> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Wednesday, March 13, 2019 11:36 PM
> To: Joyce Kong (Arm Technology China) ;
> dev@dpdk.org
> Cc: step...@networkplumber.org; Honnappa Nagarahalli
> ; tho...@monjalon.net; nd
> ; jerin.ja...@caviumnetworks.com; Gavin Hu (Arm
>
> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Wednesday, March 13, 2019 5:41 PM
> To: Joyce Kong (Arm Technology China) ;
> dev@dpdk.org
> Cc: step...@networkplumber.org; Honnappa Nagarahalli
> ; tho...@monjalon.net; nd
> ; jerin.ja...@caviumnetworks.com; Gavin Hu (Arm
> T
v6:
Add rte_ticketlock.h in lib/librte_eal/common/include/arch/arm/.
Sort header inside ticketlock files by alphabetical order.
v5:
Change the variants inside rte_ticket_lock from unint to uint16_t for binary
compatibility with the plain spin lock(suggested by Honnappa Nagarahalli)
The spinlock implementation is unfair, some threads may take locks
aggressively while leaving the other threads starving for long time.
This patch introduces ticketlock which gives each waiting thread a
ticket and they can take the lock one by one. First come, first serviced.
This avoids starvatio
> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Wednesday, March 13, 2019 9:31 PM
> To: Joyce Kong (Arm Technology China) ;
> dev@dpdk.org
> Cc: step...@networkplumber.org; Honnappa Nagarahalli
> ; tho...@monjalon.net; nd
> ; jerin.ja...@caviumnetworks.com; Gavin Hu (Arm
> T
Add test cases for ticket lock, recursive ticket lock,
and ticket lock performance.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
Reviewed-by: Phil Yang
Signed-off-by: Joyce Kong
---
MAINTAINERS| 1 +
app/test/Makefile | 1 +
app/test/autotest_data.py | 6 +
Signed-off-by: Wenzhuo Lu
---
drivers/net/ice/ice_rxtx.c | 16 +++
drivers/net/ice/ice_rxtx.h | 2 ++
drivers/net/ice/ice_rxtx_vec_sse.c | 41 ++
3 files changed, 55 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ice/ice_rx
Signed-off-by: Wenzhuo Lu
---
drivers/net/ice/Makefile| 19 ++
drivers/net/ice/ice_rxtx.c | 16 +-
drivers/net/ice/ice_rxtx.h | 2 +
drivers/net/ice/ice_rxtx_vec_avx2.c | 613
drivers/net/ice/meson.build | 15 +
5 fil
Signed-off-by: Wenzhuo Lu
---
doc/guides/nics/features/ice_vec.ini | 2 +
drivers/net/ice/ice_rxtx.c| 19 +
drivers/net/ice/ice_rxtx.h| 4 +
drivers/net/ice/ice_rxtx_vec_common.h | 133 +
drivers/net/ice/ice_rxtx_vec_sse.c| 135
Signed-off-by: Wenzhuo Lu
---
drivers/net/ice/ice_rxtx.c | 10 --
drivers/net/ice/ice_rxtx.h | 3 ++
drivers/net/ice/ice_rxtx_vec_avx2.c | 64 +
3 files changed, 74 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ice/ice_rxtx.c b/
Signed-off-by: Wenzhuo Lu
---
doc/guides/rel_notes/release_19_05.rst | 4 +
drivers/net/ice/ice_rxtx.c | 13 ++-
drivers/net/ice/ice_rxtx.h | 2 +
drivers/net/ice/ice_rxtx_vec_avx2.c| 158 +
4 files changed, 175 insertions(+), 2 del
Add function pointers of buffer releasing for RX and
TX queues, for vector functions will be added for RX
and TX.
Signed-off-by: Wenzhuo Lu
---
drivers/net/ice/ice_rxtx.c | 24 +++-
drivers/net/ice/ice_rxtx.h | 5 +
2 files changed, 20 insertions(+), 9 deletions(-)
diff
The TX setting functions is not called.
Fixes: 17c7d0f9d6a4 ("net/ice: support basic Rx/Tx")
Signed-off-by: Wenzhuo Lu
---
drivers/net/ice/ice_ethdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index a23c63a..b804be1 100644
--
Use SSE and AVX2 instructions in ICE RX and TX path.
---
v2:
- Updated feature doc.
- Fixed checklog and checkpatch issues.
v3:
- Fixed potential compile issue on non-X86 platform.
Wenzhuo Lu (8):
net/ice: fix Tx function setting
net/ice: add pointer for queue buffer release
net/ice: su
Signed-off-by: Wenzhuo Lu
---
config/common_base| 1 +
doc/guides/nics/features/ice_vec.ini | 33 +++
drivers/net/ice/Makefile | 3 +
drivers/net/ice/ice_ethdev.c | 2 -
drivers/net/ice/ice_ethdev.h | 2 +
drivers/net/ice/ice_rxtx.c
The following changes since commit 239912fa798e6e671072ca7ff987afd74c1e506c:
git: ignore build directories (2019-03-13 11:57:05 +0100)
are available in the Git repository at:
http://dpdk.org/git/next/dpdk-next-eventdev
for you to fetch changes up to 744407cf7b80f9e5c886c2304211b429febb4394
Hi，qi
> -Original Message-
> From: Zhang, Qi Z
> Sent: Friday, March 15, 2019 9:20 AM
> To: David Harton (dharton)
> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
> ; dev@dpdk.org; Zhao1, Wei
>
> Subject: RE: [PATCH v2] net/ixgbe: Restore vlan filter/extend for ixgbevf
>
>
>
> > -Original
> -Original Message-
> From: Zhang, Qi Z
> Sent: Friday, March 15, 2019 9:20 AM
> To: David Harton (dharton)
> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
> ; dev@dpdk.org; Zhao1, Wei
>
> Subject: RE: [PATCH v2] net/ixgbe: Restore vlan filter/extend for ixgbevf
>
>
>
> > -Original Mes
Hi Jerin,
> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Wednesday, March 13, 2019 2:09 AM
> To: Joyce Kong (Arm Technology China) ;
> dev@dpdk.org
> Cc: chao...@linux.vnet.ibm.com; nd ;
> bruce.richard...@intel.com; tho...@monjalon.net;
> hemant.agra...@nxp.com; sta...@dp
Within rte_hash_reset, calling a while loop to dequeue one by
one from the ring, while not using them at all, is wasting cycles,
The patch just flush the ring by resetting the indices can save cpu
cycles.
Fixes: b26473ff8f4a ("hash: add reset function")
Fixes: 75706568a7eb ("hash: add extendable b
Currently, the flush is done by dequeuing the ring in a while loop. It is
much simpler to flush the queue by resetting the head and tail indices.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Gavin Hu
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
V1: To flush a ring not in use, dequeue one by one is wasting cpu cycles.
The patch is to just resetting the head and tail indices to save cpu
cycle.
V2: Fix the coding style issue(commit message line too long)
V3: Allow experimental API for meson build
V4:
- Include the ring perf test
Hi Stephen,
> -Original Message-
> From: Stephen Hemminger
> Sent: Thursday, March 14, 2019 11:54 PM
> To: Joyce Kong (Arm Technology China)
> Cc: dev@dpdk.org; nd ; Gavin Hu (Arm Technology China)
> ; jer...@marvell.com; konstantin.anan...@intel.com;
> chao...@linux.vnet.ibm.com; bruce.
Hi Qi,
> -Original Message-
> From: Zhang, Qi Z
> Sent: Monday, March 11, 2019 11:27 AM
> To: Lu, Wenzhuo ; dev@dpdk.org
> Cc: Lu, Wenzhuo
> Subject: RE: [dpdk-dev] [PATCH v2 3/8] net/ice: support vector SSE in RX
>
> Hi:
>
> > -Original Message-
> > From: dev [mailto:dev-boun..
> -Original Message-
> From: David Harton (dharton) [mailto:dhar...@cisco.com]
> Sent: Thursday, March 14, 2019 11:51 PM
> To: Zhang, Qi Z
> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
> ; dev@dpdk.org
> Subject: RE: [PATCH v2] net/ixgbe: Restore vlan filter/extend for ixgbevf
>
> Hi Qi,
>
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger
> Sent: Friday, March 15, 2019 12:21 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger
> Subject: [dpdk-dev] [PATCH v3] ethdev: check for invalid device name
>
> Do not allow creating a ethernet d
> -Original Message-
> From: Zhang, Qi Z
> Sent: Monday, March 11, 2019 3:04 PM
> To: Lu, Wenzhuo ; Yang, Qiming
>
> Cc: dev@dpdk.org; Stillwell Jr, Paul M ; Yigit,
> Ferruh ; Zhang, Qi Z
> Subject: [PATCH v3 01/38] net/ice/base: add switch resource allocation and
> free
>
> Add two APIs
> >> @@ -1072,10 +1071,23 @@ __rte_hash_add_key_with_hash(const struct
> rte_hash *h, const void *key,
> >>bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
> >>/* Use the first location of the new bucket */
> >>(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
> >> - (h->buckets_ex
On Fri, Mar 15, 2019 at 3:02 AM Stephen Hemminger
wrote:
>
> The driver multiple rxq allocation logs a message at error level
> but it really is a debug message.
>
> Fixes: 51fafb89a9a0 ("net/bnxt: get rid of ff pools and use VNIC info array")
> Signed-off-by: Stephen Hemminger
> ---
> drivers/n
Hi,
Below is a list of directories, files or functions which we
need to check to make basic DPDK works on Windows.
If something is missing, please complete.
The goal of this list is to make a status of what is already done,
and plan what should be done next. It will help to share the workload
amo
14/03/2019 03:58, Hyong Youb Kim:
> On Wed, Mar 13, 2019 at 10:29:53PM +0100, Thomas Monjalon wrote:
> > 13/03/2019 22:11, John Daley (johndale):
> > > From: Thomas Monjalon
> > > > 13/03/2019 19:32, Ferruh Yigit:
> > > > > On 3/5/2019 7:11 AM, Hyong Youb Kim wrote:
> > > > > > The driver currentl
The driver multiple rxq allocation logs a message at error level
but it really is a debug message.
Fixes: 51fafb89a9a0 ("net/bnxt: get rid of ff pools and use VNIC info array")
Signed-off-by: Stephen Hemminger
---
drivers/net/bnxt/bnxt_rxq.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-
Silence messages that are not errors.
Stephen Hemminger (2):
net/bnxt: silence iova warnings
net/bnxt: suppress supprious error log
drivers/net/bnxt/bnxt_ethdev.c | 6 ++
drivers/net/bnxt/bnxt_rxq.c| 3 ++-
2 files changed, 4 insertions(+), 5 deletions(-)
--
2.17.1
When using bnxt on bare-metal with vfio-pci, the driver logs an
unnecessary warning. Hardware works fine, message is not urgent.
Change it to INFO level.
Fixes: 62196f4e0941 ("mem: rename address mapping function to IOVA")
Signed-off-by: Stephen Hemminger
---
drivers/net/bnxt/bnxt_ethdev.c | 6 +
We have 41 responses. Today tech board decided to extend the deadline by
another week. We would like to extend the survey till 23rd March 2019.
Please take some time to provide your valuable feedback.
Thank you,
Honnappa
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Thursda
On Wed, 2019-03-13 at 14:14 +0530, Jerin Jacob wrote:
> On Wed, 2019-03-13 at 09:16 +0100, Thomas Monjalon wrote:
> > 13/03/2019 09:02, Jerin Jacob Kollanukkaran:
> > > On Tue, 2019-03-12 at 21:33 +0100, Thomas Monjalon wrote:
> > > > 12/03/2019 20:25, Jerin Jacob Kollanukkaran:
> > > > > On Fri, 2
On Wed, 2019-03-13 at 15:09 +, Bruce Richardson wrote:
> The check for a valid configuration in build-tags.sh relied on the
> output
> of "make showconfig" rather than checking directly for a config file
> of
> that name. This broke when as part of the rename of the
> linuxapp/bsdapp
> configs
Hajkowski :
> From: Marcin Hajkowski
>
> Function rte_power_set_env will no longer return
> success on attempt to set env in initialized state.
>
> Signed-off-by: Marcin Hajkowski
> ---
>
For further patches, please remove the legal disclaimer at the bottom.
Reviewed-by: Rami Rosen
On 3/14/2019 5:03 PM, Ferruh Yigit wrote:
> Minutes 14 March 2019
> -
>
> Agenda:
> * Release Dates
> * Subtrees
> * OvS
> * Opens
>
>
> Participants:
> * Debian
> * Intel
> * Mellanox
> * RedHat
>
>
> Release Dates
> -
>
> * v19.05 dates, no change:
> * RC1:
When I try building I'm still getting this error
/root/dpdk/app/test-pmd/bpf_cmd.c:23:11: error: initialization discards
'const' qualifier from pointer target type [-Werror=discarded-qualifiers]
.val = &stdout,
On 13/03/2019 17:06, Natanael Copa wrote:
A set of patches to fix build with m
Minutes 14 March 2019
-
Agenda:
* Release Dates
* Subtrees
* OvS
* Opens
Participants:
* Debian
* Intel
* Mellanox
* RedHat
Release Dates
-
* v19.05 dates, no change:
* RC1: Friday, 29 March
* Release: Friday, 10 May
* Schedule web page updated according
Do not allow creating a ethernet device with a name over the
allowed maximum (or zero length). This is safer than silently truncating
which is what happens now.
Signed-off-by: Stephen Hemminger
Acked-by: Andrew Rybchenko
---
v3 -- fix whitespace issue
lib/librte_ethdev/rte_ethdev.c | 12 ++
Do not allow creating a ethernet device with a name over the
allowed maximum (or zero length). This is safer than silently truncating
which is what happens now.
Signed-off-by: Stephen Hemminger
Acked-by: Andrew Rybchenko
---
v2 - fix zero length name test
lib/librte_ethdev/rte_ethdev.c | 12 ++
On Wed, 2019-03-13 at 22:22 +, Carrillo, Erik G wrote:
> -Original Message-
> > From: Pavan Nikhilesh Bhagavatula [mailto:pbhagavat...@marvell.com]
> > Sent: Tuesday, March 12, 2019 3:41 PM
> > To: Jerin Jacob Kollanukkaran ; Van Haaren,
> > Harry
> > ; Rao, Nikhil ;
> > Carrillo,
> > E
On Thu, 14 Mar 2019 21:15:02 +0800
Joyce Kong wrote:
> - success = rte_atomic32_cmpset((volatile uint32_t *)&rwl->cnt,
> - (uint32_t)x, (uint32_t)(x + 1));
> + success = __atomic_compare_exchange_n(&rwl->cnt, &x, x+1, 1,
> +
On Thu, 14 Mar 2019 11:26:05 +
Matan Azrad wrote:
> Hi
>
> From: Stephen Hemminger
> > The vdev_netvsc virtual driver that is used to do initialization on Hyper-
> > V/Azure won't work without failsafe and tap device.
> > If the related devices aren't present, it causes confusing errors late
Hi Qi,
> -Original Message-
> From: Zhang, Qi Z
> Sent: Thursday, March 14, 2019 11:14 AM
> To: David Harton (dharton)
> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
> ; dev@dpdk.org
> Subject: RE: [PATCH v2] net/ixgbe: Restore vlan filter/extend for ixgbevf
>
>
>
> > -Original Message--
On Thu, 14 Mar 2019 11:13:10 +
Matan Azrad wrote:
> Hi
>
> From: Stephen Hemminger
> > The return value from bus->find_device is a rte_device which is not safe to
> > cast to a rte_vdev_device structure.
> > It doesn't really matter since only being checked for NULL but static
> > checkers
On Wed, 2019-03-13 at 14:58 -0700, Stephen Hemminger wrote:
> The octeontx driver is creating vdev with name "OCTEONTX_PMD"
> which is an artifact from how RTE_PMD_REGISTER_VDEV arguments
> work.
>
> Change to use the same convention as all the other network
> drivers ie "net_octeontx").
>
> Sig
> -Original Message-
> From: David Harton (dharton) [mailto:dhar...@cisco.com]
> Sent: Thursday, March 14, 2019 9:38 PM
> To: David Harton (dharton) ; Zhang, Qi Z
>
> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
> ; dev@dpdk.org
> Subject: RE: [PATCH v2] net/ixgbe: Restore vlan filter/extend f
Introduce a new api to retrieve per queue statistics from the drivers.
The api objectives:
- easily add some common per queue statistics and have it exposed
through the user xstats api while the user stats api is left untouched
- remove the limitations on the per queue statistics count (inherited
Nothing more than the title.
Signed-off-by: David Marchand
---
drivers/net/af_packet/rte_eth_af_packet.c | 49 +--
1 file changed, 33 insertions(+), 16 deletions(-)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/drivers/net/af_packet/rte_eth_af_packet.c
in
On Mon, Mar 11, 2019 at 7:09 PM David Marchand
wrote:
> On Mon, Mar 11, 2019 at 6:22 PM Ferruh Yigit
> wrote:
>
>> On 3/4/2019 11:18 AM, David Marchand wrote:
>> > According to the api, the q_errors[] per queue statistic is for
>> reception
>> > errors not transmit errors.
>> > This is a first c
> Subject: [PATCH v3 3/3] test/rwlock: amortize the cost of getting time
>
> Instead of getting timestamp per iteration, amortize its overhead can help to
> get more precise benchmarking results.
>
> Fixes: af75078fece3 ("first public release")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Joyce Kong
From: Marcin Hajkowski
On attempt to set_env in already initialized state notify
user by returning error that operation cannot be performed.
Signed-off-by: Marcin Hajkowski
---
doc/guides/rel_notes/release_19_05.rst | 4
lib/librte_power/rte_power.c | 3 ++-
lib/librte_power/rte
From: Marcin Hajkowski
Test all existing power environment configuration to verify if related
data is properly initialized and clean in set/unset scenarios.
Signed-off-by: Marcin Hajkowski
---
app/test/test_power.c | 155 --
1 file changed, 120 insertion
From: Marcin Hajkowski
Set all power environment related function pointers to NULL
when unset is being made.
Signed-off-by: Marcin Hajkowski
---
lib/librte_power/rte_power.c | 21 -
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/lib/librte_power/rte_power.c b
From: Marcin Hajkowski
Due to lack of thread safety in exisiting solution
use spinlock mechanism for atomic
modification of power environment related data.
Fixes: 445c6528b5 ("power: common interface for guest and host")
Cc: sta...@dpdk.org
Signed-off-by: Marcin Hajkowski
---
doc/guides/rel_n
From: Marcin Hajkowski
Modifications to assure thread safety of rte_power APIs for
power env set and unset, better user notification by returning more
suitable value and internal data cleaning corrections.
Marcin Hajkowski (4):
power: fix non thread-safe power env modification
power: return
From: Marcin Hajkowski
Function rte_power_set_env will no longer return
success on attempt to set env in initialized state.
Signed-off-by: Marcin Hajkowski
---
doc/guides/rel_notes/deprecation.rst | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/
On 12.03.2019 20:11, Stephen Hemminger wrote:
> When fslmc is built as part of a general distribution, the
> bus code will log errors when other devices are present.
>
> This could confuse users it is not an error.
>
> Fixes: 50245be05d1a ("bus/fslmc: support device blacklisting")
> Signed-off-by
From: Marcin Hajkowski
Use new guest channel API to send confirmation
message for received power command.
Signed-off-by: Marcin Hajkowski
---
examples/vm_power_manager/channel_monitor.c | 64 +++--
1 file changed, 58 insertions(+), 6 deletions(-)
diff --git a/examples/vm_power
From: Marcin Hajkowski
Extend vm_power_guest to check incoming confirmations
of messages previously sent to host.
Signed-off-by: Marcin Hajkowski
---
examples/vm_power_manager/guest_cli/Makefile | 1 +
.../guest_cli/vm_power_cli_guest.c| 65 +++
2 files changed, 5
From: Marcin Hajkowski
Added new experimental API rte_power_guest_channel_receive_msg
which gives possibility to receive messages send to guest.
Signed-off-by: Marcin Hajkowski
---
lib/librte_power/channel_commands.h| 5 +++
lib/librte_power/guest_channel.c | 57
From: Marcin Hajkowski
Extend guest channel API to allow bidirectional
communication. Modify power manager host and guest
side to communicate in both directions.
Marcin Hajkowski (4):
power: fix invalid socket indicator value
power: extend guest channel api for reading
power: process incom
From: Marcin Hajkowski
Currently 0 is being used for not connected slot indication.
This is not consistent with linux doc which identifies 0 as valid
(connected) slot, thus modification was done to change it.
Fixes: cd0d5547 ("power: vm communication channels in guest")
Cc: sta...@dpdk.org
Sign
On Fri, Mar 08, 2019 at 03:56:37PM +0800, Gavin Hu wrote:
> External Email
>
> --
> The __sync builtin based implementation generates full memory barriers
> ('dmb ish') on Arm platforms. Using C11 atomic builtins to generate one w
> -Original Message-
> From: Chaitanya Babu, TalluriX
> Sent: Thursday, March 14, 2019 1:35 PM
> To: dev@dpdk.org
> Cc: Pattan, Reshma ; Parthasarathy, JananeeX M
> ; rm...@marvell.com;
> shsha...@marvell.com; Xing, Beilei ; Zhang, Qi Z
> ; Chaitanya Babu, TalluriX
> ; sta...@dpdk.org
>
Hi Qi,
This patch was rejected with no feedback.
Can you share why?
Without this patch users are not able to call the rte_eth_dev_vlan_filter() API
for ixgbevf based ports because VLAN_FILTER cannot be enabled when calling
rte_eth_dev_configure().
Or, am I missing something?
Thanks,
Dave
>
strcat does not check the destination length and there might be
chances of string overflow so instead of strcat, strlcat is used.
Fixes: 540a211084 ("bnx2x: driver core")
Fixes: e163c18a15 ("net/i40e: update ptype and pctype info")
Cc: sta...@dpdk.org
Signed-off-by: Chaitanya Babu Talluri
---
v6
On 3/4/19 1:14 PM, Luca Boccassi wrote:
On Mon, 2019-03-04 at 11:12 -0500, Michael Santana wrote:
GitHub is a service used by developers to store repositories. GitHub
provides service integrations that allow 3rd party services to access
developer repositories and perform actions. One of these
strcat does not check the destination length and there might be
chances of string overflow so instead of strcat, strlcat is used.
Fixes: 6f4eec2565 ("test/crypto: enhance scheduler unit tests")
Cc: sta...@dpdk.org
Signed-off-by: Chaitanya Babu Talluri
---
app/test/test_cryptodev.c | 3 ++-
1 fi
> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Wednesday, March 13, 2019 2:09 AM
> To: Joyce Kong (Arm Technology China) ;
> dev@dpdk.org
> Cc: chao...@linux.vnet.ibm.com; nd ;
> bruce.richard...@intel.com; tho...@monjalon.net;
> hemant.agra...@nxp.com; sta...@dpdk.org; Hon
Instead of getting timestamp per iteration, amortize its
overhead can help to get more precise benchmarking results.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
Reviewed-by: Ola Liljedahl
Reviewed-by: Ruifeng Wang
Signed-off
Add performance test on all available cores to benchmark
the scaling up performance of rw_lock.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Suggested-by: Gavin Hu
Signed-off-by: Joyce Kong
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Ola Liljedahl
Reviewed-by: Gavin Hu
From: Gavin Hu
The __sync builtin based implementation generates full memory
barriers ('dmb ish') on Arm platforms. Using C11 atomic builtins
to generate one way barriers.
Here is the assembly code of __sync_compare_and_swap builtin.
__sync_bool_compare_and_swap(dst, exp, src);
0x0090
v3: Fix headline format error.
v2: Rebase and modify the rwlock test case to address the comments in v1.
v1: Reimplement rwlock with atomic builtins, and add a rwlock perf test
on all available cores to benchmark the improvement.
We tested the patches on three arm64 platforms.
Thursday, March 7, 2019 9:42 AM, Yongseok Koh:
> Subject: [dpdk-dev] [PATCH 0/6] net/mlx: enable secondary process to
> register DMA memory
>
> RFC:
> https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fma
> ils.dpdk.org%2Farchives%2Fdev%2F2019-
> March%2F125517.html&data=02%7C01%7C
Hi Koh,
Thursday, March 7, 2019 9:33 AM, Yongseok Koh:
> Subject: [PATCH 2/4] net/mlx5: replace IPC socket with EAL API
>
> Socket API is used for IPC in order for secondary process to acquire Verb
> command file descriptor. The FD is used to remap UAR address. The new
> multi-process APIs (rte_
Hi Koh,
Thursday, March 7, 2019 9:33 AM, Yongseok Koh:
> Subject: [PATCH 3/4] net/mlx5: rework PMD global data init
>
> There's more need to have PMD global data structure. It should be initialized
> once per a process regardless of how many PMD instances are probed.
> mlx5_init_once() is called
When mac_address update in bond_mode_8023ad_mac_address_update,
bonding port's mac_addr should update also.
Signed-off-by: Liang Zhang
---
drivers/net/bonding/rte_eth_bond_8023ad.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/bonding/rte_eth_bond_8023a
When mac_address update in bond_mode_8023ad_mac_address_update,
bonding port's mac_addr should update also.
Signed-off-by: Liang Zhang
---
drivers/net/bonding/rte_eth_bond_8023ad.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/net/bonding/rte_eth_bond_802
Hi
From: Stephen Hemminger
> The vdev_netvsc virtual driver that is used to do initialization on Hyper-
> V/Azure won't work without failsafe and tap device.
> If the related devices aren't present, it causes confusing errors later in
> initialization when it crafts devargs and attempts to send th
A bit of an old thread, but I just tried to update the OFED 4.5 as this
doc patch suggests and DPDK (19.02 or master) do not compile anymore for
mlx5?
Was the doc updated too soon or should I do something special to clean
4.4 and update 4.5?
I did install the OFED with --upsteam-libs and --d
Hi
From: Stephen Hemminger
> The return value from bus->find_device is a rte_device which is not safe to
> cast to a rte_vdev_device structure.
> It doesn't really matter since only being checked for NULL but static checkers
> might find a bug here.
>
Fix line is missing.
> Signed-off-by: Steph
The maximum packet length (max_pkt_len) from the firmware does not
include CRC, so do not subtract 4 when deriving the max MTU. This
change effectively increases the max MTU by 4B. Apps often assume max
MTU = max_rx_pkt_len - 14 (ethernet header), and attempt to set the
MTU to that value (i.e. set
print function name in IFPGA_RAWDEV_PMD_FUNC_TRACE.
The original code just print ">>", no other useful infomation is
printed.
A new line goes after every IFPGA log.
Fixes: ef1e8ede3da5 ("raw/ifpga: add Intel FPGA bus rawdev driver")
Cc: rosen...@intel.com
Cc: andy@intel.com
Cc: sta...@dpdk.org
On 3/14/2019 6:37 AM, Liron Himi wrote:
>
>
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, March 13, 2019 18:58
> To: Liron Himi
> Cc: dev@dpdk.org; Alan Winkowski
> Subject: Re: [PATCH v2] net/kni: calc mbuf&mtu according to given mb_pool
>
> On 3/10/2019 2:27 PM, Liro
Monday, March 11, 2019 9:58 PM, Yongseok Koh:
> Subject: Re: [PATCH] net/mlx5: fix packet inline on Tx queue wraparound
>
>
> > On Mar 10, 2019, at 12:14 AM, Shahaf Shuler
> wrote:
> >
> > Inlining a packet to WQE that cross the WQ wraparound, i.e. the WQE
> > starts on the end of the ring and e
On Wed, Mar 06, 2019 at 08:45:57AM -0600, Gage Eads wrote:
> This commit adds an implementation of the lock-free stack push, pop, and
> length functions that use __atomic builtins, for systems that benefit from
> the finer-grained memory ordering control.
>
> Signed-off-by: Gage Eads
Reviewed-by
On Wed, Mar 06, 2019 at 08:45:56AM -0600, Gage Eads wrote:
> This commit adds support for a lock-free (linked list based) stack to the
> stack API. This behavior is selected through a new rte_stack_create() flag,
> RTE_STACK_F_LF.
>
> The stack consists of a linked list of elements, each containin
On Wed, Mar 06, 2019 at 08:45:54AM -0600, Gage Eads wrote:
> stack_autotest performs positive and negative testing of the stack API, and
> exercises the push and pop datapath functions with all available lcores.
>
> Signed-off-by: Gage Eads
Reviewed-by: Olivier Matz
On Wed, Mar 06, 2019 at 08:45:52AM -0600, Gage Eads wrote:
> The rte_stack library provides an API for configuration and use of a
> bounded stack of pointers. Push and pop operations are MT-safe, allowing
> concurrent access, and the interface supports pushing and popping multiple
> pointers at a t
Hi Stephen,
I see failures in performance tests caused by this patch:
http://mails.dpdk.org/archives/test-report/2019-March/076705.html
http://mails.dpdk.org/archives/test-report/2019-March/076704.html
After applying your patch, the devices will not be probed:
'''
Zero length Ethernet device nam
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Saturday, March 2, 2019 10:43 AM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; sta...@dpdk.org
> Subject: [PATCH 3/3] eal: fix multi-process probe failure handling
>
> If probe fails in multi-process context, the
95 matches
Mail list logo
