[dpdk-dev] [PATCH] doc: add meter, sched, power and KNI

On Wed, Sep 18, 2013 at 12:17 PM, Thomas Monjalon wrote: > KNI was new in DPDK 1.3. > The libraries meter, sched and power were new in DPDK 1.4. > The library sched includes some dependencies: approx, bitmap and red. > > Signed-off-by: Thomas Monjalon > Acked-by: David Marchand -- David Mar

[dpdk-dev] [PATCH] log: remove app path from syslog id

This reverts commit "log: get full path as syslog id" (494a02537f1) and restore the original patch from Stephen Hemminger (04210699eee). Signed-off-by: Thomas Monjalon --- lib/librte_eal/linuxapp/eal/eal.c |6 +- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/lib/librte_eal

[dpdk-dev] [PATCH] pmd: use byte ordering functions from dpdk

CPU should always use little endian on Intel but it is more consistent to use DPDK macros. Signed-off-by: Thomas Monjalon --- pmd/vmx_user.h | 14 +++--- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/pmd/vmx_user.h b/pmd/vmx_user.h index 4a1a95c..7181a3b 100644 --- a/pm

[dpdk-dev] [PATCH] doc: add meter, sched, power and KNI

30/09/2013 10:41, David Marchand : > On Wed, Sep 18, 2013 at 12:17 PM, Thomas Monjalon wrote: > > > > KNI was new in DPDK 1.3. > > The libraries meter, sched and power were new in DPDK 1.4. > > The library sched includes some dependencies: approx, bitmap and red. > > > > Signed-off-by: Thomas Mon

[dpdk-dev] [PATCH] Add support for Tx->Rx loopback mode for 82599.

27/09/2013 10:30, Ivan Boule : > On 09/26/2013 03:34 PM, Qinglai Xiao wrote: > > 82599 has two loopback operation modes, Tx->Rx and Rx->Tx. > > For the time being only Tx->Rx is supported. > > > > The new field lpbk_mode added in struct rte_eth_conf defines loopback > > operation mode for certain

[dpdk-dev] [PATCH] pmd: use byte ordering functions from dpdk

On 09/30/2013 10:55 AM, Thomas Monjalon wrote: > CPU should always use little endian on Intel > but it is more consistent to use DPDK macros. > > Signed-off-by: Thomas Monjalon > --- > pmd/vmx_user.h | 14 +++--- > 1 file changed, 7 insertions(+), 7 deletions(-) Acked-by: Damien Millesc

[dpdk-dev] [vmxnet3-usermap PATCH] kmod: remove useless debug hack

27/09/2013 17:13, Damien Millescamps : > On 09/27/2013 05:07 PM, Thomas Monjalon wrote: > > The PCI address was stored in unused variables of the netdev. > > It has been introduced in commit > > 75ab826258c1099e2e56ec48fd17dfa559cd. But it is a useless hack. > > > > Signed-off-by: Thomas Monja

[dpdk-dev] [vmxnet3-usermap PATCH] pmd: use byte ordering functions from dpdk

30/09/2013 11:07, Damien Millescamps : > On 09/30/2013 10:55 AM, Thomas Monjalon wrote: > > CPU should always use little endian on Intel > > but it is more consistent to use DPDK macros. > > > > Signed-off-by: Thomas Monjalon > > --- > > > > pmd/vmx_user.h | 14 +++--- > > 1 file chang

[dpdk-dev] L3FWD LPM IP lookup performance question

On 26/09/2013 23:16, Chris Pappas wrote: > we are having some numbers regarding the performance of L3FWD and would > like to confirm that they make sense. > So, for L3FWD and 1500byte packets we get 120Gbps out of 12x10Gbps ports > (so we get full throughput) and for 64byte packets we get 80Gbps.

[dpdk-dev] [dpdk-announce] seminar - get started with dpdk.org

FYI, there will be a seminar on Tuesday November the 5th in the San Francisco bay area. Register at: http://www.6wind.com/seminars/dpdk/ It is for engineers who need a deep dive into the Intel(r) DPDK: the seminar will cover its design, the details of available protocol stack enhancemen

[dpdk-dev] [PATCH] log: remove app path from syslog id

On Mon, 30 Sep 2013 11:40:56 -0700 Stephen Hemminger wrote: > On Mon, 30 Sep 2013 10:57:16 +0200 > Thomas Monjalon wrote: > > > Hi Stephen, > > > > 30/09/2013 10:43, Thomas Monjalon : > > > This reverts commit "log: get full path as syslog id" (494a02537f1) > > > and restore the original patch