Change references to master/slave lcore to main/worker.
For l2fwd, l3fwd and link_status examples.
Acked-by: Anatoly Burakov
Signed-off-by: Stephen Hemminger
---
app/pdump/main.c | 2 +-
examples/ip_pipeline/thread.c| 14 +++---
examp
Replace master with main and slave with worker.
Fix the wording in comments.
Acked-by: Anatoly Burakov
Signed-off-by: Stephen Hemminger
---
.../multi_process/client_server_mp/mp_server/main.c| 10 +-
examples/multi_process/simple_mp/main.c| 4 ++--
examples/multi_pr
Use main instead of master in the QoS examples.
Replace the "mst" command line argument with "mnc"
Acked-by: Anatoly Burakov
Signed-off-by: Stephen Hemminger
---
examples/qos_meter/main.c| 4 ++--
examples/qos_sched/args.c| 26 +-
examples/qos_sched/cmdline.c |
Simple replacement.
Acked-by: Anatoly Burakov
Signed-off-by: Stephen Hemminger
---
examples/ipsec-secgw/event_helper.c | 6 +++---
examples/ipsec-secgw/ipsec-secgw.c | 4 ++--
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/examples/ipsec-secgw/event_helper.c
b/examples/ipsec-s
Replace use of the term master lcore with main lcore in
the example programs.
Signed-off-by: Stephen Hemminger
---
examples/bbdev_app/main.c | 14 +--
examples/bond/main.c| 32 -
examples/distributor/main.c | 10 --
Hi David,
W dniu 09.10.2020 o 14:53, David Marchand pisze:
> Hello Lukasz,
>
> On Thu, Oct 8, 2020 at 11:17 PM Lukasz Wojciechowski
> wrote:
>> I'm here if you have any questions or suggestions
> Unfortunately, I can see a timeout on the distributor autotest in Travis:
> https://travis-ci.com/git
On Fri, 9 Oct 2020 14:38:38 -0700
Stephen Hemminger wrote:
> As announced in 20.08 release notes, the terms for lcore role
> will change in 20.11 release.
>
> This is a project wide patchset to terminolgy used for DPDK lcore.
> The term "master" referring to lcore is replaced with "main" and
>
During review and verification of the patch created by Sarosh Arif:
"test_distributor: prevent memory leakages from the pool" I found out
that running distributor unit tests multiple times in a row causes fails.
So I investigated all the issues I found.
There are few synchronization issues that mi
rte_distributor_return_pkt function which is run on worker cores
must wait for distributor core to clear handshake on retptr64
before using those buffers. While the handshake is set distributor
core controls buffers and any operations on worker side might overwrite
buffers which are unread yet.
Sam
Synchronization of data exchange between distributor and worker cores
is based on 2 handshakes: retptr64 for returning mbufs from workers
to distributor and bufptr64 for passing mbufs to workers.
Without proper order of verifying those 2 handshakes a deadlock may
occur. This can happen when worker
The burst version of distributor implementation was missing proper
handling of worker shutdown. A worker processing packets received
from distributor can call rte_distributor_return_pkt() function
informing distributor that it want no more packets. Further calls to
rte_distributor_request_pkt() or
rte_distributor_request_pkt and rte_distributor_get_pkt dereferenced
oldpkt parameter when in RTE_DIST_ALG_SINGLE even if number
of returned buffers from worker to distributor was 0.
This patch passes NULL to the legacy API when number of returned
buffers is 0. This allows passing NULL as oldpkt p
Statistics of handled packets are cleared and read on main lcore,
while they are increased in workers handlers on different lcores.
Without synchronization occasionally showed invalid values.
This patch uses atomic acquire/release mechanisms to synchronize.
Fixes: c3eabff124e6 ("distributor: add
In the single legacy version of the distributor synchronization
requires continues exchange of buffers between distributor
and workers. Empty buffers are sent if only handshake
synchronization is required.
However calls to the rte_distributor_return_pkt()
with 0 buffers in single mode were ignored
The sanity test with worker shutdown delegates all bufs
to be processed by a single lcore worker, then it freezes
one of the lcore workers and continues to send more bufs.
The freezed core shuts down first by calling
rte_distributor_return_pkt().
The test intention is to verify if packets assigned
Sanity tests with mbuf alloc and shutdown tests assume that
mbufs passed to worker cores are freed in handlers.
Such packets should not be returned to the distributor's main
core. The only packets that should be returned are the packets
send after completion of the tests in quit_workers function.
Instead of making delays in test code and waiting
for worker hopefully to reach proper states,
synchronize worker shutdown test cases with spin lock
on atomic variable.
Fixes: c0de0eb82e40 ("distributor: switch over to new API")
Cc: david.h...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Lukasz W
During quit_workers function distributor's main core processes
some packets to wake up pending worker cores so they can quit.
As quit_workers acts also as a cleanup procedure for next test
case it should also collect these packages returned by workers'
handlers, so the cyclic buffer with returned p
After introducing burst API there were some artefacts in the
API documentation from legacy single API.
Also the rte_distributor_poll_pkt() function return values
mismatched the implementation.
Fixes: c0de0eb82e40 ("distributor: switch over to new API")
Cc: david.h...@intel.com
Cc: sta...@dpdk.org
All of the former tests analyzed only statistics
of packets processed by all workers.
The new test verifies also if packets are processed
on workers as expected.
Every packets processed by the worker is marked
and analyzed after it is returned to distributor.
This test allows finding issues in mat
Fix improper indexes while comparing tags.
In the find_match_scalar() function:
* j iterates over flow tags of following packets;
* w iterates over backlog or in flight tags positions.
Fixes: 775003ad2f96 ("distributor: add new burst-capable library")
Cc: david.h...@intel.com
Cc: sta...@dpdk.org
rte_distributor_flush() is using total_outstanding()
function to calculate if it should still wait
for processing packets. However in burst mode
only backlog packets were counted.
This patch fixes that issue by counting also in flight
packets. There are also sum fixes to properly keep
count of in
The patch clears distributors returns buffer
in clear_returns() by setting start and count to 0.
Fixes: 775003ad2f96 ("distributor: add new burst-capable library")
Cc: david.h...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Lukasz Wojciechowski
Acked-by: David Hunt
---
lib/librte_distributor/r
> > > > Hi Honnappa,
> > > >
> > > > From a quick walkthrough, I have some questions/comments, please
> > > > see below.
> > > Hi Olivier, appreciate your input.
> > >
> > > >
> > > > On Tue, Oct 06, 2020 at 08:29:05AM -0500, Honnappa Nagarahalli wrote:
> > > > > Add scatter gather APIs to avoid
W dniu 09.10.2020 o 23:41, Lukasz Wojciechowski pisze:
>
> Hi David,
>
> W dniu 09.10.2020 o 14:53, David Marchand pisze:
>> Hello Lukasz,
>>
>> On Thu, Oct 8, 2020 at 11:17 PM Lukasz Wojciechowski
>> wrote:
>>> I'm here if you have any questions or suggestions
>> Unfortunately, I can see a tim
On Fri, Oct 9, 2020 at 9:36 AM Lance Richardson
wrote:
>
> The fast mbuf free offload for non-vector mode requires
> additional checks in order to handle long tx buffer
> descriptors, so dedicated functions are needed for
> vector- and non-vector-modes.
>
> Fixes: 103169df2880 ("net/bnxt: support
>Subject: Re: [dpdk-dev] [PATCH] net/failsafe: check correct error code while
>handling sub-device add
>
>On 05/10/20 11:42 +0200, Gaëtan Rivet wrote:
>> Hi,
>>
>> On 02/10/20 17:01 -0700, Long Li wrote:
>> > From: Long Li
>> >
>> > When adding a sub-device, it's possible that the sub-device is
>>
> With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
> There are use cases where this module is required, for example while
> testing the virtual ports in OvS, the virtual ports are bound to igb_uio
> module inside a VM. So, this patch provides a Makefile which can be used to
> bu
Olivier, thank you so much for helping figure out this, it does work as the
code you changed, so we can fix the issue without this patch series. My
question is can it also work for normal mbuf or indirect mbuf? (I mean pkt is
direct mbuf or indirect mbuf)
At 2020-10-09 19:55:25, "Olivier Matz"
Hi, power
> -Original Message-
> From: Power, Ciara
> Sent: Friday, October 9, 2020 10:03 PM
> To: Guo, Jia ; dev@dpdk.org
> Cc: Xing, Beilei
> Subject: RE: [PATCH v3 04/18] net/i40e: add checks for max SIMD bitwidth
>
> Hi Jeff,
>
> >-Original Message-
> >From: Guo, Jia
> >Se
On Fri, Oct 9, 2020 at 6:47 AM Jiawei Wang wrote:
>
> When using full offload, all traffic will be handled by the HW, and
> forwarded to the requested VF or wire and the control application does
> not see this traffic anymore. So there's a need for an action that
> enables the control application
Ferruh Yigit wrote:
> Sent: Saturday, October 10, 2020 2:53 AM
> To: oulijun ; wenzhuo...@intel.com;
> beilei.x...@intel.com; adrien.mazarg...@6wind.com; Phil Yang
>
> Cc: dev@dpdk.org; linux...@huawei.com
> Subject: Re: [PATCH v4] RSS key use with testpmd
>
> On 10/9/2020 1:09 PM, oulijun wrot
From: Yi Yang
rte_gso_segment decreased refcnt of pkt by one, but
it is wrong if pkt is external mbuf, pkt won't be
freed because of incorrect refcnt, the result is
application can't allocate mbuf from mempool because
mbufs in mempool are run out of.
One correct way is application should call
rt
From: Kiran Kumar K
While creating flow with action type RSS, action type is not being
set to RSS, and action type is being set to unicast. Therefore it breaks
RSS functionality. This patch add changes to program the RSS action
properly.
Fixes: 4092e4845d ("net/octeontx2: add flow operations")
301 - 334 of 334 matches
Mail list logo
