On 2015/04/01 20:13, Mcnamara, John wrote:
>> -Original Message-
>> From: Masaru Oki [mailto:m-oki at stratosphere.co.jp]
>> Sent: Wednesday, April 1, 2015 11:14 AM
>> To: Mcnamara, John
>> Cc: Tetsuya Mukawa; De Lara Guarch, Pablo; dev at dpdk.org
>> Subject: Re: [dpdk-dev] Cannot build do
Hi Thomas,
> What is the relation between link status timeout and qos_sched?
[LCM] Validation team found qos_sched test failure on i40e. The sample depends
on link speed to calc the percentage.
The root cause comes from that i40e link_get hasn't support wait_to_complete
well.
I agree with you i
Hi Thomas,
First and foremost, We found this problem with using Qos example on Fedora21
platform, there are our reproduce test steps as follows.
We used this example found FVL 4*10G NIC link status caused to our Qos
example could not boot normally in our dpdk2.0 Release Cycle;
In addition,
<< igb_uio and rte_kni are unlikely to be accepted upstream since they have
intrinsic security problems.
Can you use VFIO?>>
Hi Stephen,
Thanks for the reply. Can you please elaborate on the security issue?Thanks.
Regards
Suyash
-Original Message-
From: Stephen Hemminger [mailto:step.
The uio drivers are not secured by an iommu.
Therefore, you could misuse the NIC to DMA read/write into any part of
memory, e.g. reading or writing to memory of the host or other containers.
This is a security breach if you enable a container to do this by giving it
access via uio, because you hav
Container itself is not considered as a secured solution that could provide
strict resource isolation which
VT could provide. Basically, we have 4 different configuration as below, you
could pick most appropriate one
depending on usage scenarios.
1) VT + VFIO: supposed to be the most secured sol
> -Original Message-
> From: Iremonger, Bernard
> Sent: Wednesday, April 1, 2015 6:20 PM
> To: Mcnamara, John; Thomas Monjalon
> Cc: Butler, Siobhan A; dev at dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v2 0/3] split programmers guide a bit
> > The main positive is that it would give us aut
- libmlx4 and libibverbs dependencies distributed with Mellanox OFED are now
also available on DPDK.org to make installation easier.
- Document Mellanox OFED and firmware versions to use.
- Add links to Mellanox and its community websites.
- Add kernel modules parameters section.
Signed-off-by:
Hi all,
I wonder if there is a possibility to call rte_eth_rx_queue_setup() from
different processes (for different RSS queues off course)
For example, the code will look something like:
>From Process 1:
retval = rte_eth_rx_queue_setup(port_num, 0, rx_ring_size,
The is an RFC patch demonstrating automatic figure references
in the documentation. The figure numbers in the generated
Html and PDF docs with by automatically numbered based on
section. Requires Sphinx >= 1.3.
The patch makes the following changes.
* Changes image:: tag to figure:: and moves ima
On Wed, Apr 01, 2015 at 03:54:27PM -0700, Deep Debroy wrote:
> Hi, I was wondering if anyone has pointers for a crypto library
> implementing AES CBC and GCM that I can use for encrypting network packets
> in a DPDK app's datapath.
>
> The app is supposed to run in a VM in the cloud. So access to
From: Lilijun
In the function map_all_hugepages(), hugepage memory is truly allocated by
memset(virtaddr, 0, hugepage_sz). Then it costs about 40s to finish the
dpdk memory initialization when 4 2M hugepages are setup in host os.
In fact we can only write one byte to finish the allocation.
Hi,
On Wed, Apr 01, 2015 at 08:18:30PM +, Raghav Sethi wrote:
> Hi folks,
>
> Hopefully this is the right place to ask questions. I'm trying to run
> testpmd (and then develop my own applications) with DPDK 1.8 and the
> Mellanox ConnectX-3. The setup script/quickstart/Getting Started guide
2015-04-02 19:30, jerry.lilijun at huawei.com:
> From: Lilijun
>
> In the function map_all_hugepages(), hugepage memory is truly allocated by
> memset(virtaddr, 0, hugepage_sz). Then it costs about 40s to finish the
> dpdk memory initialization when 4 2M hugepages are setup in host os.
Yes i
On Thu, Apr 2, 2015 at 7:55 AM, Thomas Monjalon
wrote:
> 2015-04-02 19:30, jerry.lilijun at huawei.com:
> > From: Lilijun
> >
> > In the function map_all_hugepages(), hugepage memory is truly allocated
> by
> > memset(virtaddr, 0, hugepage_sz). Then it costs about 40s to finish the
> > dpdk memo
Hi All, just to make a comment on my own email :-)
On 4/1/15, 7:44 AM, "Wiles, Keith" wrote:
>Hi all, (hoping format of the text is maintained)
>
>Bruce and myself are submitting this RFC in hopes of providing discussion
>points for the idea. Please do not get carried away with the code
>include
On 31/03/15 20:23, Olivier Matz wrote:
> From: Olivier Matz
>
> Add a new private_size field in mbuf structure that should
> be initialized at mbuf pool creation. This field contains the
> size of the application private data in mbufs.
>
> Introduce new static inline functions rte_mbuf_from_indi
Huawei/Changchun can you please ack this patch or if you are not happy with it
ask for it to be deffered but it is blocking.
Thank you
S
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Wednesday, April 1, 2015 8:58 PM
> To: Xie, Huaw
This patchset contains refactoring steps for the `eventfd_link' module
of the DPDK's `librte_vhost' part.
Pavel Boldin (5):
vhost: eventfd_link: moving ioctl to a function
vhost: eventfd_link: add function fget_from_files
vhost: eventfd_link: fix ioctl return values
vhost: eventfd_link: re
Move ioctl `EVENTFD_COPY' handler code to an inline function.
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 171 ++-
1 file changed, 89 insertions(+), 82 deletions(-)
diff --git a/lib/librte_vhost/eventfd_link/eventfd_link.c
b/lib/librte_vhost/eventfd_link/eventfd_li
Fix ioctl return values:
* `-EFAULT' when unable to fetch user supplied arguments,
* `-ESRCH' when no target process is found,
* `-ESTALE' when unable to get `struct files',
* `-EBADF' when unable to get `struct file' for fd.
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 46 ++
Move copy-pasted code of `fget' for different `struct files' to
the added `fget_from_files' function.
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 36 +++-
1 file changed, 20 insertions(+), 16 deletions(-)
diff --git a/lib/librte_vhost/eventfd_link/eventfd_link.c
b/
Replace copy-pasted `fget_from_files' -> `filp_close' with
a `sys_close' call.
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 49 +++-
1 file changed, 12 insertions(+), 37 deletions(-)
diff --git a/lib/librte_vhost/eventfd_link/eventfd_link.c
b/lib/librte_vhost/eventf
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 9 +
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/lib/librte_vhost/eventfd_link/eventfd_link.c
b/lib/librte_vhost/eventfd_link/eventfd_link.c
index 9bc52a3..0ee7357 100644
--- a/lib/librte_vhost/eventfd_link/eventfd_link.c
Hi Olivier,
> -Original Message-
> From: Olivier Matz [mailto:olivier.matz at 6wind.com]
> Sent: Tuesday, March 31, 2015 8:23 PM
> To: dev at dpdk.org
> Cc: Ananyev, Konstantin; zoltan.kiss at linaro.org; Richardson, Bruce;
> Olivier Matz
> Subject: [PATCH v3 1/5] mbuf: fix clone support
These are the last patches needed for packaging the release of dpdk-2.0.0.
It was tested to generate a RPM on Fedora 20 without fuse.
The package includes PDF doc and enable features for vhost, pcap and Xen.
If nobody see something wrong in these patches, they will be applied
tomorrow, April 3rd i
The fuse library is needed for vhost-cuse as required in commit 28a1ccca41bf.
The case vhost-user was forgotten for application linking.
Fixes: 28a1ccca41bf ("vhost: add build option for vhost-user")
Signed-off-by: Thomas Monjalon
---
mk/rte.app.mk | 2 +-
1 file changed, 1 insertion(+), 1 dele
In case of documents without image, an empty rm command can be seen if V=1.
Remove it to avoid disturbing debugging.
Signed-off-by: Thomas Monjalon
---
mk/rte.sdkdoc.mk | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mk/rte.sdkdoc.mk b/mk/rte.sdkdoc.mk
index f91e079..9952f25
Since -core suffix was removed from the package names in commit
6f2760ecdf4e, the file name should also be updated.
The alignment of build commands is also changed to prepare next patch.
Signed-off-by: Thomas Monjalon
---
pkg/{dpdk-core.spec => dpdk.spec} | 48 +++---
Enable vhost-user and build PDF doc.
Inkscape and TeXLive are required to convert .svg and .rst to .pdf.
Temporary sphinx files .* (.doctrees/ and .buildinfo) are cleaned.
Tested on Fedora 20.
Signed-off-by: Thomas Monjalon
---
pkg/dpdk.spec | 13 +
1 file changed, 9 insertions(+),
Signed-off-by: Thomas Monjalon
---
doc/guides/rel_notes/index.rst | 2 +-
doc/guides/rel_notes/rel_description.rst| 2 +-
lib/librte_eal/common/include/rte_version.h | 4 ++--
pkg/dpdk.spec | 2 +-
4 files changed, 5 insertions(+), 5 deletions(-)
di
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of
> xuelin.shi at freescale.com
> Sent: Tuesday, March 31, 2015 8:26 AM
> To: Ananyev, Konstantin
> Cc: dev at dpdk.org; Xuelin Shi
> Subject: [dpdk-dev] [PATCH v3] ixgbe: fix data access on big endian cpu
>
> F
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen
> Hemminger
> Sent: Tuesday, March 24, 2015 3:55 PM
> To: Ananyev, Konstantin
> Cc: dev at dpdk.org; Stephen Hemminger
> Subject: Re: [dpdk-dev] [PATCH] ixgbe: do not include CRC in Tx byte count
>
> O
Signed-off-by: Siobhan Butler
---
doc/guides/rel_notes/rel_description.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/rel_notes/rel_description.rst
b/doc/guides/rel_notes/rel_description.rst
index c8ff483..2fb5379 100644
--- a/doc/guides/rel_notes/rel_descript
2015-04-02 21:41, Siobhan Butler:
> --- a/doc/guides/rel_notes/rel_description.rst
> +++ b/doc/guides/rel_notes/rel_description.rst
> -fixed bugs and known issues for Data Plane Development Kit (DPDK) release
> version 1.7.0.
> +fixed bugs and known issues for Data Plane Development Kit (DPDK) rel
Signed-off-by: Siobhan Butler
---
doc/guides/rel_notes/new_features.rst | 38 +--
1 file changed, 18 insertions(+), 20 deletions(-)
diff --git a/doc/guides/rel_notes/new_features.rst
b/doc/guides/rel_notes/new_features.rst
index e3edec4..cb58409 100644
--- a/doc/
Signed-off-by: Siobhan Butler
---
doc/guides/rel_notes/known_issues.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/rel_notes/known_issues.rst
b/doc/guides/rel_notes/known_issues.rst
index 6c81fcf..4c43191 100644
--- a/doc/guides/rel_notes/known_issues.rst
+++
-Note: This patch relies on patch 'doc: remove release version from known
issues'
-Added issue with failing unit test for link bonding to known issues
Signed-off-by: Siobhan Butler
---
doc/guides/rel_notes/known_issues.rst | 28
1 file changed, 28 insertions(+)
dif
> -Original Message-
> From: Butler, Siobhan A
> Sent: Thursday, April 2, 2015 9:42 PM
> To: dev at dpdk.org
> Cc: Butler, Siobhan A
> Subject: [PATCH] doc: update version number in release notes description
>
> Signed-off-by: Siobhan Butler
> ---
> doc/guides/rel_notes/rel_description.
The qos_scheduler has a 32 bit speed value and therefore I doubt it will
work work at 40G
On Wed, Apr 1, 2015 at 6:44 PM, Liang, Cunming
wrote:
> Hi Thomas,
>
> > What is the relation between link status timeout and qos_sched?
> [LCM] Validation team found qos_sched test failure on i40e. The sam
40 matches
Mail list logo
