Signed-off-by: Pablo de Lara
---
examples/netmap_compat/Makefile |3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/examples/netmap_compat/Makefile b/examples/netmap_compat/Makefile
index d398e5f..52d8086 100644
--- a/examples/netmap_compat/Makefile
+++ b/examples/netmap_c
> Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> recv/xmit
>
> On Wed, Oct 01, 2014 at 09:12:44AM +, Hiroshi Shimamoto wrote:
> > > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > > recv/xmit
> > >
> > > On Tue, Sep 30, 2014 at 11:52:00PM +0
RTE_DRV_LOG macro has changed, so now it requires at least 2 arguments,
which have been added in ixgbe_bypass, specifying log type, to fix compilation
error
Signed-off-by: Pablo de Lara
---
lib/librte_pmd_ixgbe/ixgbe_82599_bypass.c | 10 +-
lib/librte_pmd_ixgbe/ixgbe_bypass.c |
On Thu, Oct 02, 2014 at 02:07:09AM +, Hiroshi Shimamoto wrote:
> > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > recv/xmit
> >
> > On Wed, Oct 01, 2014 at 11:33:23PM +, Hiroshi Shimamoto wrote:
> > > > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add bran
On Wed, Oct 01, 2014 at 11:33:23PM +, Hiroshi Shimamoto wrote:
> > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > recv/xmit
> >
> > On Wed, Oct 01, 2014 at 09:12:44AM +, Hiroshi Shimamoto wrote:
> > > > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add bran
On Thu, Oct 02, 2014 at 10:43:52AM +0900, Tetsuya Mukawa wrote:
> I haven't known the options. Thanks.
> Anyway, I understand I shouldn't change link order, but should check why
> '--start-group/--end-group' doesn't work on my environment.
> I will describe more in the email for Thomas.
>
> Regard
I was needing cmdline_set_prompt(struct cmdline * cl, const char * prompt) to
be more dynamic with the prompt.
What I would like to be able to do is change the prompt on the fly in my
Pktgen-DPDK application. The reason is I have added some limited ANSI color
support and would like to remove t
When enabling RTE_LIBRTE_MEMPOOL_DEBUG and compiling with clang
compiler an error occurs, because ifdefed code now includes GCC pragmas.
GCC 4.4 is when push_options and pop_options pragma show up.
Rework to include Thomas?s suggestion to drop push/pop pragma directives for
ignore/error directiv
Acked-by: Sergio Gonzalez Monroy
On Mon, Sep 15, 2014 at 03:23:51PM -0400, Neil Horman wrote:
> Adding a document describing rudimentary ABI policy and adding notice space
> for
> any deprecation announcements
>
> Signed-off-by: Neil Horman
> CC: Thomas Monjalon
> CC: "Richardson, Bruce"
> -
Thomas, I will submit a v3 patch in a few minutes.
On Oct 1, 2014, at 9:57 AM, Wiles, Roger Keith
wrote:
> Hi Thomas,
>
> Changing the macros to:
>
> #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> #ifndef __INTEL_COMPILER
> #pragma GCC diagnostic ignored "-Wcast-qual"
> #endif
> .
> .
> #ifndef __INTEL_CO
On Wed, Oct 01, 2014 at 12:01:10PM -0400, Neil Horman wrote:
> On Wed, Oct 01, 2014 at 04:43:10PM +0100, Bruce Richardson wrote:
> > On Wed, Oct 01, 2014 at 11:02:27AM -0400, Neil Horman wrote:
> > > On Wed, Oct 01, 2014 at 03:36:45PM +0200, Thomas Monjalon wrote:
> > > > 2014-09-28 08:27, Neil Hor
On Wed, Oct 01, 2014 at 11:02:27AM -0400, Neil Horman wrote:
> On Wed, Oct 01, 2014 at 03:36:45PM +0200, Thomas Monjalon wrote:
> > 2014-09-28 08:27, Neil Horman:
> > > On Sun, Sep 28, 2014 at 05:28:44AM +, Wiles, Roger Keith wrote:
> > > > Check the FILE *f and rte_mempool *mp pointers for NUL
On Wed, Oct 01, 2014 at 10:56:20AM -0400, Neil Horman wrote:
> On Wed, Oct 01, 2014 at 02:47:00PM +, Pattan, Reshma wrote:
> >
> >
> > > -Original Message-
> > > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > > Sent: Tuesday, September 30, 2014 2:40 PM
> > > To: Richardson, B
>
> Hi,
>
> I want to run dpdk l2fwd-ivshmem application. I could not find any
> documentation on it. While digging the forum I found that I need to have
> memnic-pmd installed(http://dpdk.org/doc/memnic-pmd) . But I am not
> sure where do I download memnic-pmd. I am using dpdk-1.7.1
>
> Can any
On Oct 1, 2014, at 10:43 AM, Bruce Richardson
wrote:
> On Wed, Oct 01, 2014 at 11:02:27AM -0400, Neil Horman wrote:
>> On Wed, Oct 01, 2014 at 03:36:45PM +0200, Thomas Monjalon wrote:
>>> 2014-09-28 08:27, Neil Horman:
On Sun, Sep 28, 2014 at 05:28:44AM +, Wiles, Roger Keith wrote:
>>>
> *Handled gracefull shutdown of rx and tx threads upon SIGINT.
> *Gracefull shutdown of worker threads will be handled in
>future enhancements.
>
> Signed-off-by: Reshma Pattan
You have sent a patch which depends of the previous one, right?
It's OK but for next time, p
2014-09-28 08:27, Neil Horman:
> On Sun, Sep 28, 2014 at 05:28:44AM +, Wiles, Roger Keith wrote:
> > Check the FILE *f and rte_mempool *mp pointers for NULL and
> > return plus print out a message if RTE_LIBRTE_MEMPOOL_DEBUG is enabled.
> >
> > Signed-off-by: Keith Wiles
>
> I'm fine with th
From: Reshma Pattan
A new sample app that shows the usage of the distributor library. This
app works as follows:
* An RX thread runs which pulls packets from each ethernet port in turn
and passes those packets to worker using a distributor component.
* The workers take the packets in turn, and
v3:
Set rte_errno inside rte_alarm_cancel() to inform caller about canceling result.
v2:
Eliminate a race between rte_alarm_set() used in context of executing callback
function and other threads that use rte_alarm_cancel().
Signed-off-by: Pawel Wodkowski
---
lib/librte_eal/common/include/rt
Fix the descriptor initialization loop, so that it initializes
the i40e_tx_desc::cmd_type_offset_bsz for the correct index
into the tx_ring array.
Previously it would use the index once to initialize the txd
local variable, then again when setting cmd_type_offset_bsz.
Signed-off-by: Jim Harris
-
On Fri, Sep 26, 2014 at 10:45:49AM -0400, Neil Horman wrote:
> On Fri, Sep 26, 2014 at 12:41:33PM +0200, Thomas Monjalon wrote:
> > Hi Neil,
> >
> > 2014-09-24 14:19, Neil Horman:
> > > Ping Thomas. I know you're busy, but I would like this to not fall off
> > > anyones
> > > radar. You alluded
2014-09-28 05:30, Wiles, Roger Keith:
> When enabling RTE_LIBRTE_MEMPOOL_DEBUG and compiling with clang
> compiler an error occurs, because ifdefed code now includes GCC pragmas.
>
> GCC 4.4 is when push_options and pop_options pragma show up.
>
> Signed-off-by: Keith Wiles
[...]
> -#ifndef __IN
Hi Thomas,
Changing the macros to:
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wcast-qual"
#endif
.
.
#ifndef __INTEL_COMPILER
#pragma GCC diagnostic error "-Wcast-qual"
#endif
Works and is a good solution. I normally do not like negative ?ifndef?
> -Original Message-
> From: Neil Horman [mailto:nhorman at tuxdriver.com]
> Sent: Tuesday, September 30, 2014 2:40 PM
> To: Richardson, Bruce
> Cc: Pattan, Reshma; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3] distributor_app: new sample app
>
> On Tue, Sep 30, 2014 at 01:18:28PM
From: Reshma Pattan
*Handled gracefull shutdown of rx and tx threads upon SIGINT.
*Gracefull shutdown of worker threads will be handled in
future enhancements.
Signed-off-by: Reshma Pattan
---
examples/distributor_app/main.c | 12 ++--
1 files changed
From: Tetsuya Mukawa
'null PMD' is a driver of the virtual device particulary designed to measure
performance of DPDK PMDs. When an application call rx, null PMD just allocates
mbufs and returns those. Also tx, the PMD just frees mbufs.
The PMD has following options.
- size: specify packe size a
From: Tetsuya Mukawa
Hi,
Here are patches to add the new PMD like '/dev/null'.
This PMD is a driver for virtual device. When an application call rx,
it just allocates mbufs and returns those. Also tx, it just frees mbufs.
Main purpose of the PMD is measuring rough throughputs of a VDEV PMD.
To
2014-10-01 06:50, Neil Horman:
> On Wed, Oct 01, 2014 at 01:27:03PM +0900, mukawa at igel.co.jp wrote:
> > When CONFIG_RTE_BUILD_SHARED_LIB is enabled, linking errors occured
> > while compiling. It seems those errors are caused by wrong link order
> > of some libraries. The patch fixes it like fol
Hello,
On 09/04/2014 08:34 AM, Ouyang Changchun wrote:
> Fix one issue in virtio TX: it needs one more vring entry to hold
> the virtio header when transmitting packets, it is used later to
> determine whether to free more entries from used vring.
>
> Signed-off-by: Changchun Ouyang
> Reviewed-by
Self-NAK.
Reason: Incomplete patch.
Will send updated next version soon.
-Original Message-
From: Pattan, Reshma
Sent: Wednesday, October 1, 2014 2:34 PM
To: dev at dpdk.org
Cc: Pattan, Reshma
Subject: [PATCH v4] distributor_app: gracefull shutdown of tx/rx threads on
SIGINT
From: Resh
From: Tetsuya Mukawa
When CONFIG_RTE_BUILD_SHARED_LIB is enabled, linking errors occured
while compiling. It seems those errors are caused by wrong link order
of some libraries. The patch fixes it like following.
1. librte_eal
2. librte_malloc
3. librte_mempool
4. librte_ring
5. librte_pmd_bond
Acked-by: Sergio Gonzalez Monroy
On Tue, Sep 30, 2014 at 11:18:00AM -0400, Neil Horman wrote:
> Add initial pass header files to support symbol versioning.
>
> ---
> Change notes
> v2)
> * Fixed ifdef in rte_compat.h to test for RTE_BUILD_SHARED_LIB instead of the
> non-existant RTE_SYMBOL_VERSI
Acked-by: Sergio Gonzalez Monroy
On Mon, Sep 15, 2014 at 03:23:50PM -0400, Neil Horman wrote:
> To differentiate libraries that break ABI, we add a library version number
> suffix to the library, which must be incremented when a given libraries ABI is
> broken. This patch enforces that addition,
On Mon, Sep 15, 2014 at 03:23:49PM -0400, Neil Horman wrote:
> Add linker version script files to each DPDK library to put a stake in the
> ground from which we can start cleaning up API's
>
> Signed-off-by: Neil Horman
> CC: Thomas Monjalon
> CC: "Richardson, Bruce"
> ---
> lib/librte_acl/Mak
Hi,
How well does DPDK play with other applications using huge pages?
Looking at eal_init/eal_hugepage_info_init it seems that DPDK will try to
grab All available huge pages.
Is there an existing way to limit the number of huge pages taken ?
My goal is to be able to run several applications each w
> > >
> > > 1)I had sent v5 patch which handles graceful shutdown of rx and tx
> > > threads upon SIGINT
> > I see it and will take a look shortly, thanks.
> >
> > > 2)Worker thread graceful shutdown was not handled as of now as it needs
> > > some change in lcore_worker logic , which will be d
On Wed, Oct 01, 2014 at 04:43:10PM +0100, Bruce Richardson wrote:
> On Wed, Oct 01, 2014 at 11:02:27AM -0400, Neil Horman wrote:
> > On Wed, Oct 01, 2014 at 03:36:45PM +0200, Thomas Monjalon wrote:
> > > 2014-09-28 08:27, Neil Horman:
> > > > On Sun, Sep 28, 2014 at 05:28:44AM +, Wiles, Roger K
2014-09-29 18:09, Damjan Marion:
> On 17 Sep 2014, at 09:32, Olivier MATZ wrote:
> > On 09/12/2014 12:25 AM, damarion at cisco.com wrote:
> > > If VIRTIO_NET_F_CTRL_VQ is not negotiated hw->cvq will be NULL
> > >
> > > Signed-off-by: Damjan Marion
> > > ---
> > > lib/librte_pmd_virtio/virtio_rx
On Tue, Sep 30, 2014 at 11:18:00AM -0400, Neil Horman wrote:
> Add initial pass header files to support symbol versioning.
>
> ---
> Change notes
> v2)
> * Fixed ifdef in rte_compat.h to test for RTE_BUILD_SHARED_LIB instead of the
> non-existant RTE_SYMBOL_VERSIONING
>
> * Fixed VERSION_SYMBOL m
On Wed, Oct 01, 2014 at 03:20:22PM +0100, Pawel Wodkowski wrote:
> v3:
> Set rte_errno inside rte_alarm_cancel() to inform caller about canceling
> result.
>
> v2:
> Eliminate a race between rte_alarm_set() used in context of executing callback
> function and other threads that use rte_
On Wed, Oct 01, 2014 at 03:36:45PM +0200, Thomas Monjalon wrote:
> 2014-09-28 08:27, Neil Horman:
> > On Sun, Sep 28, 2014 at 05:28:44AM +, Wiles, Roger Keith wrote:
> > > Check the FILE *f and rte_mempool *mp pointers for NULL and
> > > return plus print out a message if RTE_LIBRTE_MEMPOOL_DEB
On Wed, Oct 01, 2014 at 02:47:00PM +, Pattan, Reshma wrote:
>
>
> > -Original Message-
> > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > Sent: Tuesday, September 30, 2014 2:40 PM
> > To: Richardson, Bruce
> > Cc: Pattan, Reshma; dev at dpdk.org
> > Subject: Re: [dpdk-dev] [P
For apps that were using default rte_eth_rxconf and rte_eth_txconf
structures, these have been removed and now they are obtained by
calling rte_eth_dev_info_get, just before setting up RX/TX queues.
Signed-off-by: Pablo de Lara
---
examples/dpdk_qat/main.c | 44 ++
Many sample apps use duplicated code to set rte_eth_txconf and rte_eth_rxconf
structures. This patch allows the user to get a default optimal RX/TX
configuration
through rte_eth_dev_info get, and still any parameters may be tweaked as wished,
before setting up queues.
Besides, if a NULL pointer i
To guarantee that RX/TX configuration structures are reseted
before modifying them, plus the other dev info fields,
dev info structure is zeroed beforehand.
Signed-off-by: Pablo de Lara
---
lib/librte_ether/rte_ethdev.c |7 +++
1 files changed, 3 insertions(+), 4 deletions(-)
diff --git
These patches modified the dev info structure to include optimal values
for the RX/TX configuration structures (rte_eth_rxconf and rte_eth_txconf),
so users can get these configurations and modify or use them directly,
to set up RX/TX queues. Besides, most of the apps that were modifying little
or
Hello Pablo,
I agree with Bruce comments.
I have a single comment: I would have preferred to have a separate patch
for the memset() on dev_info (could be the first patch of this patchset).
All the more so as it is not detailed in the commit log.
Thanks.
--
David Marchand
On Wed, Oct 1, 2014
On Wed, Oct 01, 2014 at 12:25:52PM +0100, Sergio Gonzalez Monroy wrote:
> On Mon, Sep 15, 2014 at 03:23:49PM -0400, Neil Horman wrote:
> > Add linker version script files to each DPDK library to put a stake in the
> > ground from which we can start cleaning up API's
> >
> > Signed-off-by: Neil Hor
(2014/09/30 22:05), Thomas Monjalon wrote:
> 2014-09-30 18:56, mukawa at igel.co.jp:
>> --- /dev/null
>> +++ b/lib/librte_pmd_null/Makefile
>> @@ -0,0 +1,58 @@
>> +# BSD LICENSE
>> +#
>> +# Copyright (C) 2014 Nippon Telegraph and Telephone Corporation.
>> +# All rights reserved.
>> +#
>> +#
(2014/09/30 20:23), Neil Horman wrote:
> On Tue, Sep 30, 2014 at 06:56:10PM +0900, mukawa at igel.co.jp wrote:
>> From: Tetsuya Mukawa
>>
>> Signed-off-by: Tetsuya Mukawa
>> ---
>> mk/rte.app.mk | 4
>> 1 file changed, 4 insertions(+)
>>
>> diff --git a/mk/rte.app.mk b/mk/rte.app.mk
>> inde
On Wed, Oct 01, 2014 at 12:21:05PM +0300, Alex Markuze wrote:
> Hi,
> How well does DPDK play with other applications using huge pages?
> Looking at eal_init/eal_hugepage_info_init it seems that DPDK will try to
> grab All available huge pages.
>
> Is there an existing way to limit the number of h
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Wednesday, October 01, 2014 10:49 AM
> To: dev at dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: [PATCH v3 0/3] Get default RX/TX configuration
>
> These patches modified the dev info structure to include optimal values
> for th
On Tue, Sep 30, 2014 at 01:06:32PM -0400, Neil Horman wrote:
> On Tue, Sep 30, 2014 at 04:26:02PM +0100, Bruce Richardson wrote:
> > This patch takes the existing TX flags defined for the mbuf and shifts
> > each uniquely defined one left so that additional RX flags can be
> > defined without havin
On Tue, Sep 30, 2014 at 11:52:00PM +, Hiroshi Shimamoto wrote:
> Hi,
>
> > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > recv/xmit
> >
> > On Tue, Sep 30, 2014 at 11:14:40AM +, Hiroshi Shimamoto wrote:
> > > From: Hiroshi Shimamoto
> > >
> > > To reduce instr
On Wed, Oct 01, 2014 at 09:00:57AM +0100, Pablo de Lara wrote:
> Many sample apps use duplicated code to set rte_eth_txconf and rte_eth_rxconf
> structures. This patch allows the user to get a default optimal RX/TX
> configuration
> through rte_eth_dev_info get, and still any parameters may be twe
On Wed, Oct 01, 2014 at 09:00:57AM +0100, Pablo de Lara wrote:
> Many sample apps use duplicated code to set rte_eth_txconf and rte_eth_rxconf
> structures. This patch allows the user to get a default optimal RX/TX
> configuration
> through rte_eth_dev_info get, and still any parameters may be twe
Hi Alex,
There option in EAL when you starts DPDK where by configure the amount of
memory consume by DPDK.
? -m MB
Memory to allocate. See also --socket-mem.
? --socket-mem
Set the memory to allocate on specific sockets (use comma separated
values).
Regards,
Choi, Sy Jong
Platf
> Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> recv/xmit
>
> On Tue, Sep 30, 2014 at 11:52:00PM +, Hiroshi Shimamoto wrote:
> > Hi,
> >
> > > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > > recv/xmit
> > >
> > > On Tue, Sep 30, 2014 at 1
For apps that were using default rte_eth_rxconf and rte_eth_txconf
structures, these have been removed and now they are obtained by
calling rte_eth_dev_info_get, just before setting up RX/TX queues.
Signed-off-by: Pablo de Lara
---
examples/dpdk_qat/main.c | 44 ++
Many sample apps use duplicated code to set rte_eth_txconf and rte_eth_rxconf
structures. This patch allows the user to get a default optimal RX/TX
configuration
through rte_eth_dev_info get, and still any parameters may be tweaked as wished,
before setting up queues.
Besides, if a NULL pointer i
These patches modified the dev info structure to include optimal values
for the RX/TX configuration structures (rte_eth_rxconf and rte_eth_txconf),
so users can get these configurations and modify or use them directly,
to set up RX/TX queues. Besides, most of the apps that were modifying little
or
2014-10-01 00:01, Hiroshi Shimamoto:
> > The patch is ok. For the commit message, is it better
> > "to reduce branch mispredication"?
>
> yes, that seems more suitable to explain the situation.
>
> Thomas, what do you think? Can you replace the message when you apply
> this patch?
Yes, I did it
On Wed, Oct 01, 2014 at 09:47:21AM +0100, Bruce Richardson wrote:
> On Tue, Sep 30, 2014 at 01:06:32PM -0400, Neil Horman wrote:
> > On Tue, Sep 30, 2014 at 04:26:02PM +0100, Bruce Richardson wrote:
> > > This patch takes the existing TX flags defined for the mbuf and shifts
> > > each uniquely def
On Wed, Oct 01, 2014 at 09:12:44AM +, Hiroshi Shimamoto wrote:
> > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > recv/xmit
> >
> > On Tue, Sep 30, 2014 at 11:52:00PM +, Hiroshi Shimamoto wrote:
> > > Hi,
> > >
> > > > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/
On Wed, Oct 01, 2014 at 09:44:45AM +0100, Bruce Richardson wrote:
> On Tue, Sep 30, 2014 at 11:52:00PM +, Hiroshi Shimamoto wrote:
> > Hi,
> >
> > > Subject: Re: [dpdk-dev] [memnic PATCH v2 6/7] pmd: add branch hint in
> > > recv/xmit
> > >
> > > On Tue, Sep 30, 2014 at 11:14:40AM +, Hir
On Wed, Oct 01, 2014 at 01:27:03PM +0900, mukawa at igel.co.jp wrote:
> From: Tetsuya Mukawa
>
> When CONFIG_RTE_BUILD_SHARED_LIB is enabled, linking errors occured
> while compiling. It seems those errors are caused by wrong link order
> of some libraries. The patch fixes it like following.
>
>
On Wed, Oct 01, 2014 at 11:15:31AM +0100, Sergio Gonzalez Monroy wrote:
> On Tue, Sep 30, 2014 at 11:18:00AM -0400, Neil Horman wrote:
> > Add initial pass header files to support symbol versioning.
> >
> > ---
> > Change notes
> > v2)
> > * Fixed ifdef in rte_compat.h to test for RTE_BUILD_SHARED
Hi Thomas,
> Subject: Re: [dpdk-dev] [memnic PATCH v2 0/7] MEMNIC PMD performance
> improvement
>
> > This patchset improves MEMNIC PMD performance.
> >
> > Hiroshi Shimamoto (7):
> > guest: memnic-tester: PMD benchmark in guest
> > pmd: remove needless assignment
> > pmd: use helper macro
Hi,
> Subject: RE: [memnic PATCH v2 6/7] pmd: add branch hint in recv/xmit
>
> The patch is ok. For the commit message, is it better
> "to reduce branch mispredication"?
yes, that seems more suitable to explain the situation.
Thomas, what do you think? Can you replace the message when you apply
69 matches
Mail list logo
