Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: Tuesday, October 13, 2020 2:37 PM
> To: Bing Zhao
> Cc: Ori Kam ; ferruh.yi...@intel.com;
> arybche...@solarflare.com; m...@ashroe.eu; nhor...@tuxdriver.com;
> bernard.iremon...@intel.com; beilei.x...@intel.com;
> wenzhuo...
13/10/2020 03:13, Bing Zhao:
> From: Thomas Monjalon
> > 08/10/2020 14:05, Bing Zhao:
> > > In the release notes, 2 ports hairpin mode feature is added.
> > >
> > > In rte flow part, one suggestion is added to mention that metadata
> > > could be used to connect the hairpin RX and TX flows if the
Current implementation for PF RSS config wrap function has some
potential bugs about GTPU, e.g., same input set for GTPU inner and
non-TUN have different hash values, which should be same. Thus, we
use extra pre and post processing to re-config GTPU rules.
Signed-off-by: Junfeng Guo
---
drivers/
> -Original Message-
> From: dev On Behalf Of Ferruh Yigit
> Sent: Monday, October 12, 2020 4:33 PM
> To: Zhang, RobinX ; dev@dpdk.org
> Cc: Xing, Beilei ; Wu, Jingjing
> ;
> Yang, Qiming ; Yang, SteveX
>
> Subject: Re: [dpdk-dev] [PATCH 8/8] net/iavf: support check DD bit of a RX
> de
> -Original Message-
> From: Omkar Maslekar
> Sent: Monday, October 12, 2020 6:20 PM
> To: dev@dpdk.org
> Cc: bruce.richard...@intel.com; ciara.lof...@intel.com;
> omkar.masle...@intel.com; d...@linux.vnet.ibm.com; jer...@marvell.com;
> Ruifeng Wang ; Honnappa Nagarahalli
>
> Subject: [
From: Chengchang Tang
This patch adds checking whether the related Tx or Rx queue has been setup
in the queue-related API functions to avoid illegal address access. And
validity check of the queue_id is also added in the API functions
rte_eth_dev_rx_intr_enable and rte_eth_dev_rx_intr_disable.
S
> -Original Message-
> From: Bruce Richardson
> Sent: Monday, October 12, 2020 5:38 PM
> To: Guo, Jia
> Cc: Power, Ciara ; dev@dpdk.org; Xing, Beilei
>
> Subject: Re: [dpdk-dev] [PATCH v3 04/18] net/i40e: add checks for max SIMD
> bitwidth
>
> On Sat, Oct 10, 2020 at 02:07:15AM +,
Hi Akhil,
comments inline
W dniu 11.10.2020 o 00:11, Akhil Goyal pisze:
> The API ``rte_security_session_create`` takes only single
> mempool for session and session private data. So the
> application need to create mempool for twice the number of
> sessions needed and will also lead to wastage o
When async unregister function is invoked in certain vhost event
callbacks (e.g. vring state change), deadlock may occur due to
recursive spinlock acquire. This patch uses trylock() primitive in
the unregister API to avoid deadlock.
Fixes: 78639d54563a ("vhost: introduce async enqueue registration
Add check on the async vector buffer usage to prevent the buf overrun.
If the unused vector buffer is not sufficient to prepare for next
packet's iov creation, an async transfer will be triggered immediately
to free the vector buffer.
Fixes: 78639d54563a ("vhost: introduce async enqueue registrati
Current async ops allows check_completed_copies() callback to return
arbitrary number of async iov segments finished from backend async
devices. This design creates complexity for vhost to handle breaking
transfer of a single packet (i.e. transfer completes in the middle
of a async descriptor) and
Allocate async internal memory buffer by rte_malloc(), replacing array
declaration inside vq structure. Dynamic allocation can help to save
memory footprint when async path is not registered.
Signed-off-by: Patrick Fu
---
lib/librte_vhost/vhost.c | 69 ++--
li
This series applies optimization and fixes to the vhost
async data path.
v4:
- fix transfer error handling in async submit function (patch 1/4)
- add spinlock in async register function (patch 4/4)
- no changes in patch 2/4 & 3/4
v3:
- fix a typo in vhost error log (checkpatch warning)
- fix
> -Original Message-
> From: Burakov, Anatoly
> Sent: Monday, October 12, 2020 17:29
> To: Wang, Haiyue ; dev@dpdk.org
> Cc: Ma, Liang J ; Guo, Jia ; Hunt,
> David
> ; Ananyev, Konstantin ;
> jerinjac...@gmail.com;
> Richardson, Bruce ; tho...@monjalon.net;
> McDaniel, Timothy
> ; Eads,
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: Tuesday, October 13, 2020 5:31 AM
> To: Bing Zhao
> Cc: Ori Kam ; ferruh.yi...@intel.com;
> arybche...@solarflare.com; m...@ashroe.eu; nhor...@tuxdriver.com;
> bernard.iremon...@intel.com; beilei.x...@intel.com;
> wenzhuo...
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Tuesday, October 13, 2020 00:25
> To: Wang, Haiyue ; Power, Ciara
> ; dev@dpdk.org
> Cc: Zhao1, Wei ; Guo, Jia
> Subject: RE: [PATCH v3 11/18] net/ixgbe: add checks for max SIMD bitwidth
>
>
> > > -Original Message-
> > >
09/10/2020 14:39, Savinay Dharmappa:
> DPDK sched library allows runtime configuration of the pipe profiles
> to the pipes of the subport once scheduler hierarchy is constructed.
> However, to change the subport level bandwidth, existing hierarchy
> needs to be dismantled and whole process of bui
Add QLogic vendor id support for BCM57840 device ids.
Fixes: 9fb557035d90 ("bnx2x: enable PMD build")
Cc: sta...@dpdk.org
Reported-by: Souvik Dey
Signed-off-by: Rasesh Mody
---
drivers/net/bnx2x/bnx2x_ethdev.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/bnx2x/bnx2x_ethd
Hi Konstantin,
Appreciate your feedback.
>
>
> > Add scatter gather APIs to avoid intermediate memcpy. Use cases that
> > involve copying large amount of data to/from the ring can benefit from
> > these APIs.
> >
> > Signed-off-by: Honnappa Nagarahalli
> > ---
> > lib/librte_ring/mes
When a device is inserted into an existing BDF slot
that has not been probed, we must overwrite the old
PCI ID with the ID of the new function. Otherwise
we may not probe the function with the correct driver,
if at all.
Signed-off-by: Jim Harris
---
drivers/bus/pci/linux/pci.c | 4 +++-
1 file c
12/10/2020 22:58, Harris, James R:
>
> On 10/7/20, 8:06 AM, "Thomas Monjalon" wrote:
>
> Hi Jim,
>
> Sorry I see nobody reviewed your patch.
>
> Jim Harris wrote:
> > + memcpy(&dev2->id, &dev->id, sizeof(dev2->id));
> [...]
> > + memcmp(&dev2->id, &dev->id, sizeof(dev
12/10/2020 18:46, Ferruh Yigit:
> Queue stats are stored in 'struct rte_eth_stats' as array and array size
> is defined by 'RTE_ETHDEV_QUEUE_STAT_CNTRS' compile time flag.
>
> As a result of technical board discussion, decided to remove the queue
> statistics from 'struct rte_eth_stats' in the lon
08/10/2020 14:05, Bing Zhao:
> struct rte_eth_hairpin_conf {
> - uint16_t peer_count; /**< The number of peers. */
> + uint32_t peer_count:16; /**< The number of peers. */
Why not keeping uint16_t?
> + uint32_t tx_explicit:1; /**< Explicit TX flow rule mode. */
> + uint32_t manua
08/10/2020 14:05, Bing Zhao:
> In the release notes, 2 ports hairpin mode feature is added.
>
> In rte flow part, one suggestion is added to mention that metadata
> could be used to connect the hairpin RX and TX flows if the hairpin
> is working in explicit TX flow rule mode.
>
> In the testpmd c
09/10/2020 15:38, Ferruh Yigit:
> On 10/9/2020 2:37 PM, Min Hu (Connor) wrote:
> > Adding Connor as additional maintainer to bonding.
> >
> > Signed-off-by: Min Hu (Connor)
> > Reviewed-by: Wei Hu (Xavier)
>
> Acked-by: Ferruh Yigit
Applied, thanks
09/10/2020 09:14, Maxime Coquelin:
>
> On 10/1/20 12:22 PM, Chas Williams wrote:
> > rte_raw_cksum_mbuf can fail, so we should check to see if it
> > has. If so, return with an error.
> >
> > Fixes: 96cb6711939e ("net/virtio: support Rx checksum offload")
> >
> > Signed-off-by: Chas Williams <3c
On 10/7/20, 8:06 AM, "Thomas Monjalon" wrote:
Hi Jim,
Sorry I see nobody reviewed your patch.
Jim Harris wrote:
> + memcpy(&dev2->id, &dev->id, sizeof(dev2->id));
[...]
> + memcmp(&dev2->id, &dev->id, sizeof(dev2->id)))
Why using memcpy and memcmp instead of sim
08/10/2020 05:13, Sachin Saxena (OSS):
> From: Sachin Saxena
>
> The diagram to show dpaa2 drivers brief
> was missing in dpaa2.html file.
>
> fix a typo in encoding for a literal block
> to make it visible in generated doc file.
>
> Fixes: 846a8305f277 ("add DPAA2 NIC details")
> Cc: sta...@dp
12/10/2020 12:43, Dekel Peled:
> --- a/lib/librte_ip_frag/rte_ip_frag.h
> +++ b/lib/librte_ip_frag/rte_ip_frag.h
> +/* struct ipv6_extension_fragment moved to librte_net/rte_ip.h and renamed.
> */
> +#define ipv6_extension_fragment rte_ipv6_fragment_ext
This struct name did not have rte_ pre
12/10/2020 12:43, Dekel Peled:
> - * Note: IPv6 options are handled by dedicated pattern items, see
> - * RTE_FLOW_ITEM_TYPE_IPV6_EXT.
> + * Dedicated flags indicate existence of specific extension headers.
> + * Every type of extension header can use a dedicated pattern item, or
> + * the generic
Hi, Andrew
You are right - the code duplication of rte_eth_rx_queue_setup() code was large
and it did not look well indeed.
I've updated the code, now rte_eth_rx_queue_setup() and
rte_eth_rxseg_queue_setup()
share the underlying internal routine __rte_eth_rx_queue_setup().
Of course, there is s
The split feature for receiving packets was added to the mlx5
PMD, now Rx queue can receive the data to the buffers belonging
to the different pools and the memory of all the involved pool
must be registered for DMA operations in order to allow hardware
to store the data.
Signed-off-by: Viacheslav
The scatter-gather elements should be configured
accordingly to support the buffer split feature.
The application provides the desired settings for
the segments at the beginning of the packets and
PMD pads the buffer chain (if needed) with attributes
of last specified segment to accommodate the pac
Only the regular rx_burst routine is updated to support split,
because the vectorized ones does not support scatter and MPRQ
does not support split at all.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_rxq.c | 11 +--
drivers/net/mlx5/mlx5_rxtx.c | 3 ++-
2 files change
If Rx queue is configured with split feature the extended
setup with specified segment sizes and pool will be performed.
Signed-off-by: Viacheslav Ovsiienko
---
app/test-pmd/cmdline.c | 12 ++--
app/test-pmd/testpmd.c | 38 --
app/test-pmd/testpmd.h |
This patch add support for RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT
providing per queue configuration for this offload.
Signed-off-by: Viacheslav Ovsiienko
---
app/test-pmd/cmdline.c | 21 +++--
app/test-pmd/config.c | 9 +
2 files changed, 20 insertions(+), 10 deletions(-)
dif
The routine to provide Rx queue setup with specifying
extended receiving buffer description is added.
It allows application to specify desired segment
lengths, data position offsets in the buffer
and dedicated memory pool for each segment.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5
Add command line parameter:
--rxpkts=X[,Y]
Sets the length of segments to scatter packets on receiving if split
feature is engaged. Affects only the queues configured with split
offloads (currently BUFFER_SPLIT is supported only).
Add interactive mode command:
testpmd> set txpkts (x[,y]*)
Wher
The command line parameter --mbuf-size is updated, it can handle
the multiple values like the following:
--mbuf-size=2176,512,768,4096
specifying the creation the extra memory pools with the requested
mbuf data buffer sizes. If some buffer split feature is engaged
the extra memory pools can be us
The DPDK datapath in the transmit direction is very flexible.
An application can build the multi-segment packet and manages
almost all data aspects - the memory pools where segments
are allocated from, the segment lengths, the memory attributes
like external buffers, registered for DMA, etc.
In th
The DPDK datapath in the transmit direction is very flexible.
An application can build the multi-segment packet and manages
almost all data aspects - the memory pools where segments
are allocated from, the segment lengths, the memory attributes
like external buffers, registered for DMA, etc.
In th
On Fri, Oct 09, 2020 at 11:21:29AM +0100, Ciara Power wrote:
> External Email
>
> --
> Make is no longer supported for compiling DPDK, references are now
> removed in the documentation.
>
> Signed-off-by: Ciara Power
> Reviewed-
On 10/9/20 9:02 AM, Anatoly Burakov wrote:
Currently, it is not possible to check support for intrinsics that
are platform-specific, cannot be abstracted in a generic way, or do not
have support on all architectures. The CPUID flags can be used to some
extent, but they are only defined for the
On 10/9/20 9:02 AM, Anatoly Burakov wrote:
From: Liang Ma
Add two new power management intrinsics, and provide an implementation
in eal/x86 based on UMONITOR/UMWAIT instructions. The instructions
are implemented as raw byte opcodes because there is not yet widespread
compiler support for the
On Fri, Oct 09, 2020 at 11:21:27AM +0100, Ciara Power wrote:
> Make is no longer supported for compiling DPDK, references are now
> removed in the documentation.
Hi Ciara,
Thanks for updating the platform guides for octeontx and octeontx2.
All looks good for octeontx2 but for octeontx platf
>> Here instead of recreating each packet separately, we use clones counter
>> to resend the same mbuf to the line multiple times.
>>
> Do you have any numbers on how much performance improvement gained?
Hi Ferruh,
Yes, I'll post that in v1. In general, on our 100G device in default
configurati
On 10/12/20 3:19 AM, Omkar Maslekar wrote:
rte_cldemote is similar to a prefetch hint - in reverse. cldemote(addr)
enables software to hint to hardware that line is likely to be shared.
Useful in core-to-core communications where cache-line is likely to be
shared. ARM and PPC implementation is
> Hi Akhil,
>
> This was introduced in patch (24054e3640a2).
>
> Fixes: 24054e3640a2 ("test/crypto: use separate session mempools")
>
Applied to dpdk-next-crypto
Cc: sta...@dpdk.org
Thanks.
12/10/2020 12:43, Dekel Peled:
> This patch updates 20.11 release notes with the changes included in
> patches of this series:
> 1) MLX5 support of matching on IPv4/IPv6 fragmented/non-fragmented
>packets.
> 2) ABI change in ethdev struct rte_flow_item_ipv6.
>
> Signed-off-by: Dekel Peled
> A
Running dpdk-helloworld on Linux with lib numa present,
but no kernel support for NUMA (CONFIG_NUMA=n) causes
ret_service_init() to fail with EAL: error allocating
rte services array.
alloc_seg() calls get_mempolicy to verify that the allocation
has happened on the correct socket, but receives ENO
> This patch removes enumerators RTE_CRYPTO_CIPHER_LIST_END,
> RTE_CRYPTO_AUTH_LIST_END, RTE_CRYPTO_AEAD_LIST_END to prevent
> some problems that may arise when adding new crypto algorithms.
>
> Signed-off-by: Arek Kusztal
> ---
Acked-by: Akhil Goyal
Will squash both the patches while applying
Running dpdk-helloworld on Linux with lib numa present,
but no kernel support for NUMA (CONFIG_NUMA=n) causes
ret_service_init() to fail with EAL: error allocating
rte services array.
alloc_seg() calls get_mempolicy to verify that the allocation
has happened on the correct socket, but receives ENO
This patch removes enumerators RTE_CRYPTO_CIPHER_LIST_END,
RTE_CRYPTO_AUTH_LIST_END, RTE_CRYPTO_AEAD_LIST_END to prevent
some problems that may arise when adding new crypto algorithms.
Signed-off-by: Arek Kusztal
---
lib/librte_cryptodev/rte_crypto_sym.h | 36 ++-
1 file
This patch removes deprecation notice about removing
LIST_END enumerators from Cryptodev.
Signed-off-by: Arek Kusztal
---
doc/guides/rel_notes/deprecation.rst | 5 -
1 file changed, 5 deletions(-)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation.rst
inde
This patchset removes enumerators RTE_CRYPTO_CIPHER_LIST_END,
RTE_CRYPTO_AUTH_LIST_END, RTE_CRYPTO_AEAD_LIST_END from symmetric
crypto API to prevent some problems that may arise when adding
new crypto algorithms.
v2:
- combined patches into one series
- added removal of deprecation notice
v3:
- r
\ -vfio_spapr_unmap_walk(const struct rte_memseg_list *msl,
- const struct rte_memseg *ms, void *arg)
+vfio_spapr_size_walk(const struct rte_memseg_list *msl, void *arg)
{
- int *vfio_container_fd = arg;
+ struct spapr_size_walk_param *param = arg;
+ uint64_t max = (uint64_t
>> Subject: [PATCH v2 2/2] eventdev: update app and examples for new
>eventdev ABI
>>
>> Several data structures and constants changed, or were added,
>> in the previous patch. This commit updates the dependent
>> apps and examples to use the new ABI.
>>
>> Signed-off-by: Timothy McDaniel
With f
>This commit implements the eventdev ABI changes required by
>the DLB PMD.
>
>Signed-off-by: Timothy McDaniel
For octeontx/octeontx2
Acked-by: Pavan Nikhilesh
>---
> drivers/event/dpaa/dpaa_eventdev.c | 3 +-
> drivers/event/dpaa2/dpaa2_eventdev.c | 5 +-
> drivers/event/
Add new internal wrapper function for use by pci drivers as a
.probe function to attach to an event interface. Same as
rte_event_pmd_pci_probe, except the caller can specify the name.
Updated rte_event_pmd_pci_probe so as to not duplicate
code.
Signed-off-by: Timothy McDaniel
---
lib/librte_ev
Add new internal wrapper function for use by pci drivers as a
.probe function to attach to an event interface. Same as
rte_event_pmd_pci_probe, except the caller can specify the name.
Updated rte_event_pmd_pci_probe so as to not duplicate
code.
Signed-off-by: Timothy McDaniel
---
lib/librte_ev
On 10/9/2020 2:46 PM, Jiawei Wang wrote:
This patch set implement the flow-based traffic sampling.
The solution is introduced a new rte_flow action that will sample the incoming
traffic and send a duplicated traffic with the specified ratio to the
application, while the original packet will co
On 9/25/2020 10:07 AM, Igor Russkikh wrote:
When testing high performance numbers, it is often that CPU performance
limits the max values device can reach (both in pps and in gbps)
Here instead of recreating each packet separately, we use clones counter
to resend the same mbuf to the line multip
>
> The API ``rte_security_session_create`` takes only single
> mempool for session and session private data. So the
> application need to create mempool for twice the number of
> sessions needed and will also lead to wastage of memory as
> session private data need more memory compared to session
On Mon, Sep 28, 2020 at 2:01 AM Thomas Monjalon wrote:
> The option RTE_EAL_ALWAYS_PANIC_ON_ERROR was off by default,
> and not customizable with meson. It is completely removed.
>
> The function rte_dump_registers is a trace of the bare metal support
> era, and was not supported in userland. It i
rte_cldemote is similar to a prefetch hint - in reverse. cldemote(addr)
enables software to hint to hardware that line is likely to be shared.
Useful in core-to-core communications where cache-line is likely to be
shared. ARM and PPC implementation is provided with NOP and can be added
if any equiv
We are including this in rte_prefetch.h since it is the most closely
related code location.rte_cldemte is similar to a prefetch hint -in reverse
Omkar Maslekar (1):
eal: add cache-line demote support
app/test/test_prefetch.c | 4
doc/guides/rel_notes/release_20_11.rs
12/10/2020 19:13, Guy Kaneti:
> From: Thomas Monjalon
> > 12/10/2020 19:06, Guy Kaneti:
> > > From: Thomas Monjalon
> > > > 12/10/2020 13:31, g...@marvell.com:
> > > > > --- a/meson_options.txt
> > > > > +++ b/meson_options.txt
> > > > > +option('ree_compiler_sdk', type: 'string', value: '',
> >
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, October 12, 2020 8:11 PM
> To: Guy Kaneti
> Cc: or...@mellanox.com; Jerin Jacob Kollanukkaran ;
> Nithin Kumar Dabilpuram ; m...@ashroe.eu;
> nhor...@tuxdriver.com; bruce.richard...@intel.com;
> anatoly.bura...@intel.com; joh
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, October 12, 2020 20:03
> To: Slava Ovsiienko ; Andrew Rybchenko
>
> Cc: dev@dpdk.org; step...@networkplumber.org; ferruh.yi...@intel.com;
> olivier.m...@6wind.com; jerinjac...@gmail.com;
> maxime.coque...@redhat.com; david.march
12/10/2020 19:09, Guy Kaneti:
> From: Thomas Monjalon
> > 12/10/2020 13:31, g...@marvell.com:
> > > From: Guy Kaneti
> > >
> > > Added Marvell OCTEON TX2 regex guide, features and updated release
> > > notes.
> >
> > I think this patch should be merged with doc changes:
I meant with "code chang
On 10/12/20 8:03 PM, Thomas Monjalon wrote:
> 12/10/2020 18:38, Andrew Rybchenko:
>> On 10/12/20 7:19 PM, Viacheslav Ovsiienko wrote:
>>> int
>>> +rte_eth_rxseg_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
>>> + uint16_t nb_rx_desc, unsigned int socket_id,
>>> +
12/10/2020 19:06, Guy Kaneti:
> From: Thomas Monjalon
> > 12/10/2020 13:31, g...@marvell.com:
> > > --- a/meson_options.txt
> > > +++ b/meson_options.txt
> > > +option('ree_compiler_sdk', type: 'string', value: '',
> > > + description: 'path to REE compiler SDK optional library for regex
> > devic
On 10/9/2020 5:16 PM, Ferruh Yigit wrote:
If the infinite Rx argument ('infinite_rx') is provided a ring is
allocated and filled in the '.rx_queue_setup' dev_ops.
Later this ring freed in the '.dev_close' dev_ops.
If the 'infinite_rx' provided and '.dev_close' called before
'.rx_queue_setup', th
Hi,
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, October 12, 2020 5:39 PM
> To: Guy Kaneti
> Cc: or...@mellanox.com; Jerin Jacob Kollanukkaran ;
> Nithin Kumar Dabilpuram ; m...@ashroe.eu;
> nhor...@tuxdriver.com; bruce.richard...@intel.com;
> anatoly.bura...@intel.com; j
>
>
> > > > > Hi Honnappa,
> > > > >
> > > > > From a quick walkthrough, I have some questions/comments, please
> > > > > see below.
> > > > Hi Olivier, appreciate your input.
> > > >
> > > > >
> > > > > On Tue, Oct 06, 2020 at 08:29:05AM -0500, Honnappa Nagarahalli wrote:
> > > > > > Add sc
Hi
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, October 12, 2020 5:33 PM
> To: Guy Kaneti
> Cc: or...@mellanox.com; Jerin Jacob Kollanukkaran ;
> Nithin Kumar Dabilpuram ; m...@ashroe.eu;
> nhor...@tuxdriver.com; bruce.richard...@intel.com;
> anatoly.bura...@intel.com; jo
12/10/2020 18:38, Andrew Rybchenko:
> On 10/12/20 7:19 PM, Viacheslav Ovsiienko wrote:
> > int
> > +rte_eth_rxseg_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
> > + uint16_t nb_rx_desc, unsigned int socket_id,
> > + const struct rte_eth_rxconf *rx_con
On 10/10/2020 9:09 AM, Thomas Monjalon wrote:
09/10/2020 22:32, Ferruh Yigit:
On 10/6/2020 9:33 AM, Olivier Matz wrote:
On Mon, Oct 05, 2020 at 01:23:08PM +0100, Ferruh Yigit wrote:
On 9/28/2020 4:43 PM, Stephen Hemminger wrote:
On Mon, 28 Sep 2020 17:24:26 +0200
Thomas Monjalon wrote:
28/0
On Mon, 12 Oct 2020 17:46:01 +0100
Ferruh Yigit wrote:
> Queue stats will be removed from basic stats to xstats.
>
> It will be PMDs responsibility to fill queue stats based on number of
> queues they have.
>
> Until all PMDs implement the xstats, a temporary
> 'RTE_ETH_DEV_QUEUE_STATS_IN_XSTAT
12/10/2020 17:56, Ananyev, Konstantin:
> > From: Ananyev, Konstantin
> > > > 12/10/2020 11:56, Slava Ovsiienko:
> > > > > We have two approaches how to specify multiple segments to split Rx
> > > packets:
> > > > > 1. update queue configuration structure 2. introduce new
> > > > > rx_queue_setup_e
Queue stats are stored in 'struct rte_eth_stats' as array and array size
is defined by 'RTE_ETHDEV_QUEUE_STAT_CNTRS' compile time flag.
As a result of technical board discussion, decided to remove the queue
statistics from 'struct rte_eth_stats' in the long term.
Instead PMDs should represent the
Queue stats will be removed from basic stats to xstats.
It will be PMDs responsibility to fill queue stats based on number of
queues they have.
Until all PMDs implement the xstats, a temporary
'RTE_ETH_DEV_QUEUE_STATS_IN_XSTATS' device flag created. PMDs switched
to the xstats should set this fla
On 10/12/20 7:19 PM, Viacheslav Ovsiienko wrote:
> The DPDK datapath in the transmit direction is very flexible.
> An application can build the multi-segment packet and manages
> almost all data aspects - the memory pools where segments
> are allocated from, the segment lengths, the memory attribut
> > -Original Message-
> > From: Ananyev, Konstantin
> > Sent: Monday, October 12, 2020 17:09
> > To: Wang, Haiyue ; Power, Ciara
> > ; dev@dpdk.org
> > Cc: Zhao1, Wei ; Guo, Jia
> > Subject: RE: [PATCH v3 11/18] net/ixgbe: add checks for max SIMD bitwidth
> >
> > > > > > From: Power,
The DPDK datapath in the transmit direction is very flexible.
An application can build the multi-segment packet and manages
almost all data aspects - the memory pools where segments
are allocated from, the segment lengths, the memory attributes
like external buffers, registered for DMA, etc.
In th
> Add scatter gather APIs to avoid intermediate memcpy. Use cases
> that involve copying large amount of data to/from the ring
> can benefit from these APIs.
>
> Signed-off-by: Honnappa Nagarahalli
> ---
> lib/librte_ring/meson.build| 3 +-
> lib/librte_ring/rte_ring_elem.h| 1
If Rx queue is configured with split feature the extended
setup with specified segment sizes and pool will be performed.
Signed-off-by: Viacheslav Ovsiienko
---
app/test-pmd/cmdline.c | 12 ++--
app/test-pmd/testpmd.c | 38 --
app/test-pmd/testpmd.h |
Add command line parameter:
--rxpkts=X[,Y]
Sets the length of segments to scatter packets on receiving if split
feature is engaged. Affects only the queues configured with split
offloads (currently BUFFER_SPLIT is supported only).
Add interactive mode command:
testpmd> set txpkts (x[,y]*)
Wher
The DPDK datapath in the transmit direction is very flexible.
An application can build the multi-segment packet and manages
almost all data aspects - the memory pools where segments
are allocated from, the segment lengths, the memory attributes
like external buffers, registered for DMA, etc.
In th
The routine to provide Rx queue setup with specifying
extended receiving buffer description is added.
It allows application to specify desired segment
lengths, data position offsets in the buffer
and dedicated memory pool for each segment.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5
Only the regular rx_burst routine is updated to support split,
because the vectorized ones does not support scatter and MPRQ
does not support split at all.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_rxq.c | 11 +--
drivers/net/mlx5/mlx5_rxtx.c | 3 ++-
2 files change
The split feature for receiving packets was added to the mlx5
PMD, now Rx queue can receive the data to the buffers belonging
to the different pools and the memory of all the involved pool
must be registered for DMA operations in order to allow hardware
to store the data.
Signed-off-by: Viacheslav
The command line parameter --mbuf-size is updated, it can handle
the multiple values like the following:
--mbuf-size=2176,512,768,4096
specifying the creation the extra memory pools with the requested
mbuf data buffer sizes. If some buffer split feature is engaged
the extra memory pools can be us
The scatter-gather elements should be configured
accordingly to support the buffer split feature.
The application provides the desired settings for
the segments at the beginning of the packets and
PMD pads the buffer chain (if needed) with attributes
of last specified segment to accommodate the pac
This patch add support for RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT
providing per queue configuration for this offload.
Signed-off-by: Viacheslav Ovsiienko
---
app/test-pmd/cmdline.c | 21 +++--
app/test-pmd/config.c | 9 +
2 files changed, 20 insertions(+), 10 deletions(-)
dif
> Subject: [dpdk-dev v13 0/4] cryptodev: add raw data-path APIs
>
> The Crypto Raw data-path APIs are a set of APIs designed to enable external
> libraries/applications to leverage the cryptographic processing provided by
> DPDK crypto PMDs through the cryptodev API but in a manner that is not
> d
> -Original Message-
> From: Andrew Rybchenko
> Sent: Monday, October 12, 2020 19:04
> To: NBU-Contact-Thomas Monjalon ;
> ferruh.yi...@intel.com; Slava Ovsiienko
> Cc: dev@dpdk.org; step...@networkplumber.org; Shahaf Shuler
> ; olivier.m...@6wind.com; jerinjac...@gmail.com;
> maxime.coqu
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, October 12, 2020 17:09
> To: Wang, Haiyue ; Power, Ciara
> ; dev@dpdk.org
> Cc: Zhao1, Wei ; Guo, Jia
> Subject: RE: [PATCH v3 11/18] net/ixgbe: add checks for max SIMD bitwidth
>
> > > > > From: Power, Ciara
> > > > > Se
On 10/12/20 6:14 PM, Thomas Monjalon wrote:
> 12/10/2020 11:56, Slava Ovsiienko:
>> Hi, Andrew
>>
>> Thank you for the comments.
>>
>> We have two approaches how to specify multiple segments to split Rx packets:
>> 1. update queue configuration structure
>> 2. introduce new rx_queue_setup_ex() rout
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, October 12, 2020 18:56
> To: Slava Ovsiienko ; NBU-Contact-Thomas
> Monjalon ; Andrew Rybchenko
> ; Yigit, Ferruh
> Cc: dev@dpdk.org; step...@networkplumber.org; Shahaf Shuler
> ; olivier.m...@6wind.com; jerinjac...@gmail.co
1 - 100 of 221 matches
Mail list logo
