[dpdk-dev] [PATCH v3] doc: autogenerate nic overview table from ini files

Hi John, 2016-07-29 12:59, John McNamara: > Convert the NIC feature table in the overview doc into a set of ini > files and add functions into the Sphinx conf.py file to auto-generate > them back into an RST table. I have not reviewed the Python code which generate the RST table. It works so it

[dpdk-dev] [PATCH v2] lpm: remove redundant check when adding lpm rule

When a rule with depth > 24 is added into an existing rule with depth <=24, a new tbl8 is allocated, the existing rule first fulfill whole new tbl8, so the filed vaild of each entry in this tbl8 is always true and depth of each entry is always < 24 before adding new rule with depth > 24.

[dpdk-dev] [PATCH v2] net/i40e: fix Rx statistic inconsistent

Hi,Wu jingjing and wenzhuo > -Original Message- > From: Zhao1, Wei > Sent: Monday, August 1, 2016 4:58 PM > To: 'Kyle Larose' > Cc: dev at dpdk.org > Subject: RE: [dpdk-dev] [PATCH v2] net/i40e: fix Rx statistic inconsistent > > Hi, Kyle Larose >The core problem is i40e has no

[dpdk-dev] [PATCH v2] examples: fix unusual-interpreter

*update in v2* - use #!/usr/bin/env python as usually recommended and suggested in the discussion Due to regular lintian checks in Debian packaging it surfaced that these two scripts had a space in their #! statement which renders it to be human, but not shell readable. Fixes: 8673a3e8

[dpdk-dev] [PATCH] i40e: enable i40e pmd on ARM platform

And add read memory barrier to avoid status inconsistency between two RX descriptors readings. Signed-off-by: Jianbo Liu --- config/defconfig_arm64-armv8a-linuxapp-gcc | 2 +- doc/guides/nics/overview.rst | 2 +- drivers/net/i40e/i40e_rxtx.c | 2 ++ 3 files changed,

[dpdk-dev] [PATCH v2] net/i40e: fix Rx statistic inconsistent

Hi, Wujingjing and Kyle Larose > -Original Message- > From: Zhao1, Wei > Sent: Tuesday, August 2, 2016 11:27 AM > To: Wu, Jingjing ; Lu, Wenzhuo > > Cc: dev at dpdk.org > Subject: RE: [dpdk-dev] [PATCH v2] net/i40e: fix Rx statistic inconsistent > > Hi,Wu jingjing and wenzhuo > > >

[dpdk-dev] [PATCH v3 4/4] eal: fix end character check in --lcores argument

Hi, Thomas, Yigit > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Friday, July 29, 2016 12:06 AM > To: Dai, Wei > Cc: dev at dpdk.org; Yigit, Ferruh > Subject: Re: [dpdk-dev] [PATCH v3 4/4] eal: fix end character check in > --lcores > argument

[dpdk-dev] [PATCH] qat: change the session structure to be variable sized

This patch changes the qat session data structure sent to qat from a fixed size to a variable size which is dependent on the size of the chosen algorithm. This reduces the amount of bytes which are transferred across PCIe and thus helps to increase qat performance when the accelerator is

[dpdk-dev] [PATCH] net/mlx5: Fix possible NULL deref in RX path

On 01/08/16 19:43, Adrien Mazarguil wrote: > Hi Sagi, > > On Mon, Aug 01, 2016 at 11:44:21AM +0300, Sagi Grimberg wrote: >> The user is allowed to call ->rx_pkt_burst() even without free >> mbufs in the pool. In this scenario we'll fail allocating a rep mbuf >> on the first iteration (where pkt

[dpdk-dev] [PATCH] net/mlx5: Fix possible NULL deref in RX path

On Tue, Aug 02, 2016 at 12:31:35PM +0300, Sagi Grimberg wrote: > > > On 01/08/16 19:43, Adrien Mazarguil wrote: > >Hi Sagi, > > > >On Mon, Aug 01, 2016 at 11:44:21AM +0300, Sagi Grimberg wrote: > >>The user is allowed to call ->rx_pkt_burst() even without free > >>mbufs in the pool. In this

[dpdk-dev] [PATCH v2] examples: fix unusual-interpreter

> -Original Message- > From: Christian Ehrhardt [mailto:christian.ehrhardt at canonical.com] > Sent: Tuesday, August 2, 2016 7:40 AM > To: christian.ehrhardt at canonical.com; thomas.monjalon at 6wind.com; > Dumitrescu, Cristian ; dev at dpdk.org > Subject: [PATCH v2] examples: fix

[dpdk-dev] [PATCH v3 4/4] eal: fix end character check in --lcores argument

2016-08-02 08:22, Dai, Wei: > Hi, Thomas, Yigit > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > 2016-07-28 16:26, Ferruh Yigit: > > > On 7/27/2016 12:27 PM, Wei Dai wrote: > > > > With --lcores 'a-b at c-d', eal_parse_cores() fails because > > > > eal_parse_set() fails due to

[dpdk-dev] [PATCH] net/mlx5: Fix possible NULL deref in RX path

On 02/08/16 12:58, Adrien Mazarguil wrote: > On Tue, Aug 02, 2016 at 12:31:35PM +0300, Sagi Grimberg wrote: >> >> >> On 01/08/16 19:43, Adrien Mazarguil wrote: >>> Hi Sagi, >>> >>> On Mon, Aug 01, 2016 at 11:44:21AM +0300, Sagi Grimberg wrote: The user is allowed to call ->rx_pkt_burst()

[dpdk-dev] [PATCH] table: add missing exports

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Aleksey Katargin > Sent: Monday, August 1, 2016 10:01 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH] table: add missing exports > > Signed-off-by: Aleksey Katargin > --- >

[dpdk-dev] [PATCH] net/mlx5: Fix possible NULL deref in RX path

On Tue, Aug 02, 2016 at 01:47:55PM +0300, Sagi Grimberg wrote: > > > On 02/08/16 12:58, Adrien Mazarguil wrote: > >On Tue, Aug 02, 2016 at 12:31:35PM +0300, Sagi Grimberg wrote: > >> > >> > >>On 01/08/16 19:43, Adrien Mazarguil wrote: > >>>Hi Sagi, > >>> > >>>On Mon, Aug 01, 2016 at 11:44:21AM

[dpdk-dev] [PATCH v2] net/mlx5: Fix possible NULL deref in RX path

The user is allowed to call ->rx_pkt_burst() even without free mbufs in the pool. In this scenario we'll fail allocating a rep mbuf on the first iteration (where pkt is still NULL). This would cause us to deref a NULL pkt (reset refcount and free). Fix this by checking the pkt before freeing it.

[dpdk-dev] [PATCH v2] net/mlx5: Fix possible NULL deref in RX path

On Tue, Aug 02, 2016 at 03:02:18PM +0300, Sagi Grimberg wrote: > The user is allowed to call ->rx_pkt_burst() even without free > mbufs in the pool. In this scenario we'll fail allocating a rep mbuf > on the first iteration (where pkt is still NULL). This would cause us > to deref a NULL pkt

[dpdk-dev] [dpdk-announce] DPDK Community Survey - about to close

Hi all, That's the first time a DPDK survey is published. It will help us in our future progress to decide what are the most important stuff to work on. Please do not wait to fill it out. It closes on August 4. Thanks for taking 2 minutes now to give your feedback. When you will have done your

[dpdk-dev] DPDK Community Survey - about to close

Just 2 minutes for DPDK ;) http://surveymonkey.com/r/DPDK_Community_Survey 2016-08-02 14:39, Thomas Monjalon: > Hi all, > > That's the first time a DPDK survey is published. > It will help us in our future progress to decide what are the most > important stuff to work on. > > Please do

[dpdk-dev] [RFC] scripts: make load-devel-config not to appear as executable

Quoting the first line of the script: "#! /bin/echo must be loaded with ." Given that we should drop the .sh file ending as well as the executable flag - both are not needed to source the file. Signed-off-by: Christian Ehrhardt --- MAINTAINERS | 2 +- scripts/checkpatches.sh

[dpdk-dev] [PATCH v3] net/mlx5: fix possible NULL deref in Rx path

The user is allowed to call ->rx_pkt_burst() even without free mbufs in the pool. In this scenario we'll fail allocating a rep mbuf on the first iteration (where pkt is still NULL). This would cause us to deref a NULL pkt (reset refcount and free). Fix this by checking the pkt before freeing it.

[dpdk-dev] how to design high performance QoS support for a large amount of subscribers

Hi, I am trying to add QoS support for a high performance VNF with large amount of subscribers (millions). It requires to support guaranteed bit rate for different service level of subscribers. I.e. four service levels need to be supported: * Diamond, 500M * Gold, 100M *

[dpdk-dev] [RFC] scripts: make load-devel-config not to appear as executable

2016-08-02 15:54, Christian Ehrhardt: > Quoting the first line of the script: "#! /bin/echo must be loaded with ." > Given that we should drop the .sh file ending as well as the executable > flag - both are not needed to source the file. Hmmm, it is still a file containing some shell commands,

[dpdk-dev] [PATCH 1/2] lpm: fix tlb8 only not freed for depth=24

On Mon, Aug 01, 2016 at 03:03:20PM +0800, Wei Dai wrote: > When all rules with depth > 24 are deleted in a same tlb8 group > and only leave a rule with depth <= 24 in this group, the tlb8 > group should be recycled. > The title needs a bit of rewording, I think e.g. lpm: fix freeing unused

[dpdk-dev] [PATCH 2/2] app/test: add a case to verify lpm tlb8 recycle

On Mon, Aug 01, 2016 at 03:03:44PM +0800, Wei Dai wrote: > As a bug-fix for lpm tlb8 recycle is introduced, > add a test case to verify tlb8 group is correctly > freed when it only includes a rule with depth=24. > > Signed-off-by: Wei Dai Acked-by: Bruce Richardson

[dpdk-dev] [PATCH v2] lpm: remove redundant check when adding lpm rule

On Tue, Aug 02, 2016 at 10:09:25AM +0800, Wei Dai wrote: > When a rule with depth > 24 is added into an existing > rule with depth <=24, a new tbl8 is allocated, the existing > rule first fulfill whole new tbl8, so the filed vaild of typo "valid" > each entry in this tbl8 is always true and

[dpdk-dev] [PATCH v2] net/i40e: fix Rx statistic inconsistent

Hello Wei, On Tue, Aug 2, 2016 at 2:59 AM, Zhao1, Wei wrote: > Hi, Wujingjing and Kyle Larose > > > >> -Original Message- >> From: Zhao1, Wei >> Sent: Tuesday, August 2, 2016 11:27 AM >> To: Wu, Jingjing ; Lu, Wenzhuo >> >> Cc: dev at dpdk.org >> Subject: RE: [dpdk-dev] [PATCH v2]

[dpdk-dev] [RFC] Generic flow director/filtering/classification API

On 16-07-23 02:10 PM, John Fastabend wrote: > On 16-07-21 12:20 PM, Adrien Mazarguil wrote: >> Hi Jerin, >> >> Sorry, looks like I missed your reply. Please see below. >> > > Hi Adrian, > > Sorry for a bit delay but a few comments that may be worth considering. > > To start with completely

[dpdk-dev] [PATCH] net/i40e: fix null pointer dereferences when using VMDQ+RSS

When using VMDQ+RSS, the queue ids used by the application are not contiguous (see i40e_pf_config_rss). Most of the driver already handled this, but there were a few cases where it assumed all configured queues had been setup. Fixes: 4861cde46116 ("i40e: new poll mode driver") Fixes: 6b4537128394

[dpdk-dev] [RFC 0/4] Use Google Test as DPDK unit test framework

I've been trying out using google test as a possible replacement for our unit test framework and have put to together this series of patches with help from Anatoly as RFC to get peoples thoughts on migrating to google test. To facilitate google test this rfc patch set contains build system

[dpdk-dev] [RFC 1/4] mk: Add support for C++ compilation

From: Anatoly Burakov Adding support for compiling C++ files as part of the build system Signed-off-by: Declan Doherty --- mk/internal/rte.compile-pre.mk | 52 ++ mk/target/generic/rte.vars.mk | 3 +++

[dpdk-dev] [RFC 2/4] examples: add c++ example application

From: Anatoly Burakov Example application for C++ compilation Signed-off-by: Declan Doherty --- examples/Makefile| 1 + examples/helloworld-cpp/Makefile | 51 + examples/helloworld-cpp/c_code.c | 5 ++

[dpdk-dev] [RFC 3/4] eal: add command line option to log output to stdout

Adds new command line options which allows the user to stop application echoing log output to stdout, logs are still written to syslog. Signed-off-by: Declan Doherty --- lib/librte_eal/common/eal_common_log.c | 14 ++ lib/librte_eal/common/eal_common_options.c | 8

[dpdk-dev] [RFC 4/4] app/test-gtest: example google test application

Adds a new application to demonstrate how google test could be used as a new unit test framework. To compile both ${GTEST_DIR} and ${GMOCK_DIR} the install paths to google test and google mock directories respectively must be defined/exported. Signed-off-by: Declan Doherty --- app/Makefile

[dpdk-dev] eal: map shared config into exact same address as primary process (for freebsd)

Hello I am getting a segmentation fault on freebsd 10 due to the shared config mismatch between the primary and secondary process - The following commit seems to have fixed this issue long time back on Linux but was never ported to freebsd.