[dpdk-dev] I have a problem in setting up DPDK 2.1.0 in Fedora OS release 20 (Heisenbug). I cannot r

Dear DPDK experts. Thank you very much for your best great efforts and precious answers. As you suggested, I reinstalled newer version of Fedora 22. I succeeded to communicate test-pmd in Fedora 22 (linux kernel version 4.2.3-200.fc22.x86_64, DPDK 2.1.0). The steps are as follows. sudo yum

[dpdk-dev] [PATCH v4 5/7] mk: Add rule for installing documentation

Hi Olivier, Ooops I'm going to fix that :) Thanks. Mario. From: Olivier MATZ [olivier.m...@6wind.com] Sent: Friday, October 16, 2015 12:30 PM To: Arevalo, Mario Alfredo C; dev at dpdk.org Subject: Re: [PATCH v4 5/7] mk: Add rule for installing documentatio

[dpdk-dev] [PATCH v4 1/7] mk: Add rule for installing headers

Hi Olivier, thank you for your feedback , more comments below :) Thanks. Mario. From: Olivier MATZ [olivier.m...@6wind.com] Sent: Friday, October 16, 2015 12:29 PM To: Arevalo, Mario Alfredo C; dev at dpdk.org Cc: Panu Matilainen Subject: Re: [PATCH v4 1/7

[dpdk-dev] [PATCH] eal: don't reset getopt lib

On Mon, Oct 19, 2015 at 11:36:41AM +0100, Bruce Richardson wrote: > On Thu, Oct 15, 2015 at 07:46:04PM +0800, Tiwei Bie wrote: > > Someone may need to call rte_eal_init() with a fake argc/argv array > > in the middle of using getopt() to parse its own unrelated argc/argv > > parameters. So getopt l

[dpdk-dev] [PATCH v2] eal: don't reset getopt lib

Someone may need to call rte_eal_init() with a fake argc/argv array in the middle of using getopt() to parse its own unrelated argc/argv parameters. So getopt lib shouldn't be reset by rte_eal_init(). Now eal will always save optind, optarg and optopt (and optreset on FreeBSD) at the beginning, in

[dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD

On 2015/10/19 18:45, Bruce Richardson wrote: > On Mon, Oct 19, 2015 at 10:32:50AM +0100, Loftus, Ciara wrote: >>> On 2015/10/16 21:52, Bruce Richardson wrote: On Mon, Aug 31, 2015 at 12:55:26PM +0900, Tetsuya Mukawa wrote: > The patch introduces a new PMD. This PMD is implemented as thin >

[dpdk-dev] [PATCH v3 0/4] support for netronome nfp-6xxx card

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Alejandro.Lucero > Sent: Friday, October 16, 2015 11:45 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v3 0/4] support for netronome nfp-6xxx card > > From: "Alejandro.Lucero" > > This patchset adds a n

[dpdk-dev] [PATCH] ixgbe: prefetch packet headers in vector PMD receive function

> -Original Message- > From: Zoltan Kiss [mailto:zoltan.kiss at linaro.org] > Sent: Monday, October 19, 2015 5:30 PM > To: Ananyev, Konstantin; Richardson, Bruce; dev at dpdk.org > Subject: Re: [PATCH] ixgbe: prefetch packet headers in vector PMD receive > function > > > > On 15/10/15

[dpdk-dev] [PATCH 00/34] update e1000 base driver

Hi Wenzhuo, Isn't it too late to have it included in DPDK 2.2? For reference: http://dpdk.org/dev/roadmap If you consider it for 2.3, please use the patchwork status "Deferred". For older versions of the patchset, please use the status "Superseded". Thanks

[dpdk-dev] [PATCH v3] librte_cfgfile(rte_cfgfile.h): modify the macros values

2015-09-04 11:58, Jasvinder Singh: > -#define CFG_NAME_LEN 32 > -#define CFG_VALUE_LEN 64 > +#ifndef CFG_NAME_LEN > +#define CFG_NAME_LEN 64 > +#endif Build fails: examples/qos_sched/cfg_file.h:40:0: error: "CFG_NAME_LEN" redefined

[dpdk-dev] Inconsistent statistics counters for pmd_i40e

Hi Eimear This is the link I have. https://downloadcenter.intel.com/download/24769 I guess that the version seen in the web page comes from a different parallel universe. You should see the actual fw version inside the zip file. Thanks /Arnon On Mon, Oct 19, 2015 at 5:30 PM, Eimear Morrissey <

[dpdk-dev] [PATCH v3 3/5] test_table: added check for bulk add/delete to acl table unit test

Hi, Some changes are needed. Please send a v4. 2015-10-13 09:34, Marcin Kerlin: > Added to acl table unit test check for bulk add and bulk delete. > > Signed-off-by: Maciej Gajdzica > Acked-by: Cristian Dumitrescu ERROR:BAD_SIGN_OFF: Unrecognized email address Build fails: test_table_acl.c:(.

[dpdk-dev] [PATCH] ixgbe: prefetch packet headers in vector PMD receive function

On 15/10/15 16:43, Ananyev, Konstantin wrote: > > >> -Original Message- >> From: Zoltan Kiss [mailto:zoltan.kiss at linaro.org] >> Sent: Thursday, October 15, 2015 11:33 AM >> To: Ananyev, Konstantin; Richardson, Bruce; dev at dpdk.org >> Subject: Re: [PATCH] ixgbe: prefetch packet header

[dpdk-dev] [PATCH v6 0/4] bonding corrections and additions

On 19/10/15 16:36, Eric Kinzie wrote: > This patchset makes a couple of small corrections to the bonding driver > and introduces the ability to use an external state machine for mode > 4 operation. > > Changes in v2: >. eliminate external_sm field in 802.3ad configuration > (rte_eth_bond_8

[dpdk-dev] [PATCH v2 1/3] port: add mp/mc ring ports

2015-09-24 11:55, Piotr Azarewicz: > ring_multi_reader input port (on top of multi consumer rte_ring) > ring_multi_writer output port (on top of multi producer rte_ring) > > Signed-off-by: Piotr Azarewicz > --- > lib/librte_port/rte_port_ring.c | 311 > +++ >

[dpdk-dev] [PATCH v2 2/3] port: fix ras ring ports

2015-09-24 11:55, Piotr Azarewicz: > Bug fixes for ring ports with IPv4/IPv6 reassembly support. > Previous implementation can't work properly due to incorrect choosing > process function. > Also, assuming that, when processing ip packet, ip header is know we can > set l3_len parameter here. > > S

[dpdk-dev] [PATCH 0/4]librte_port: modify macros to access packet meta-data

> > From: Fan Zhang > > > > This patchset links to ABI change announced for librte_port. Macros to > > access the packet meta-data stored within the packet buffer has been > > adjusted to cover the packet mbuf structure. > > Acked-by: Cristian Dumitrescu Applied in 1 commit (such change must b

[dpdk-dev] Inconsistent statistics counters for pmd_i40e

Hi Eimear, I just experienced the same problem with firmware versions 4.23 and 4.33 (dpdk 2.0). Did not get to try the latest which is 4.5. Looking at the code, I don't see that this counter is being read any differently than its peer counters and I suspect the nic itself. Can you tell which firmw

[dpdk-dev] [PATCH v4 6/7] mk: Add rule for installing sdk files

On 10/16/2015 10:31 PM, Olivier MATZ wrote: > Hi Panu, > > On 10/05/2015 10:20 PM, Mario Carrillo wrote: >> Add hierarchy-file support to the DPDK makefiles, scripts, >> examples, tools, config files and headers. >> >> When invoking "make install-sdk" makefiles, scripts, >> examples, tools, config

[dpdk-dev] [PATCH 0/4]librte_port: modify macros to access packet meta-data

2015-09-11 14:35, roy.fan.zhang at intel.com: > app/test-pipeline/main.h | 2 ++ > app/test-pipeline/pipeline_hash.c | 34 ++- > app/test-pipeline/pipeline_lpm.c | 2 +- > app/test-pipeline/pipeline_lpm_ipv6.c | 2 +- > app/test/test_table.h

[dpdk-dev] [PATCH 4/5] virtio: use any layout on transmit

On 10/20/2015 12:43 AM, Stephen Hemminger wrote: > On Mon, 19 Oct 2015 16:28:30 + > "Xie, Huawei" wrote: > >> On 10/19/2015 1:16 PM, Stephen Hemminger wrote: >>> Virtio supports a feature that allows sender to put transmit >>> header prepended to data. It requires that the mbuf be writeable,

[dpdk-dev] [Q] l2fwd in examples directory

Let me clarify my mixed stuffs. My processor is L5520, family 6, model 26 that is based on Nehalem microarchitecture according to wikipedia ( https://en.wikipedia.org/wiki/Nehalem_(microarchitecture)), it does not have PCI interface on chipset. Therefore, "rte_eth_dev_socket_id(portid) always ret

[dpdk-dev] [Q] l2fwd in examples directory

My NUT has Xeon L5520 that is based on Nehalem microarchitecture. Does Nehalem supports PCIe interface on chipset? Anyhow, 'lstopo' shows as below and it seems that my PCI devices are connected to socket #0. I'm still wondering why rte_eth_dev_socket_id(portid) always returns -1. mslee at myhost:

[dpdk-dev] [PATCH 4/5] virtio: use any layout on transmit

On 10/19/2015 1:16 PM, Stephen Hemminger wrote: > Virtio supports a feature that allows sender to put transmit > header prepended to data. It requires that the mbuf be writeable, correct > alignment, and the feature has been negotiatied. If all this works out, > then it will be the optimum way to

[dpdk-dev] [PATCH 1/5] virtio: clean up space checks on xmit

On 10/19/2015 11:48 PM, Stephen Hemminger wrote: > On Mon, 19 Oct 2015 08:02:07 + > "Xie, Huawei" wrote: > >> On 10/19/2015 1:16 PM, Stephen Hemminger wrote: >>> The space check for transmit ring only needs a single conditional. >>> I.e only need to recheck for space if there was no space in f

[dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD

On 10/19/2015 01:50 PM, Tetsuya Mukawa wrote: > On 2015/10/19 18:45, Bruce Richardson wrote: >> On Mon, Oct 19, 2015 at 10:32:50AM +0100, Loftus, Ciara wrote: On 2015/10/16 21:52, Bruce Richardson wrote: > On Mon, Aug 31, 2015 at 12:55:26PM +0900, Tetsuya Mukawa wrote: >> The patch int

[dpdk-dev] [PATCH 4/4] librte_port: modify release notes and deprecation notice

2015-09-11 14:35, roy.fan.zhang at intel.com: > @@ -74,7 +76,7 @@ The libraries prepended with a plus sign were incremented > in this version. > librte_pipeline.so.1 > librte_pmd_bond.so.1 > + librte_pmd_ring.so.2 > - librte_port.so.1 > + librte_port.so.2 The updated libra

[dpdk-dev] [PATCH 3/5] virtio: use indirect ring elements

On 10/19/2015 11:47 PM, Stephen Hemminger wrote: > On Mon, 19 Oct 2015 13:19:50 + > "Xie, Huawei" wrote: > >>> static int >>> -virtqueue_enqueue_xmit(struct virtqueue *txvq, struct rte_mbuf *cookie) >>> +virtqueue_enqueue_xmit(struct virtqueue *txvq, struct rte_mbuf *cookie, >>> +

[dpdk-dev] [PATCH v3 1/1] ip_pipeline: added dynamic pipeline reconfiguration

Up till now pipeline was bound to thread selected in the initial config. This patch allows binding pipeline to other threads at runtime using CLI commands. v2 changes: - deleted debug printfs v3 changes: - add timer for thread message request - fix bug that the new functionality can't work - fix

[dpdk-dev] [PATCH v2 7/8] example/ip_pipeline/pipeline: update flow_classification pipeline

2015-10-13 14:57, Jasvinder Singh: > From: Fan Zhang > + table_params.ops = > + &rte_table_hash_key16_ext_dosig_ops; > + } It doesn't build with shared library. pipeline_flow_classification_be.c:(.text+0xa84): und

[dpdk-dev] DPDK User Space: Session onUseability and Ease of Use

On 2015-10-13 18:36, Mcnamara, John wrote: > > * More sample apps > > - Some more examples of using secondary processes. One thing I would appreciate is more basic samples for the more advanced functionality. For example, the qos_sched example is (in my opimion) quite hard to follow since it h

[dpdk-dev] [PATCH v2 6/8] example/ip_pipeline: add parse_hex_string for internal use

2015-10-13 14:57, Jasvinder Singh: > From: Fan Zhang > +static uint32_t > +get_hex_val(char c) > +{ > + switch (c) { > + case '0': > + case '1': > + case '2': > + case '3': > + case '4': > + case '5': > + case '6': > + case '7': > + case '8': > + case '9

[dpdk-dev] [dpdk-dev, PATCHv6 1/6] ethdev: enhance rte_eth_(tx|rx)q_info struct

On Tue, 20 Oct 2015 00:06:19 +0200 Amine Kherbouche wrote: > + uint16_t used_desc; /**< number of used descriptors */ > + uint16_t free_desc; /**< number of free descriptors */ These two fields are obviously not SMP sfe. Also, they are redundant with the existing queue_co

[dpdk-dev] [dpdk-dev, PATCHv6 5/6] i40e: enhance eth_(rxq|txq)_info_get to retrieve more queue information

On Tue, 20 Oct 2015 00:06:23 +0200 Amine Kherbouche wrote: > According to new fields in struct rte_eth_rxq_info, those are filled to > add additional information about queue descriptors. > > Signed-off-by: Amine Kherbouche > --- > drivers/net/i40e/i40e_rxtx.c |4 > 1 file changed, 4 i

[dpdk-dev] [PATCH 8/8] librte_table: modify release notes and deprecation notice

2015-10-12 16:30, Mcnamara, John: > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon > > If a v2 is needed, please squash the release notes changes with the API > > changes (patches 1 and 2). > > Hi Thomas, > > Could you clarify this? In general shouldn't we keep all > lib

[dpdk-dev] Inconsistent statistics counters for pmd_i40e

Arnon Warshavsky wrote on 10/19/2015 03:01:46 PM: > From: Arnon Warshavsky > To: Eimear Morrissey/Ireland/IBM at IBMIE > Cc: dev at dpdk.org > Date: 10/19/2015 03:01 PM > Subject: Re: [dpdk-dev] Inconsistent statistics counters for pmd_i40e > > Hi Eimear, > > I just experienced the same problem

[dpdk-dev] [PATCH v3] i40e: Add a workaround to drop flow control frames from VFs

This patch adds a workaround to drop flow control frames from being transmitted from VSIs. With this patch in place a malicious VF cannot send flow control or PFC packets out on the wire. Signed-off-by: Jingjing Wu --- v3: - fix typo v2: - reword comments drivers/net/i40e/i40e_ethdev.c | 30 +

[dpdk-dev] [PATCH v6 0/9] Dynamic RSS Configuration for Bonding

On 16/10/15 11:00, Tomasz Kulasek wrote: > OVERVIEW > > 1) Setting .rxmode.mq_mode for bonding device to ETH_MQ_RX_RSS makes bonding > device fully RSS-capable, so all slaves are synchronized with its > configuration. > This mode is intended to provide RSS configuration as known from "dyn

[dpdk-dev] [PATCH] igb: fix IEEE1588 frame identification in i210

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Pablo de Lara > Sent: Monday, October 19, 2015 2:20 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH] igb: fix IEEE1588 frame identification in i210 > > Fixed issue where the flag PKT_RX_IEEE1588_PTP was no

[dpdk-dev] [PATCH] igb: fix IEEE1588 frame identification in i210

Fixed issue where the flag PKT_RX_IEEE1588_PTP was not being set in Intel I210 NIC, as EtherType in RX descriptor is in bits 8:10 of Packet Type and not in the default bits 0:2. Fixes known issue "IEEE1588 support possibly not working with an Intel Ethernet Controller I210 NIC" Signed-off-by: Pab

[dpdk-dev] [PATCH v2] eal: don't reset getopt lib

On Mon, Oct 19, 2015 at 09:13:10PM +0800, Tiwei Bie wrote: > Someone may need to call rte_eal_init() with a fake argc/argv array > in the middle of using getopt() to parse its own unrelated argc/argv > parameters. So getopt lib shouldn't be reset by rte_eal_init(). > > Now eal will always save opt

[dpdk-dev] [PATCH v2] eal:Map rte cfg and uio at the end of hugepage mem

On Sat, Oct 17, 2015 at 10:48:29AM +0300, Nissim Nisimov wrote: > * this patch removes unnecessary call to rte_eal_memory_init() introduced in > the first version. > > Problem: > In DPDK Primary/Secondary module we assume mapping same regions of virtual > memory addresses for Primary process and

[dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD

> -Original Message- > From: Panu Matilainen [mailto:pmatilai at redhat.com] > Sent: Monday, October 19, 2015 2:26 PM > To: Tetsuya Mukawa ; Richardson, Bruce > ; Loftus, Ciara > Cc: dev at dpdk.org; ann.zhuangyanying at huawei.com > Subject: Re: [dpdk-dev] [RFC PATCH v2] vhost: Add VHOS

[dpdk-dev] [PATCH v2 1/1] ethdev: distinguish between drop and error stats

Make a distniction between dropped packets and error statistics to allow a higher level fault management entity to interact with DPDK and take appropriate measures when errors are detected. It will also provide valuable information for any applications that collects/extracts DPDK stats, such applic

[dpdk-dev] [PATCH 3/5] virtio: use indirect ring elements

On 10/19/2015 1:16 PM, Stephen Hemminger wrote: > The virtio ring in QEMU/KVM is usually limited to 256 entries > and the normal way that virtio driver was queuing mbufs required > nsegs + 1 ring elements. By using the indirect ring element feature > if available, each packet will take only one rin

[dpdk-dev] Inconsistent statistics counters for pmd_i40e

Hi, I'm having issues measuring packets dropped at the NIC in both the 2.0.0 and 2.1.0 versions of DPDK on an X710 Intel NIC. In dpdk-2.0.0 Using rte_eth_xstats the rx_packets and rx_bytes counters increase as expected, however rx_missed_errors is always 0 even if a sleep statement is added bet

[dpdk-dev] [PATCH 2/3] vhost: check that a device exists during reset_owner

On Fri, Oct 16, 2015 at 11:08:49AM +0200, Jerome Jutteau wrote: > virtio-net search for it's device in reset_owner. > The function don't check the return result of get_config_ll_entry > which can be NULL. > > Signed-off-by: Jerome Jutteau > --- > lib/librte_vhost/virtio-net.c | 2 ++ > 1 file ch

[dpdk-dev] [PATCH v5 0/4] bonding corrections and additions

On 30/09/15 18:48, Eric Kinzie wrote: > This patchset makes a couple of small corrections to the bonding driver > and introduces the ability to use an external state machine for mode > 4 operation. > > Changes in v2: >. eliminate external_sm field in 802.3ad configuration > (rte_eth_bond

[dpdk-dev] [PATCH v3] ip_pipeline: add more functions to routing-pipeline

This patch adds following features to the routing-pipeline to enable it for various NFV use-cases; 1.Fast-path ARP table enable/disable 2.Double-tagged VLAN (Q-in-Q) packet enacapsulation for the next-hop 3.MPLS encapsulation for the next-hop 4.Add colour (Traffic-class for QoS) to the MPLS tag 5.

[dpdk-dev] [PATCH v2 4/4] vhost: change method to get device in reset_owner

Using get_config_ll_entry in reset_owner don't show any error when the device is not found. This patch fix this by using get_device instead instead of get_config_ll_entry. Signed-off-by: Jerome Jutteau --- lib/librte_vhost/virtio-net.c | 15 +++ 1 file changed, 7 insertions(+), 8 del

[dpdk-dev] [PATCH v2 3/4] vhost: protect user_get_vring_base from unknown devices

get_device return is not checked and may cause segfault when device is not found. This patch fix this. Signed-off-by: Jerome Jutteau --- lib/librte_vhost/vhost_user/virtio-net-user.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/librte_vhost/vhost_user/virtio-net-user.c b/lib/librte

[dpdk-dev] [PATCH v2 2/4] vhost: check that a device exists during reset_owner

virtio-net search for it's device in reset_owner. The function don't check the return result of get_config_ll_entry which can be NULL. Signed-off-by: Jerome Jutteau --- lib/librte_vhost/virtio-net.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_

[dpdk-dev] [PATCH v2 1/4] vhost: avoid device identifier to be reset to 0 in reset_owner

virtio-net clean and init device after a VHOST_USER_RESET_OWNER. This reset device identifier to 0 and break ll_root listing logic. This patch keep the old device identifier and re-write it on the cleaned device. Signed-off-by: Jerome Jutteau --- lib/librte_vhost/virtio-net.c | 3 +++ 1 file cha

[dpdk-dev] [PATCH v2 0/4] vhost: Fix virtio-net on VHOST_USER_RESET_OWNER

Hi, I have a bug when Qemu with two vhost interfaces gently stops (SIGINT). When stopping, it sends two RESET_OWNER for each interface: - Before stopping, we have two interfaces identifers: 0 and 1. - The first reset_owner call resets device 1 (and this id device_fh) to zero, the device list now

[dpdk-dev] [PATCH 2/3] vhost: check that a device exists during reset_owner

Hi Yuanhan, 2015-10-19 6:35 GMT+02:00 Yuanhan Liu : > I would call get_device() here, which dumps an error message when > it's NULL so that user will get noticed. > > Besides that, the 3 patches look good to me, and, > > Acked-by: Yuanhan Liu Thanks for your review, a v2 is coming soon with get_

[dpdk-dev] [PATCH] eal: don't reset getopt lib

On Thu, Oct 15, 2015 at 07:46:04PM +0800, Tiwei Bie wrote: > Someone may need to call rte_eal_init() with a fake argc/argv array > in the middle of using getopt() to parse its own unrelated argc/argv > parameters. So getopt lib shouldn't be reset by rte_eal_init(). > > Now eal will always save opt

[dpdk-dev] [PATCH v6 00/13] vhost-user multiple queues enabling

On Fri, Oct 09, 2015 at 01:45:59PM +0800, Yuanhan Liu wrote: > This patch set enables vhost-user multiple queues. > > Overview > > > It depends on some QEMU patches that has already been merged to upstream. > Those qemu patches introduce some new vhost-user messages, for vhost-user > mq

[dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD

On 2015/10/16 21:52, Bruce Richardson wrote: > On Mon, Aug 31, 2015 at 12:55:26PM +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 PMD can have 'iface' paramete

[dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD

On Mon, Oct 19, 2015 at 10:32:50AM +0100, Loftus, Ciara wrote: > > On 2015/10/16 21:52, Bruce Richardson wrote: > > > On Mon, Aug 31, 2015 at 12:55:26PM +0900, Tetsuya Mukawa wrote: > > >> The patch introduces a new PMD. This PMD is implemented as thin > > wrapper > > >> of librte_vhost. It means l

[dpdk-dev] [Q] l2fwd in examples directory

On Mon, Oct 19, 2015 at 04:39:41PM +0900, Moon-Sang Lee wrote: > My NUT has Xeon L5520 that is based on Nehalem microarchitecture. > Does Nehalem supports PCIe interface on chipset? For nehalem, I think having the PCI numa node reported as -1 is normal, as it's not directly connected to the physic

[dpdk-dev] [PATCH 4/5] virtio: use any layout on transmit

On Mon, 19 Oct 2015 16:28:30 + "Xie, Huawei" wrote: > "When using legacy interfaces, transitional drivers which have not > negotiated VIRTIO_F_ANY_LAYOUT > MUST use a single descriptor for the struct virtio_net_hdr on both > transmit and receive, with the > network data in the following descr

[dpdk-dev] [PATCH 4/5] virtio: use any layout on transmit

On Mon, 19 Oct 2015 16:28:30 + "Xie, Huawei" wrote: > On 10/19/2015 1:16 PM, Stephen Hemminger wrote: > > Virtio supports a feature that allows sender to put transmit > > header prepended to data. It requires that the mbuf be writeable, correct > > alignment, and the feature has been negotia

[dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD

> On 2015/10/16 21:52, Bruce Richardson wrote: > > On Mon, Aug 31, 2015 at 12:55:26PM +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 PMD can have 'ifa

[dpdk-dev] [PATCH v4] mbuf/ip_frag: move mbuf chaining to common code

Hi Simon, On 10/15/2015 09:01 AM, Simon Kagstrom wrote: > Chaining/segmenting mbufs can be useful in many places, so make it > global. > > Signed-off-by: Simon Kagstrom > Signed-off-by: Johan Faltstrom Acked-by: Olivier Matz Thanks!

[dpdk-dev] [PATCH] tools/setup.sh: let function quit to exit directly (may convenient for use); replace tab by space;

>From 49090c56383f1255e3ea1991f51e83b1ed6fb8d6 Mon Sep 17 00:00:00 2001 From: z00182565 Date: Mon, 19 Oct 2015 16:43:59 +0800 Subject: [PATCH] tools/setup.sh: let function quit to exit directly (may convenient for use); replace tab by space; --- tools/setup.sh | 679 +++

[dpdk-dev] [PATCH 1/5] virtio: clean up space checks on xmit

On Mon, 19 Oct 2015 08:02:07 + "Xie, Huawei" wrote: > On 10/19/2015 1:16 PM, Stephen Hemminger wrote: > > The space check for transmit ring only needs a single conditional. > > I.e only need to recheck for space if there was no space in first check. > I see you reorganized the code. It is mor

[dpdk-dev] [PATCH 3/5] virtio: use indirect ring elements

On Mon, 19 Oct 2015 13:19:50 + "Xie, Huawei" wrote: > > static int > > -virtqueue_enqueue_xmit(struct virtqueue *txvq, struct rte_mbuf *cookie) > > +virtqueue_enqueue_xmit(struct virtqueue *txvq, struct rte_mbuf *cookie, > > + int use_indirect) > > { > > struct vq_desc_

[dpdk-dev] [PATCH] fm10k: add Intel Boulder Rapid NIC support

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Michael Qiu > Sent: Friday, September 25, 2015 10:31 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH] fm10k: add Intel Boulder Rapid NIC support > > Boulder Rapid is Intel new NIC within fm10k family. > T

[dpdk-dev] [PATCH 2/2] i40e: Enlarge the number of supported queues

> -Original Message- > From: Wu, Jingjing > Sent: Monday, October 19, 2015 4:30 PM > To: Zhang, Helin; dev at dpdk.org > Cc: Pei, Yulong; Liu, Yong > Subject: RE: [PATCH 2/2] i40e: Enlarge the number of supported queues > > Hi, helin > > Few comments > > > a/drivers/net/i40e/i40e_ethde

[dpdk-dev] [PATCH v6 4/4] bond mode 4: tests for external state machine

From: Eric Kinzie This adds test cases for exercising the external state machine API to the mode 4 autotest. Signed-off-by: Eric Kinzie --- app/test/test_link_bonding_mode4.c | 210 ++-- 1 file changed, 201 insertions(+), 9 deletions(-) diff --git a/app/te

[dpdk-dev] [PATCH v6 3/4] bond mode 4: allow external state machine

From: Eric Kinzie Provide functions to allow an external 802.3ad state machine to transmit and recieve LACPDUs and to set the collection/distribution flags on slave interfaces. Size of struct rte_eth_bond_8023ad_conf changed. Increment LIBABIVER and version bond_mode_8023ad_setup and

[dpdk-dev] [PATCH v6 2/4] bond mode 4: do not ignore multicast

From: Eric Kinzie The bonding PMD in mode 4 puts all enslaved interfaces into promiscuous mode in order to receive LACPDUs and must filter unwanted packets after the traffic has been "collected". Allow broadcast and multicast through so that ARP and IPv6 neighbor discovery continue to work. Fix

[dpdk-dev] [PATCH v6 1/4] bond mode 4: copy entire config structure

From: Eric Kinzie Copy all needed fields from the mode8023ad_private structure in bond_mode_8023ad_conf_get(). This help ensure that a subsequent call to rte_eth_bond_8023ad_setup() is not passed uninitialized data that would result in either incorrect behavior or a failed sanity check.

[dpdk-dev] [PATCH v6 0/4] bonding corrections and additions

This patchset makes a couple of small corrections to the bonding driver and introduces the ability to use an external state machine for mode 4 operation. Changes in v2: . eliminate external_sm field in 802.3ad configuration (rte_eth_bond_8023ad_conf). . stop bonding device before changing

[dpdk-dev] [PATCH v3] i40e: Add a workaround to drop flow control frames from VFs

Hi, > -Original Message- > From: Wu, Jingjing > Sent: Monday, October 19, 2015 2:32 PM > To: dev at dpdk.org > Cc: Wu, Jingjing; Lu, Wenzhuo; Pei, Yulong > Subject: [PATCH v3] i40e: Add a workaround to drop flow control frames > from VFs > > This patch adds a workaround to drop flow contr

[dpdk-dev] [PATCH 2/2] i40e: Enlarge the number of supported queues

Hi, helin Few comments > a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c index > 4b70588..3bdcaa4 100644 > --- a/drivers/net/i40e/i40e_ethdev.c > +++ b/drivers/net/i40e/i40e_ethdev.c > @@ -2240,113 +2240,88 @@ i40e_pf_parameter_init(struct rte_eth_dev > *dev) { > struct i

[dpdk-dev] Question about unsupported transceivers

On 10/18/2015 06:06 PM, Alex Forster wrote: > On 10/15/15, 3:53 PM, "Alexander Duyck" wrote: > > It looks like you are probably seeing interfaces be unbound and then rebound. As such you are likely pushing things outside of the array boundary. One solution might just be to at more

[dpdk-dev] [PATCH 1/5] virtio: clean up space checks on xmit

On 10/19/2015 1:16 PM, Stephen Hemminger wrote: > The space check for transmit ring only needs a single conditional. > I.e only need to recheck for space if there was no space in first check. I see you reorganized the code. It is more clear and readable with your change, but no check is removed. We

[dpdk-dev] [PATCH v2 6/7] virtio: simple tx routine

On 10/19/2015 12:17 PM, Stephen Hemminger wrote: > On Sun, 18 Oct 2015 14:29:03 +0800 > Huawei Xie wrote: > >> bulk free of mbufs when clean used ring. >> shift operation of idx could be further saved if vq_free_cnt means >> free slots rather than free descriptors. >> >> Signed-off-by: Huawei Xie

[dpdk-dev] [PATCH v2 6/7] virtio: simple tx routine

On 10/19/2015 12:17 PM, Stephen Hemminger wrote: > On Sun, 18 Oct 2015 14:29:03 +0800 > Huawei Xie wrote: > >> + >> +for (i = 1; i < VIRTIO_TX_FREE_NR; i++) { >> +m = (struct rte_mbuf *)vq->vq_descx[desc_idx++].cookie; >> +if (likely(m->pool == free[0]->pool)) >> +

[dpdk-dev] [PATCH v2 6/7] virtio: simple tx routine

On 10/19/2015 12:19 PM, Stephen Hemminger wrote: > +static inline void __attribute__((always_inline)) > +virtio_xmit_cleanup(struct virtqueue *vq) > +{ > > Please don't use always inline, frustrating the compiler isn't going > to help. always inline is scattered elsewhere in the dpdk code. What is

[dpdk-dev] [PATCH v2 2/7] virtio: add software rx ring, fake_buf into virtqueue

On 10/19/2015 12:20 PM, Stephen Hemminger wrote: On Sun, 18 Oct 2015 14:28:59 +0800 Huawei Xie wrote: + if (vq->sw_ring) + rte_free(vq->sw_ring); + Do not need to test for NULL before calling rte_free. Better to just rely o

[dpdk-dev] [PATCH v2 0/3] Support for flow director behavior "passthru" on Intel FVL NIC

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Andrey Chilikin > Sent: Wednesday, September 30, 2015 9:43 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v2 0/3] Support for flow director behavior > "passthru" on Intel FVL NIC > > This patch set adds

[dpdk-dev] RSS API discussion

Hi N?lio, > -Original Message- > From: N?lio Laranjeiro [mailto:nelio.laranjeiro at 6wind.com] > Sent: Friday, October 16, 2015 11:28 PM > To: Lu, Wenzhuo > Cc: dev at dpdk.org; Adrien Mazarguil; Olga Shern > Subject: Re: RSS API discussion > > On Fri, Oct 16, 2015 at 01:40:00PM +, Lu

[dpdk-dev] Question about unsupported transceivers

On 10/15/15, 3:53 PM, "Alexander Duyck" wrote: >>> It looks like you are probably seeing interfaces be unbound and then >>> rebound. As such you are likely pushing things outside of the array >>> boundary. One solution might just be to at more ",1"s if you are only >>> going to be doing this k