100, Thomas Monjalon wrote: > 2016-03-18 10:52, Tomasz Kulasek: > > +#if !defined(NO_HASH_MULTI_LOOKUP) && defined(__ARM_NEON) > > I think we should use CONFIG_RTE_ARCH_ARM_NEON here. > Any ARM maintainer to confirm? __ARM_NEON should work existing GCC, but

[dpdk-dev] [PATCH v8 00/11] Add API to get supported packet types

On Mon, Mar 14, 2016 at 03:42:45PM +0800, Jianfeng Tan wrote: > To achieve this, a new function pointer, dev_supported_ptypes_get, is added > into struct eth_dev_ops. For those devices who do not implement it, it > means it does not support any ptypes. > > v8: > - Rebased on

[dpdk-dev] Issues with openvswitch2.5+dpdk2.2+kvm/virtio-pci

Hi, I was trying to replicate a setup that I have working on physical devices (ixgbe) under kvm since there is a virtio pmd driver. TL;DR: - under KVM with virtio-pci (working on baremetal with ixgbe cards) - adding dpdk port to ovs fails with memzone already exists and causes a segfault - I

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

On Thu, Mar 17, 2016 at 04:29:32PM +0100, Thomas Monjalon wrote: > 2016-02-24 14:47, Ilya Maximets: > > Implementation of rte_vhost_enqueue_burst() based on lockless ring-buffer > > algorithm and contains almost all to be thread-safe, but it's not. > > > > This set adds required changes. > > > >

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

CC to list. On 18.03.2016 15:19, Ilya Maximets wrote: > > > On 18.03.2016 14:42, Ilya Maximets wrote: >> On 18.03.2016 14:30, Xie, Huawei wrote: >>> On 3/18/2016 7:00 PM, Ilya Maximets wrote: On 18.03.2016 13:47, Xie, Huawei wrote: > On 3/18/2016 6:39 PM, Ilya Maximets wrote: >> On

[dpdk-dev] [PATCH v4] vhost: use SMP barriers instead of compiler ones.

Since commit 4c02e453cc62 ("eal: introduce SMP memory barriers") virtio uses architecture dependent SMP barriers. vHost should use them too. Fixes: 4c02e453cc62 ("eal: introduce SMP memory barriers") Signed-off-by: Ilya Maximets --- lib/librte_vhost/vhost_rxtx.c | 7 --- 1 file changed, 4

[dpdk-dev] [PATCH] arm: detect NEON by RTE_MACHINE_CPUFLAG_NEON flag only

On Fri, 18 Mar 2016 14:49:57 +0100 Thomas Monjalon wrote: > 2016-03-18 13:00, Jan Viktorin: > > The RTE_MACHINE_CPUFLAG_NEON was only a result of the gcc testing. > > However, the target CPU may not support NEON or the user can disable to > > use it (as it does not always improve the

[dpdk-dev] [PATCH v12 1/2] ethdev: Add a new event type to notify a queue state changed event

2016-03-15 17:31, Tetsuya Mukawa: > This patch adds a below event type. > - RTE_ETH_EVENT_QUEUE_STATE_CHANGE > This event is used for notifying a queue state changed event. [...] > enum rte_eth_event_type { > RTE_ETH_EVENT_UNKNOWN, /**< unknown event type */ >

[dpdk-dev] [PATCH v12 2/2] vhost: Add VHOST PMD

2016-03-18 22:41, Tetsuya Mukawa: > 2016/03/18 ??9:27 "Bruce Richardson" : > > I hope to get this set merged for RC2 very soon. Can you provide an > > update for the nic overview.rst doc listing out the features of > > this new PMD. [...] > I've sent the v12 patch with vhost.rst. > Could you

[dpdk-dev] L2 Forwarding Sample Applications

>Please let me know the purpose of writing these sample applications in DPDK- > >* L2fwd-keepalive/main.c > >* L2fwd-jobstats/main.c > >* L2fwd-ivshmem/guest/guest.c > >* L2fwd-ivshmem/host/host.c I am not sure what your question is trying ask here, but these

[dpdk-dev] L2 Forwarding Sample Applications

>::DISCLAIMER:: > > >The contents of this e-mail and any attachment(s) are confidential and >intended for the named recipient(s) only. >E-mail

[dpdk-dev] [PATCH v6] examples/l3fwd: em path performance fix

It seems that for the most use cases, previous hash_multi_lookup provides better performance, and more, sequential lookup can cause significant performance drop. This patch sets previously optional hash_multi_lookup method as default. It also provides some minor optimizations such as queue drain

[dpdk-dev] [PATCH v2] ring: check for zero objects mc dequeue / mp enqueue

On Fri, Mar 18, 2016 at 01:47:29PM +0100, Mauricio V?squez wrote: > Hi, > > > On Fri, Mar 18, 2016 at 11:35 AM, Thomas Monjalon 6wind.com > > wrote: > > > 2016-03-18 11:27, Olivier Matz: > > > On 03/18/2016 11:18 AM, Bruce Richardson wrote: > > > >>> + /* Avoid the unnecessary cmpset

[dpdk-dev] [PATCH v12 2/2] vhost: Add VHOST PMD

On Fri, Mar 18, 2016 at 11:03:56PM +0900, Tetsuya Mukawa wrote: > On 2016/03/18 22:52, Thomas Monjalon wrote: > > 2016-03-18 22:41, Tetsuya Mukawa: > >> 2016/03/18 ??9:27 "Bruce Richardson" : > >>> I hope to get this set merged for RC2 very soon. Can you provide an > >>> update for the nic

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

On 18.03.2016 13:47, Xie, Huawei wrote: > On 3/18/2016 6:39 PM, Ilya Maximets wrote: >> >> On 18.03.2016 13:27, Xie, Huawei wrote: >>> On 3/18/2016 6:23 PM, Ilya Maximets wrote: On 18.03.2016 13:08, Xie, Huawei wrote: > On 2/24/2016 7:47 PM, Ilya Maximets wrote: >> *

[dpdk-dev] [PATCH 2/2] mlx5: fix handling of NULL RSS key

Update function can be called with no key to enable or disable a RSS protocol, or with a key to be applied to the desired protocols. Fixes: 2f97422e7759 ("mlx5: support RSS hash update and get") Signed-off-by: Nelio Laranjeiro --- drivers/net/mlx5/mlx5_rss.c | 6 -- 1 file changed, 6

[dpdk-dev] [PATCH 1/2] mlx5: fix overwritten RSS configuration

RSS configuration provided by the application should not be used as storage by the PMD. Fixes: 2f97422e7759 ("mlx5: support RSS hash update and get") Signed-off-by: Nelio Laranjeiro --- drivers/net/mlx5/mlx5.h| 1 + drivers/net/mlx5/mlx5_ethdev.c | 1 + drivers/net/mlx5/mlx5_rss.c|

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

On Fri, 18 Mar 2016 12:45:03 + "Kulasek, TomaszX" wrote: > > -Original Message- > > From: Jan Viktorin [mailto:viktorin at rehivetech.com] > > Sent: Friday, March 18, 2016 12:57 > > To: Thomas Monjalon > > Cc: Jerin Jacob ; Kulasek, TomaszX > > ; dev at dpdk.org; jianbo.liu at

[dpdk-dev] [PATCH v2] ring: check for zero objects mc dequeue / mp enqueue

Hi, On Fri, Mar 18, 2016 at 11:35 AM, Thomas Monjalon wrote: > 2016-03-18 11:27, Olivier Matz: > > On 03/18/2016 11:18 AM, Bruce Richardson wrote: > > >>> + /* Avoid the unnecessary cmpset operation below, which is > also > > >>> +* potentially harmful when n equals 0. */ > > >>>

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

On 18.03.2016 13:27, Xie, Huawei wrote: > On 3/18/2016 6:23 PM, Ilya Maximets wrote: >> On 18.03.2016 13:08, Xie, Huawei wrote: >>> On 2/24/2016 7:47 PM, Ilya Maximets wrote: * Wait until it's our turn to add our buffer @@ -979,7 +979,7 @@ rte_vhost_dequeue_burst(struct

[dpdk-dev] ixgbe TX function selection

On 18/03/16 00:45, Lu, Wenzhuo wrote: > Hi Zoltan, > > >> -Original Message- >> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zoltan Kiss >> Sent: Friday, March 18, 2016 1:11 AM >> To: Wu, Jingjing; dev at dpdk.org >> Subject: Re: [dpdk-dev] ixgbe TX function selection >> >> >>

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

On 18.03.2016 13:08, Xie, Huawei wrote: > On 2/24/2016 7:47 PM, Ilya Maximets wrote: >> * Wait until it's our turn to add our buffer >> @@ -979,7 +979,7 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t >> queue_id, >> entry_success++; >> } >> >> -

[dpdk-dev] [PATCH] arm: detect NEON by RTE_MACHINE_CPUFLAG_NEON flag only

The RTE_MACHINE_CPUFLAG_NEON was only a result of the gcc testing. However, the target CPU may not support NEON or the user can disable to use it (as it does not always improve the performance). The RTE_MACHINE_CPUFLAG_NEON detection is now based on both, the __ARM_NEON_FP feature from gcc and

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

Hello Thomas, Jerin, Tomasz, all... On Fri, 18 Mar 2016 12:00:24 +0100 Thomas Monjalon wrote: > 2016-03-18 16:22, Jerin Jacob: > > On Fri, Mar 18, 2016 at 11:04:49AM +0100, Thomas Monjalon wrote: > > > 2016-03-18 10:52, Tomasz Kulasek: > > > > +#if !defined(NO_HASH_MULTI_LOOKUP) &&

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

On 18.03.2016 12:46, Yuanhan Liu wrote: > On Fri, Mar 18, 2016 at 10:34:56AM +0100, Thomas Monjalon wrote: >> 2016-03-18 17:16, Yuanhan Liu: >>> On Fri, Mar 18, 2016 at 09:09:04AM +0100, Thomas Monjalon wrote: 2016-03-18 16:00, Yuanhan Liu: > On Thu, Mar 17, 2016 at 04:29:32PM +0100,

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

> -Original Message- > From: Jan Viktorin [mailto:viktorin at rehivetech.com] > Sent: Friday, March 18, 2016 12:57 > To: Thomas Monjalon > Cc: Jerin Jacob ; Kulasek, TomaszX > ; dev at dpdk.org; jianbo.liu at linaro.org > Subject: Re: [dpdk-dev] [PATCH v5] examples/l3fwd: em path

[dpdk-dev] [PATCH v4 07/12] librte_ether: extend flow director struct

Hi Jingjing, 2016-03-10 11:25, Jingjing Wu: > This patch changed rte_eth_fdir_flow from union to struct to > support more packets formats, for example, Vxlan and GRE tunnel > packets with IP inner frame. I think we need a lot more explanations about how it should work. >From this point we should

[dpdk-dev] [PATCH v12 2/2] vhost: Add VHOST PMD

On Tue, Mar 15, 2016 at 05:31:41PM +0900, Tetsuya Mukawa wrote: > The patch introduces a new PMD. This PMD is implemented as thin wrapper > of librte_vhost. It means librte_vhost is also needed to compile the PMD. > The vhost messages will be handled only when a port is started. So start > a port

[dpdk-dev] [PATCH] examples/l3fwd: prefer probed NEON flag to ARM gcc flag

Fixes: 64d3955de1de ("examples/l3fwd: fix ARM build") Suggested-by: Jerin Jacob Signed-off-by: Thomas Monjalon --- examples/l3fwd/l3fwd_em.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c index 0adf8f4..e8e7ca1 100644

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

2016-03-18 16:22, Jerin Jacob: > On Fri, Mar 18, 2016 at 11:04:49AM +0100, Thomas Monjalon wrote: > > 2016-03-18 10:52, Tomasz Kulasek: > > > +#if !defined(NO_HASH_MULTI_LOOKUP) && defined(__ARM_NEON) > > > > I think we should use CONFIG_RTE_ARCH_ARM_NEON here. > > Any ARM maintainer to confirm?

[dpdk-dev] [PATCH] app: fix for lpm in ip_pipeline

2016-03-17 09:47, Michal Jastrzebski: > From: Michal Kobylinski > > Updated ip_pipeline app is using new changes from LPM library > (Increased number of next hops and added new config structure > for LPM IPv4). > > Fixes: 7164439d017d ("lpm: add a new config structure for IPv4") Fixes:

[dpdk-dev] [PATCH] eal: add missing long-options for short option arguments

On Thu, Mar 3, 2016 at 4:02 PM, Wiles, Keith wrote: >>On Thu, Feb 25, 2016 at 11:12 PM, Wiles, Keith >>wrote: On Thu, Feb 25, 2016 at 01:09:16PM -0600, Keith Wiles wrote: > A number of short options for EAL are missing long options > and this patch adds those missing options. >

[dpdk-dev] [PATCH v2] ring: check for zero objects mc dequeue / mp enqueue

2016-03-18 11:27, Olivier Matz: > On 03/18/2016 11:18 AM, Bruce Richardson wrote: > >>> + /* Avoid the unnecessary cmpset operation below, which is also > >>> +* potentially harmful when n equals 0. */ > >>> + if (n == 0) > >>> > >> > >> What about using unlikely here? > >> > >

[dpdk-dev] [PATCH v2] enic: fix incorrect setting of rx descriptor limit

From: Nelson Escobar On initialization, the rq descriptor count was set to the limit of the vic. When the requested number of rx descriptors was less than this count, enic_alloc_rq() was incorrectly setting the count to the lower value. This results in later calls to

[dpdk-dev] [PATCH v2] ring: check for zero objects mc dequeue / mp enqueue

Hi, On 03/18/2016 11:18 AM, Bruce Richardson wrote: >>> diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h >>> index 943c97c..eb45e41 100644 >>> --- a/lib/librte_ring/rte_ring.h >>> +++ b/lib/librte_ring/rte_ring.h >>> @@ -431,6 +431,11 @@ __rte_ring_mp_do_enqueue(struct

[dpdk-dev] [PATCH v3] enic: update enic PMD maintainer and pointer to the guide.

Change maintainers for ENIC PMD and fix pointer to enic documentation in MAINTAINERS. Signed-off-by: John Daley --- replace removed line MAINTAINERS | 3 ++- doc/guides/nics/enic.rst | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

2016-03-18 10:10, Xie, Huawei: > On 3/18/2016 5:55 PM, Ilya Maximets wrote: > > Hi all. > > And what about first patch of this series: > > "vhost: use SMP barriers instead of compiler ones." ? > > > > It's not about thread safety in terms of 'lockless'. It is the standalone > > patch that fixes

[dpdk-dev] [PATCH v11 5/8] ethdev: add speed capabilities

2016-03-18 10:28, Adrien Mazarguil: > On Thu, Mar 17, 2016 at 07:09:02PM +0100, Thomas Monjalon wrote: > > --- a/drivers/net/mlx4/mlx4.c > > +++ b/drivers/net/mlx4/mlx4.c > > @@ -4301,6 +4301,8 @@ mlx4_dev_infos_get(struct rte_eth_dev *dev, struct > > rte_eth_dev_info *info) > > 0);

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

2016-03-18 10:52, Tomasz Kulasek: > +#if !defined(NO_HASH_MULTI_LOOKUP) && defined(__ARM_NEON) I think we should use CONFIG_RTE_ARCH_ARM_NEON here. Any ARM maintainer to confirm? Note that there is already another occurence of this compiler flag: examples/l3fwd/l3fwd_em.c:#elif

[dpdk-dev] [PATCH v5] examples/l3fwd: em path performance fix

It seems that for the most use cases, previous hash_multi_lookup provides better performance, and more, sequential lookup can cause significant performance drop. This patch sets previously optional hash_multi_lookup method as default. It also provides some minor optimizations such as queue drain

[dpdk-dev] Fwd: EAL: map_all_hugepages(): mmap failed: Cannot allocate memory

On 3/18/2016 6:41 AM, John Wei wrote: > I am setting up OVS inside a Linux container. This OVS is built using DPDK > library. > During the startup of ovs-vswitchd, it core dumped due to fail to mmap. >in eal_memory.c > virtaddr = mmap(vma_addr, hugepage_sz, PROT_READ |

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

On 3/18/2016 6:39 PM, Ilya Maximets wrote: > > On 18.03.2016 13:27, Xie, Huawei wrote: >> On 3/18/2016 6:23 PM, Ilya Maximets wrote: >>> On 18.03.2016 13:08, Xie, Huawei wrote: On 2/24/2016 7:47 PM, Ilya Maximets wrote: >* Wait until it's our turn to add our buffer > @@

[dpdk-dev] [PATCH 1/2] mbuf: Add rte_pktmbuf_copy

On Fri, 18 Mar 2016 17:03:51 + "Pattan, Reshma" wrote: > Hi, > > > > >-Original Message- > > > >From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen > > > >Hemminger > > > >Sent: Friday, July 10, 2015 1:38 AM > > > >To: dev at dpdk.org > > > >Cc: Mike Davison ; Stephen

[dpdk-dev] [PATCH v4] examples/l3fwd: em path performance fix

It seems that for the most use cases, previous hash_multi_lookup provides better performance, and more, sequential lookup can cause significant performance drop. This patch sets previously optional hash_multi_lookup method as default. It also provides some minor optimizations such as queue drain

[dpdk-dev] [PATCH] examples/l3fwd: fix validation for queue id of config tuple

Added validation for queue id of config parameter tuple. This validation enforces user to enter queue ids of a port from 0 and in sequence. This additional validation on queue ids avoids ixgbe crash caused by null rxq pointer access inside ixgbe_dev_rx_init. Reason for null rxq is, L3fwd

[dpdk-dev] [PATCH v2] ring: check for zero objects mc dequeue / mp enqueue

On Fri, Mar 18, 2016 at 11:27:18AM +0100, Olivier Matz wrote: > Hi, > > On 03/18/2016 11:18 AM, Bruce Richardson wrote: > >>> diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h > >>> index 943c97c..eb45e41 100644 > >>> --- a/lib/librte_ring/rte_ring.h > >>> +++

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

2016-03-18 17:16, Yuanhan Liu: > On Fri, Mar 18, 2016 at 09:09:04AM +0100, Thomas Monjalon wrote: > > 2016-03-18 16:00, Yuanhan Liu: > > > On Thu, Mar 17, 2016 at 04:29:32PM +0100, Thomas Monjalon wrote: > > > > 2016-02-24 14:47, Ilya Maximets: > > > > > Implementation of rte_vhost_enqueue_burst()

[dpdk-dev] [PATCH v11 5/8] ethdev: add speed capabilities

On Thu, Mar 17, 2016 at 07:09:02PM +0100, Thomas Monjalon wrote: > From: Marc Sune > > The speed capabilities of a device can be retrieved with > rte_eth_dev_info_get(). > > The new field speed_capa is initialized in the drivers without > taking care of device characteristics in this patch. >

[dpdk-dev] [PATCH] ixgbe: fix reta query and update on x550

For x550 device, the reta table has 512 entries, but in function ixgbe_dev_rss_reta_query and ixgbe_dev_rss_reta_update we use an "uint8_t i" to traverse the entries, this will lead the function to an endless loop. This patch changes the data type from uint8_t to uint16_t to fix the issue.

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

On 3/18/2016 6:23 PM, Ilya Maximets wrote: > On 18.03.2016 13:08, Xie, Huawei wrote: >> On 2/24/2016 7:47 PM, Ilya Maximets wrote: >>> * Wait until it's our turn to add our buffer >>> @@ -979,7 +979,7 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, >>> uint16_t queue_id, >>>

[dpdk-dev] [PATCH] enic: don't set enic->config.rq_desc_count in enic_alloc_rq()

On Thu, Mar 17, 2016 at 03:46:50PM -0700, John Daley wrote: > From: Nelson Escobar > > When the requested number of rx descriptors was less than the amount > configured on the vic, enic_alloc_rq() was incorrectly setting > enic->config.rq_desc_count to the lower value. This screwed up later >

[dpdk-dev] Fwd: EAL: map_all_hugepages(): mmap failed: Cannot allocate memory

Thanks for the reply. Upon further debugging, I was able to root caused the issue. In the cgroup, in addition to limiting the CPU, I also limited the node where my OVS can allocate the memory (cpuset.mems). I understand that DPDK first grab all the memory, then pick the best memory pages, then

[dpdk-dev] [PATCH v2] ring: check for zero objects mc dequeue / mp enqueue

On Thu, Mar 17, 2016 at 05:09:08PM +0100, Mauricio V?squez wrote: > Hi Lazaros, > > On Thu, Mar 17, 2016 at 4:49 PM, Lazaros Koromilas > wrote: > > > Issuing a zero objects dequeue with a single consumer has no effect. > > Doing so with multiple consumers, can get more than one thread to

[dpdk-dev] DPDK and HW offloads

As I look at how the ethernet device interface in DPDK has exploded in complexity; it makes life very hard for end users. The goal has been to enable all the cool hardware features, but it has put blinders on the driver devlopers; they are ignoring the fact that real applications can't just

[dpdk-dev] [RFC] vhost user: add error handling for fd > 1023

Protect against DPDK crash when allocation of listen fd >= 1023. For events on fd:s >1023, the current implementation will trigger an abort due to access outside of allocated bit mask. Corrections would include: * Match fdset_add() signature in fd_man.c to fd_man.h * Handling of return codes

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

On 3/18/2016 5:55 PM, Ilya Maximets wrote: > Hi all. > And what about first patch of this series: > "vhost: use SMP barriers instead of compiler ones." ? > > It's not about thread safety in terms of 'lockless'. It is the standalone > patch that fixes many times discussed issue with barriers on

[dpdk-dev] Performance issue with uio_pci_generic driver

On Wed, Mar 16, 2016 at 11:59:34PM +, Simon Jouet wrote: > Hi everyone, > > First off I would like to thanks tmonjalo, Harry Van Harren and Bruce > Richardson for the input they gave while I was trying to figure out the issue > and pushing me to report the problem here ? > > Okay, so I was

[dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones.

On 2/24/2016 7:47 PM, Ilya Maximets wrote: >* Wait until it's our turn to add our buffer > @@ -979,7 +979,7 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t > queue_id, > entry_success++; > } > > - rte_compiler_barrier(); > + rte_smp_rmb();

[dpdk-dev] [PATCH] ixgbe: avoid unnessary break when checking at the tail of rx hwring

On Thu, Mar 17, 2016 at 10:20:01AM +0800, Jianbo Liu wrote: > On 16 March 2016 at 19:14, Bruce Richardson > wrote: > > On Wed, Mar 16, 2016 at 03:51:53PM +0800, Jianbo Liu wrote: > >> Hi Wenzhuo, > >> > >> On 16 March 2016 at 14:06, Lu, Wenzhuo wrote: > >> > HI Jianbo, > >> > > >> > > >> >>

[dpdk-dev] [PATCH v2] enic: update enic PMD maintainer and pointer to the guide.

Change maintainers for ENIC PMD and fix pointer to enic documentation in MAINTAINERS. Signed-off-by: John Daley --- MAINTAINERS | 4 ++-- doc/guides/nics/enic.rst | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8b21979..65669c3

[dpdk-dev] [PATCH v4] examples/l3fwd: em path performance fix

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Tomasz Kulasek > Sent: Friday, March 18, 2016 10:37 > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v4] examples/l3fwd: em path performance fix > > It seems that for the most use cases, previous

[dpdk-dev] virtio-pci and vdev=eth_pcap combined lead to a hang on virtnet_set_rx_mode (lcore-slave)

Hi, TL;DR When using --vdev=eth_pcap0 on testpmd "quit" the guest runs into a blocked cpu on virtnet_set_rx_mode (lcore-slave). Using these devices actually appers to be fine, but on the release path (testpmd quit) the issue triggers. Maybe virtio-pci and vdev=eth_pcap are just incompatible, but

[dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().

2016-03-18 16:00, Yuanhan Liu: > On Thu, Mar 17, 2016 at 04:29:32PM +0100, Thomas Monjalon wrote: > > 2016-02-24 14:47, Ilya Maximets: > > > Implementation of rte_vhost_enqueue_burst() based on lockless ring-buffer > > > algorithm and contains almost all to be thread-safe, but it's not. > > > > >

[dpdk-dev] [PATCH v11 5/8] ethdev: add speed capabilities

2016-03-18 05:18, Chen, Jing D: > > --- a/drivers/net/fm10k/fm10k_ethdev.c > > +++ b/drivers/net/fm10k/fm10k_ethdev.c > > @@ -1410,6 +1410,10 @@ fm10k_dev_infos_get(struct rte_eth_dev *dev, > > .nb_min = FM10K_MIN_TX_DESC, > > .nb_align = FM10K_MULT_TX_DESC, > > }; > >

[dpdk-dev] L2 Forwarding Sample Applications

2016-03-18 05:11, Vivek Gupta: > The contents of this e-mail and any attachment(s) are confidential Don't be afraid, I won't read your confidential message ;)

[dpdk-dev] QEDE pmd v2 patches

2016-03-18 01:43, Rasesh Mody: > Hi Thomas, Bruce, > > We didn't see automated build email for all the patches that we submitted to > dpdk.org. Is this expected? The email below is for the whole patchset: Patchwork ID: 11395-11402 > One of our patch, "[PATCH v2 04/10] qede: Add base

[dpdk-dev] [PATCH] enic: change maintainers

2016-03-17 15:43, John Daley: > Change maintainers for ENIC PMD. > > Signed-off-by: John Daley > --- > doc/guides/nics/enic.rst | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) Please update the MAINTAINERS file.

[dpdk-dev] Document2

-- next part -- A non-text attachment was scrubbed... Name: Document2.zip Type: application/zip Size: 5011 bytes Desc: Document2.zip URL: <http://dpdk.org/ml/archives/dev/attachments/20160318/ad1fc10d/attachment-0001.zip>

[dpdk-dev] [PATCH v11 5/8] ethdev: add speed capabilities

Hi, Best Regards, Mark > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Friday, March 18, 2016 2:09 AM > To: marcdevel at gmail.com; Richardson, Bruce; Doherty, Declan; Ananyev, > Konstantin; Lu, Wenzhuo; Zhang, Helin; Chen, Jing D; harish.patil

[dpdk-dev] L2 Forwarding Sample Applications

Please let me know the purpose of writing these sample applications in DPDK- * L2fwd-keepalive/main.c * L2fwd-jobstats/main.c * L2fwd-ivshmem/guest/guest.c * L2fwd-ivshmem/host/host.c Thanks & Regards Vivek Gupta ::DISCLAIMER::

[dpdk-dev] [PATCH] ixgbe: fix reta query and update on x550

Hi, > -Original Message- > From: Wang, Xiao W > Sent: Friday, March 18, 2016 10:28 AM > To: Zhang, Helin > Cc: dev at dpdk.org; Lu, Wenzhuo; Wang, Xiao W > Subject: [PATCH] ixgbe: fix reta query and update on x550 > > For x550 device, the reta table has 512 entries, but in function >

[dpdk-dev] [PATCH] kni: set kni mac on ioctl_create

Hi Sergey > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Sergey Balabanov > Sent: Friday, August 28, 2015 9:06 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH] kni: set kni mac on ioctl_create > > There is a situation when ioctl returns zero mac

[dpdk-dev] QEDE pmd v2 patches

Hi Thomas, Bruce, We didn't see automated build email for all the patches that we submitted to dpdk.org. Is this expected? One of our patch, "[PATCH v2 04/10] qede: Add base driver", doesn't show up on dpdk patchworks site http://dpdk.org/dev/patchwork/project/dpdk/list. Is there any action

[dpdk-dev] [PATCH 2/8] app/test/test: Fix missing brackets

> -Original Message- > From: Aaron Conole [mailto:aconole at redhat.com] > Sent: Friday, February 26, 2016 2:49 AM > To: dev at dpdk.org > Cc: Lu, Wenzhuo ; Zhang, Helin > ; Ananyev, Konstantin > ; Richardson, Bruce > > Subject: [PATCH 2/8] app/test/test: Fix missing brackets > > The

  1   2   >