10/03/2021 02:48, oulijun:
> Can we add an API such as rte_eth_get_device(pord_id)
>
> for example:
> struct rte_eth_dev *
> rte_eth_get_device(uint16_t port_id)
> {
> return &rte_eth_devices[port_id];
> }
An application is not supposed to access the struct rte_eth_dev.
Which info do you
On Tuesday, March 9, 2021 10:25 PM, Ferruh Yigit wrote:
> On 3/5/2021 11:23 AM, Jiawen Wu wrote:
> > For more different devices, update device ID and subsystem id.
> >
> > Signed-off-by: Jiawen Wu
> > ---
> > drivers/net/txgbe/base/txgbe_devids.h | 44 ++---
> > drivers/net/txgb
> On 3/9/2021 10:19 AM, Ciara Loftus wrote:
> > This commit introduces support for preferred busy polling
> > to the AF_XDP PMD. This feature aims to improve single-core
> > performance for AF_XDP sockets under heavy load.
> >
> > A new vdev arg is introduced called 'busy_budget' whose default
> >
On Wed, Mar 10, 2021 at 12:13 PM Igor Russkikh wrote:
>
>
>
> > On Fri, Mar 5, 2021 at 6:44 PM Balazs Nemeth wrote:
> >>
> >> This patch set optimizes qede_{rx,tx}_entry and introduces
> >> rte_pktmbuf_free_bulk in qede_process_tx_compl. The overall performance
> >> improvement depends on the use
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Tuesday, March 9, 2021 8:55 PM
> To: Juraj Linkeš ; Jerin Jacob
>
> Cc: Bruce Richardson ; Ruifeng Wang
> ; vcchu...@amazon.com; Dharmik Thakkar
> ; hemant.agra...@nxp.com; Ajit Khaparde
> (ajit.khapa...@broadcom.com) ;
> ferruh.
From: Kalesh AP
In the init path, driver ignores few of the HWRM command failures.
There is no need to log the error message in those cases.
Fixes: 3fb93bc7c349 ("net/bnxt: initialize parent PF information")
Fixes: 4e3f887bec4b ("net/bnxt: support HWRM port PHY qcaps")
Cc: sta...@dpdk.org
Signe
From: Kalesh AP
Fix to return an error when the HWRM version that the driver
is compiled against is incompatible with the FW that is actually
running on the card. This is determined based on the req length
indicated by FW against the value supported in the HWRM.
Fixes: 804e746c7b73 ("net/bnxt: a
From: Kalesh AP
This series contain couple of bug fixes in bnxt PMD.
Kalesh AP (2):
net/bnxt: fix HWRM and FW incompatibility handling
net/bnxt: mute some failure logs
drivers/net/bnxt/bnxt_hwrm.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
--
2.10.1
>
> On 3/9/2021 10:19 AM, Ciara Loftus wrote:
> > Prior to this commit, the maximum batch sizes for zero-copy and copy-
> mode
> > rx and copy-mode tx were set to 32. Apart from zero-copy tx, the user
> > could never rx/tx any more than 32 packets at a time and without
> inspecting
> > the code th
Hi
> -Original Message-
> From: Thomas Monjalon
> Subject: [PATCH 08/11] app: fix exit messages
>
> Some applications were printing useless messages with rte_exit()
> after showing the help. Using exit() is enough in this case.
>
> Some applications were using a redundant printf or fpri
Hi
> -Original Message-
> From: Thomas Monjalon
> Subject: [PATCH 10/11] app/regex: fix usage text
>
> The usage syntax help includes the program name which was fake.
> It is replaced with the real name from argv.
>
> Signed-off-by: Thomas Monjalon
> ---
> app/test-regex/main.c | 4 ++
Hi Haifei,
PSB
> -Original Message-
> From: Haifei Luo
> Subject: [PATCH 1/4] ethdev: add rte API for single flow dump
>
> Previous implementations support dump all the flows.Add new ones
> to dump one flow.
> New API added: rte_flow_dump.
>
> Signed-off-by: Haifei Luo
> ---
> doc/gu
> On Fri, Mar 5, 2021 at 6:44 PM Balazs Nemeth wrote:
>>
>> This patch set optimizes qede_{rx,tx}_entry and introduces
>> rte_pktmbuf_free_bulk in qede_process_tx_compl. The overall performance
>> improvement depends on the use-case; in a physical-virtual-physical test
>> on a ThunderX2 99xx sy
based on the original commit and the usage of rte_bsf64 it appears the
function should always have returned uint32_t instead of int which is
consistent with the cast introduced in the return statement.
Fixes: 4e261f551986 ("eal: add 64-bit bsf and 32-bit safe bsf
functions")
Cc: anatoly.bura...@in
From: Hongbo Zheng
Adjust the format of hns3 RAS related structures to resolve
the static check warnings of reviewbot_c.This patch has no
impact on function.
The correspond warnings of reviewbot_c:
When struct and union members are initialized, each member
is initialized on a separate line.
Sig
From: Hongbo Zheng
Add support for query Tx descriptor status in hns3 driver. Check the
descriptor specified and provide the status information of the
corresponding descriptor.
Signed-off-by: Hongbo Zheng
Signed-off-by: Min Hu (Connor)
---
doc/guides/nics/features/hns3.ini | 1 +
doc/gu
From: Hongbo Zheng
Add support for query Rx descriptor status in hns3 driver. Check the
descriptor specified and provide the status information of the
corresponding descriptor.
Signed-off-by: Hongbo Zheng
Signed-off-by: Min Hu (Connor)
---
doc/guides/nics/features/hns3.ini | 1 +
doc/gu
This patch added function level imissed stats for PF and VF. In kunpeng920,
imissed is supported, only including RPU drop stats in PF. In kunpeng930,
imissed is supported,including RPU drop stats and SSU drop stats in PF.
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_cmd.h | 14
This patch added oerrors stats for PF in kunpeng930.
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_ethdev.h | 1 +
drivers/net/hns3/hns3_stats.c | 61 ++
2 files changed, 62 insertions(+)
diff --git a/drivers/net/hns3/hns3_ethdev.h b/drivers/
From: Hongbo Zheng
The current RAS code stores the reported RAS statistics in xstats.
This part of statistics is of little use in practice, and because
of the change of RAS scheme on Kunpeng930, the driver can not
obtain the RAS information any more, so this patch delete these
redundant RAS stati
This series add five features according to the 21.05 roadmap, and
also two cleanups added.
Chengchang Tang (1):
net/hns3: support for outer UDP cksum
Chengwen Feng (2):
net/hns3: support runtime config to select IO burst func
net/hns3: support Tx push quick doorbell to improve perf
Hongbo
From: Chengchang Tang
Kunpeng930 support outer UDP cksum, this patch add support for it.
Signed-off-by: Chengchang Tang
Signed-off-by: Min Hu (Connor)
---
doc/guides/rel_notes/release_21_05.rst | 1 +
drivers/net/hns3/hns3_cmd.c| 3 ++
drivers/net/hns3/hns3_ethdev.c | 3
From: Chengwen Feng
Currently, the driver support multiple IO burst function and auto
selection of the most appropriate function based on offload
configuration.
Most applications such as l2fwd/l3fwd don't provide the means to
change offload configuration, so it will use the auto selection's io
b
From: Chengwen Feng
Kunpeng 930 support Tx push mode which could improve performance, It
works like below:
1. Add pcie bar45 which support driver direct write the Tx descriptor
or tail reg to it.
2. Support three operations: a) direct write one Tx descriptor, b)
direct write two Tx descriptors, c
From: Hongbo Zheng
Adjust the format of hns3 RAS related structures to resolve
the static check warnings of reviewbot_c.This patch has no
impact on function.
The correspond warnings of reviewbot_c:
When struct and union members are initialized, each member
is initialized on a separate line.
Sig
From: Hongbo Zheng
The current RAS code stores the reported RAS statistics in xstats.
This part of statistics is of little use in practice, and because
of the change of RAS scheme on Kunpeng930, the driver can not
obtain the RAS information any more, so this patch delete these
redundant RAS stati
This patch added function level imissed stats for PF and VF. In kunpeng920,
imissed is supported, only including RPU drop stats in PF. In kunpeng930,
imissed is supported,including RPU drop stats and SSU drop stats in PF.
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_cmd.h | 14
From: Hongbo Zheng
Add support for query Rx descriptor status in hns3 driver. Check the
descriptor specified and provide the status information of the
corresponding descriptor.
Signed-off-by: Hongbo Zheng
Signed-off-by: Min Hu (Connor)
---
doc/guides/nics/features/hns3.ini | 1 +
doc/gu
From: Hongbo Zheng
Add support for query Tx descriptor status in hns3 driver. Check the
descriptor specified and provide the status information of the
corresponding descriptor.
Signed-off-by: Hongbo Zheng
Signed-off-by: Min Hu (Connor)
---
doc/guides/nics/features/hns3.ini | 1 +
doc/gu
This patch added oerrors stats for PF in kunpeng930.
Signed-off-by: Min Hu (Connor)
---
drivers/net/hns3/hns3_ethdev.h | 1 +
drivers/net/hns3/hns3_stats.c | 61 ++
2 files changed, 62 insertions(+)
diff --git a/drivers/net/hns3/hns3_ethdev.h b/drivers/
From: Chengchang Tang
Kunpeng930 support outer UDP cksum, this patch add support for it.
Signed-off-by: Chengchang Tang
Signed-off-by: Min Hu (Connor)
---
doc/guides/rel_notes/release_21_05.rst | 1 +
drivers/net/hns3/hns3_cmd.c| 3 ++
drivers/net/hns3/hns3_ethdev.c | 3
From: Chengwen Feng
Currently, the driver support multiple IO burst function and auto
selection of the most appropriate function based on offload
configuration.
Most applications such as l2fwd/l3fwd don't provide the means to
change offload configuration, so it will use the auto selection's io
b
From: Chengwen Feng
Kunpeng 930 support Tx push mode which could improve performance, It
works like below:
1. Add pcie bar45 which support driver direct write the Tx descriptor
or tail reg to it.
2. Support three operations: a) direct write one Tx descriptor, b)
direct write two Tx descriptors, c
This series add five features according to the 21.05 roadmap, and
also two cleanups added.
Chengchang Tang (1):
net/hns3: support for outer UDP cksum
Chengwen Feng (2):
net/hns3: support runtime config to select IO burst func
net/hns3: support Tx push quick doorbell to improve perf
Hongbo
> -Original Message-
> From: Christian Ehrhardt
> Sent: Monday, March 8, 2021 11:28 PM
> > On Thu, Mar 4, 2021 at 11:43 AM Yu, PingX wrote:
> >
> > Update the test result for Intel part. Test are almost finished except
> > cryptodev
> and 5 issues are found.
> > 1. Failed build DPDK with
In i40e NEON vector rx path, the packet descs processing is incorrect.
This caused wrong packet type been filled in mbuf.
To fix this, when shifting the pktlen field to be 16-bit aligned, it
only needs to process the high 16bit of the packet descs instead of
the high 32bit.
Test Results:
Architec
The measure_perf function should be executed after worker threads exit
to collect correct perf data. Otherwise, while workers are running, the
main thread may get incomplete data from workers.
In the meanwhile, remove unnecessary barrier in the test.
For signal variables "ldata.done" and "ldata.st
For smp barriers in app/test, remove the unnecessary barriers
and fix some bugs.
v2:
1. remove ring stress test patch for that Honnappa will
do some changes for rte_remote_launch APIs
v3:
1. change the patch tag (Jerin)
Feifei Wang (1):
test/trace: collect perf data after worker threads exit
The measure_perf function should be executed after worker threads exit
to collect correct perf data. Otherwise, while workers are running, the
main thread may get incomplete data from workers.
In the meanwhile, remove unnecessary barrier in the test.
For signal variables "ldata.done" and "ldata.st
For smp barriers in app/test, remove the unnecessary barriers
and fix some bugs.
v2:
1. remove ring stress test patch for that Honnappa will
do some changes for rte_remote_launch APIs
v3:
1. change the patch tag (Jerin)
Feifei Wang (1):
test/trace: collect perf data after worker threads exit
On Tue, Mar 9, 2021 at 4:52 AM Ferruh Yigit wrote:
>
> On 3/8/2021 10:34 PM, Ajit Khaparde wrote:
> > Fix formatting in testpmd user guide for hairpin operation.
> >
> > Fixes: 01817b10d27c ("app/testpmd: change hairpin queues setup")
> > Cc:sta...@dpdk.org
> >
> > Signed-off-by: Ajit Khaparde
>
在 2021/3/9 17:53, Ferruh Yigit 写道:
On 3/9/2021 8:49 AM, oulijun wrote:
在 2021/3/9 1:33, Ferruh Yigit 写道:
On 3/5/2021 9:57 AM, Lijun Ou wrote:
From: Chengwen Feng
This patch support tx_done_cleanup command:
tx_done_cleanup port (port_id) (queue_id) (free_cnt)
Users must make sure there
This series add meson build for Hisilicon kunpeng CPU.
Lijun Ou (4):
config/arm: add Hisilicon kunpeng920 implementer
config/arm: add Hisilicon kunpeng930 implementer
config/arm: add kunpeng920 meson cross compile target
config/arm: add kunpeng930 meson cross compile target
config/arm/ar
Here add arm64 cross compile support for Hisilicon kunpeng920.
Signed-off-by: Chengchang Tang
Signed-off-by: Lijun Ou
---
config/arm/arm64_kunpeng920_linux_gcc | 19 +++
doc/guides/linux_gsg/cross_build_dpdk_for_arm64.rst | 4
2 files changed, 23 insertions(+
Here addes Kunpeng920 config back which was deleted.
Fixes: 91c730fd4e09 ("config/arm: remove unused or superfluous variables")
Signed-off-by: Chengchang Tang
Signed-off-by: Lijun Ou
---
V1->V2:
- rewrite patch title.
- split the patch into two.
---
config/arm/meson.build | 20
Here add arm64 cross compile support for Hisilicon kunpeng930.
Signed-off-by: Chengchang Tang
Signed-off-by: Lijun Ou
---
config/arm/arm64_kunpeng930_linux_gcc | 19 +++
doc/guides/linux_gsg/cross_build_dpdk_for_arm64.rst | 1 +
2 files changed, 20 insertions(+)
Here add Hisilicon kunpeng930 config back which was deleted.
Fixes: 91c730fd4e09 ("config/arm: remove unused or superfluous variables")
Signed-off-by: Chengchang Tang
Signed-off-by: Lijun Ou
---
-rewrite the patch title.
-split the patch into two.
---
config/arm/meson.build | 7 +++
1 file
On Wed, 10 Mar 2021 00:31:04 +0100
Thomas Monjalon wrote:
> The main intent of this series is to provide a nice help
> for the --log-level option.
> More patches are added to improve options help in general.
>
> Thomas Monjalon (11):
> eal: explain argv behaviour during init
> eal: improve o
On Tue, 9 Mar 2021 10:15:13 +0200
Haifei Luo wrote:
> +__rte_experimental
> +int
> +rte_flow_dump(uint16_t port_id, struct rte_flow *flow,
> + FILE *file, struct rte_flow_error *error);
> +
The flow argument should be const since dumping does not change
its state.
UMR WQE can convert multiple mkey's memory sapce to contiguous space.
Take advantage of the UMR WQE, scattered mbuf in one operation can be
converted to an indirect mkey. The RegEx which only accepts one mkey
can now process the whole scattered mbuf.
The maximum scattered mbuf can be supported in
This commits adds the scattered mbuf input support.
Signed-off-by: Suanming Mou
---
app/test-regex/main.c | 134 ++
1 file changed, 109 insertions(+), 25 deletions(-)
diff --git a/app/test-regex/main.c b/app/test-regex/main.c
index aea4fa6b88..82cffaacfa
This commit adds the UMR capability bits.
Signed-off-by: Suanming Mou
---
drivers/common/mlx5/linux/meson.build | 2 ++
drivers/common/mlx5/mlx5_devx_cmds.c | 5 +
drivers/common/mlx5/mlx5_devx_cmds.h | 3 +++
3 files changed, 10 insertions(+)
diff --git a/drivers/common/mlx5/linux/meson.
The scattered mbuf was not supported in mlx5 RegEx driver. This patch
set adds the support of scattered mbuf by UMR WQE.
UMR WQE can convert multiple mkey's memory sapce to contiguous space.
Take advantage of the UMR WQE, scattered mbuf in one operation can be
converted to an indirect mkey. The Re
Add API mlx5_flow_dump_rule to support the feature.
Modify mlx5_socket since one extra arg flow_ptr is added.
Signed-off-by: Haifei Luo
---
drivers/net/mlx5/linux/mlx5_socket.c | 27 ++---
drivers/net/mlx5/mlx5.h | 3 +++
drivers/net/mlx5/mlx5_flow.c | 3
add mlx5 APIs for single flow dump feature
Signed-off-by: Haifei Luo
---
drivers/common/mlx5/linux/meson.build | 4
drivers/common/mlx5/linux/mlx5_glue.c | 13 +
drivers/common/mlx5/linux/mlx5_glue.h | 1 +
drivers/common/mlx5/mlx5_devx_cmds.c | 10 ++
drivers/common/
Add support for single flow dump.
The CLIs to dump one rule: flow dump PORT rule ID
to dump all: flow dump PORT all
Examples:
testpmd> flow dump 0 all
testpmd> flow dump 0 rule 0
Signed-off-by: Haifei Luo
---
app/test-pmd/cmdline_flow.c | 55 +
app/tes
Previous implementations support dump all the flows.Add new ones
to dump one flow.
New API added: rte_flow_dump.
Signed-off-by: Haifei Luo
---
doc/guides/nics/mlx5.rst| 10 +++--
doc/guides/prog_guide/rte_flow.rst | 44 +
lib/librte_ethdev/rte
Dump all the flows is supported.Some customers require to dump info
for one flow. To implement this requirement,
add the CLI to dump one rule: flow dump PORT rule ID
the CLI to dump all: flow dump PORT all
Examples:
testpmd> flow dump 0 all
testpmd> flow dump 0 rule 0
Also new AP
use ~0ULL instead of -1ULL to avoid contridctory application of '-' sign
to integer literal where the desired type is unsigned.
Signed-off-by: Tyler Retzlaff
---
lib/librte_eal/common/eal_common_fbarray.c | 12 ++--
lib/librte_power/rte_power_pmd_mgmt.c | 2 +-
2 files changed, 7 i
The options help text was including an incomplete and redundant
summary of the options before explaining each. The summary is dropped.
The details of the option --hairpin-mode had an extra space,
breaking the alignment with the next line.
Signed-off-by: Thomas Monjalon
---
app/test-pmd/paramete
The usage syntax help includes the program name which was fake.
It is replaced with the real name from argv.
Signed-off-by: Thomas Monjalon
---
app/test-regex/main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/app/test-regex/main.c b/app/test-regex/main.c
index ba09b2
Use rte_set_application_usage_hook() in the test applications,
so the full help including EAL options can be printed in one go
with the EAL option -h or --help.
Signed-off-by: Thomas Monjalon
---
app/pdump/main.c | 2 ++
app/proc-info/main.c
Some applications were printing useless messages with rte_exit()
after showing the help. Using exit() is enough in this case.
Some applications were using a redundant printf or fprintf() before
calling rte_exit(). The messages are unified in a single rte_exit().
Some rte_exit() calls were missing
The option --log-level was not completely described in the usage text,
and it was difficult to guess the names of the log types and levels.
A new value "help" is accepted after --log-level to give more details
about the syntax and listing the log types and levels.
The array "levels" used for leve
The parsing check for invalid log level was not trying to catch
irrelevant numeric values.
A log level 0 or too high is now a failure in options parsing
so it can be caught early.
Signed-off-by: Thomas Monjalon
---
lib/librte_eal/common/eal_common_options.c | 2 +-
1 file changed, 1 insertion(+)
RTE_DIM(...) and RTE_LOG_DEBUG were used to get the highest log level.
For better clarity a new constant RTE_LOG_MAX is introduced
and mapped to RTE_LOG_DEBUG.
Signed-off-by: Thomas Monjalon
---
lib/librte_eal/common/eal_common_log.c | 8
lib/librte_eal/common/eal_common_options.c |
Some private log functions had a wrong "rte_" prefix.
All private log functions are moved from eal_private.h
to the new file eal_log.h:
rte_eal_log_init -> eal_log_init
rte_log_save_regexp -> eal_log_save_regexp
rte_log_save_pattern -> eal_log_save_pattern
eal_log_s
The macros OPT_HELP and OPT_HELP_NUM were not used where appropriate.
Signed-off-by: Thomas Monjalon
---
lib/librte_eal/common/eal_common_options.c | 2 +-
lib/librte_eal/freebsd/eal.c | 2 +-
lib/librte_eal/linux/eal.c | 2 +-
lib/librte_eal/windows/eal.c
The description of the EAL options was printed before the application
description provided via the hook.
It is better to let the application print the global syntax
and describes the detail of the EAL options below.
Also, some useless lines are removed,
and the alignment of few options is fixed.
After argument parsing done by rte_eal_init(),
the remaining arguments are to be parsed by the application
by progressing in the argv array.
In this context, the first string represented by argv[0] is still
the same program name as the original argv[0],
while the next strings are the application ar
The main intent of this series is to provide a nice help
for the --log-level option.
More patches are added to improve options help in general.
Thomas Monjalon (11):
eal: explain argv behaviour during init
eal: improve options usage text
eal: use macros for help option
eal: move private lo
2021-02-18 13:40 (UTC+0200), Tal Shnaiderman:
> The hard-coded thread priority for Windows threads in eal
> is REALTIME_PRIORITY_CLASS/THREAD_PRIORITY_TIME_CRITICAL.
>
> This results in issues with DPDK threads causing OS thread starvation
> and eventually a bugcheck.
>
> The fix reduce the threa
On Wed, 10 Mar 2021 00:30:24 +0530
Shanmugasundaram M wrote:
> Dear Team,
>
> we are using 18.11.1-6WIND DPDK. we are trying to get EAL Debug messages
> and we are not able to see any one from them in /var/log/messages. Kindly
> let me know --log-level=8 is enough or --log-level=*8 is correct O
Hi Shijith,
Please see a question in-line:
> -Original Message-
> From: Shijith Thotton
> Sent: Monday, March 8, 2021 2:46 PM
> To: Carrillo, Erik G
> Cc: Shijith Thotton ; Pavan Nikhilesh
> ; Jerin Jacob ;
> dev@dpdk.org
> Subject: [PATCH 1/3] eventdev: introduce adapter flags for peri
> >
> > > > > > >
> > > > > > > On Tue, Mar 09, 2021 at 08:58:39AM +, Juraj Linkeš wrote:
> > > > > > > > Honnappa, Thomas, Bruce, Jerin, you've comments in the past.
> > > > > > > > Do you have
> > > > > > > any further input?
> > > > > > > >
> > > > > > > > I think we just need to agree on t
Hi Andrew,
Thanks for the reply PDB,
> -Original Message-
> From: Andrew Rybchenko
> Sent: Tuesday, March 9, 2021 5:28 PM
> Subject: Re: [dpdk-dev] [RFC] ethdev: add sanity packet checks
>
> On 3/9/21 6:08 PM, Ori Kam wrote:
> > Hi
> >
> >> -Original Message-
> >> From: dev On B
Hi
> -Original Message-
> From: Ajit Khaparde
> Subject: Re: [dpdk-dev] [RFC] ethdev: add sanity packet checks
>
> On Sun, Mar 7, 2021 at 10:46 AM Ori Kam wrote:
> >
> > Hi
> >
> > > -Original Message-
> > > From: Thomas Monjalon
> > > Sent: Thursday, March 4, 2021 12:46 PM
> >
Dear Team,
we are using 18.11.1-6WIND DPDK. we are trying to get EAL Debug messages
and we are not able to see any one from them in /var/log/messages. Kindly
let me know --log-level=8 is enough or --log-level=*8 is correct OR
--log-level=eal,debug is correct ?
Appreciate your quick response.
reg
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Tuesday, March 9, 2021 5:05 PM
> To: Juraj Linkeš ; Jerin Jacob
>
> Cc: Bruce Richardson ; Ruifeng Wang
> ; vcchu...@amazon.com; Dharmik Thakkar
> ; hemant.agra...@nxp.com; Ajit Khaparde
> (ajit.khapa...@broadcom.com) ;
> ferruh.
On 3/9/2021 4:08 PM, Ed Czeck wrote:
- Rename extension functions with rte_pmd_ark prefix
- Move extension prototype to rte_pmd_ark.h
- Update local function documentation
Signed-off-by: Ed Czeck
---
v3:
- split function rename from previous commit
v4:
- reorder patches renaming before adding
On 3/9/2021 4:08 PM, Ed Czeck wrote:
In this commit we generalize the movement of user-specified
meta data between mbufs and FPGA AXIS tuser fields using
user-defined hook functions.
- Previous use of PMD dynfields are removed
- Hook function added to ark_user_ext
- Add hook function calls in Rx
On 3/9/2021 10:19 AM, Ciara Loftus wrote:
Prior to this commit, the maximum batch sizes for zero-copy and copy-mode
rx and copy-mode tx were set to 32. Apart from zero-copy tx, the user
could never rx/tx any more than 32 packets at a time and without inspecting
the code the user wouldn't be aware
On 3/9/2021 10:19 AM, Ciara Loftus wrote:
This commit introduces support for preferred busy polling
to the AF_XDP PMD. This feature aims to improve single-core
performance for AF_XDP sockets under heavy load.
A new vdev arg is introduced called 'busy_budget' whose default
value is 64. busy_budge
No, I am sorry, I have not tested it. I was able to remove rte_kni from our
requirements so this is no longer a blocker for us.
-Andrew
> On Mar 9, 2021, at 3:47 AM, Juraj Linkeš wrote:
>
> Hi Folks,
>
> Does anyone have any comments? Is the patch ready? If so, please send acks or
> reviewed
Aaron Conole writes:
> Bruce Richardson writes:
>
>> On Tue, Mar 02, 2021 at 10:07:26AM +0100, David Marchand wrote:
>>> On Wed, Feb 10, 2021 at 3:56 PM Aaron Conole wrote:
>>> > diff --git a/doc/guides/contributing/testing.rst
>>> > b/doc/guides/contributing/testing.rst
>>> > new file mode 10
tc ov watermark is initialized with computed value of
max tc ov watermark.
Signed-off-by: Savinay Dharmappa
---
v2: fix spelling error.
---
lib/librte_sched/rte_sched.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_sched/rte_sched.c b/lib/librte_sched/rte_sched.
remove unnecessary includes
no functional changes
Signed-off-by: Ed Czeck
---
drivers/net/ark/ark_ethdev.c | 17 ++---
drivers/net/ark/ark_pktchkr.c | 4
drivers/net/ark/ark_pktgen.c | 20 ++--
drivers/net/ark/ark_pktgen.h | 1 +
4 files changed, 17 insertio
In this commit we generalize the movement of user-specified
meta data between mbufs and FPGA AXIS tuser fields using
user-defined hook functions.
- Previous use of PMD dynfields are removed
- Hook function added to ark_user_ext
- Add hook function calls in Rx and Tx paths
- Update guide with examp
- Rename extension functions with rte_pmd_ark prefix
- Move extension prototype to rte_pmd_ark.h
- Update local function documentation
Signed-off-by: Ed Czeck
---
v3:
- split function rename from previous commit
v4:
- reorder patches renaming before adding
---
drivers/net/ark/ark_ethdev.c | 32
- New PCIe IDs using net/ark driver
- Update Version IDs and structures specified by hardware
- New internal descriptor status for TX
- Adjust data placement in RX operations, headroom in retained
for segmented mbufs
Signed-off-by: Ed Czeck
---
doc/guides/nics/ark.rst | 5 ++
drivers/n
Allocate mbufs for Rx path in bulk of at least 64 buffers
to improve performance. Allow recovery even without
a Rx operation to support lack of buffers in pool.
Fixes: be410a861598 ("net/ark: add recovery for lack of mbufs")
Cc: sta...@dpdk.org
Signed-off-by: Ed Czeck
---
drivers/net/ark/ark_et
Fixes: b33ccdb17f55 ("net/ark: provide API for hardware modules MPU RQP and
pktdir")
Cc: sta...@dpdk.org
Signed-off-by: Ed Czeck
---
drivers/net/ark/ark_ethdev.c | 1 +
drivers/net/ark/ark_pktdir.c | 2 +-
drivers/net/ark/ark_pktdir.h | 2 +-
3 files changed, 3 insertions(+), 2 deletions(-)
di
> > > > >
> > > > > On Tue, Mar 09, 2021 at 08:58:39AM +, Juraj Linkeš wrote:
> > > > > > Honnappa, Thomas, Bruce, Jerin, you've comments in the past.
> > > > > > Do you have
> > > > > any further input?
> > > > > >
> > > > > > I think we just need to agree on the allowlist/blocklist
> > > >
tc ov watermark is intialized with computed value of
max tc ov watermark.
Signed-off-by: Savinay Dharmappa
---
lib/librte_sched/rte_sched.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_sched/rte_sched.c b/lib/librte_sched/rte_sched.c
index 7c56880681..cd87e688e4
The DPDK testing infrastructure includes a comprehensive set of
libraries, utilities, and CI integrations for developers to test
their code changes. This isn't well documented, however.
Document the basics for adding a test suite to the infrastructure
and enabling that test suite for continuous i
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Tuesday, March 9, 2021 4:09 PM
> To: Jerin Jacob ; Juraj Linkeš
>
> Cc: Bruce Richardson ; Ruifeng Wang
> ; vcchu...@amazon.com; Dharmik Thakkar
> ; hemant.agra...@nxp.com; Ajit Khaparde
> (ajit.khapa...@broadcom.com) ;
> ferruh.
From: Qiming Chen
The d2146nt chip integrates the x722 controller. The i40e.ko version is
2.9.21, and the firmware version is Intel’s customized version 4.3. It has been
communicated with Intel Steven. The version is compatible. Each PF virtual
place has 16 VFs, and there are 2 Each proces
On 3/9/21 6:08 PM, Ori Kam wrote:
> Hi
>
>> -Original Message-
>> From: dev On Behalf Of Thomas Monjalon
>> Sent: Tuesday, March 9, 2021 11:11 AM
>> Subject: Re: [dpdk-dev] [RFC] ethdev: add sanity packet checks
>>
>> 09/03/2021 10:01, Andrew Rybchenko:
>>> On 2/28/21 10:48 PM, Ori Kam wr
> > >
> > > On Tue, Mar 09, 2021 at 08:58:39AM +, Juraj Linkeš wrote:
> > > > Honnappa, Thomas, Bruce, Jerin, you've comments in the past. Do
> > > > you have
> > > any further input?
> > > >
> > > > I think we just need to agree on the allowlist/blocklist
> > > > mechanism. The current
> > >
> > >
> > > On Tue, Mar 09, 2021 at 08:58:39AM +, Juraj Linkeš wrote:
> > > > Honnappa, Thomas, Bruce, Jerin, you've comments in the past. Do
> > > > you have
> > > any further input?
> > > >
> > > > I think we just need to agree on the allowlist/blocklist
> > > > mechanism. The current
> > >
1 - 100 of 153 matches
Mail list logo