[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

On Wed, Jun 01, 2016 at 02:39:28PM +0200, Thomas Monjalon wrote: > I was thinking to implement the library options parsing in DPDK. > But if the application implements its own options parsing without using > the DPDK one, yes the option parsing is obviously done in the application. > > > I'd say,

[dpdk-dev] [RFC] Yet another option for DPDK options

Hi Keith, I'll try to bring more context to this discussion below. 2016-06-01 15:00, Wiles, Keith: > Started from the link below, but did not want to highjack the thread. > http://dpdk.org/ml/archives/dev/2016-June/040021.html > > I was thinking about this problem from a user perspective and

[dpdk-dev] [vpp-dev] VLAN packets dropped... ?

We will be adding a patch to the i40e driver that would check the packet for presence of VLAN tag set the required PKT_RX_VLAN_PKT flag. I hope to get it done by the end of this week. -John From: Chandrasekar Kannan [mailto:ckan...@console.to] Sent: Wednesday, June 01, 2016 2:45 PM To: John

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

On Wed, Jun 01, 2016 at 12:17:50PM +0200, Thomas Monjalon wrote: > Hi, > > 2016-06-01 14:04, Yuanhan Liu: > > Hi all, > > > > I guess we (maybe just me :) have stated few times something like > > "hey, this kind of stuff is good to have, but you are trying to > > add an EAL CLI option for a

[dpdk-dev] [RFC] Yet another option for DPDK options

On Wed, Jun 1, 2016 at 7:18 PM, Bruce Richardson wrote: > On Wed, Jun 01, 2016 at 10:58:41AM -0500, Jay Rolette wrote: > > On Wed, Jun 1, 2016 at 10:00 AM, Wiles, Keith > wrote: > > > > > Started from the link below, but did not want to highjack the thread. > > >

[dpdk-dev] Suggestions for the dpdk stable tree

> -Original Message- > From: Yuanhan Liu [mailto:yuanhan.liu at linux.intel.com] > Sent: Monday, May 23, 2016 3:22 AM > To: Mcnamara, John > Cc: Christian Ehrhardt ; dev > ; Stephen Hemminger ; Thomas > Monjalon > Subject: Re: [dpdk-dev] Suggestions for the dpdk stable tree > > > We

[dpdk-dev] [RFC] Yet another option for DPDK options

On 6/1/16, 11:18 AM, "Richardson, Bruce" wrote: >On Wed, Jun 01, 2016 at 10:58:41AM -0500, Jay Rolette wrote: >> On Wed, Jun 1, 2016 at 10:00 AM, Wiles, Keith >> wrote: >> >> > Started from the link below, but did not want to highjack the thread. >> >

[dpdk-dev] [PATCH v6 1/5] mempool: support external handler

On 6/1/2016 5:19 PM, David Hunt wrote: > Until now, the objects stored in a mempool were internally stored in a > ring. This patch introduces the possibility to register external handlers > replacing the ring. > > The default behavior remains unchanged, but calling the new function >

[dpdk-dev] [PATCH v6 5/5] mbuf: get default mempool handler from configuration

By default, the mempool handler used for mbuf allocations is a multi producer and multi consumer ring. We could imagine a target (maybe some network processors?) that provides an hardware-assisted pool mechanism. In this case, the default configuration for this architecture would contain a

[dpdk-dev] [PATCH v6 4/5] app/test: test external mempool handler

Use a minimal custom mempool external handler and check that it also passes basic mempool autotests. Signed-off-by: Olivier Matz Signed-off-by: David Hunt --- app/test/test_mempool.c | 114 1 file changed, 114 insertions(+) diff --git

[dpdk-dev] [PATCH v6 3/5] mempool: add default external mempool handler

The first patch in this series added the framework for an external mempool manager. This patch in the series adds a set of default handlers based on rte_ring. v6 changes: split out into a separate patch for easier review. Signed-off-by: David Hunt Signed-off-by: Olivier Matz ---

[dpdk-dev] [PATCH v6 2/5] mempool: remove rte_ring from rte_mempool struct

Now that we're moving to an external mempoool handler, which uses a void *pool as a pointer to the pool data, remove the unneeded ring pointer from the mempool struct. Signed-off-by: David Hunt --- app/test/test_mempool_perf.c | 1 - lib/librte_mempool/rte_mempool.h | 1 - 2 files changed,

[dpdk-dev] [PATCH v6 1/5] mempool: support external handler

Until now, the objects stored in a mempool were internally stored in a ring. This patch introduces the possibility to register external handlers replacing the ring. The default behavior remains unchanged, but calling the new function rte_mempool_set_handler() right after

[dpdk-dev] [PATCH v6 0/5] mempool: add external mempool manager

Here's the latest version of the External Mempool Manager patchset. It's re-based on top of the latest head as of 1st June 2016, including Olivier's 35-part patch series on mempool re-org [1] [1] http://dpdk.org/ml/archives/dev/2016-May/039229.html Note: After applying the last patch, run "make

[dpdk-dev] [RFC] Yet another option for DPDK options

On Wed, Jun 01, 2016 at 10:58:41AM -0500, Jay Rolette wrote: > On Wed, Jun 1, 2016 at 10:00 AM, Wiles, Keith > wrote: > > > Started from the link below, but did not want to highjack the thread. > > http://dpdk.org/ml/archives/dev/2016-June/040021.html > > > > I was thinking about this problem

[dpdk-dev] [PATCH v5 1/3] mempool: support external handler

On Wed, Jun 01, 2016 at 11:46:20AM +0100, Hunt, David wrote: > > > On 5/31/2016 10:11 PM, Jerin Jacob wrote: > > On Tue, May 31, 2016 at 10:41:00PM +0200, Olivier MATZ wrote: > > > Hi, > > > > > > On 05/31/2016 06:03 PM, Jerin Jacob wrote: > > > > On Tue, May 31, 2016 at 04:37:02PM +0100, Hunt,

[dpdk-dev] [PATCH v5 8/8] doc: update doc for virtio-user

On Mon, May 30, 2016 at 10:55:39AM +, Jianfeng Tan wrote: > Signed-off-by: Huawei Xie > Signed-off-by: Jianfeng Tan > --- > doc/guides/rel_notes/release_16_07.rst | 4 > 1 file changed, 4 insertions(+) > > diff --git a/doc/guides/rel_notes/release_16_07.rst >

[dpdk-dev] [PATCH v5 7/8] virtio-user: add a new vdev named virtio-user

On Mon, May 30, 2016 at 10:55:38AM +, Jianfeng Tan wrote: > diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c > b/drivers/net/virtio/virtio_user/virtio_user_dev.c > index 41d8ad1..5e4f60b 100644 > --- a/drivers/net/virtio/virtio_user/virtio_user_dev.c > +++

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

I recently felt tired enough of specifying various options for EAL, so I came up to use ini-based configuration. EAL parameters from dedicated section of ini file are parsed to argv array which is subsequently fed to rte_eal_init(). Quite handy, but maybe a little overkill. On 01.06.2016

[dpdk-dev] [PATCH v5 6/8] virtio-user: add new virtual pci driver for virtio

On Mon, May 30, 2016 at 10:55:37AM +, Jianfeng Tan wrote: > This patch implements another new instance of struct virtio_pci_ops to > drive the virtio-user virtual device. Instead of rd/wr ioport or PCI > configuration space, this virtual pci driver will rd/wr the virtual > device struct

[dpdk-dev] Can't build DPDK-16.04 on CentOS 6.8

Guys, I'm trying to build DPDK-16.04 on CentOS 6.8, but it is failing, here is the error: --- ... == Build lib/librte_eal/linuxapp == Build lib/librte_eal/linuxapp/eal == Build lib/librte_eal/linuxapp/igb_uio CC eal.o CC eal_hugepage_info.o CC eal_memory.o LD

[dpdk-dev] [PATCH 1/3] vhost: pre update used ring for Tx and Rx

On Wed, Jun 01, 2016 at 06:40:41AM +, Xie, Huawei wrote: > On 5/3/2016 8:42 AM, Yuanhan Liu wrote: > > Pre update and update used ring in batch for Tx and Rx at the stage > > while fetching all avail desc idx. This would reduce some cache misses > > and hence, increase the performance a bit. >

[dpdk-dev] [PATCH v5 3/8] virtio: enable use virtual address to fill desc

On Mon, May 30, 2016 at 10:55:34AM +, Jianfeng Tan wrote: > This patch is related to how to calculate relative address for vhost > backend. > > The principle is that: based on one or multiple shared memory regions, > vhost maintains a reference system with the frontend start address, >

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

2016-06-01 21:19, Yuanhan Liu: > On Wed, Jun 01, 2016 at 02:39:28PM +0200, Thomas Monjalon wrote: > > I was thinking to implement the library options parsing in DPDK. > > But if the application implements its own options parsing without using > > the DPDK one, yes the option parsing is obviously

[dpdk-dev] [PATCH v5 2/8] virtio: clean up virtio_dev_queue_setup

On Wed, Jun 01, 2016 at 07:44:33AM +, Tan, Jianfeng wrote: > Hi Yuanhan, > > > -Original Message- > > From: Yuanhan Liu [mailto:yuanhan.liu at linux.intel.com] > > Sent: Wednesday, June 1, 2016 3:38 PM > > To: Tan, Jianfeng > > Cc: dev at dpdk.org; Xie, Huawei; rich.lane at

[dpdk-dev] [PATCH] ivshmem: document a potential segmentation fault in rte_ring

Commit 4768c475 added a pointer to the memzone in rte_ring. However, all memzones are residing in local mem_config, therefore accessing the memzone pointer inside the guest in an IVSHMEM-shared rte_ring will cause segmentation fault. This issue is unlikely to ever get fixed, as this would require

[dpdk-dev] [PATCH v5 2/8] virtio: clean up virtio_dev_queue_setup

On Mon, May 30, 2016 at 10:55:33AM +, Jianfeng Tan wrote: > Abstract vring hdr desc init as an inline method. What's this patch for then? In your last version, it will be invoked twice, but it turned out to be wrong. So, why keeping this change? I didn't see it improves anything.

[dpdk-dev] [PATCH v3] virtio: split virtio rx/tx queue

On Mon, May 30, 2016 at 05:06:20PM +0800, Huawei Xie wrote: > We keep a common vq structure, containing only vq related fields, > and then split others into RX, TX and control queue respectively. > > Signed-off-by: Huawei Xie > --- > v2: > - don't split virtio_dev_rx/tx_queue_setup > v3: > - fix

[dpdk-dev] [PATCH] ivshmem: add all memzones of mempool to metada

> From: Yigit, Ferruh > Sent: Wednesday, June 1, 2016 2:18 PM > To: dev at dpdk.org > Cc: Burakov, Anatoly ; Olivier Matz > ; Yigit, Ferruh > Subject: [PATCH] ivshmem: add all memzones of mempool to metada > > Mempool consist of multiple memzones, at least from two of them. > ivshmem assumes

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

Not to highjack this thread I created another one ? please have a look, thanks. http://dpdk.org/ml/archives/dev/2016-June/040079.html Regards, Keith -Original Message- From: dev on behalf of Thomas Monjalon Date: Wednesday, June 1, 2016 at 9:03 AM To:

[dpdk-dev] [PATCH v2 6/6] ip_pipeline: update release notes

Signed-off-by: Jasvinder Singh Acked-by: Cristian Dumitrescu --- doc/guides/rel_notes/release_16_07.rst | 10 ++ 1 file changed, 10 insertions(+) diff --git a/doc/guides/rel_notes/release_16_07.rst b/doc/guides/rel_notes/release_16_07.rst index 30e78d4..d8215bc 100644 ---

[dpdk-dev] [PATCH v2 5/6] ip_pipeline: sample config file on adding various network layer components

The sample configuration file demonstrates that network layer components such as TCP, UDP, ICMP etc, can be easily integrated into ip pipeline infrastructure. Similarily, various other functionalities such as IP Reassembly for input traffic with local destination and IP Fragmentation to enforce

[dpdk-dev] [PATCH v2 4/6] ip_pipeline: automatic routes update with the change in nic ports state

The routing pipeline registers a callback function with the nic ports and this function is invoked for updating the routing entries (corrsponding to local host and directly attached network) tables whenever the nic ports change their states (up/down). Signed-off-by: Jasvinder Singh Acked-by:

[dpdk-dev] [PATCH v2 3/6] ip_pipeline: assign nic ports mac address to the routing pipeline outports

As a result of tracking, output ports of routing pipelines are linked with physical nic ports(potentially through other pipeline instances). Thus, the mac addresses of the NIC ports are assigned to routing pipeline out ports which are connected to them and are further used in routing table entries

[dpdk-dev] [PATCH v2 2/6] ip_pipeline: linking routing pipeline output ports with NIC ports

This commit implements tracking mechanism for linking routing pipeline output ports to physical NIC ports. Once all the pipelines of the application are initialised, mechanism is invoked during post initialisation phase for relating routing pipeline output with NIC ports by navigating through the

[dpdk-dev] [PATCH v2 1/6] ip_pipeline: increase macros values

To allow more queues, pipeline types, threads, source/sink ports,etc., in the ip pipeline application, larger values of macros are set. Signed-off-by: Jasvinder Singh Acked-by: Cristian Dumitrescu --- examples/ip_pipeline/app.h | 12 ++-- examples/ip_pipeline/pipeline_be.h | 8

[dpdk-dev] [PATCH v2 0/6] ip_pipeline: routing pipeline improvements

This commit adds following features to the routing pipeline; 1. Implements the tracking mechanism for the routing pipeline for identifying the physical nic port where a specific output ports of the routing pipeline are eventually connected. Depending upon the application, tracking could involve

[dpdk-dev] [RFC] Yet another option for DPDK options

Started from the link below, but did not want to highjack the thread. http://dpdk.org/ml/archives/dev/2016-June/040021.html I was thinking about this problem from a user perspective and command line options are very difficult to manage specifically when you have a large number of options as we

[dpdk-dev] [PATCH 1/3] vhost: pre update used ring for Tx and Rx

On Wed, Jun 01, 2016 at 06:40:41AM +, Xie, Huawei wrote: > > /* Retrieve all of the head indexes first to avoid caching issues. */ > > for (i = 0; i < count; i++) { > > - desc_indexes[i] = vq->avail->ring[(vq->last_used_idx + i) & > > -

[dpdk-dev] [PATCH v2 02/20] thunderx/nicvf: add pmd skeleton

On Tue, May 31, 2016 at 09:53:55AM -0700, Stephen Hemminger wrote: > On Sun, 29 May 2016 22:16:46 +0530 > Jerin Jacob wrote: > > > + > > +static struct itimerspec alarm_time = { > > + .it_interval = { > > + .tv_sec = 0, > > + .tv_nsec = NICVF_INTR_POLL_INTERVAL_MS *

[dpdk-dev] [PATCH 2/3] vhost: optimize dequeue for small packets

On Wed, Jun 01, 2016 at 06:24:18AM +, Xie, Huawei wrote: > On 5/3/2016 8:42 AM, Yuanhan Liu wrote: > > Both current kernel virtio driver and DPDK virtio driver use at least > > 2 desc buffer for Tx: the first for storing the header, and the others > > for storing the data. > > Tx could

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

2016-06-01 19:40, Yuanhan Liu: > On Wed, Jun 01, 2016 at 12:17:50PM +0200, Thomas Monjalon wrote: > > 2016-06-01 14:04, Yuanhan Liu: > > > Apparently, adding a new EAL option like "--force-legacy" looks > > > wrong. > > > > > > The generic yet elegant solution I just thought of while having > > >

[dpdk-dev] [PATCH 2/2] qede: return LAN stats to MFW

> > > >> -Original Message- >> From: Harish Patil [mailto:harish.patil at qlogic.com] >> Sent: Wednesday, June 1, 2016 3:16 PM >> To: Thomas Monjalon >> Cc: dev at dpdk.org; Richardson, Bruce ; >> Rasesh >> Mody ; Dept-Eng DPDK Dev > EngDPDKDev at qlogic.com> >> Subject: Re: [dpdk-dev]

[dpdk-dev] [PATCH 2/2] qede: return LAN stats to MFW

> -Original Message- > From: Harish Patil [mailto:harish.patil at qlogic.com] > Sent: Wednesday, June 1, 2016 3:16 PM > To: Thomas Monjalon > Cc: dev at dpdk.org; Richardson, Bruce ; Rasesh > Mody ; Dept-Eng DPDK Dev EngDPDKDev at qlogic.com> > Subject: Re: [dpdk-dev] [PATCH 2/2] qede:

[dpdk-dev] [dpdk-dev,v5,1/3] mempool: support external handler

On Tue, 31 May 2016 22:40:59 +0200 Olivier MATZ wrote: > Hi, > > On 05/31/2016 03:47 PM, Hunt, David wrote: > > On 5/31/2016 1:06 PM, Jan Viktorin wrote: > >> On Tue, 31 May 2016 10:09:42 +0100 > >> "Hunt, David" wrote: > >> > >>> The *p pointer is the opaque data for a given mempool

[dpdk-dev] [PATCH] ivshmem: add all memzones of mempool to metada

Mempool consist of multiple memzones, at least from two of them. ivshmem assumes mempool and elements are all in same memzone. Updating code to add all memzones when a mempool added. Fixes: d1d914ebbc25 ("mempool: allocate in several memory chunks by default") Signed-off-by: Ferruh Yigit ---

[dpdk-dev] [PATCH 2/2] qede: return LAN stats to MFW

> >2016-05-31 19:21, Harish Patil: >> >> >On Fri, May 06, 2016 at 09:21:31PM -0700, Rasesh Mody wrote: >> >> From: Harish Patil >> >> >> >> Under certain scenarios, MFW periodically polls the driver >> >> for LAN statistics. This patch implements the osal hook to >> >> fill in the stats. >> >>

[dpdk-dev] [PATCH] virtio: use volatile to get used->idx in the loop

On Wed, Jun 01, 2016 at 05:40:08AM +, Xie, Huawei wrote: > On 5/30/2016 4:20 PM, Yuanhan Liu wrote: > > On Wed, May 25, 2016 at 12:16:41AM +0800, Huawei Xie wrote: > >> There is no external function call or any barrier in the loop, > >> the used->idx would only be retrieved once. > >> > >>

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

Hi all, I guess we (maybe just me :) have stated few times something like "hey, this kind of stuff is good to have, but you are trying to add an EAL CLI option for a specific subsystem/driver, which is wrong". One recent example that is still fresh in my mind is the one from Christian [0], that

[dpdk-dev] [PATCH 1/5] pci: fix access to PCI config space in bsd

Hi Bruce, On Tuesday, May 05/31/16, 2016 at 09:20:13 -0700, Bruce Richardson wrote: > On Fri, May 06, 2016 at 01:13:15PM +0530, Rahul Lakkireddy wrote: > > PCIOCREAD and PCIOCWRITE ioctls to read/write PCI config space fail > > with EPERM due to missing write permission. Fix by opening /dev/pci/

[dpdk-dev] [vpp-dev] VLAN packets dropped... ?

Awesome!. Thanks for the quick response John!. -Chandra On Wed, Jun 1, 2016 at 1:02 PM, John Lo (loj) wrote: > We will be adding a patch to the i40e driver that would check the packet > for presence of VLAN tag set the required PKT_RX_VLAN_PKT flag. I hope to > get it done by the end of this

[dpdk-dev] dpdk compilation issue on cumuluslinux

Hi All, I am working on installing dpdk on cumuluslinux(2.5.7v). I have followed the steps as mentioned in the dpdk quick start guide for installation, but the facing issues during compilation. Steps followed: >git clone git://dpdk.org/dpdk >make config T=x86_64-native-linuxapp-gcc >sed -ri

[dpdk-dev] [PATCH v2] mempool: replace c memcpy code semantics with optimized rte_memcpy

On Tue, May 31, 2016 at 11:05:30PM +0200, Olivier MATZ wrote: > Hi Jerin, Hi Olivier, > > >>> /* Add elements back into the cache */ > >>> - for (index = 0; index < n; ++index, obj_table++) > >>> - cache_objs[index] = *obj_table; > >>> + rte_memcpy(_objs[0], obj_table, sizeof(void *)

[dpdk-dev] [PATCH] port: add kni interface support

Hi Cristian, No problem. Enjoy your travel. :-) B.R. Ethan 2016-05-30 22:40 GMT+08:00 Dumitrescu, Cristian < cristian.dumitrescu at intel.com>: > Hi Wei Jie, > > Thank you for submitting this patch. I am currently travelling, I will > review your patch and come back to you hopefully later this

[dpdk-dev] [RFC] kernel paramters like DPDK CLI options

Hi, 2016-06-01 14:04, Yuanhan Liu: > Hi all, > > I guess we (maybe just me :) have stated few times something like > "hey, this kind of stuff is good to have, but you are trying to > add an EAL CLI option for a specific subsystem/driver, which is > wrong". Yes > One recent example that is

[dpdk-dev] dpdk compilation issue on cumuluslinux

On 6/1/2016 8:37 AM, Raja Jayapal wrote: > > > Hi All, > > I am working on installing dpdk on cumuluslinux(2.5.7v). > I have followed the steps as mentioned in the dpdk quick start guide for > installation, but the facing issues during compilation. > > Steps followed: >> git clone

[dpdk-dev] [PATCH v2] qat: fix phys address of content descriptor

From: Arkadiusz Kusztal Fix an error with computation of physical address of content descriptor in the symmetric operations session Fixes: 1703e94ac5ce ("qat: add driver for QuickAssist devices") Signed-off-by: Arkadiusz Kusztal --- v2: Added fixes line to commit

[dpdk-dev] [REQUEST] New repository request for project SPP

2016-05-31 19:11, Ferruh Yigit: > On 5/27/2016 2:59 PM, Thomas Monjalon wrote: > > 2016-05-26 17:48, Ferruh Yigit: > >> SPP: Soft Patch Panel, a new project on top of DPDK library. > >> > >> > >> Code is close to its first release, and we would like to open source the > >> project and host it

[dpdk-dev] [PATCH v5 1/3] mempool: support external handler

On 5/31/2016 10:11 PM, Jerin Jacob wrote: > On Tue, May 31, 2016 at 10:41:00PM +0200, Olivier MATZ wrote: >> Hi, >> >> On 05/31/2016 06:03 PM, Jerin Jacob wrote: >>> On Tue, May 31, 2016 at 04:37:02PM +0100, Hunt, David wrote: On 5/31/2016 9:53 AM, Jerin Jacob wrote: > On Mon, May

[dpdk-dev] [vpp-dev] VLAN packets dropped... ?

Just checking back on this thread to see where things are. Are we saying this is a bug in dpdk or vpp ?. That part wasn't quite clear to me. -Chandra On Thu, May 26, 2016 at 3:56 PM, John Daley (johndale) wrote: > John, > As just discussed, what you suggest was considered but there are

[dpdk-dev] [PATCH 2/2] qede: return LAN stats to MFW

2016-05-31 19:21, Harish Patil: > > >On Fri, May 06, 2016 at 09:21:31PM -0700, Rasesh Mody wrote: > >> From: Harish Patil > >> > >> Under certain scenarios, MFW periodically polls the driver > >> for LAN statistics. This patch implements the osal hook to > >> fill in the stats. > >> > >>

[dpdk-dev] [RFC] Yet another option for DPDK options

On Wed, 1 Jun 2016 17:18:26 +0100 Bruce Richardson wrote: > On Wed, Jun 01, 2016 at 10:58:41AM -0500, Jay Rolette wrote: > > On Wed, Jun 1, 2016 at 10:00 AM, Wiles, Keith > > wrote: > > > > > Started from the link below, but did not want to highjack the thread. > > >

[dpdk-dev] [PATCH] mbuf: extend rte_mbuf_prefetch_part* to support more prefetching methods

On Wed, Jun 01, 2016 at 11:29:47AM +0800, Jianbo Liu wrote: > On 1 June 2016 at 03:28, Olivier MATZ wrote: > > Hi Jianbo, > > > > On 05/31/2016 05:06 AM, Jianbo Liu wrote: > >> Change the inline function to macro with parameters > >> > >> Signed-off-by: Jianbo Liu > >> > >> [...] > >> ---

[dpdk-dev] [PATCH] mbuf: extend rte_mbuf_prefetch_part* to support more prefetching methods

On 1 June 2016 at 03:28, Olivier MATZ wrote: > Hi Jianbo, > > On 05/31/2016 05:06 AM, Jianbo Liu wrote: >> Change the inline function to macro with parameters >> >> Signed-off-by: Jianbo Liu >> >> [...] >> --- a/lib/librte_mbuf/rte_mbuf.h >> +++ b/lib/librte_mbuf/rte_mbuf.h >> @@ -849,14 +849,15

[dpdk-dev] SR-IOV/DPDK/VPP with vfio-pci

I have been attempting to VPP (dpdk) application with SR-IOV enabled. Using the vfio-pci driver/i40e/XL710nics/. I'm encountering a SEGV on the i40e code path. Has anyone else seen this behaviour ?. full mail thread discussion with vpp-dev is here -

[dpdk-dev] dpdk pipeline multi app

tnx but i want to run other process like rxtx_callbacks or customized script. On 31 May 2016 at 17:42, Singh, Jasvinder wrote: > Hi Ramin, > > > > -Original Message- > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ramin Najjarbashi > > Sent: Tuesday, May 31, 2016 8:19 AM > >

[dpdk-dev] [REQUEST] New repository request for project SPP

On 6/1/2016 10:48 AM, Thomas Monjalon wrote: > 2016-05-31 19:11, Ferruh Yigit: >> On 5/27/2016 2:59 PM, Thomas Monjalon wrote: >>> 2016-05-26 17:48, Ferruh Yigit: SPP: Soft Patch Panel, a new project on top of DPDK library. Code is close to its first release, and we would like

[dpdk-dev] [RFC] Yet another option for DPDK options

On Wed, Jun 1, 2016 at 10:00 AM, Wiles, Keith wrote: > Started from the link below, but did not want to highjack the thread. > http://dpdk.org/ml/archives/dev/2016-June/040021.html > > I was thinking about this problem from a user perspective and command line > options are very difficult to

[dpdk-dev] [dpdk-dev,v5,1/3] mempool: support external handler

On 5/31/2016 9:40 PM, Olivier MATZ wrote: [...] >> +/** Structure defining a mempool handler. */ > Later in the text, I suggested to rename rte_mempool_handler to > rte_mempool_ops. > I believe that it explains the purpose of this struct better. It > would improve >

[dpdk-dev] [PATCH v3 2/2] examples/ethtool: get reg width to allocate memory

From: Zyta Szpak Version 2 of fixing the fixed register width assumption. Not every device uses 32-bit wide register. The app was allocating too little space for 64-bit registers which resulted in memory corruption. This commit resolves this by getting the size of register in

[dpdk-dev] [PATCH v3 1/2] ethdev: add callback to get register size in bytes

From: Zyta Szpak Version 2 of fixing the fixed register width assumption. rte_eth_dev_get_reg_length and rte_eth_dev_get_reg callbacks do not provide register size to the app in any way. It is needed to allocate proper number of bytes before retrieving registers content with

[dpdk-dev] [PATCH v2 2/2] igb: VF supports mailbox interruption for PF link up/down

In this scenario, kernel PF + DPDK VF, when PF finds the link state changes, up -> down or down -> up, it will send a message to VF by mailbox. This link state change may be triggered by PHY disconnection/reconnection, configuration like *ifconfig down/up* or interface parameter, like MTU, change.

[dpdk-dev] [PATCH v2 1/2] ixgbe: VF supports mailbox interruption for PF link up/down

In this scenario, kernel PF + DPDK VF, when PF finds the link state changes, up -> down or down -> up, it will send a message to VF by mailbox. This link state change may be triggered by PHY disconnection/reconnection, configuration like *ifconfig down/up* or interface parameter, like MTU, change.

[dpdk-dev] [PATCH v2 0/2] support mailbox interruption on ixgbe/igb VF

This patch set addes the support of the mailbox interruption on VF. So, VF can receice the messges for physical link down/up. And register a reset callback in the handler. PS: This patch set is splitted from a previous patch set, *automatic link recovery on ixgbe/igb VF*. v2: - Reword the commit

[dpdk-dev] about rx checksum flags

> -Original Message- > From: Stephen Hemminger [mailto:stephen at networkplumber.org] > Sent: Tuesday, May 31, 2016 11:03 PM > To: Olivier MATZ > Cc: Yuanhan Liu; dev at dpdk.org; Ananyev, Konstantin; Richardson, Bruce; > Adrien Mazarguil; Tan, Jianfeng > Subject: Re: [dpdk-dev] about

[dpdk-dev] [RFC] Yet another option for DPDK options

On Wed, Jun 01, 2016 at 03:00:11PM +, Wiles, Keith wrote: > The INI file is too flat and I wanted a hierarchy in the data, the JSON data > is similar and XML is just hard to read. I don't think it's fair to say JSON lacks hierarchy. Personally it is working great in my current application.

[dpdk-dev] [PATCH v5 2/8] virtio: clean up virtio_dev_queue_setup

Hi Yuanhan, > -Original Message- > From: Yuanhan Liu [mailto:yuanhan.liu at linux.intel.com] > Sent: Wednesday, June 1, 2016 3:38 PM > To: Tan, Jianfeng > Cc: dev at dpdk.org; Xie, Huawei; rich.lane at bigswitch.com; mst at > redhat.com; > nakajima.yoshihiro at lab.ntt.co.jp; p.fedin at

[dpdk-dev] [PATCH 3/3] vhost: arrange virtio_net fields for better cache sharing

On 5/3/2016 8:42 AM, Yuanhan Liu wrote: > the ifname[] field takes so much space, that it seperate some frequently > used fields into different caches, say, features and broadcast_rarp. > > This patch move all those fields that will be accessed frequently in Rx/Tx > together (before the ifname[]

[dpdk-dev] [PATCH 1/3] vhost: pre update used ring for Tx and Rx

On 5/3/2016 8:42 AM, Yuanhan Liu wrote: > Pre update and update used ring in batch for Tx and Rx at the stage > while fetching all avail desc idx. This would reduce some cache misses > and hence, increase the performance a bit. > > Pre update would be feasible as guest driver will not start

[dpdk-dev] [PATCH 2/3] vhost: optimize dequeue for small packets

On 5/3/2016 8:42 AM, Yuanhan Liu wrote: > Both current kernel virtio driver and DPDK virtio driver use at least > 2 desc buffer for Tx: the first for storing the header, and the others > for storing the data. Tx could prepend some space for virtio net header whenever possible, so that it could

[dpdk-dev] [PATCH] virtio: check if devargs is NULL before checking its value

On 5/27/2016 10:08 AM, Yuanhan Liu wrote: > On Wed, May 25, 2016 at 12:47:30PM +0200, Thomas Monjalon wrote: >>> - dev->devargs->type != RTE_DEVTYPE_WHITELISTED_PCI) { >>> + (!dev->devargs || >>> +dev->devargs->type != RTE_DEVTYPE_WHITELISTED_PCI)) { >>

[dpdk-dev] [PATCH] virtio: use volatile to get used->idx in the loop

On 5/30/2016 4:20 PM, Yuanhan Liu wrote: > On Wed, May 25, 2016 at 12:16:41AM +0800, Huawei Xie wrote: >> There is no external function call or any barrier in the loop, >> the used->idx would only be retrieved once. >> >> Signed-off-by: Huawei Xie >> --- >> drivers/net/virtio/virtio_ethdev.c | 3

[dpdk-dev] [PATCH v3 20/35] mempool: allocate in several memory chunks by default

On 5/18/2016 12:04 PM, Olivier Matz wrote: > Introduce rte_mempool_populate_default() which allocates > mempool objects in several memzones. > > The mempool header is now always allocated in a specific memzone > (not with its objects). Thanks to this modification, we can remove > many specific

[dpdk-dev] [PATCH] app/test: fix bond device name too long

Test case: link_bonging_autotest Package:dpdk.org master branch newest commit + this patch Test cmdline: ./x86_64-native-linuxapp-gcc/app/test -c -n 1 Exec link_bonging_autotest cmdl Test environment: OS: dpdk-rhel72 3.10.0-327.el7.x86_64 Gcc: gcc version 4.8.5 20150623 (Red

[dpdk-dev] [PATCH v5 1/3] mempool: support external handler

On Tue, May 31, 2016 at 10:41:00PM +0200, Olivier MATZ wrote: > Hi, > > On 05/31/2016 06:03 PM, Jerin Jacob wrote: > > On Tue, May 31, 2016 at 04:37:02PM +0100, Hunt, David wrote: > >> > >> > >> On 5/31/2016 9:53 AM, Jerin Jacob wrote: > >>> On Mon, May 30, 2016 at 12:27:26PM +0100, Hunt, David

[dpdk-dev] [PATCH] app/test: fix bond device name too long

Tester-by: huilong xu Test case: link_bonging_autotest Package:dpdk.org master branch newest commit + this patch Test cmdline: ./x86_64-native-linuxapp-gcc/app/test -c -n 1 Exec link_bonging_autotest cmdl Test environment: OS: dpdk-rhel72 3.10.0-327.el7.x86_64 Gcc: gcc version

[dpdk-dev] about memzone name size issue

Hi , I will tester-by this patch, thanks a lot. > -Original Message- > From: Iremonger, Bernard > Sent: Tuesday, May 31, 2016 9:59 PM > To: Wiles, Keith; Xu, HuilongX; dev at dpdk.org > Subject: RE: [dpdk-dev] about memzone name size issue > > Hi Huilong, > > > -Original

[dpdk-dev] [PATCH v2 5/5] testpmd: show topology at forwarding start

This patch show topology at forwarding start. "show config fwd" also does this, but showing it directly can reduce the possibility of misconfiguration. Signed-off-by: Zhihong Wang --- app/test-pmd/cmdline.c | 2 +- app/test-pmd/config.c | 4 ++-- app/test-pmd/testpmd.c | 2 +-

[dpdk-dev] [PATCH v2 4/5] testpmd: handle all rxqs in rss setup

This patch removes constraints in rxq handling when multiqueue is enabled to handle all the rxqs. Current testpmd forces a dedicated core for each rxq, some rxqs may be ignored when core number is less than rxq number, and that causes confusion and inconvenience. Signed-off-by: Zhihong Wang

[dpdk-dev] [PATCH v2 3/5] testpmd: show throughput in port stats

This patch adds throughput numbers (in the period since last use of this command) in port statistics display for "show port stats (port_id|all)". Signed-off-by: Zhihong Wang --- app/test-pmd/config.c | 20 1 file changed, 20 insertions(+) diff --git

[dpdk-dev] [PATCH v2 2/5] testpmd: configurable tx_first burst number

This patch enables configurable tx_first burst number. Use "start tx_first (burst_num)" to specify how many bursts of packets to be sent before forwarding start, or "start tx_first" like before for the default 1 burst send. Signed-off-by: Zhihong Wang --- app/test-pmd/cmdline.c

[dpdk-dev] [PATCH v2 1/5] testpmd: add retry option

This patch adds retry option in testpmd to prevent most packet losses. It can be enabled by "set fwd retry". All modes except rxonly support this option. Adding retry mechanism expands test case coverage to support scenarios where packet loss affects test results. Signed-off-by: Zhihong Wang

[dpdk-dev] [PATCH v2 0/5] vhost/virtio performance loopback utility

This patch enables vhost/virtio pmd performance loopback test in testpmd. All the features are for general usage. The loopback test focuses on the maximum full-path packet forwarding performance between host and guest, it runs vhost/virtio pmd only without introducing extra overhead. Therefore,

[dpdk-dev] [PATCH v2] mempool: replace c memcpy code semantics with optimized rte_memcpy

Hi Jerin, >>> /* Add elements back into the cache */ >>> - for (index = 0; index < n; ++index, obj_table++) >>> - cache_objs[index] = *obj_table; >>> + rte_memcpy(_objs[0], obj_table, sizeof(void *) * n); >>> >>> cache->len += n; >>> >>> >> >> I also checked in the