During PF initialization, PF will generate an initial mac address
for VFs, the purpose is to help VF keep a constant mac address between
its startup/shutdown cycles. Now this is not necessary, since we already
provide an API to set VF's MAC address from PF side
(rte_pmd_i40e_set_vf_mac_addr).
Appli
On Wednesday 22 February 2017 01:52 AM, Stephen Hemminger wrote:
> On Tue, 21 Feb 2017 14:56:15 +0530
> Shijith Thotton wrote:
>
>> The patch series provides initial version of virtual function poll mode
>> driver for Cavium LiquidIO II server adapters. This version adds support
>> for LiquidIO
Hi Ferruh:
Sorry to reply this late, I think I missed your email.
> -Original Message-
> From: Yigit, Ferruh
> Sent: Saturday, January 21, 2017 1:39 AM
> To: Zhang, Qi Z ; Wu, Jingjing ;
> Zhang, Helin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: no more initial
In the IOV scenario, multi RX queues can be assigned
to one VF. If the dropping is not enabled, when no
descriptors are available for one queue, this queue
can block others.
Fixes: 00e30184daa0 ("ixgbe: add PF support")
CC: sta...@dpdk.org
Suggested-by: Liang-min Wang
Signed-off-by: Wenzhuo Lu
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Yuanhan Liu
> Sent: Wednesday, February 22, 2017 9:38 AM
> To: Maxime Coquelin
> Cc: Liang, Cunming ; Tan, Jianfeng
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC PATCH] net/virtio: Align Virtio-net header on
> c
cc the EAL maintainer, David Marchand.
On Mon, Feb 20, 2017 at 10:04:47PM +0800, hanxue...@126.com wrote:
> From: Huanle Han
>
> rte_eal_dev_detach() didn't remove dev from dev_device_list
> after free the dev. So the following attached dev wrote to
> the freed memory (tailq entry of previous de
On Mon, Feb 20, 2017 at 10:04:45PM +0800, hanxue...@126.com wrote:
> From: Huanle Han
>
> The dev detachable flag was removed by
> commit f229eb4 ("net/virtio: fix rewriting LSC flag").
>
> Signed-off-by: Huanle Han
> ---
> drivers/net/virtio/virtio_ethdev.c | 1 +
> 1 file changed, 1 insertio
On Mon, Feb 20, 2017 at 10:04:46PM +0800, hanxue...@126.com wrote:
> From: Huanle Han
>
> This commit fixs segment fault when rte_eth_dev_close()
> is called on a virtio dev more than once.
> Assigning zero after free to avoids freed memory to
> be accessed again.
Thanks for the fix! And here ar
On Tue, Feb 21, 2017 at 03:25:30PM +0100, Matthias Gatto wrote:
> fdset_add increment pfdset->num, but fdset_del doesn't decrement pfdset->num,
> so if we call fdset_add then fdset_del in a loop witout calling
> fdset_shrink, we can easily exceed MAX_FDS with only a few number of fds
> used.
I'm a
On Tue, Feb 21, 2017 at 06:32:43PM +0100, Maxime Coquelin wrote:
> This patch aligns the Virtio-net header on a cache-line boundary to
> optimize cache utilization, as it puts the Virtio-net header (which
> is always accessed) on the same cache line as the packet header.
>
> For example with an ap
Thanks for reminder, will follow:)
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Tuesday, February 21, 2017 4:15 PM
> To: Zhang, Qi Z ; Wu, Jingjing ;
> Zhang, Helin
> Cc: dev@dpdk.org; Zhang, Qi Z ; sta...@dpdk.org
> Subject: RE: [dpdk-stable] [PATCH v3] net/i40e: fix compil
Regarding m->timestamp I have previously argued for keeping it NIC specific,
and not normalizing it. But I have changed my mind: Normalizing it makes gives
the user the ability to transparently swap out a NIC from one vendor with one
from another vendor. And with a hardware timestamp from the NI
> -Original Message-
> From: jblu...@gmail.com [mailto:jblu...@gmail.com] On Behalf Of Jan Blunck
> Sent: Tuesday, February 21, 2017 7:18 PM
> To: Ananyev, Konstantin
> Cc: Richardson, Bruce ; Olivier MATZ
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC 0/8] mbuf: structure reorganizati
On Tue, 21 Feb 2017 14:56:15 +0530
Shijith Thotton wrote:
> The patch series provides initial version of virtual function poll mode
> driver for Cavium LiquidIO II server adapters. This version adds support
> for LiquidIO II CN2350 210SV adapter.
>
> Patch series includes driver documentation do
On Tue, Feb 21, 2017 at 6:26 PM, Ananyev, Konstantin
wrote:
> Hi Jan,
>
>> -Original Message-
>> From: jblu...@gmail.com [mailto:jblu...@gmail.com] On Behalf Of Jan Blunck
>> Sent: Tuesday, February 21, 2017 5:05 PM
>> To: Richardson, Bruce
>> Cc: Olivier MATZ ; Ananyev, Konstantin
>> ;
The coremask option in DPDK is difficult to use and we should be
promoting the use of the corelist (-l) option. The patch
adjusts the docs to use -l EAL option instead of the -c option.
The patch only changes the docs and not the code as the -c option
will continue to exist unless it is removed in
This patch aligns the Virtio-net header on a cache-line boundary to
optimize cache utilization, as it puts the Virtio-net header (which
is always accessed) on the same cache line as the packet header.
For example with an application that forwards packets at L2 level,
a single cache-line will be ac
Hi Jan,
> -Original Message-
> From: jblu...@gmail.com [mailto:jblu...@gmail.com] On Behalf Of Jan Blunck
> Sent: Tuesday, February 21, 2017 5:05 PM
> To: Richardson, Bruce
> Cc: Olivier MATZ ; Ananyev, Konstantin
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC 0/8] mbuf: structure reorg
On Tue, Feb 21, 2017 at 5:38 PM, Bruce Richardson
wrote:
> On Tue, Feb 21, 2017 at 05:12:12PM +0100, Jan Blunck wrote:
>>
>> Access through PMD specific function pointers should be relatively
>> fast on access. Modern architecture optimize that use case well
>> enough.
>>
> The cost of doing a fun
Rather than reading the size directly from the ring structure,
use the dedicated function for that purpose.
Signed-off-by: Bruce Richardson
---
drivers/crypto/null/null_crypto_pmd_ops.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/crypto/null/null_crypto_pmd_ops.c
This patchset contains some minor fixes and improvements which
I found in the context of preparing a new patchset for the
rte_ring code. Having these merged separately reduces the
number of patches in the ring set once I get it finished and so
should make everyone's life easier.
Bruce Richardson (
The code indentation in the example app files used spaces rather than
tabs for indentation, and as such did not conform to DPDK conventions.
This left those modifying the code in a bind - to fix things on a line
by line basis so as to avoid checkpatch errors, or to keep things
consistent within the
RTE_RING_SZ_MASK is redefined here with the original definition in
rte_ring.h. Since rte_ring.h is already included, just remove the
duplicate definition here.
Fixes: caa7028276b8 ("app/pdump: add tool for packet capturing")
Signed-off-by: Bruce Richardson
---
app/pdump/main.c | 1 -
1 file cha
Applications and other libraries should not be reading inside the
rte_ring structure directly to get the ring size. Instead add a fn
to allow it to be queried.
Signed-off-by: Bruce Richardson
---
lib/librte_ring/rte_ring.h | 14 ++
1 file changed, 14 insertions(+)
diff --git a/lib/l
On Tue, Feb 21, 2017 at 05:12:12PM +0100, Jan Blunck wrote:
> On Tue, Feb 21, 2017 at 10:54 AM, Olivier MATZ wrote:
> > Hi Jan,
> >
> > On Mon, 20 Feb 2017 10:27:40 +0100, Jan Blunck
> > wrote:
> >> On Fri, Feb 17, 2017 at 3:17 PM, Olivier Matz
> >> wrote:
> >> >
> >> > Sorry, I don't really get
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of David Hunt
> Sent: Tuesday, February 21, 2017 3:18 AM
> To: dev@dpdk.org
> Cc: Richardson, Bruce ; Hunt, David
>
> Subject: [dpdk-dev] [PATCH v7 16/17] doc: distributor library changes for
> new burst api
>
> Sign
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
> Sent: Tuesday, February 21, 2017 12:03 PM
> To: techbo...@dpdk.org
> Cc: dev@dpdk.org; Richardson, Bruce
> Subject: [dpdk-dev] [PATCH] doc: add details on requirements for patch ack
> and merge
On Tue, Feb 21, 2017 at 10:54 AM, Olivier MATZ wrote:
> Hi Jan,
>
> On Mon, 20 Feb 2017 10:27:40 +0100, Jan Blunck
> wrote:
>> On Fri, Feb 17, 2017 at 3:17 PM, Olivier Matz
>> wrote:
>> >
>> > Sorry, I don't really get your point. My comprehension of the
>> > timestamp usage in a PMD is as follo
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pascal Mazon
> Sent: Tuesday, February 21, 2017 1:15 PM
> To: Wiles, Keith
> Cc: dev@dpdk.org; Pascal Mazon
> Subject: [dpdk-dev] [PATCH] doc: add features doc for net/tap
>
> Signed-off-by: Pascal Mazon
Acke
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Keith Wiles
> Sent: Friday, February 10, 2017 2:01 PM
> To: dev@dpdk.org
> Cc: iryz...@nfware.com; thomas.monja...@6wind.com
> Subject: [dpdk-dev] [PATCH v3] doc: use corelist instead of coremask
>
> The coremask o
Add support for Intel QuickAssist Technology device D15xx
Signed-off-by: Fiona Trahe
---
drivers/crypto/qat/rte_qat_cryptodev.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/crypto/qat/rte_qat_cryptodev.c
b/drivers/crypto/qat/rte_qat_cryptodev.c
index 5b34f5e..386a449 100644
--
This patch adds packet size based distribution scheduling mode
to cryptodev scheduler PMD. In this mode, there are 2 cryptodev
slaves (slave 0 and slave 1), for all enqueued crypto ops
with packet payload over 127 bytes will be distributed to slave 0,
the rest will goes to slave 1.
Signed-off-by:
On Tue, Feb 21, 2017 at 04:04:40PM +0100, Olivier MATZ wrote:
> Hi Morten,
>
> On Tue, 21 Feb 2017 15:20:23 +0100, Morten Brørup
> wrote:
> > Comments at the end.
> >
> >
> > > -Original Message-
> > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> > > Sent: Thursda
Comments inline.
> -Original Message-
> From: Olivier MATZ [mailto:olivier.m...@6wind.com]
> Sent: Tuesday, February 21, 2017 4:05 PM
> To: Morten Brørup
> Cc: Olivier Matz; Bruce Richardson; Ananyev, Konstantin; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC 0/8] mbuf: structure reorganizat
This patch adds an API to get the run-time slaves number and list
of a cryptodev scheduler PMD.
Signed-off-by: Fan Zhang
---
drivers/crypto/scheduler/rte_cryptodev_scheduler.c | 31 ++
drivers/crypto/scheduler/rte_cryptodev_scheduler.h | 23
.../scheduler/rte
Hi Morten,
On Tue, 21 Feb 2017 15:20:23 +0100, Morten Brørup
wrote:
> Comments at the end.
>
>
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> > Sent: Thursday, February 16, 2017 5:14 PM
> > To: Bruce Richardson
> > Cc: Ananyev, Konstantin;
This patch extend next_hop field from 8-bits to 21-bits in LPM library
for IPv6.
Added versioning symbols to functions and updated
library and applications that have a dependency on LPM library.
Signed-off-by: Vladyslav Buslov
---
app/test/test_lpm6.c| 115 ++
2017-02-21 13:46, Bruce Richardson:
> On Fri, Feb 17, 2017 at 12:16:59PM +0100, Thomas Monjalon wrote:
> > 2017-02-17 10:22, Richardson, Bruce:
> > > 5. Accept and review new libraries
> > > * Discussion begun on this topic, but no consensus reached before time
> > > ran out
> > > * Most members
On 2/21/2017 1:42 PM, Shreyansh Jain wrote:
> Thanks for the suggestions about rte_* renaming in DPAA2 PMD.
> I create a draft patch for a single symbol change. (applies over v7
> of DPAA2 PMD)
>
> Can you tell me if this is the direction you were suggesting?
>
> I see two issues in this approach
The number of extended statistics counters is queried through ETHTOOL.
ETHTOOL provides a different number when the link is up or down.
Since extended statistics query occurs at device start,
segmentation fault might happen when changing the link state before and
after the device start.
this commi
Interface name is queried, however never used.
Signed-off-by: Shahaf Shuler
Acked-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5_stats.c | 5 -
1 file changed, 5 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_stats.c b/drivers/net/mlx5/mlx5_stats.c
index 20c957e..0c80e4f 100644
--- a/driv
On Tue, Feb 21, 2017 at 03:20:23PM +0100, Morten Brørup wrote:
> Comments at the end.
>
>
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> > Sent: Thursday, February 16, 2017 5:14 PM
> > To: Bruce Richardson
> > Cc: Ananyev, Konstantin; dev@dp
Some scheduling modes may need extra options to be configured,
this patch adds the function prototype for setting/getting
options.
Signed-off-by: Fan Zhang
---
drivers/crypto/scheduler/rte_cryptodev_scheduler.c | 57 ++
drivers/crypto/scheduler/rte_cryptodev_scheduler.h | 27
Comments at the end.
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> Sent: Thursday, February 16, 2017 5:14 PM
> To: Bruce Richardson
> Cc: Ananyev, Konstantin; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC 0/8] mbuf: structure reorganization
>
>
fdset_add increment pfdset->num, but fdset_del doesn't decrement pfdset->num,
so if we call fdset_add then fdset_del in a loop witout calling
fdset_shrink, we can easily exceed MAX_FDS with only a few number of fds
used.
So my solution is simply to call fdset_shrink in fdset_add
when it exceed MAX
On Tue, Feb 21, 2017 at 03:12:32PM +0100, Thomas Monjalon wrote:
> 2017-02-21 12:02, Bruce Richardson:
> > +#. Once a patch has been acked by the relevant maintainer, reviewers may
> > still comment on it for a further
> > + two weeks. After that time, the patch should be merged into the
> > re
2017-02-21 12:02, Bruce Richardson:
> +#. Once a patch has been acked by the relevant maintainer, reviewers may
> still comment on it for a further
> + two weeks. After that time, the patch should be merged into the relevent
> git tree for the next release.
> + Additional notes and restrictio
Adding support for the next items: eth, vlan, ipv4, udp, tcp and for the
next actions: queue, drop
Signed-off-by: Vasily Philipov
---
drivers/net/mlx4/Makefile|3 +-
drivers/net/mlx4/mlx4.c | 60 ++-
drivers/net/mlx4/mlx4.h |3 +
drivers/net/mlx4/mlx4_flow.c | 1053 ++
Make some structs/defines visible from different source files by placing
them into mlx4.h header.
Signed-off-by: Vasily Philipov
---
drivers/net/mlx4/mlx4.c | 183 ++
drivers/net/mlx4/mlx4.h | 187 +++-
2 fil
On Fri, Feb 17, 2017 at 12:16:59PM +0100, Thomas Monjalon wrote:
> 2017-02-17 10:22, Richardson, Bruce:
> > 4. Issue of review and timely feedback
> > * Discussion focused on review of patches for existing DPDK
> > components/libraries
> > * Agreed that patch maintainers are primarily responsibl
Hi Hemant,
> > + * Scheduler node capabilities
> > + */
> > +struct rte_scheddev_node_capabilities {
...
> > + /**< Lowest priority supported. The value of 1 indicates that
> > +* only priority 0 is supported, which essentially means that
> > +* Strict Priorit
(Modified subject to: "Re: [PATCHv7 03/47] common/dpaa2: adding qbman
driver")
On Tuesday 21 February 2017 07:12 PM, Shreyansh Jain wrote:
Thanks for the suggestions about rte_* renaming in DPAA2 PMD.
I create a draft patch for a single symbol change. (applies over v7
of DPAA2 PMD)
Can you tel
Thanks for the suggestions about rte_* renaming in DPAA2 PMD.
I create a draft patch for a single symbol change. (applies over v7
of DPAA2 PMD)
Can you tell me if this is the direction you were suggesting?
I see two issues in this approach which are somewhat problematic for
me to change all the s
Signed-off-by: Pascal Mazon
---
doc/guides/nics/features/tap.ini | 19 +++
1 file changed, 19 insertions(+)
create mode 100644 doc/guides/nics/features/tap.ini
diff --git a/doc/guides/nics/features/tap.ini b/doc/guides/nics/features/tap.ini
new file mode 100644
index 000
Hello everyone,
A meeting of the DPDK technical board will occur next week, on
the 1st of March 2017 at 3pm UTC (4pm France, 11pm PRC, 7am US Pacific).
The meeting takes place on the #dpdk-board channel on IRC (freenode).
This meeting is public, so anybody can join. Only topics on the agenda
will
On Fri, Feb 10, 2017 at 02:05:49PM +, Cristian Dumitrescu wrote:
> The rte_flow feature breaks the current monolithic approach for ethdev and
> introduces the new generic flow API to ethdev using a plugin-like approach.
>
> Basically, the rte_flow API is still logically part of ethdev:
> - It
On 2/20/2017 2:17 PM, Jan Blunck wrote:
> This introduces different initcall macros to allow for late registration of
> the virtual device bus.
>
> Signed-off-by: Jan Blunck
> Tested-by: Ferruh Yigit
<...>
>
> -#define RTE_INIT(func) \
> -static void __attribute__((constructor, used)) func(v
On 2/20/2017 2:17 PM, Jan Blunck wrote:
> This adds the rte_vdev_device_name() helper function to retrieve the
> rte_vdev_device name which makes moving the name of the low-level
> device into struct rte_device easier in the future.
>
> Signed-off-by: Jan Blunck
<...>
> +const char *
> +rte_vde
On Tue, Feb 21, 2017 at 11:37:09AM +, Vladyslav Buslov wrote:
> Hello Bruce,
>
> Thanks for reviewing my code.
>
> I noticed errors generated by checkpatch.
> However all of them are due to original formatting of files. (e.g. code
> copy-pasted by me as-is from same file or modifications to
Add to the contributors guide the requirements and guidelines for
getting patches acked and merged. It details at what point the review
comments and the ack's need to be received in order to have a given
patch merged into a release.
These guidelines are as agreed by the DPDK technical board at the
On 21/2/2017 3:17 AM, David Hunt wrote:
Note: LIBABIVER is also bumped up in the Makefile
Signed-off-by: David Hunt
---
lib/librte_distributor/rte_distributor.c | 10 +-
lib/librte_distributor/rte_distributor_v20.c | 10 ++
lib/librte_distributor/rte_distrib
This patch adds enqueue and dequeue operations to
rte_cryptodev_scheduler_ops structure. This helps improving
the performance by reducing unnecessary function calls.
Signed-off-by: Fan Zhang
---
drivers/crypto/scheduler/rte_cryptodev_scheduler.c | 6 +
.../scheduler/rte_cryptodev_scheduler_
Wednesday, February 8, 2017 3:58 PM, Shahaf Shuler:
> Subject: [dpdk-dev] [PATCH 0/2] net/mlx5 add rxq interrupt support
>
> This patchset adds support for rxq interrupts on MLX5 PMD.
> The first patch introduces changes on eal_interrupt to support external
> interrupt handlers.
> The second patch
Hello Bruce,
Thanks for reviewing my code.
I noticed errors generated by checkpatch.
However all of them are due to original formatting of files. (e.g. code
copy-pasted by me as-is from same file or modifications to original lines
unrelated to formatting)
I decided to preserve original formatti
2017-02-20 11:16, Bruce Richardson:
> On Mon, Feb 20, 2017 at 04:08:33AM +, David Hunt wrote:
> > When a file is renamed, a normal diff will include all the code of
> > the renamed file, and checkpatch will find warnings and errors,
> > even though it's just a rename.
> >
> > This change will
On Sun, Feb 19, 2017 at 07:14:59PM +0200, Vladyslav Buslov wrote:
> This patch extend next_hop field from 8-bits to 21-bits in LPM library
> for IPv6.
>
> Added versioning symbols to functions and updated
> library and applications that have a dependency on LPM library.
>
> Signed-off-by: Vladysl
2017-02-17 13:28, Olivier Matz:
> As announced in the deprecation notice, remove the functions for
> single/multi producer/consumer enqueue/dequeue.
>
> Signed-off-by: Olivier Matz
Series applied, thanks
2017-02-21 10:43, Ferruh Yigit:
> On 2/21/2017 10:22 AM, Thomas Monjalon wrote:
> > The directory scripts does not exist anymore.
> > The files have been moved but some paths were not updated
> > in the maintainers list.
> >
> > Fixes: 9a98f50e890b ("scripts: move to devtools")
> >
> > Signed-off
2017-02-16 12:06, Ferruh Yigit:
> On 2/16/2017 8:50 AM, Thomas Monjalon wrote:
> > When removing log history functions, the map has not been updated.
> >
> > Fixes: d7e61ad3ae36 ("log: remove deprecated history dump")
> >
> > Reported-by: Olivier Matz
> > Signed-off-by: Thomas Monjalon
>
> Ack
On 2/21/2017 10:22 AM, Thomas Monjalon wrote:
> The directory scripts does not exist anymore.
> The files have been moved but some paths were not updated
> in the maintainers list.
>
> Fixes: 9a98f50e890b ("scripts: move to devtools")
>
> Signed-off-by: Thomas Monjalon
Acked-by: Ferruh Yigit
On 2/10/2017 7:35 PM, Cristian Dumitrescu wrote:
This patch introduces the generic ethdev API for the hierarchical scheduler
capability.
Main features:
- Exposed as ethdev plugin capability (similar to rte_flow approach)
- Capability query API per port and per hierarchy node
- Scheduling algorit
Hi Olivier,
> -Original Message-
> From: Olivier MATZ [mailto:olivier.m...@6wind.com]
> Sent: Tuesday, February 21, 2017 9:54 AM
> To: Ananyev, Konstantin
> Cc: Olivier Matz ; Jan Blunck
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC 0/8] mbuf: structure reorganization
>
> Hi Konstanti
On 21/2/2017 3:17 AM, David Hunt wrote:
Move files out of the way so that we can replace with new
versions of the distributor libtrary. Files are named in
such a way as to match the symbol versioning that we will
apply for backward ABI compatibility.
Signed-off-by: David Hunt
---
---snip--
The directory scripts does not exist anymore.
The files have been moved but some paths were not updated
in the maintainers list.
Fixes: 9a98f50e890b ("scripts: move to devtools")
Signed-off-by: Thomas Monjalon
---
MAINTAINERS | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git
Signed-off-by: David Hunt
---
doc/guides/prog_guide/packet_distrib_lib.rst | 3 +++
1 file changed, 3 insertions(+)
diff --git a/doc/guides/prog_guide/packet_distrib_lib.rst
b/doc/guides/prog_guide/packet_distrib_lib.rst
index b5bdabb..c070eaa 100644
--- a/doc/guides/prog_guide/packet_distrib_l
Signed-off-by: David Hunt
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 8305237..e9033ec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -501,6 +501,7 @@ F: doc/guides/sample_app_ug/ip_reassembly.rst
Distributor
M: Bruce Richardson
+M: Davi
and give distributor it's own thread
Signed-off-by: David Hunt
---
examples/distributor/main.c | 280 ++--
1 file changed, 192 insertions(+), 88 deletions(-)
diff --git a/examples/distributor/main.c b/examples/distributor/main.c
index 7621ff9..0856b57 100
Signed-off-by: David Hunt
---
examples/distributor/main.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/examples/distributor/main.c b/examples/distributor/main.c
index 6634e2f..7621ff9 100644
--- a/examples/distributor/main.c
+++ b/examples/distributor/main.c
@@ -1,8
Signed-off-by: David Hunt
---
lib/librte_distributor/Makefile | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/lib/librte_distributor/Makefile b/lib/librte_distributor/Makefile
index 5b599c6..3017398 100644
--- a/lib/librte_distributor/Makefile
+++ b/lib/librte_distributor/Ma
This will allow us to see what's going on at various stages
throughout the sample app, with per-second visibility
Signed-off-by: David Hunt
---
examples/distributor/main.c | 139 +++-
1 file changed, 123 insertions(+), 16 deletions(-)
diff --git a/example
Signed-off-by: David Hunt
---
app/test/test_distributor_perf.c | 117 +--
1 file changed, 76 insertions(+), 41 deletions(-)
diff --git a/app/test/test_distributor_perf.c b/app/test/test_distributor_perf.c
index a7e4823..30ab1a5 100644
--- a/app/test/test_distr
Note: LIBABIVER is also bumped up in the Makefile
Signed-off-by: David Hunt
---
lib/librte_distributor/rte_distributor.c | 10 +-
lib/librte_distributor/rte_distributor_v20.c | 10 ++
lib/librte_distributor/rte_distributor_version.map | 14 ++
3 files
Add an optimised version of the in-flight flow matching algorithm
using SIMD instructions. This should give up to 1.5x over the scalar
versions performance.
Falls back to scalar version if SSE4.2 not available
Signed-off-by: David Hunt
---
lib/librte_distributor/Makefile|
In the next few patches, we'll want to test old and new API,
so here we're allowing different parameters to be passed to
the tests, instead of just a distributor struct.
Signed-off-by: David Hunt
---
app/test/test_distributor.c | 64 +
1 file changed,
Signed-off-by: David Hunt
---
app/test/test_distributor.c | 115 +++-
1 file changed, 82 insertions(+), 33 deletions(-)
diff --git a/app/test/test_distributor.c b/app/test/test_distributor.c
index 8866e31..c345382 100644
--- a/app/test/test_distributor.c
+
Signed-off-by: David Hunt
---
app/test/test_distributor.c | 292
1 file changed, 187 insertions(+), 105 deletions(-)
diff --git a/app/test/test_distributor.c b/app/test/test_distributor.c
index fdfa793..8866e31 100644
--- a/app/test/test_distributor.c
This patch includes public header file which will be used once
we add in the symbol versioning for v20 and v1705 APIs.
Also includes v1702 private header file, and code for new
burst-capable distributor library.
The new distributor code contains a very similar API to the legacy code,
but now send
Signed-off-by: David Hunt
---
lib/librte_distributor/rte_distributor_private.h | 61
1 file changed, 61 insertions(+)
diff --git a/lib/librte_distributor/rte_distributor_private.h
b/lib/librte_distributor/rte_distributor_private.h
index 2d85b9b..c8e0f98 100644
--- a/lib
We'll be adding content in here common to both burst and
legacy APIs.
Signed-off-by: David Hunt
---
lib/librte_distributor/rte_distributor_private.h | 136 +++
lib/librte_distributor/rte_distributor_v20.c | 72 +---
2 files changed, 137 insertions(+), 71 deletion
we will start the symbol versioning by renaming all legacy functions
Signed-off-by: David Hunt
---
app/test/test_distributor.c| 104 +++--
app/test/test_distributor_perf.c | 28 +++---
examples/distributor/main.c|
Move files out of the way so that we can replace with new
versions of the distributor libtrary. Files are named in
such a way as to match the symbol versioning that we will
apply for backward ABI compatibility.
Signed-off-by: David Hunt
---
app/test/test_distributor.c | 2 +-
This patch aims to improve the throughput of the distributor library.
It uses a similar handshake mechanism to the previous version of
the library, in that bits are used to indicate when packets are ready
to be sent to a worker and ready to be returned from a worker. One main
difference is that in
> > Signed-off-by: Ferruh Yigit
>
> Acked-by: John McNamara
Applied, thanks
2017-02-20 12:15, Mcnamara, John:
> 17.05 Schedule (Proposed)
> Proposal deadline:March 3
> Integration deadline: March 30
> Release: May 2
It seems to make a consensus.
I have sent an update for the website:
http://dpdk.org/ml/archives/web/2017-February/00
Hi Jan,
On Mon, 20 Feb 2017 10:27:40 +0100, Jan Blunck
wrote:
> On Fri, Feb 17, 2017 at 3:17 PM, Olivier Matz
> wrote:
> >
> > Sorry, I don't really get your point. My comprehension of the
> > timestamp usage in a PMD is as following:
> >
> > rx_burst(struct rxq *rxq, ...)
> > {
> > unsi
Hi Morten,
On Tue, 21 Feb 2017 10:22:57 +0100, Morten Brørup
wrote:
> Hi Olivier,
>
> There has been a lot of debate about the size and location (1st or
> 2nd cache line) of the mbuf fields.
>
> May I suggest that you add a comment to each field briefly mentioning
> why it has a specific size (
Hi Andrey,
On Sun, 19 Feb 2017 19:04:58 +, "Chilikin, Andrey"
wrote:
> While doing this fields reshuffling, any chance to put uint16_t
> vlan_tci_outer beside uint16_t vlan_tci? It will allow to treat QinQ
> tags as a single 32-bit tag, if needed, and use it for other
> tag/labels like MPLS,
Hi Konstantin,
On Fri, 17 Feb 2017 18:42:01 +, "Ananyev, Konstantin"
wrote:
> Hi guys,
>
> > > My point is that I still doubt that it belongs into the first
> > > cacheline. It requires accessing other structures for converting
> > > into nanoseconds anyway. Optimally I would like to see thi
Signed-off-by: Shijith Thotton
Signed-off-by: Jerin Jacob
Signed-off-by: Derek Chickles
Signed-off-by: Venkat Koppula
Signed-off-by: Mallesham Jatharakonda
---
drivers/net/liquidio/lio_ethdev.c | 68 +--
drivers/net/liquidio/lio_ethdev.h | 5 +++
drivers/n
1 - 100 of 156 matches
Mail list logo
