> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Friday, February 28, 2014 5:26 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 09/11] device-args: replace use-device eal
> option by pci-whitelist and vdev
>
> This commit splits the
> Hi all,
>
> I have a quick question regarding the performance of DPDK l2fwd (Same
> problem with l3fwd). I am seeing that when we start multiple ports (e.g.,
> 12 ports), for 64 byte packets, the RX rate is only at around 11 Mpps per
> port, instead of 14.88 Mpps which is the line rate (with
If you disable mempool caches, you may be able to run more processes than you
have cores, but other issues with duplicate core id's might arise, and your
application performance will suffer as the memory pools will be very
significantly slower.
However, there is no requirement that the lcore_id
> Hi,
> I have some doubts on the DPDK multi-process support:
>
> 1) According to the Programmers Guide (pag. 109 - 20.3 Multi-process
> Limitations), one of the multi-process limitations is:
>
> "All Intel(r) DPDK processes running as a single application and using shared
> memory must have
Hi,
can you please give a few more details about your setup? What version of the
Intel DPDK are you using? I tried using the command you give below on my system
with 82599-based NICs and testpmd starts up without any issues.
Here's the (clipped for brevity) output that I get:
$ sudo ./testpmd
>
> What has been your experience of using DPDK based app's in NUMA mode
> with multiple sockets where some cores are present on one socket and
> other cores on some other socket.
>
> I am migrating my application from one intel machine with 8 cores, all in
> one socket to a 32 core machine
The Intel DPDK does not at present support interrupts for dropped packets. Only
support for link status change interrupts are supported at this time, but since
the basics are there, it is possible with a bit of work to add handling for
other interrupts if so needed.
Regards,
/Bruce
>
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 11/11] kvargs: add test case in app/test
>
> Add a file app/test/test_kvargs.c that checks the
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 10/11] kvargs: make the NULL key to match all
> entries
>
> In rte_kvargs_process() and
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 09/11] kvargs: add the key in handler pameters
>
> This argument can be useful when
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 08/11] kvargs: add const attribute in handler
> parameters
>
> The "value" argument is read-only and
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 07/11] kvargs: be strict when matching a key
>
> When we match a key in is_valid_key() and
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 06/11] kvargs: simpler parsing and allow
> duplicated keys
>
> Remove the rte_kvargs_add_pair()
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 05/11] kvargs: rework API to fix memory leak
>
> Before the patch, a call to rte_kvargs_tokenize()
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 06/11] kvargs: simpler parsing and allow
> duplicated keys
>
> Remove the rte_kvargs_add_pair() function
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 04/11] kvargs: remove useless size field
>
> This value was not very useful as the size of the table is
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 03/11] kvargs: remove driver name in
> arguments
>
> Now that rte_kvargs is a generic library, there is
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 02/11] kvargs: use the new library in pmd_pcap
>
> The rte_kvargs library is a reworked copy of
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Tuesday, January 28, 2014 4:07 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 01/11] kvargs: add a new library to parse
> key/value arguments
>
> Copy the code from
>
> It's probably due to a frequency scaling.
> The timer based is initialized when DPDK initialize and the CPU can change
> its frequency, breaking next timers.
>
> The fix is to control the CPU frequency.
> Please try this, without your patch:
> for g in
> If someone wants to implement forwarding application that receives
> packets from ETH_A and send those to ETH_B.
> Also above application is split to 3 processes like following.
> [ETH_A]-->Process_A --> [Ring_A] --> Process_B --> [Ring_B] --> Process_C --
> > [ETH_B] (All 3 processes are
The mbufs returned by the pcap pmd RX function were constantly
reused, instead of being allocated on demand. This has been fixed.
Signed-off-by: Bruce Richardson
---
lib/librte_pmd_pcap/rte_eth_pcap.c | 37 +--
1 files changed, 26 insertions(+), 11 deletions(-)
Hi Mats,
yes, you are right, there is an issue in the pcap driver that it is not
allocating mbufs correctly. We are working on a fix.
Regards,
/Bruce
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Mats Liljegren
> Sent: Tuesday, November 26, 2013 1:07 PM
>
> Hi,
>
> I have a question about how to know corresponding device from port
> number.
> For example, if I have 4 Ethernet devices and 2 Ring PMDs, I will get 6 ports
> during initialization.
> In the case, how can I know which port corresponds last Ring PMD?
[BR] Firstly, to identify the
nal Message-
> From: Prashant Upadhyaya [mailto:prashant.upadhyaya at aricent.com]
> Sent: Monday, November 25, 2013 4:08 AM
> To: Richardson, Bruce; dev at dpdk.org
> Subject: RE: Query regarding multiple processes in DPDK
>
> Hi Bruce,
>
> One more question --
>
Hi Prashant
> ===
> The EAL also supports an auto-detection mode (set by EAL --proc-type=auto
> flag), whereby an Intel(r) DPDK process is started as a secondary instance if
> a primary instance is already running.
> ===
>
> So does this mean that if I have a DPDK exe foo.out, then when I run
The Intel DPDK should work fine on RHEL 6.4. There should be no need to update
your glibc, since this is subversion 12 (> 7), rather than 1.2.
Regards,
/Bruce
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Michael Quicquaro
> Sent: Thursday, November 21,
201 - 227 of 227 matches
Mail list logo