Acked-by: Chengwen Feng
On 2023/10/27 12:15, Huisong Li wrote:
> Add maximum Rx buffer size display.
>
> Signed-off-by: Huisong Li
> ---
> app/test-pmd/config.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
> index b9fdb7e8f1..2ac6f1
Acked-by: Chengwen Feng
On 2023/10/27 12:15, Huisong Li wrote:
> The "min_rx_bufsize" in struct rte_eth_dev_info stands for the minimum
> Rx buffer size supported by hardware. Actually, some engines also have
> the maximum Rx buffer specification, like, hns3. If mbuf data room size
> in mempool
@all
The patch "[PATCH 1/4] net/hns3: fix a typo" has been moved to patchset
"[0/8] net/hns3: add some bugfix for hns3", see
https://patches.dpdk.org/project/dpdk/cover/20231027060947.3183983-1-haij...@huawei.com/
On 2023/10/18 19:32, lihuisong (C) wrote:
hns3 patch can be stripped from this
Acked-by: Chengwen Feng
On 2023/10/27 12:15, Huisong Li wrote:
> This patch reports the maximum buffer size hardware supported.
>
> Signed-off-by: Huisong Li
> ---
> drivers/net/hns3/hns3_common.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/net/hns3/hns3_common.c b/drive
Acked-by: Chengwen Feng
On 2023/8/2 10:55, Huisong Li wrote:
> The command "tso set " is used to enable UFO, please
> see commit ce8e6e742807 ("app/testpmd: support UFO in checksum engine")
>
> The above patch configures the RTE_MBUF_F_TX_UDP_SEG to enable UFO only if
> tso_segsz is set. Then t
From: Dengdui Huang
PF driver get all interrupt states by reading three registers. This logic
code block is distributed in many places. So this patch extracts a common
function to do this to improve the maintaince.
Fixes: f53a793bb7c2 ("net/hns3: add more hardware error types")
Fixes: 3988ab0eee
From: Dengdui Huang
Currently, when the IMP or Global reset detected, the vector0
interrupt is enabled before the reset process is completed.
At this moment, if the initialization of IMP is not completed,
and the vector0 interrupt may continue to be reported. In this
scenario, the IMP/global rese
From: Dengdui Huang
Currently, the driver proactively checks whether interrupt exist
(by checking reset registers), related reset delay task is scheduled.
When a reset whose level is equal to or lower than the current level
is detected, there is unnecessary to add delay task and print logs.
Thi
From: Dengdui Huang
The reset event is checked and done in primary. And the secondary
doesn't check and display reset log. There is a patch to remove the
check code for secondary. please see commit a8f1f7cf1b42 ("net/hns3:
fix crash when secondary process access FW")
This patch removes the redun
This patch fixes a typo.
Fixes: c09c7847d892 ("net/hns3: support traffic management")
Cc: sta...@dpdk.org
Signed-off-by: Jie Hai
Acked-by: Huisong Li
Acked-by: Chengwen Feng
---
drivers/net/hns3/hns3_tm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/hns3
This patchset contains some bugfix for hns3 pmd.
Dengdui Huang (6):
net/hns3: fix unchecked Rx free threshold
net/hns3: fix double stats for IMP and global reset
net/hns3: remove reset log in secondary
net/hns3: fix multiple reset detected log
net/hns3: fix the imp/global reset interrupt
From: Dengdui Huang
There is a stats counter for IMP and global reset in PF driver.
hns3 driver has two following task to detect reset event:
(1) interrupte handled task(A): triggered by interrupt and detect
which reset level. And the reset service will be executed
after 10us.
(2) polling
From: Dengdui Huang
To reduce the frequency of updating the head pointer of Rx queue,
driver just updates this pointer when the number of processed
descriptors is greater than the Rx free threshold. If the Rx free
threshold is set to a value greater than or equal to the number of
descriptors in R
From: Huisong Li
Driver may fail to allocate bulk mbufs for Neon and SVE when rearm
mbuf. Currently, driver keeps going to handle packets even if there
isn't available descriptors to receive packets at this moment.
As a result, driver probably fills the mbufs with invalid data to
application and
The "min_rx_bufsize" in struct rte_eth_dev_info stands for the minimum
Rx buffer size supported by hardware. Actually, some engines also have
the maximum Rx buffer specification, like, hns3. If mbuf data room size
in mempool is greater then the maximum Rx buffer size supported by HW,
the data size
The "min_rx_bufsize" in struct rte_eth_dev_info stands for the minimum
Rx buffer size supported by hardware. Actually, some engines also have
the maximum Rx buffer specification, like, hns3.
If mbuf data room size in mempool is greater then the maximum Rx buffer
size supported by HW, the data size
Add maximum Rx buffer size display.
Signed-off-by: Huisong Li
---
app/test-pmd/config.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index b9fdb7e8f1..2ac6f15773 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -881,6 +881,8
This patch reports the maximum buffer size hardware supported.
Signed-off-by: Huisong Li
---
drivers/net/hns3/hns3_common.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/hns3/hns3_common.c b/drivers/net/hns3/hns3_common.c
index c4d47f43fe..cfce9ddd0f 100644
--- a/drivers/net/hn
Implement the corresponding nfp vDPA operation functions.
Signed-off-by: Shujing Dong
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/vdpa/nfp/nfp_vdpa.c | 213
1 file changed, 213 insertions(+)
diff --git a/drivers/vdp
Add the logic to process vDPA notify relay.
Signed-off-by: Chaoyong He
Signed-off-by: Shujing Dong
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/vdpa/nfp/nfp_vdpa.c | 155 +++
drivers/vdpa/nfp/nfp_vdpa_core.c | 61
drivers/vdpa/nfp/nfp
Add the vDPA datapath update logic.
Signed-off-by: Chaoyong He
Signed-off-by: Shujing Dong
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/common/nfp/nfp_common_ctrl.h | 1 +
drivers/vdpa/nfp/nfp_vdpa.c | 318 +++
drivers/vdpa/nfp/nfp_vdpa_core.c
Add the hardware initialize logic.
Signed-off-by: Chaoyong He
Signed-off-by: Shujing Dong
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/vdpa/nfp/meson.build | 1 +
drivers/vdpa/nfp/nfp_vdpa.c | 10 ++
drivers/vdpa/nfp/nfp_vdpa_core.c | 54 +
Add the logic of remap PCI memory.
Signed-off-by: Chaoyong He
Signed-off-by: Shujing Dong
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/vdpa/nfp/nfp_vdpa.c | 65 -
1 file changed, 64 insertions(+), 1 deletion(-)
diff --git a/drivers/vdpa/nfp/nfp
Add the basic framework of vDPA PMD.
Signed-off-by: Chaoyong He
Signed-off-by: Shujing Dong
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/common/nfp/nfp_common_pci.c | 1 +
drivers/common/nfp/nfp_common_pci.h | 1 +
drivers/vdpa/nfp/meson.build| 3 +-
drivers/vdpa/nfp
Introduce the very basic NFP vDPA library, and add entry for the NFP
vDPA PMD in the release notes.
Signed-off-by: Shujing Dong
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
MAINTAINERS| 6 +++
doc/guides/rel_notes/release_23_11.rst |
Move the device module to the common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/common/nfp/meson.build| 1 +
drivers/{net/nfp/nfpcore => common/nfp}/nfp_dev.c | 0
drivers/{net/nfp/nfpcore => common/nfp}/nfp_dev.h | 3 +++
d
Move the platform module to the common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/{net/nfp/nfpcore => common/nfp}/nfp_platform.h | 0
drivers/net/nfp/nfdk/nfp_nfdk_dp.c | 2 +-
drivers/net/nfp/nfp_net_ctrl.c
Move the queue enable/disable logic to the common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/common/nfp/nfp_common.c | 49
drivers/common/nfp/nfp_common.h | 7 +
drivers/common/nfp/version.map | 2 ++
Add the nfp common module in the nfp common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/common/nfp/meson.build | 3 +-
drivers/common/nfp/nfp_common.c | 177 +++
drivers/common/nfp/nfp_common.h | 232 +++
Add the common ctrl module.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/common/nfp/nfp_common_ctrl.h | 374 +++
drivers/net/nfp/nfp_net_ctrl.h | 365 +-
2 files changed, 375 insertions(+), 364 deletio
Rename parameter 'hw' into 'net_hw' in the related logic, to make the
name more accurate.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.c | 8 +--
drivers/net/nfp/nfp_ethdev.c| 86 +++
drivers/net/nf
Extract the 'mac_addr' data filed into the super class, prepare for the
upcoming common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/nfp_ethdev.c | 14 +++---
drivers/net/nfp/nfp_ethdev_vf.c | 18 +-
drivers/n
Extract the 'reconfig_lock' data field into the super class, also change
the parameter of the related APIs, prepare for the upcoming common
library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.c | 50 +
drivers/net/nfp/
Change the parameter of some functions from 'struct nfp_net_hw' into the
super class 'struct nfp_hw', prepare for the upcoming common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.c | 24 ++--
.../net/nfp/flowe
Extract the 'ctrl' data filed into the super class, prepare for the
upcoming common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.c | 8 ++---
drivers/net/nfp/nfd3/nfp_nfd3_dp.c | 2 +-
drivers/net/nfp/nfdk/nfp_nfdk_dp
Extract the 'ctrl_bar' data filed into the super class, prepare for the
upcoming common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.c | 8
drivers/net/nfp/nfp_ethdev.c| 14 +++---
drivers/net/n
Extract the 'qcp_cfg' data field into the super class, prepare for the
upcoming common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/nfp_net_common.c | 8
drivers/net/nfp/nfp_net_common.h | 2 +-
2 files changed, 5 insertions(+),
Extract the 'cap' and 'cap_ext' data field into the super class, ready
for the upcoming common library.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.c | 6 +-
drivers/net/nfp/nfd3/nfp_nfd3_dp.c | 12 ++--
drivers/net/nfp/nfdk/n
Rename the 'nfp_common' module into 'nfp_net_common' module, because
which is more suitable and we will add 'nfp_common' module in the
'drivers/common/nfp' directory.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/flower/nfp_flower.h
Rename the 'nfp_ctrl' module into 'nfp_net_ctrl' module, because which
is more suitable and we will add 'nfp_common_ctrl' module in the
'drivers/common/nfp' directory.
Signed-off-by: Chaoyong He
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/meson.build| 2
Modify the logic of NFP VF PMD, make it using of the NFP common module
and link into the 'nfp_drivers_list'.
Signed-off-by: Chaoyong He
Signed-off-by: Shujing Dong
Reviewed-by: Long Wu
Reviewed-by: Peng Zhang
---
drivers/net/nfp/meson.build | 2 +-
drivers/net/nfp/nfp_ethdev_vf.c | 14 ++
A new NFP vdpa PMD will be added to support vdpa operations by NFP
adapters.
This vdpa PMD share some logic with the net/nfp PMD. So create a new
common library in drivers/common for NFP PMDs.
We import a 'nfp_class_driver' layer and which can support various
device type in addition to the ethern
This patch series aims to add the NFP vDPA PMD, we also grab the common
logic into the `drivers/common/nfp` directory.
---
v4:
* Try to fix compile error in clang environment.
* Merge the modify of release notes into suitable commit.
* Rewrite the commit headline as the advise of reviewer.
v3:
* R
Add co-maintainer for DMA perf app.
Signed-off-by: Gowrishankar Muthukrishnan
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 4083658697..b81eb1d5c0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1773,6 +1773,7 @@ F: doc/guides/testpmd_app_ug/
https://bugs.dpdk.org/show_bug.cgi?id=1306
Bug ID: 1306
Summary: hash: internal hash key pointer overflow
Product: DPDK
Version: 23.11
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
P
> On 10/26/2023 7:42 AM, Chaoyong He wrote:
> > This patch series aims to add the NFP vDPA PMD, we also grab the
> > common logic into the `drivers/common/nfp` directory.
> >
> > ---
> > v3:
> > * Replace 'pthread_xxx' API with 'rte_thread_xxx' API.
> > * Replace '__atomic_xxx' built-ins with 'rte_
On 10/19/2023 7:54 AM, Chaoyong He wrote:
> Add the corresponding logics to support the offload of
> represented port action.
>
> Signed-off-by: Chaoyong He
>
Applied to dpdk-next-net/main, thanks.
On 10/26/2023 6:11 PM, Stephen Hemminger wrote:
> Other signals may occur causing read to get interrupted.
> Loop until quit flag is set by signal, a character is entered,
> or end of file. This fixes bug where testpmd would exit early
> because of signal used by TAP device.
>
> Bugzilla ID: 1305
On Thu, Oct 26, 2023 at 10:00:33PM +0200, Thomas Monjalon wrote:
> 26/10/2023 16:19, Thomas Monjalon:
> > Real-time thread priority was been forbidden on Unix
> > because of problems they can cause.
> > Warnings and helpers are added to avoid deadlocks,
> > so real-time can be allowed on all system
Release status meeting minutes 2023-10-26
=
Agenda:
* Release Dates
* Subtrees
* Roadmaps
* LTS
* Defects
* Opens
Participants:
* AMD
* ARM
* Intel
* Marvell
* Nvidia
* Red Hat
Release Dates
-
The following are the current working dates for 23
From: Jeremy Spewock
Modifies the current process so that we bind to os_driver_for_dpdk from
the configuration file before running test suites and bind back to the
os_driver afterwards. This allows test suites to assume that the ports
are bound to a DPDK supported driver or bind to either driver
From: Jeremy Spewock
Currently in the DTS framework there is nothing that allows you to bind
ports on the SUT to different drivers, but the ability to do so is
necessary in the case of many different test suites. This change allows
developers to bind to either os_driver or os_driver_for_dpdk whic
I recently ran into issues using the above Dockerfile because of the
version of poetry. I found that installing poetry with pip3 rather than apt
fixed my issue with it.
On Tue, Oct 17, 2023 at 9:52 AM Paul Szczepanek
wrote:
>
> On 03/11/2022 13:46, Juraj Linkeš wrote:
> > The Dockerfile defines
On Thu, 26 Oct 2023 21:55:24 +0200
Thomas Monjalon wrote:
> > To be safe the sleep has to be longer than the system clock tick.
> > Most systems are built today with HZ=250 but really should be using HZ=1000
> > on modern CPU's.
>
> If it has to be more than 1 ms,
> we should mention it is a s
26/10/2023 16:19, Thomas Monjalon:
> Real-time thread priority was been forbidden on Unix
> because of problems they can cause.
> Warnings and helpers are added to avoid deadlocks,
> so real-time can be allowed on all systems.
>
> Thomas Monjalon (2):
> eal: add thread yield functions
> eal/un
26/10/2023 18:28, Stephen Hemminger:
> On Thu, 26 Oct 2023 16:08:02 +0200
> Morten Brørup wrote:
>
> > > > In our recent tests, nanosleep() itself took around 50 us. So you need
> > > > to
> > > sleep longer than that for your thread not to be runnable when the
> > > nanosleep()
> > > wakes u
26/10/2023 18:50, Morten Brørup:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Thursday, 26 October 2023 18.07
> >
> > 26/10/2023 17:54, Bruce Richardson:
> > > On Thu, Oct 26, 2023 at 04:59:51PM +0200, Morten Brørup wrote:
> > > > > From: Morten Brørup [mailto:m...@smartsharesy
Add SG copy support.
Signed-off-by: Gowrishankar Muthukrishnan
---
app/test-dma-perf/benchmark.c | 274 +-
app/test-dma-perf/config.ini | 19 ++-
app/test-dma-perf/main.c | 34 -
app/test-dma-perf/main.h | 5 +-
4 files changed, 292 insertions(+
Validate copied memory to ensure DMA copy did not fail.
Signed-off-by: Gowrishankar Muthukrishnan
---
app/test-dma-perf/benchmark.c | 23 +--
app/test-dma-perf/main.c | 16 +++-
app/test-dma-perf/main.h | 2 +-
3 files changed, 33 insertions(+), 8 delet
From: Amit Prakash Shukla
Add support to test performance for "device to memory" and
"memory to device" data transfer.
Signed-off-by: Amit Prakash Shukla
---
app/test-dma-perf/benchmark.c | 67 +++
app/test-dma-perf/config.ini | 37 +++
app/test
From: Amit Prakash Shukla
Add support to skip running a dma-perf test-case.
Signed-off-by: Amit Prakash Shukla
---
app/test-dma-perf/config.ini | 2 ++
app/test-dma-perf/main.c | 23 +++
app/test-dma-perf/main.h | 1 +
3 files changed, 26 insertions(+)
diff --git
Improve dma-perf application to support PCI dev and SG copy,
along with additional supports below:
- validate copied memory
- skip tests if not opted.
v5:
- Additional patches included to apply as one series.
Amit Prakash Shukla (2):
app/dma-perf: add skip support
app/dma-perf: add PCI dev
Added additional checks for compiler support of specific cpu arch
flags to fix incorrect error reporting.
Without this patch, meson build reports '__SSE4_2__' not defined
error for x86 builds when the compiler does not support the specified
cpu_instruction_set (or) machine argument.
Signed-off-by
On 10/16/2023 9:59 PM, Joshua Washington wrote:
> Before this patch, max_rx_pktlen was always set to UINT16_MAX. This, in
> conjunction with the MTU fix, causes problems with testpmd, as setting the
> packet length with the --max-pkt-len flag causes the MTU to be set
> higher than possible due to u
Other signals may occur causing read to get interrupted.
Loop until quit flag is set by signal, a character is entered,
or end of file. This fixes bug where testpmd would exit early
because of signal used by TAP device.
Bugzilla ID: 1305
Fixes: 0fd1386c30c3 ("app/testpmd: cleanup cleanly from sign
> From: Stephen Hemminger [mailto:step...@networkplumber.org]
> Sent: Thursday, 26 October 2023 18.32
>
> On Thu, 26 Oct 2023 09:33:42 +0200
> Morten Brørup wrote:
>
> > > From: Stephen Hemminger [mailto:step...@networkplumber.org]
> > > Sent: Wednesday, 25 October 2023 23.33
> > >
> > > On Wed,
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Thursday, 26 October 2023 18.07
>
> 26/10/2023 17:54, Bruce Richardson:
> > On Thu, Oct 26, 2023 at 04:59:51PM +0200, Morten Brørup wrote:
> > > > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > > > Sent: Thursday, 26 October
>+We will work on this proposal, it is not finalized yet.
>+Its not DLB2 specific as commenters say, we are looking into if there is
>another way doing it.
>+If it will end up common and not DLB specific for other drivers as well we
>will add function to pci common.
As far as we know this prob
On 8/31/23 11:04, Juraj Linkeš wrote:
The tool used to generate developer docs is sphinx, which is already
used in DPDK. The configuration is kept the same to preserve the style.
Sphinx generates the documentation from Python docstrings. The docstring
format most suitable for DTS seems to be the
vfio-pci driver in Linux kernel 6.2 enables PASID by default.
In DLB hardware, enabling PASID puts DLB in SIOV mode. This
breaks DLB PF-PMD mode. For DLB PF-PMD mode to function properly
PASID needs to be disabled for kernel 6.2.
In this commit this issue is addressed and PASID is disabled
by writ
On Thu, Oct 26, 2023 at 04:24:54AM +, Ruifeng Wang wrote:
> > -Original Message-
> > From: Tyler Retzlaff
> > Sent: Thursday, October 26, 2023 6:38 AM
> > To: Ruifeng Wang
> > Cc: dev@dpdk.org; Akhil Goyal ; Anatoly Burakov
> > ; Andrew Rybchenko
> > ; Bruce
> > Richardson ; Chenbo X
On Thu, 26 Oct 2023 09:33:42 +0200
Morten Brørup wrote:
> > From: Stephen Hemminger [mailto:step...@networkplumber.org]
> > Sent: Wednesday, 25 October 2023 23.33
> >
> > On Wed, 25 Oct 2023 19:54:06 +0200
> > Morten Brørup wrote:
> >
> > > I agree with Thomas on this.
> > >
> > > If you wan
On Thu, 26 Oct 2023 16:08:02 +0200
Morten Brørup wrote:
> > > In our recent tests, nanosleep() itself took around 50 us. So you need to
> > >
> > sleep longer than that for your thread not to be runnable when the
> > nanosleep()
> > wakes up again, because 50 us has already passed in "nanosle
26/10/2023 17:54, Bruce Richardson:
> On Thu, Oct 26, 2023 at 04:59:51PM +0200, Morten Brørup wrote:
> > > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > > Sent: Thursday, 26 October 2023 16.50
> > >
> > > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > > Sent: Thursday, 26
> Replace the use of gcc builtin __atomic_xxx intrinsics with
> corresponding rte_atomic_xxx optional stdatomic API
>
> Signed-off-by: Tyler Retzlaff
> ---
Acked-by: Akhil Goyal
On Thu, Oct 26, 2023 at 04:59:51PM +0200, Morten Brørup wrote:
> > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > Sent: Thursday, 26 October 2023 16.50
> >
> > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > Sent: Thursday, 26 October 2023 16.31
> > >
> > > 26/10/2023 16:08
> Replace the use of gcc builtin __atomic_xxx intrinsics with
> corresponding rte_atomic_xxx optional stdatomic API
>
> Signed-off-by: Tyler Retzlaff
Acked-by: Akhil Goyal
On 10/21/2023 5:10 AM, lihuisong (C) wrote:
>
> 在 2023/10/20 23:12, Ferruh Yigit 写道:
>> On 10/20/2023 2:05 PM, Bruce Richardson wrote:
>>> For those using the function comments as a guide, provide the name of
>>> the correct callback function to use when wanting to count dropped
>>> packets from t
Updated the l3fwd-power app to configure the uncore env before invoking
any uncore APIs. With auto-detection in 'rte_power_uncore_init()' it is
too late because other APIs already called.
Bugzilla ID: 1304
Fixes: ac1edcb6621a ("power: refactor uncore power management API")
Cc: karen.ke...@intel.co
> From: Morten Brørup [mailto:m...@smartsharesystems.com]
> Sent: Thursday, 26 October 2023 16.50
>
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Thursday, 26 October 2023 16.31
> >
> > 26/10/2023 16:08, Morten Brørup:
> > > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
>
On 10/26/2023 7:42 AM, Chaoyong He wrote:
> This patch series aims to add the NFP vDPA PMD, we also grab the common
> logic into the `drivers/common/nfp` directory.
>
> ---
> v3:
> * Replace 'pthread_xxx' API with 'rte_thread_xxx' API.
> * Replace '__atomic_xxx' built-ins with 'rte_atomic_xxx'.
>
On 10/26/2023 7:43 AM, Chaoyong He wrote:
> Add a entry for the NFP vDPA PMD in the release notes.
>
> Signed-off-by: Chaoyong He
> Reviewed-by: Long Wu
> Reviewed-by: Peng Zhang
>
Can you please squash this patch to relevant commit:
18/25] drivers/vdpa: introduce the NFP vDPA library
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Thursday, 26 October 2023 16.31
>
> 26/10/2023 16:08, Morten Brørup:
> > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > Sent: Thursday, 26 October 2023 16.05
> > >
> > > 26/10/2023 15:57, Morten Brørup:
> > > > > From: Morten
On 10/26/2023 7:42 AM, Chaoyong He wrote:
> This patch series aims to add the NFP vDPA PMD, we also grab the common
> logic into the `drivers/common/nfp` directory.
>
> ---
> v3:
> * Replace 'pthread_xxx' API with 'rte_thread_xxx' API.
> * Replace '__atomic_xxx' built-ins with 'rte_atomic_xxx'.
>
26/10/2023 16:08, Morten Brørup:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Thursday, 26 October 2023 16.05
> >
> > 26/10/2023 15:57, Morten Brørup:
> > > > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > > > Sent: Thursday, 26 October 2023 15.45
> > > >
> > > > >
When adding an API for creating threads,
the real-time priority has been forbidden on Unix.
There is a known issue with ring behaviour,
but it should not be completely forbidden.
Real-time thread can block some kernel threads on the same core,
making the system unstable.
That's why a sleep is add
When running real-time threads, we may need to force scheduling
kernel threads or other real-time threads.
New functions are added to address these cases.
The yield functions should not have any interest for normal threads.
Note: other purposes may be addressed with rte_pause() or rte_delay_*().
Real-time thread priority was been forbidden on Unix
because of problems they can cause.
Warnings and helpers are added to avoid deadlocks,
so real-time can be allowed on all systems.
Thomas Monjalon (2):
eal: add thread yield functions
eal/unix: allow creating thread with real-time priority
From: Shai Brandes
This release introduces:
* Upgraded ENA HAL.
* Support for connection tracking allowance utilization metric.
* Support for reporting rx overrun errors in xstats.
* Support for ENA-express metrics.
Signed-off-by: Shai Brandes
Reviewed-by: Amit Bernstein
---
drivers/net/ena/e
From: Shai Brandes
ENA-express is powered by AWS scalable reliable datagram (SRD)
technology. SRD is a high performance network transport protocol
that uses dynamic routing to increase throughput and minimize
tail latency.
The driver expose the following ENA-express metrics via xstats:
* ena_srd
From: Shai Brandes
RX overrun error occur when a packet arrives but there are
not enough free buffers in the RX ring to receive it.
The driver publishes the extended statistics with the RX
buffer overrun errors as reported by the device.
Signed-off-by: Shai Brandes
Reviewed-by: Amit Bernstein
From: Shai Brandes
The driver publishes network performance metrics that the
application can use to troubleshoot performance issues,
monitor the workload, and benchmark applications to determine
whether they maximize the performance.
This patch adds support for the connection tracking allowance
From: Shai Brandes
ENA maintains a HAL that is shared by all supported host drivers.
Main features introduced to the HAL:
[1] Reworked the mechanism that queries the performance metrics
from the device.
[2] Added support for a new metric that allows monitoring the
available tracked connec
From: Shai Brandes
Hi,
This patchset contains alignment of the driver to the latest HAL version
which adds support for retrieving new metrics from the device and opens
a path to use additional device features that are not yet supported by
the driver.
The new driver features are mostly about add
On Thu, Oct 26, 2023 at 3:57 PM Morten Brørup
wrote:
>
> > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > Sent: Thursday, 26 October 2023 15.45
> >
> > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > Sent: Thursday, 26 October 2023 15.37
> > >
> > > 25/10/2023 18:31, Thoma
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Thursday, 26 October 2023 16.05
>
> 26/10/2023 15:57, Morten Brørup:
> > > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > > Sent: Thursday, 26 October 2023 15.45
> > >
> > > > From: Thomas Monjalon [mailto:tho...@monjalon.ne
26/10/2023 15:57, Morten Brørup:
> > From: Morten Brørup [mailto:m...@smartsharesystems.com]
> > Sent: Thursday, 26 October 2023 15.45
> >
> > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > Sent: Thursday, 26 October 2023 15.37
> > >
> > > 25/10/2023 18:31, Thomas Monjalon:
> > > > Rea
> From: Morten Brørup [mailto:m...@smartsharesystems.com]
> Sent: Thursday, 26 October 2023 15.45
>
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Thursday, 26 October 2023 15.37
> >
> > 25/10/2023 18:31, Thomas Monjalon:
> > > Real-time thread priority was been forbidden on Unix
On Thu, Oct 26, 2023 at 2:32 AM Tyler Retzlaff
wrote:
>
> Replace the use of gcc builtin __atomic_xxx intrinsics with
> corresponding rte_atomic_xxx optional stdatomic API.
>
> v3:
> * add missing atomic specification on head variable
> in struct rte_ring_headtail
> * adapt to use rte_atom
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Thursday, 26 October 2023 15.37
>
> 25/10/2023 18:31, Thomas Monjalon:
> > Real-time thread priority was been forbidden on Unix
> > because of problems they can cause.
> > Warnings and helpers are added to avoid deadlocks,
> > so real-ti
1 - 100 of 183 matches
Mail list logo
