Instead of polling for tail to be updated, use wfe instruction.
Signed-off-by: Gavin Hu
Reviewed-by: Ruifeng Wang
Reviewed-by: Steve Capper
Reviewed-by: Ola Liljedahl
Reviewed-by: Honnappa Nagarahalli
---
lib/librte_ring/rte_ring_c11_mem.h | 4 ++--
lib/librte_ring/rte_ring_generic.h | 3 +--
In acquiring a spinlock, cores repeatedly poll the lock variable.
This is replaced by rte_wait_until_equal API.
Running the micro benchmarking and the testpmd and l3fwd traffic tests
on ThunderX2, Ampere eMAG80 and Arm N1SDP, everything went well and no
notable performance gain nor degradation was
The rte_wait_until_equal_xxx APIs abstract the functionality of 'polling
for a memory location to become equal to a given value'[1].
Use the API for the rte spinlock and ring implementations.
[1] http://patches.dpdk.org/cover/62703/
Gavin Hu (2):
spinlock: use wfe to reduce contention on aarch
Volatile has no ordering semantics. The rte_timer structure defines
timer status as a volatile variable and uses the rte_r/wmb barrier
to guarantee inter-thread visibility.
This patch optimized the volatile operation with c11 atomic operations
and one-way barrier to save the performance penalty. A
> -Original Message-
> From: Carrillo, Erik G
> Sent: Friday, April 24, 2020 9:27 AM
> To: Honnappa Nagarahalli ; Phil Yang
> ; rsanf...@akamai.com; dev@dpdk.org
> Cc: tho...@monjalon.net; david.march...@redhat.com; Ananyev,
> Konstantin ; jer...@marvell.com;
> hemant.agra...@nxp.com; Gavi
arm64 Travis CI uses container environment.
Because performance of the environment has fluctuation, false
positive failures and time outs happened from time to time.
This patch series relax test criteria to stablize test result.
Ruifeng Wang (4):
test/cycles: restore original delay function
t
test_delay_us_sleep registers sleep based delay for testing.
The change of default delay function is not expected.
Restore defalut delay function to fix the issue.
Fixes: a51639cc720a ("eal: add nanosleep based delay function")
Cc: sta...@dpdk.org
Signed-off-by: Ruifeng Wang
Reviewed-by: Gavin
rte_delay_us_xxx could have more deviation than expected when system
load is high. Test case failures were observed on Travis CI which run
unit test in container for aarch64.
Use looser criteria for cycle tests on aarch64.
Signed-off-by: Ruifeng Wang
Reviewed-by: Gavin Hu
---
app/test/test_cyc
aarch64 jobs are running in containers. Tests may take longer time
when system load is high.
Use bigger time out value for aarch64 test jobs to stabilize test
result.
Signed-off-by: Ruifeng Wang
Reviewed-by: Gavin Hu
---
.travis.yml | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
di
The unit test time out setting was the same for jobs on different
platforms. Due to difference of running environments, platforms
could have different time out expecations.
Provide TIMEOUT_FACTOR as a knob to change the time out setting.
Signed-off-by: Ruifeng Wang
Reviewed-by: Gavin Hu
---
.c
24/04/2020 05:21, Joyce Kong:
> --- a/doc/api/doxy-api-index.md
> +++ b/doc/api/doxy-api-index.md
> - **containers**:
> + [bitmap] (@ref rte_bitmap.h),
>[mbuf] (@ref rte_mbuf.h),
>[mbuf pool ops] (@ref rte_mbuf_pool_ops.h),
>[ring] (@ref rt
This patch fixes the issue that the queue region does not
take effect due to incorrectly setting the flow type.
Fixes: ecad87d22383 ("net/i40e: move RSS to flow API")
Cc: sta...@dpdk.org
Signed-off-by: Shougang Wang
---
drivers/net/i40e/i40e_flow.c | 34 +++---
1 fil
On Wed, Apr 22, 2020 at 11:45:52PM +0200, Lukasz Wojciechowski wrote:
> This set of patches introduces a global rte_debug flag for dpdk.
> This will allow easy switch to debug build configuration using a single
> flag. In the debug mode a RTE_DEBUG macro is defined to 1
> and for every enabled to b
On 23-Apr-20 9:04 PM, David Marchand wrote:
On Thu, Apr 23, 2020 at 6:34 PM Burakov, Anatoly
wrote:
diff --git a/lib/librte_eal/common/eal_common_memory.c
b/lib/librte_eal/common/eal_common_memory.c
index cc7d54e0c..2d9564b28 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/lib
On Fri, Apr 24, 2020 at 10:12:10AM +0100, Burakov, Anatoly wrote:
> On 23-Apr-20 9:04 PM, David Marchand wrote:
> > On Thu, Apr 23, 2020 at 6:34 PM Burakov, Anatoly
> > wrote:
> > > > diff --git a/lib/librte_eal/common/eal_common_memory.c
> > > > b/lib/librte_eal/common/eal_common_memory.c
> > >
23/04/2020 08:41, Ray Kinsella:
> Change references to abi 20.0.1 to use abi v21, add myself as the map
> file maintainer to more closely monitor future abi changes. Add
> suppressions that were missed on changes to librte_lpm.
>
> Signed-off-by: Ray Kinsella
Please could you add a reference to
On Tue, Apr 21, 2020 at 01:25:31AM +0200, Thomas Monjalon wrote:
> The EAL options and app-specific options are separated
> with double dashes.
>
> The help of testpmd, test-acl and pdump were missing
> the dashes after EAL options.
> Note: testpmd was completely missing the EAL options.
>
> Fixe
20/04/2020 09:53, Maxime Coquelin:
> The goal is to make the table more readable.
>
> Mark as partially supported features that are supported in
> the genric Virtio driver but not in the vectorized ones.
>
> Suggested-by: Thomas Monjalon
> Signed-off-by: Maxime Coquelin
Looks good, thanks.
No
This patch fixes the issue that the queue region does not
take effect due to incorrectly setting the flow type.
Fixes: ecad87d22383 ("net/i40e: move RSS to flow API")
Cc: sta...@dpdk.org
Signed-off-by: Shougang Wang
---
v2:
-Update the various name.
---
drivers/net/i40e/i40e_flow.c | 34 +++
> -Original Message-
> From: Dharmappa, Savinay
> Sent: Thursday, April 23, 2020 4:25 PM
> To: dev@dpdk.org; Ananyev, Konstantin ;
> akhil.go...@nxp.com
> Subject: [PATCH v5] test/ipsec: measure libipsec performance
>
> Add new test-case to measure performance of
> ipsec data-path fun
W dniu 24.04.2020 o 11:09, Bruce Richardson pisze:
> On Wed, Apr 22, 2020 at 11:45:52PM +0200, Lukasz Wojciechowski wrote:
>> This set of patches introduces a global rte_debug flag for dpdk.
>> This will allow easy switch to debug build configuration using a single
>> flag. In the debug mode a RT
> -Original Message-
> From: Nithin Dabilpuram
> Sent: Wednesday, April 22, 2020 6:21 PM
> To: Singh, Jasvinder ; Dumitrescu, Cristian
> ; Thomas Monjalon
> ; Yigit, Ferruh ; Andrew
> Rybchenko
> Cc: dev@dpdk.org; jer...@marvell.com; kka...@marvell.com; Nithin
> Dabilpuram
> Subject: [
Commit 8a4baf06c17a ("mem: mark pages as not accessed when reserving VA")
has mapped the initialized memory with PROT_NONE, and when it's unmapped,
eal_memalloc.c should remmap the anonymous memory with PROT_NONE too.
Signed-off-by: Li Feng
---
lib/librte_eal/linux/eal_memalloc.c | 2 +-
1 file
Currently, there is no flow aging check and age-out event callback
mechanism for mlx5 driver, this patch implements it. It's included:
- Splitting the current counter container to aged or no-aged container
since reducing memory consumption. Aged container will allocate extra
memory to save the
Currently, the counter pool needs 512 ext-counter memory for no batch
counters, it's allocated separately by once, behind the 512 basic-counter
memory. This is not easy to get ext-counter pointer by corresponding
basic-counter pointer. This is also no easy for expanding some other
potential additio
Those patches implement flow aging for mlx5 driver. First patch is to modify
the current additional memory allocation for counter, so that it's easy to
get every counter additional memory location by using offsetting. Second patch
implements aging check and age-out event callback mechanism for mlx5
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't yet mapped physical
pages into it).
Use
The tracepoint symbols __rte_*_trace_* are defined via a macro,
adding prefix "__", so they cannot be found by map checker.
Those symbols defined by RTE_TRACE_POINT and RTE_TRACE_POINT_FP
are checked without the generated prefix.
The same logic is applied to per-lcore variables, previously skipped
Currently, there is no way to check the aging event or to get the current
aged flows in testpmd, this patch include those implements, it's included:
- Registering aging event based on verbose level, when set verbose > 0,
will register this event, otherwise, remove this event. In this event
only
On 24-Apr-20 10:33 AM, Feng Li wrote:
Bruce Richardson 于2020年4月24日周五 下午5:14写道：
On Fri, Apr 24, 2020 at 10:12:10AM +0100, Burakov, Anatoly wrote:
On 23-Apr-20 9:04 PM, David Marchand wrote:
On Thu, Apr 23, 2020 at 6:34 PM Burakov, Anatoly
wrote:
diff --git a/lib/librte_eal/common/eal_common
From: Chengwen Feng
Currently, when running start/clear stats&xstats/stop command many times
based on testpmd application, there are incorrect RX/TX-packets stats as
below:
-- Forward statistics for port 0 --
RX-packets: 18446744073709544808 RX-dropped: 0
> Adding per core packet handling stats to analyze traffic distribution
> when multiple cores are engaged.
>
> Since aggregating the packet stats across cores would affect
> performance, keeping the feature disabled using compile time flags.
>
> Signed-off-by: Anoob Joseph
> ---
>
> v2:
> * A
Max Rx Ring count could be < Max stat contexts. While accounting
for stat contexts, this should be also considered and
the max ring count adjusted accordingly.
Fixes: f03e66cb64ce ("net/bnxt: limit queue count for NS3/Stingray devices")
Cc: sta...@dpdk.org
Signed-off-by: Somnath Kotur
---
drive
>
> For SA outbound packets, rte_atomic64_add_return is used to generate
> SQN atomically. Use c11 atomics with RELAXED ordering for outbound SQN
> update instead of rte_atomic ops which enforce unnecessary barriers on
> aarch64.
>
> Signed-off-by: Phil Yang
> Reviewed-by: Ruifeng Wang
> Review
On 24-Apr-20 11:50 AM, Li Feng wrote:
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't y
On 24-Apr-20 11:42 AM, Li Feng wrote:
Commit 8a4baf06c17a ("mem: mark pages as not accessed when reserving VA")
has mapped the initialized memory with PROT_NONE, and when it's unmapped,
eal_memalloc.c should remmap the anonymous memory with PROT_NONE too.
Signed-off-by: Li Feng
---
lib/librte
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Previously, virtio split ring vectorized path was enabled by default.
> This is not suitable for everyone because that path dose not follow
> virtio spec. Add new devarg for virtio vectorized path selection. By
> default vectorized path is disabled.
>
>
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Add new devarg for virtio user device vectorized path selection. By
> default vectorized path is disabled.
>
> Signed-off-by: Marvin Liu
>
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
On Fri, Apr 24, 2020 at 12:23:44PM +0100, Burakov, Anatoly wrote:
> On 24-Apr-20 11:50 AM, Li Feng wrote:
> > Currently, even though memory is mapped with PROT_NONE, this does not
> > cause it to be excluded from core dumps. This is counter-productive,
> > because in a lot of cases, this memory wil
On 24-Apr-20 12:36 PM, Bruce Richardson wrote:
On Fri, Apr 24, 2020 at 12:23:44PM +0100, Burakov, Anatoly wrote:
On 24-Apr-20 11:50 AM, Li Feng wrote:
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
becau
> inet_pton4 and inet_pton6 was reimplemented. Replacing implementation of
> inet_pton4 and inet_pton6 with libc inet_pton function
> Bugzilla ID: 365
NACK
After that patch ispec-secgw wouldn't even start.
Next time before submitting a patch - spend some time to test it first.
> Cc: dev@dpdk
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Optimize packed ring Rx path with SIMD instructions. Solution of
> optimization is pretty like vhost, is that split path into batch and
> single functions. Batch function is further optimized by AVX512
> instructions. Also pad desc extra structure to 16 b
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Move xmit offload and packed ring xmit enqueue function to header file.
> These functions will be reused by packed ring vectorized Tx function.
>
> Signed-off-by: Marvin Liu
>
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
Thanks,
Feng Li
Burakov, Anatoly 于2020年4月24日周五 下午7:00写道：
>
> On 24-Apr-20 10:33 AM, Feng Li wrote:
> > Bruce Richardson 于2020年4月24日周五 下午5:14写道：
> >>
> >> On Fri, Apr 24, 2020 at 10:12:10AM +0100, Burakov, Anatoly wrote:
> >>> On 23-Apr-20 9:04 PM, David Marchand wrote:
> On Thu, Apr 23, 20
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Optimize packed ring Tx path alike Rx path. Split Tx path into batch and
s/alike/like/ ?
> single Tx functions. Batch function is further optimized by AVX512
> instructions.
>
> Signed-off-by: Marvin Liu
>
> diff --git a/drivers/net/virtio/virtio_eth
> >
> > Hi Lukas,
> >
> > Apologies for delay with response.
> >
> > > Do you have any thoughts how both cases could be covered:
> > > 1. Inline not applied to inbound IPsec pkts for short duration of time
> > > after rte_eth_dev_start() but before sa_init() is executed (which creates
> > > SAs).
Thanks,
Feng Li
Burakov, Anatoly 于2020年4月24日周五 下午7:23写道：
>
> On 24-Apr-20 11:50 AM, Li Feng wrote:
> > Currently, even though memory is mapped with PROT_NONE, this does not
> > cause it to be excluded from core dumps. This is counter-productive,
> > because in a lot of cases, this memory will go
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't yet mapped physical
pages into it).
Use
On Fri, Apr 24, 2020 at 12:53 PM Thomas Monjalon wrote:
>
> The tracepoint symbols __rte_*_trace_* are defined via a macro,
> adding prefix "__", so they cannot be found by map checker.
> Those symbols defined by RTE_TRACE_POINT and RTE_TRACE_POINT_FP
> are checked without the generated prefix.
>
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't yet mapped physical
pages into it).
Use
v4:
- Internal representation now uses generic data format instead of JSON.
- Help command added to provide help text for a command.
v3:
- Removed rte_option as it is no longer used.
- General cleanup.
v2:
- Added JSON API, and unit tests, to simplify creation of valid json
response
From: Bruce Richardson
The global include path, which is used by anything built before EAL,
points to the EAL header files so they utility macros etc. can be used
anywhere in DPDK. This path included the OS-specific EAL header files,
but not the architecture-specific ones. This patch moves the se
This commit moves some of the telemetry library code to a new file in
the metrics library. No modifications are made to the moved code,
except what is needed to allow it to compile and run. The additional
code in metrics is built only when the Jansson library is present.
Telemetry functions as nor
The telemetry code that was moved into the metrics library can be
shortened, while still maintaining the same functionality.
Signed-off-by: Ciara Power
Signed-off-by: Bruce Richardson
---
lib/librte_metrics/rte_metrics_telemetry.c | 476
lib/librte_metrics/rte_metrics_tele
From: Bruce Richardson
Rather than having the telemetry library depend on the metrics
lib we invert the dependency so that metrics instead depends
on telemetry lib, and registers the needed functions with it
at init time. This prepares the way for a cleaner telemetry
architecture to be applied in
From: Bruce Richardson
The functions added in this patch will make it easier for telemetry
to convert data to correct JSON responses to telemetry requests.
Tests are also added for these json utility functions.
Signed-off-by: Bruce Richardson
---
v4: Tests included in patch with utility funct
From: Bruce Richardson
This patch introduces a new telemetry connection socket and handling
functionality. Like the existing telemetry implementation (which is
unaffected by this change) it uses a unix socket, but unlike the
existing one it does not have a fixed list of commands - instead
librari
From: Bruce Richardson
The functions added in this patch will help applications build
up data in reply to a telemetry request.
Signed-off-by: Bruce Richardson
---
lib/librte_telemetry/Makefile | 1 +
lib/librte_telemetry/meson.build | 2 +-
lib/librte_telemetry
The default commands are now added to provide the list of commands
available, help text for a specified command, and also information
about DPDK and telemetry.
Signed-off-by: Ciara Power
Signed-off-by: Bruce Richardson
---
v4: Added help command to provide help text for a command.
---
lib/libr
From: Bruce Richardson
This patch adds a python script that can be used with the new telemetry
socket. It connects as a client to the socket, and allows the user send
a command and see the JSON response.
The example usage below shows the script connecting to the new telemetry
socket, and sending
From: Bruce Richardson
The ethdev library now registers commands with telemetry, and
implements the callback functions. These commands allow the list of
ethdev ports and the xstats and link status for a port to be queried.
An example using ethdev commands is shown below:
Connecting to /var/run/
The rawdev library now registers commands with telemetry, and
implements the corresponding callback functions. These allow a list of
rawdev devices and xstats for a rawdev port to be queried.
An example usage, with ioat rawdev driver instances, is shown below:
Connecting to /var/run/dpdk/rte/dpdk
The l3fwd-power example app now registers a stats command with
telemetry, and provides a callback function to handle formatting the
power stats.
An example usage is shown below:
Connecting to /var/run/dpdk/rte/dpdk_telemetry.v2
{"version": "DPDK 20.05.0-rc0", "pid": 63384, "max_output_len": 16384
The new telemetry will now open a socket using the old telemetry path,
to ensure backward compatibility. This is not yet initialised, as it
would clash with the existing telemetry, to be removed in a later patch.
This means that both old and new telemetry socket interfaces are
handled in a common w
This patch removes the existing telemetry files, which are now redundant
as the new version of telemetry has backward compatibility for their
functionality.
Signed-off-by: Ciara Power
---
lib/librte_metrics/rte_metrics_telemetry.c|9 -
lib/librte_telemetry/Makefile |4
This patch moves telemetry further down the build, and adds it as a
dependency for EAL. Telemetry V2 is now configured to build by default,
and the legacy support is built when the telemetry config flag is set.
Telemetry now has EAL flags, shown below:
"--telemetry" = Enables telemetry (this is de
As Telemetry no longer uses rte_option, and was the only user of this
infrastructure, it can now be removed.
Signed-off-by: Ciara Power
---
lib/librte_eal/common/eal_common_options.c | 1 -
lib/librte_eal/common/eal_private.h| 28 ---
lib/librte_eal/common/meson.build | 2
From: Bruce Richardson
EAL now registers commands to provide some basic info from EAL.
Example:
Connecting to /var/run/dpdk/rte/dpdk_telemetry.v2
{"version": "DPDK 20.05.0-rc0", "pid": 72662, "max_output_len": 16384}
--> /
{"/": ["/", "/eal/app_params", "/eal/params", "/ethdev/link_status", \
The existing documentation for Telemetry is updated, and further
documentation is added.
Signed-off-by: Ciara Power
---
v4:
- Removed JSON API from docs as it is now internal.
- Updated guide to show use of data functions.
---
doc/guides/howto/telemetry.rst| 108 ++--
On Fri, Apr 24, 2020 at 08:53:11PM +0800, Li Feng wrote:
> Currently, even though memory is mapped with PROT_NONE, this does not
> cause it to be excluded from core dumps. This is counter-productive,
> because in a lot of cases, this memory will go unused (e.g. when the
> memory subsystem prealloca
24/04/2020 14:43, David Marchand:
> On Fri, Apr 24, 2020 at 12:53 PM Thomas Monjalon wrote:
> >
> > The tracepoint symbols __rte_*_trace_* are defined via a macro,
> > adding prefix "__", so they cannot be found by map checker.
> > Those symbols defined by RTE_TRACE_POINT and RTE_TRACE_POINT_FP
>
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, April 24, 2020 7:52 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Van Haaren, Harry
> Subject: Re: [PATCH v9 5/9] net/virtio: add vectorized packed ring Rx path
>
>
>
> On 4/24/20 11:24 AM, Marvi
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't yet mapped physical
pages into it).
Use
>
> Instead of polling for tail to be updated, use wfe instruction.
>
> Signed-off-by: Gavin Hu
> Reviewed-by: Ruifeng Wang
> Reviewed-by: Steve Capper
> Reviewed-by: Ola Liljedahl
> Reviewed-by: Honnappa Nagarahalli
> ---
> lib/librte_ring/rte_ring_c11_mem.h | 4 ++--
> lib/librte_ring/r
Hi Ananyev, Konstantin,
Thank you for your email. I appreciate your feedback.
Sorry for the trouble. I patched the two more files with the same
modifications so unintentionally I typed it wrong. I'm going to fix it in
v2.
In the future, I will be carefully reviewing the code and testing the
appl
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Rewrite vectorized path selection logic. Default setting comes from
> vectorized devarg, then checks each criteria.
>
> Packed ring vectorized path need:
> AVX512F and required extensions are supported by compiler and host
> VERSION_1 and IN_ORDE
On 4/24/20 11:24 AM, Marvin Liu wrote:
> Document packed virtqueue vectorized path selection logic in virtio net
> PMD.
>
> Signed-off-by: Marvin Liu
>
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, April 24, 2020 8:30 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Van Haaren, Harry
> Subject: Re: [PATCH v9 7/9] net/virtio: add vectorized packed ring Tx path
>
>
>
> On 4/24/20 11:24 AM, Marvi
On 4/24/20 3:12 PM, Liu, Yong wrote:
>> IIUC, the only difference with the non-vectorized version is the GSO
>> support removed here.
>> gso_type being in the same cacheline as flags in virtio_net_hdr, I don't
>> think checking the performance gain is worth the added maintainance
>> effort due t
On 4/24/20 3:33 PM, Liu, Yong wrote:
>
>
>> -Original Message-
>> From: Maxime Coquelin
>> Sent: Friday, April 24, 2020 8:30 PM
>> To: Liu, Yong ; Ye, Xiaolong ;
>> Wang, Zhihong
>> Cc: dev@dpdk.org; Van Haaren, Harry
>> Subject: Re: [PATCH v9 7/9] net/virtio: add vectorized packed
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, April 24, 2020 9:34 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Van Haaren, Harry
> Subject: Re: [PATCH v9 5/9] net/virtio: add vectorized packed ring Rx path
>
>
>
> On 4/24/20 3:12 PM, Liu, Y
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, April 24, 2020 9:36 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Van Haaren, Harry
> Subject: Re: [PATCH v9 7/9] net/virtio: add vectorized packed ring Tx path
>
>
>
> On 4/24/20 3:33 PM, Liu, Y
On Thu, Apr 23, 2020 at 8:48 AM Ray Kinsella wrote:
>
> Change references to abi 20.0.1 to use abi v21, add myself as the map
> file maintainer to more closely monitor future abi changes. Add
> suppressions that were missed on changes to librte_lpm.
About the lpm change below, this might be becau
Hi Gavin,
There are other sync modes added to rte_ring library. Can you please
extend this to other rte_pause() calls in the library?
Thanks,
Honnappa
> Subject: [PATCH v1 2/2] ring: use wfe to wait for ring tail update on aarch64
>
> Instead of polling for tail to be updated, use wfe
ah ok, the particular system I made the change on was Ubuntu 18.04.2.
which is libabigail 1.2.0.
Given we still support v19.11 on Ubuntu 18.04.2.
I think it's worthwhile keeping the suppression until v20.11?
Ray K
On 24/04/2020 15:10, David Marchand wrote:
> On Thu, Apr 23, 2020 at 8:48 AM Ray K
On Thu, Apr 23, 2020 at 5:25 AM Haiyue Wang wrote:
>
> Introduce __rte_internal tag to mark internal ABI function which is used
> by the drivers or other libraries.
>
> Signed-off-by: Haiyue Wang
> ---
> buildtools/check-internal-syms.sh | 57 +
> devtools/check-sym
On Fri, Apr 24, 2020 at 4:50 PM Ray Kinsella wrote:
>
> ah ok, the particular system I made the change on was Ubuntu 18.04.2.
> which is libabigail 1.2.0.
>
> Given we still support v19.11 on Ubuntu 18.04.2.
> I think it's worthwhile keeping the suppression until v20.11?
1.2 is fairly old and doe
> In an eventdev world, multiple workers (with ordered queue) will be
> working on IPsec ESP processing. The ESP header's sequence number is
> unique and has to be sequentially incremented in an orderly manner.
> This rises a need for incrementing sequence number in crypto stage
> especially in e
On 24-Apr-20 2:19 PM, Li Feng wrote:
Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't ye
On Fri, 24 Apr 2020 13:41:43 +0100
Ciara Power wrote:
> This commit moves some of the telemetry library code to a new file in
> the metrics library. No modifications are made to the moved code,
> except what is needed to allow it to compile and run. The additional
> code in metrics is built only
On Fri, Apr 24, 2020 at 08:29:53AM -0700, Stephen Hemminger wrote:
> On Fri, 24 Apr 2020 13:41:43 +0100
> Ciara Power wrote:
>
> > This commit moves some of the telemetry library code to a new file in
> > the metrics library. No modifications are made to the moved code,
> > except what is needed
> -Original Message-
> From: Liu, Yong
> Sent: Friday, April 24, 2020 9:41 PM
> To: 'Maxime Coquelin' ; Ye, Xiaolong
> ; Wang, Zhihong
> Cc: dev@dpdk.org; Van Haaren, Harry
> Subject: RE: [PATCH v9 5/9] net/virtio: add vectorized packed ring Rx path
>
>
>
> > -Original Message--
On 4/24/2020 12:07 PM, Wei Hu (Xavier) wrote:
> From: Chengwen Feng
>
> Currently, when running start/clear stats&xstats/stop command many times
> based on testpmd application, there are incorrect RX/TX-packets stats as
> below:
> -- Forward statistics for port 0
23/04/2020 14:53, Andrew Rybchenko:
> On 4/22/20 10:37 AM, Fady Bader wrote:
> > The code didn't compile when using exported mempool functions under windows.
> >
> > compilation error logs:
> > rte_mempool_exports.def : error LNK2001:
> > unresolved external symbol rte_mempool_cache_flush
> > rte_
10/03/2020 17:26, Stephen Hemminger:
> Fix spelling errors in comments.
>
> Signed-off-by: Stephen Hemminger
Applied, thanks
On 4/24/2020 11:55 AM, Bill Zhou wrote:
> Currently, there is no way to check the aging event or to get the current
> aged flows in testpmd, this patch include those implements, it's included:
> - Registering aging event based on verbose level, when set verbose > 0,
> will register this event, ot
10/03/2020 17:35, Stephen Hemminger:
> Fix spelling errors in comments (found with codespell).
>
> Note that "inbetween" is not correct in English and should
> either be two words or better yet, the in can be dropped.
> https://www.grammarly.com/blog/in-between-or-inbetween/
>
> Signed-off-by: St
On 4/23/2020 10:05 AM, Raslan Darawsheh wrote:
> When having QINQ VLAN headers in the packet, parse_ethernet
> is cabable of parsing only the first vlan.
>
> add parsing for QINQ VLAN headers in the packet.
>
> Fixes: 51f694dd40f5 ("app/testpmd: rework checksum forward engine")
> Cc: sta...@dpdk.
08/04/2020 15:11, Bruce Richardson:
> On Wed, Apr 08, 2020 at 03:07:30PM +0200, Alex Kiselev wrote:
> > rte_lpm6: fix incorrect size of tbl8 group
> > Fixes: e480688dce6d ("lpm6: add incremental update on delete")
> >
> > Signed-off-by: Alex Kiselev
> > ---
> Acked-by: Bruce Richardson
Applied,
On Fri, Apr 24, 2020 at 12:43 PM Li Feng wrote:
>
> Commit 8a4baf06c17a ("mem: mark pages as not accessed when reserving VA")
> has mapped the initialized memory with PROT_NONE, and when it's unmapped,
> eal_memalloc.c should remmap the anonymous memory with PROT_NONE too.
>
> Signed-off-by: Li Fe
1 - 100 of 138 matches
Mail list logo
