Running the tests in parallel has two drawbacks:
- the tests are racing on the hugepages allocations,
- the tests are sharing the cores to run their checks which results in
undeterministic execution time,
This results in random failures.
For better reproducibility in CI, start them all in a seri
Let's mark as skipped the tests when they are missing some requirements
like a number of used cores or specific hardware availability, like
compress, crypto or eventdev devices.
Signed-off-by: David Marchand
---
Changelog since v1:
- adapted rcu parts with changes from newly added patch 8
---
a
From: Michael Santana
The eal flags unit test assumes that a certain number of cores are
available (4 and 8 cores), however this may not always be the case.
Individual developers may run the unit test on their local desktop
which typically have 2 to 4 cores, in said case the test is bound
to fail
Based on Michael initial idea of separating the file-prefix subtest in
the eal flags test.
Let's split the biggest tests into their subparts.
It is then easier to have them fit in the 10s timeout we have configured
in Travis.
We also get a better idea of which part fails in the previously big test
The -n option is an optimisation configuration option that defaults to 0.
Such a default value makes the mempool library distributes objects as if
there was 4 memory channels, so -n 4 is the same as the default behavior.
This parameter was mandatory a long time ago, but has been optional for
a whi
Fixes: 0420378bbfc4 ("test/stack: check lock-free implementation")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
Acked-by: Aaron Conole
---
app/test/meson.build | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/app/test/meson.build b/app/test/meson.build
index 44cf561.
Setting a coremask was mandatory a long time ago but has been optional
for a while.
The checks on PCI whitelist/blacklist, vdev, memory rank, memory channel,
HPET, memory size and other miscs options have no requirement wrt cores.
Let's remove those coremasks so that we only care about it in the
d
We can have up to RTE_MAX_LCORE in a dpdk application.
Remove the limit on 128 cores and tests that are now always false.
Fixes: b87089b0bb19 ("test/rcu: add API and functional tests")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
Changelog since v1:
- new patch added to remove the local
Fixes: 3c518ca41ffa ("test/hash: remove hash scaling unit test")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
Acked-by: Aaron Conole
---
app/test/meson.build | 1 -
1 file changed, 1 deletion(-)
diff --git a/app/test/meson.build b/app/test/meson.build
index ad46515..44cf561 100644
--- a/a
Same treatment than crypto tests, move the eventdev drivers tests in the
driver list.
While at it:
- eventdev_octeontx_autotest has been renamed as
eventdev_selftest_octeontx,
- eventdev_sw_autotest has been renamed as
eventdev_selftest_sw,
Fixes: 50fb749a3972 ("event/octeontx: move test to d
From: Dharmik Thakkar
This patch rectifies slave_id to point to valid core indexes rather than
core ranks in read-write lock-free concurrency test.
It also replaces a 'for' loop with RTE_LCORE_FOREACH API.
Fixes: c7eb0972e74b ("test/hash: add lock-free r/w concurrency")
Cc: sta...@dpdk.org
Sig
Caught in one Travis run:
+ --- +
+ Test Suite : Latency Stats Unit Test Suite
+ --- +
+ TestCase [ 0] : test_latency_init succeeded
+ TestCase [ 1] : test_latency_update succeeded
[snip]
+
This subtest wants to start rwc_core_cnt[n] reader threads, while the
master core is waiting for them to report.
Fixes: c7eb0972e74b ("test/hash: add lock-free r/w concurrency")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
Acked-by: Aaron Conole
Acked-by: Yipeng Wang
---
app/test/test_ha
Fixes: 3d20ffe6ddb1 ("test: reorder test cases in meson")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
Acked-by: Aaron Conole
---
app/test/meson.build | 1 +
1 file changed, 1 insertion(+)
diff --git a/app/test/meson.build b/app/test/meson.build
index 4de856f..a51b50a 100644
--- a/app/tes
For consistency, put all specific crypto driver tests in the dedicated
list (in alphabetic order).
While at it:
- remove dead reference to cryptodev_sw_mrvl_autotest (renamed as
cryptodev_sw_mvsam_autotest),
- call the crypto scheduler test only when built,
Fixes: 9eabcb682493 ("test: update au
This is a joint effort to make the unit tests ready for CI.
The first patches are fixes that I had accumulated.
Then the second part of the series focuses on skipping tests when some
requirements are not fulfilled so that we can start them in a restrained
environment like Travis virtual machines th
This patch changes 'only_once' variable to 'display_once',
which should be atomic type due to fact, that all runner functions
can be executed in paraller way on different lcores.
Fixes: df52cb3b6e13 ("app/crypto-perf: move verify as single test type")
Cc: sta...@dpdk.org
Signed-off-by: Tomasz Joz
Currently, there's no return status check from lcore's jobs.
In case of fail - crypto-perf tool returns success anyway.
This patch adds such a detection and returns proper status at the end.
Fixes: ce8af1a4398d ("app/crypto-perf: wait for cores launched by app")
Cc: sta...@dpdk.org
Signed-off-by:
> clang raise 'pointer-sign' warnings in __atomic_compare_exchange when
> passing 'uint64_t *' to parameter of type 'int64_t *' converts between
> pointers to integer types with different sign.
>
> Fixes: 7e6e609939a8 ("stack: add C11 atomic implementation")
>
> Signed-off-by: Phil Yang
> Review
Was there any update to this patch , I am also seeing kernel crash in
kni_net_rx_normal dueing skb_put which is happening for chained mbufs.
--
Regards,
Souvik
From: dev On Behalf Of Ferruh Yigit
Sent: Wednesday, March 6, 2019 12:31 PM
To: Yangchao Zhou ; dev@dpdk.org
Subject: Re: [dpdk-dev] [
Hi All,
I am using DPDK 18.11 with linux kernel 4.19.28. I have kni
devices created and I can see a crash in the kernel with ipv6/v4 fragmented
packets. Does anyone seen this already or is there any fixes/patches available
for this .
Snippet of kernel panic
Message from syslogd@
On 6/14/2019 5:51 PM, Ferruh Yigit wrote:
> On 6/14/2019 6:31 AM, Mo, YufengX wrote:
>> Hi, Sunil Kumar Kori
>>
>> This series' patches have been merged on dpdk/master. They cause testpmd
>> core dumped on intel nics.
>
> Right, since they can provide values as "nb_seg_max = 0, nb_mtu_seg_max = 0
Testpmd tries to calculate mbuf size based on "max Rx packet size" and
"max MTU segment number".
When driver set a "nb_mtu_seg_max" to zero, it causes division by zero
segmentation fault in testpmd.
If the PMD set "nb_mtu_seg_max" to zero, testpmd shouldn't try to
calculate the mbuf size.
Fixes:
clang raise 'pointer-sign' warnings in __atomic_compare_exchange
when passing 'uint64_t *' to parameter of type 'int64_t *' converts
between pointers to integer types with different sign.
Fixes: 7e6e609939a8 ("stack: add C11 atomic implementation")
Signed-off-by: Phil Yang
Reviewed-by: Honnappa
On 6/14/2019 6:31 AM, Mo, YufengX wrote:
> Hi, Sunil Kumar Kori
>
> This series' patches have been merged on dpdk/master. They cause testpmd core
> dumped on intel nics.
Right, since they can provide values as "nb_seg_max = 0, nb_mtu_seg_max = 0",
I am sending a patch now.
>
> ./usertools/dpdk
Update v6: Update of one copyright date in documentation file.
Update v5: Update date and version from dpdk review. Rebased to latest.
Update v4: Fix warning for the DEBUG configuration.
Update v3: Squashing 3 previous patches into one as recommended.
This is adding a new PMD driver for BBDEV d
Supports for FEC 4G PMD Driver on FPGA card PAC N3000
Signed-off-by: Nicolas Chautru
---
config/common_base |6 +
doc/guides/bbdevs/fpga_lte_fec.rst | 318 +++
doc/guides/bbdevs/index.rst|1 +
drivers/baseband/Makef
Supports for FEC 4G PMD Driver on FPGA card PAC N3000
Signed-off-by: Nicolas Chautru
---
config/common_base |6 +
doc/guides/bbdevs/fpga_lte_fec.rst | 318 +++
doc/guides/bbdevs/index.rst|1 +
drivers/baseband/Makef
Update v6: Update of one copyright date in documentation file.
Update v5: Update date and version from dpdk review. Rebased to latest.
Update v4: Fix warning for the DEBUG configuration.
Update v3: Squashing 3 previous patches into one as recommended.
This is adding a new PMD driver for BBDEV d
On 6/12/2019 2:17 AM, Zhao1, Wei wrote:
>
>
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Tuesday, June 11, 2019 10:37 PM
>> To: Zhao1, Wei ; dev@dpdk.org
>> Cc: sta...@dpdk.org; Peng, Yuan ; Lu, Wenzhuo
>> ; Kevin Traynor
>> Subject: Re: [dpdk-stable] [PATCH] app/testpmd: fix of
On 6/12/2019 3:24 PM, Xuanziyang (William, Chip Application Design Logic and
Hardware Development Dept IT_Products & Solutions) wrote:
>
>> On 6/6/2019 12:06 PM, Ziyang Xuan wrote:
>>> Add various headers that define mgmt commands, cmdq commands, rx
>> data
>>> structures, tx data structures and b
On 6/4/2019 5:07 PM, Ferruh Yigit wrote:
> On 5/29/2019 10:02 PM, Lance Richardson wrote:
>> This patchset adds the following:
>> 1) Support for vector mode TX and RX.
>> 2) HWRM API update (split into multiple patches).
>> 3) Fixes for RSS reta update and query.
>>
>> It also updates the rel
On 6/14/2019 8:44 AM, David Marchand wrote:
> On Fri, Jun 14, 2019 at 9:39 AM Thomas Monjalon wrote:
>
>> 06/04/2019 05:30, Stephen Hemminger:
>>> The symbols in the EXPERIMENTAL were close to alphabetic
>>> order but running sort showed several mistakes.
>>>
>>> This has no impact on code, API,
Hi Ferruh,
Thanks for the review.
I've send a v3 and responded to your comments below.
Thanks,
Cian
> -Original Message-
> From: Yigit, Ferruh
> Sent: 12 June 2019 15:10
> To: Ferriter, Cian ; Richardson, Bruce
> ; Mcnamara, John
> ; Kovacevic, Marko
>
> Cc: dev@dpdk.org
> Subject: Re:
It can be useful to use pcap files for some rudimental performance
At a high level, this works by creaing a ring of sufficient size to
store the packets in the pcap file passed to the application. When the
rx function for this mode is called, packets are dequeued from the ring
for use by the appli
The argument lists on some of the device creation functions are quite
large. Using a struct to hold the user options parsed in
'pmd_pcap_probe' will allow for cleaner function calls and definitions.
Adding user options will also be easier.
Signed-off-by: Cian Ferriter
---
drivers/net/pcap/rte_et
From: Agalya Babu RadhaKrishnan
Added help command in error message for ip pipeline commands.
Signed-off-by: Agalya Babu RadhaKrishnan
---
examples/ip_pipeline/cli.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/examples/ip_pipeline/cli.c b/examples/ip_pipeli
Hi,
I have some question on igb_uio.
>From the below function call traces, vfio-pci module frees/allocates msi-x
vector table as part of
interrupt disable/enable. Where as igb-uio module, only masks/unmasks the
msi-x interrupt.
Does this mean, when using igb_uio, device can't undergo reset wh
Added unit test case for eal command line 'in-memory' option
which will cover below functions.
get_seg_memfd()
test_memfd_create()
pagesz_flags()
Added unit test case for eal command line 'single-file-segments' option
which will cover resize_hugefile().
Signed-off-by: Pallantla Poornima
---
app
> -Original Message-
> From: Shally Verma [mailto:shal...@marvell.com]
> Sent: Friday, June 14, 2019 1:23 PM
> To: Kusztal, ArkadiuszX ; dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ;
> shally.ve...@caviumnetworks.com
> Subject: RE: [EXT] [PATCH] cryptodev: extend api of asymmetr
Replace the mbuf pointer array in the event eth Rx adapter
callback with an event array. Using an event array allows
the application to change attributes of the events enqueued
by the SW adapter.
The callback can drop packets and populate a callback
argument with the number of dropped packets. Add
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, June 14, 2019 3:55 PM
> To: Shally Verma ; dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ;
> shally.ve...@caviumnetworks.com
> Subject: RE: [EXT] [PATCH] cryptodev: extend api of asymmetric crypto by
> sessionless
>
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, June 14, 2019 12:21 PM
> To: 'Shally Verma' ; dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ;
> shally.ve...@caviumnetworks.com
> Subject: RE: [EXT] [PATCH] cryptodev: extend api of asymmetric crypto by
> sessionless
Hi Shally,
Thanks for your feedback.
> -Original Message-
> From: Shally Verma [mailto:shal...@marvell.com]
> Sent: Wednesday, June 5, 2019 2:17 PM
> To: Kusztal, ArkadiuszX ; dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ;
> shally.ve...@caviumnetworks.com
> Subject: RE: [EXT] [PA
Hi， xiao
> -Original Message-
> From: Wang, Xiao W
> Sent: Thursday, June 13, 2019 4:24 PM
> To: Yang, Qiming ; dev@dpdk.org
> Cc: Zhao1, Wei
> Subject: RE: [dpdk-dev] [PATCH v2 1/3] net/ice: enable switch filter
>
> Hi,
>
> > -Original Message-
> > From: dev [mailto:dev-boun...
From: Ben Walker
Currently, if the bus selects IOVA as PA, the memory init can fail when
lacking access to physical addresses.
This can be quite hard for normal users to understand what is wrong
since this is the default behavior.
Catch this situation earlier in eal init by validating physical a
From: Ben Walker
When selecting the preferred IOVA mode of the pci bus, the current
heuristic ("are devices bound?", "are devices bound to UIO?", "are pmd
drivers supporting IOVA as VA?" etc..) should honor the device
white/blacklist so that an unwanted device does not impact the decision.
There
In SPDK, not all drivers are registered with DPDK at start up time.
Previously, that meant DPDK always chose to set itself up in IOVA_PA
mode. Instead, when the correct iova choice is unclear based on the
devices and drivers known to DPDK at start up time, use other heuristics
(such as whether /pro
If a forced iova-mode has been passed at init, kni is not supposed to
work.
Fixes: 075b182b54ce ("eal: force IOVA to a particular mode")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
lib/librte_kni/rte_kni.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/lib/librte_kni/rte_kni
Hi Mattias,
> A more extensive description of the purpose of the eventmode helper
> library would be helpful.
>
> Is this supposed to be a generic framework for real-world
> applications, or only something to simplify DPDK the implementation of
> DPDK example programs and similar?
This is i
On Mon, Jun 3, 2019 at 6:44 PM Walker, Benjamin
wrote:
> On Mon, 2019-06-03 at 12:48 +0200, David Marchand wrote:
> > Hello,
> >
> > On Thu, May 30, 2019 at 7:48 PM Ben Walker
> wrote:
> > > In SPDK, not all drivers are registered with DPDK at start up time.
> > > Previously, that meant DPDK alw
On Tue, Jun 4, 2019 at 2:05 AM Stephen Hemminger
wrote:
> From: Stephen Hemminger
>
> The mp_client crashes if run on Azure or any system where ethdev
> ports are owned. In that case, the tx_buffer and tx_stats for the
> real port were initialized correctly, but the wrong port was used.
>
> For
In ppc64le, expanding DMA areas always fail because we cannot remove
a DMA window. As a result, we cannot allocate more than one memseg in
ppc64le. This is because vfio_spapr_dma_mem_map() doesn't unmap all
the mapped DMA before removing the window. This patch fixes this
incorrect behavior.
I adde
On Fri, Jun 14, 2019 at 9:39 AM Thomas Monjalon wrote:
> 06/04/2019 05:30, Stephen Hemminger:
> > The symbols in the EXPERIMENTAL were close to alphabetic
> > order but running sort showed several mistakes.
> >
> > This has no impact on code, API, ABI or otherwise.
> > Purely for humans.
> >
> >
06/04/2019 05:30, Stephen Hemminger:
> The symbols in the EXPERIMENTAL were close to alphabetic
> order but running sort showed several mistakes.
>
> This has no impact on code, API, ABI or otherwise.
> Purely for humans.
>
> Signed-off-by: Stephen Hemminger
I don't think it's worth adding a la
14/06/2019 16:16, David Marchand:
> On Tue, Apr 2, 2019 at 8:51 PM Stephen Hemminger
> wrote:
>
> > Using access followed by open causes a static analysis warning
> > about Time of check versus Time of use. Also, access() and
> > open() have different UID permission checks.
> >
> > This is not a
Before submitting further revisions, please check the documentation at
http://doc.dpdk.org/guides/contributing/patches.html
You are supposed to version your patches and prune old superseded patches
in patchwork.
Thanks.
--
David Marchand
On Thu, Jun 13, 2019 at 4:23 AM Takeshi Yoshimura wrote
On Tue, Apr 2, 2019 at 8:51 PM Stephen Hemminger
wrote:
> Using access followed by open causes a static analysis warning
> about Time of check versus Time of use. Also, access() and
> open() have different UID permission checks.
>
> This is not a serious problem; but easy to fix by using errno in
58 matches
Mail list logo
