在 2020/4/27 21:27, Ferruh Yigit 写道:
On 4/27/2020 1:49 PM, Andrew Rybchenko wrote:
On 4/27/20 3:34 PM, Lijun Ou wrote:
When rte api checks the Rx RSS distribution is enable but the RSS
hash is disabled, it will return an error.
Signed-off-by: Lijun Ou
---
lib/librte_ethdev/rte_ethdev.c |
From: Alvin Zhang
Enable detach device on secondary process.
Fixes: b9eee2cb8c29 (e1000: support port hotplug)
Cc: bernard.iremon...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Alvin Zhang
---
drivers/net/e1000/em_ethdev.c | 2 +-
drivers/net/e1000/igb_ethdev.c | 4 ++--
2 files changed, 3
在 2020/4/27 20:49, Andrew Rybchenko 写道:
On 4/27/20 3:34 PM, Lijun Ou wrote:
When rte api checks the Rx RSS distribution is enable but the RSS
hash is disabled, it will return an error.
Signed-off-by: Lijun Ou
---
lib/librte_ethdev/rte_ethdev.c | 11 +++
1 file changed, 11 inserti
There several alignment warnings when including rte_memcpy header file
externally like OVS for x86.
Signed-off-by: Haiyue Wang
---
lib/librte_eal/x86/include/rte_memcpy.h | 4
1 file changed, 4 insertions(+)
diff --git a/lib/librte_eal/x86/include/rte_memcpy.h
b/lib/librte_eal/x86/include
> -Original Message-
> From: dev On Behalf Of Lukasz Wojciechowski
> Sent: Tuesday, April 28, 2020 9:22 AM
> To: Harry van Haaren ; Jerin Jacob
>
> Cc: dev@dpdk.org; l.wojciec...@partner.samsung.com; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] eal: fix lcore state bug
>
> The rte_servi
> -Original Message-
> From: Zhao1, Wei
> Sent: Wednesday, April 29, 2020 10:04 AM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Xing, Beilei ;
> maxime.le...@6wind.com
> Subject: [PATCH v4 0/3] fix i40e bug for flow filter
>
> fix i40e bug for flow filter and add comment in doc.
>
> v2:
In server mode, virtio-user inits under the assumption that vhost-user
supports a list of features. However, this could be problematic when
in_order feature is negotiated but not supported by vhost-user when
enables dequeue_zero_copy later.
Add handling when vhost-user enables dequeue_zero_copy as
Now this feature is no longer supported by kernel side, so remove the
intel PMD examples to avoid confusion.
Signed-off-by: Xiaolong Ye
---
doc/guides/howto/flow_bifurcation.rst | 227 --
doc/guides/howto/img/ixgbe_bifu_queue_idx.svg | 101
2 files changed, 328 d
> -Original Message-
> From: dev On Behalf Of Stephen Hemminger
> Sent: Tuesday, April 28, 2020 7:28 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger
> Subject: [dpdk-dev] [PATCH 1/4] net/vmbus: add missing barrier
>
> The check for event ring being empty needs a barrier to avoid any over
Tested-by:zhang,xi
Regards,
Xie Wei
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Louise Kilheeney
Sent: Monday, April 27, 2020 10:58 PM
To: dev@dpdk.org
Cc: Kilheeney, Louise ; sta...@dpdk.org
Subject: [dpdk-dev] [PATCH v2] examples/l2fwd-keepalive: fix packet
fix i40e bug for flow filter and add comment in doc.
v2:
add more comment in git log.
v3:
update git log.
v4:
update doc info.
Wei Zhao (3):
net/i40e: fix FDIR issue for ARP packets
doc: input set requirement of each pctype for FDIR
net/i40e: remove teardown when flush FDIR filter
doc/
Add input set requirement info to i40e doc.
Bugzilla ID: 403
Signed-off-by: Wei Zhao
---
doc/guides/nics/i40e.rst | 7 +++
1 file changed, 7 insertions(+)
diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst
index 416b3904e..f085a357c 100644
--- a/doc/guides/nics/i40e.rst
+++ b/
Currently, flow "pattern eth type is 0x0806 / end actions mark id
0x86 / rss / end" can't be created successfully. FDIR parser
shouldn't deny RTE_ETHER_TYPE_ARP since ARP packets will be
parsed as PCTYPE_L2_PAYLOAD. This patch fixes the issue.
Bugzilla ID: 402
Fixes: 42044b69c67d ("net/i40e: suppo
When we flush FDIR filter, we can not call i40e_fdir_teardown()
function as it will free vsi used for FDIR, then the vsi->base_queue
will be freed from pf->qp_pool, but vsi->base_queue can only get
once when do dev init in i40e_pf_setup(). If we free it, it will
never be alloc again.
Bugzilla ID:
Currently, there is no flow aging check and age-out event callback
mechanism for mlx5 driver, this patch implements it. It's included:
- Splitting the current counter container to aged or no-aged container
since reducing memory consumption. Aged container will allocate extra
memory to save the
Currently, the counter pool needs 512 ext-counter memory for no batch
counters, it's allocated separately by once, behind the 512 basic-counter
memory. This is not easy to get ext-counter pointer by corresponding
basic-counter pointer. This is also no easy for expanding some other
potential additio
Those patches implement flow aging for mlx5 driver. First patch is to modify
the current additional memory allocation for counter, so that it's easy to
get every counter additional memory location by using offsetting. Second patch
implements aging check and age-out event callback mechanism for mlx5
> -Original Message-
> From: dev On Behalf Of Suanming Mou
> Sent: Tuesday, April 28, 2020 5:14 PM
> To: Matan Azrad ; Shahaf Shuler
> ; Viacheslav Ovsiienko
>
> Cc: dev@dpdk.org; rasl...@mellanox.com; Lijian Zhang
>
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix indexed pool bitmap initi
Acked-by: Zhang,Alvin
> -Original Message-
> From: Zhao1, Wei
> Sent: Monday, April 27, 2020 9:29 AM
> To: dev@dpdk.org
> Cc: Guo, Jia ; Zhang, AlvinX ;
> Lu, Wenzhuo ; Ananyev, Konstantin
> ; Zhao1, Wei
> Subject: [PATCH] maintainers: update for Intel ixgbe/igb/igc
>
> Replace Wenzhuo
On 4/28/2020 4:50 PM, Dmitry Kozlyuk wrote:
Basic memory management supports core libraries and PMDs operating in
IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
IOVAs of hugepages allocated from user-mode. Multi-process mode is not
implemented and is forcefully disabled at st
> -Original Message-
> From: Stephen Hemminger
> Sent: Monday, April 27, 2020 4:16 PM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Wang, Yipeng1
> ; Gobriel, Sameh ;
> Richardson, Bruce
> Subject: [PATCH v3 2/4] hash: check flags on creation
>
> All API's should check that they support t
Thanks for your reply.
Using rte_hash iterate and delete keys is to free the related data's memory.
There are two reasons why rte_hash_reset() is not properly:
1) the reset function just clear all keys, the key's related data are leaked.
2) In some cases, I don't need delete all keys. Just some
This is sent by mistake, please ignore.
> -Original Message-
> From: Liu, Yong
> Sent: Wednesday, April 29, 2020 9:01 AM
> To: maxime.coque...@redhat.com; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Liu, Yong
> Subject: [PATCH v4 2/2] vhost: utilize dpdk dynamic memory allocator
Replace dynamic memory allocator with dpdk memory allocator.
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index bd1be0104..79fcb9d19 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.
If Tx zero copy enabled, gpa to hpa mapping table is updated one by
one. This will harm performance when guest memory backend using 2M
hugepages. Now utilize binary search to find the entry in mapping
table, meanwhile set the threshold to 256 entries for linear search.
Signed-off-by: Marvin Liu
Replace dynamic memory allocator with dpdk memory allocator.
Signed-off-by: Marvin Liu
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index bd1be0104..79fcb9d19 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -191,7 +191,7 @@ vhost_ba
Replace dynamic memory allocator with dpdk memory allocator.
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index bd1be0104..79fcb9d19 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.
If Tx zero copy enabled, gpa to hpa mapping table is updated one by
one. This will harm performance when guest memory backend using 2M
hugepages. Now utilize binary search to find the entry in mapping
table, meanwhile set the threshold to 256 entries for linear search.
Signed-off-by: Marvin Liu
From: Ivan Dyukov
This patch adds a support of VIRTIO_NET_F_SPEED_DUPLEX feature
for virtio driver.
There are two ways to specify speed of the link:
'speed' devarg
negotiate speed from qemu via VIRTIO_NET_F_SPEED_DUPLEX
The highest priority is devarg. If devarg is not specified,
drivers tr
On 2020-04-28 12:11 GMT+0300 tal...@mellanox.com wrote:
[snip]
> + switch (dev->kdrv) {
> + case RTE_KDRV_NONE:
> + /* Get NUMA node using DEVPKEY_Device_Numa_Node */
> + bResult = SetupDiGetDevicePropertyW(hDevInfo, pDeviceInfoData,
> + &DEVPKEY_
The mp action resources in malloc should be cleaned up via
rte_eal_cleanup.
Signed-off-by: Stephen Hemminger
Acked-by: Anatoly Burakov
---
lib/librte_eal/common/malloc_heap.c | 6 ++
lib/librte_eal/common/malloc_heap.h | 3 +++
lib/librte_eal/common/malloc_mp.c | 12
lib/li
When rte_eal_cleanup is called the rte_mp_action for VFIO
should be freed.
Fixes: edf73dd33072 ("ipc: handle unsupported IPC in action register")
Cc: anatoly.bura...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
Acked-by: Anatoly Burakov
---
lib/librte_eal/linux/eal.c
When rte_eal_cleanup is called, hotplug should unregister the
resources associated with the multi-process server.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/hotplug_mp.c | 5 +
lib/librte_eal/common/hotplug_mp.h | 6 ++
lib/librte_eal/linux/eal.c | 1 +
3 files ch
When rte_eal_cleanup is called, all control threads should exit.
For the mp thread, this best handled by closing the mp_socket
and letting the thread see that.
This also fixes potential problems where the mp_socket gets
another hard error, and the thread runs away repeating itself
by reading the s
When rte_eal_cleanup is called, free all the memory
associated with dynamic log levels and types.
Fixes: c1b5fa94a46f ("eal: support dynamic log types")
Cc: olivier.m...@6wind.com
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_log.c | 21 -
1 file chang
When rte_eal_cleanup is called it should stop all the child threads
and close the pipes between threads.
Signed-off-by: Stephen Hemminger
Acked-by: Aaron Conole
---
lib/librte_eal/linux/eal.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/lib/librte_eal/linux/eal.c b/lib/lib
When rte_eal_cleanup is called, free all the memory
associated with dynamic log levels and types.
Fixes: c1b5fa94a46f ("eal: support dynamic log types")
Cc: olivier.m...@6wind.com
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/eal_private.h | 7 +++
lib/librte_eal/freebsd/eal.c
When application calls rte_eal_cleanup on shutdown,
the DPDK log should be closed and cleaned up.
Fixes: af75078fece3 ("first public release")
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_log.c | 12
lib/librte_eal/common/eal_private.h| 13 +
Started using valgrind with DPDK, and there are lots of leftover
memory and file descriptors. This makes it hard to find application
leaks versus DPDK leaks.
The DPDK has a function that applications can use to tell it
to cleanup resources on shutdown (rte_eal_cleanup). But the
current coverage of
This patch misses two things:
1. Documentation on pci_map_resource() mentions MAP_FAILED,
while rte_mem_map() returns NULL on failure.
2. Code in drivers/bus/pci/linux passes MAP_FIXED to pci_map_resource(),
which should be changed to corresponding RTE_MAP_FORCE_ADDRESS flag
(it is renam
On 2020-04-17 13:24 GMT+0100 Burakov, Anatoly wrote:
[snip]
> > +/** Behavior on file locking conflict. */
> > +enum eal_flock_mode {
> > + EAL_FLOCK_WAIT, /**< Wait until the file gets unlocked to lock it. */
> > + EAL_FLOCK_RETURN /**< Return immediately if the file is locked. */
> > +};
>
Basic memory management supports core libraries and PMDs operating in
IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
IOVAs of hugepages allocated from user-mode. Multi-process mode is not
implemented and is forcefully disabled at startup.
Signed-off-by: Dmitry Kozlyuk
---
co
Add hugepages discovery ("large pages" in Windows terminology)
and update documentation for required privilege setup. Only 2MB
hugepages are supported and their number is estimated roughly
due to the lack or unstable status of suitable OS APIs.
Signed-off-by: Dmitry Kozlyuk
---
config/meson.buil
1. Map CPU cores to their respective NUMA nodes as reported by system.
2. Support systems with more than 64 cores (multiple processor groups).
3. Fix magic constants, styling issues, and compiler warnings.
4. Add EAL private function to map DPDK socket ID to NUMA node number.
Fixes: 53ffd9f080fc (
Limited version imported previously lacks at least SLIST macros.
Import a complete file from FreeBSD, since its license exception is
already approved by Technical Board.
Signed-off-by: Dmitry Kozlyuk
---
lib/librte_eal/windows/include/sys/queue.h | 663 +++--
1 file changed, 601
All supported OS create memory segment lists (MSL) and reserve VA space
for them in a nearly identical way. Move common code into EAL private
functions to reduce duplication.
Signed-off-by: Dmitry Kozlyuk
---
lib/librte_eal/common/eal_common_memory.c | 54 ++
lib/librte_eal/commo
Introduce OS-independent wrappers for memory management operations used
across DPDK and specifically in common code of EAL:
* rte_mem_map()
* rte_mem_unmap()
* rte_get_page_size()
* rte_mem_lock()
Windows uses different APIs for memory mapping and reservation, while
Unices reserve memory by mappi
Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
Enum rte_page_sizes has members valued above this limit, which get
wrapped to zero, resulting in compilation error (duplicate values in
enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
Remove rte_page_size
EAL common code uses file locking and truncation. Introduce
OS-independent wrappers in order to support both Linux/FreeBSD
and Windows:
* eal_file_lock: lock or unlock an open file.
* eal_file_truncate: enforce a given size for an open file.
Wrappers follow POSIX semantics, but interface is not P
Note: symbols and release notes updated for v20.05, despite this patch
now targeting v20.08, because proper sections don't yet exist.
This patchset implements basic MM with the following features:
* Hugepages are dynamically allocated in user-mode.
* Only 2MB hugepages are supported.
* IOVA
The mp action resources in malloc should be cleaned up via
rte_eal_cleanup.
Signed-off-by: Stephen Hemminger
Acked-by: Anatoly Burakov
---
lib/librte_eal/common/malloc_heap.c | 6 ++
lib/librte_eal/common/malloc_heap.h | 3 +++
lib/librte_eal/common/malloc_mp.c | 12
lib/li
When rte_eal_cleanup is called the rte_mp_action for VFIO
should be freed.
Fixes: edf73dd33072 ("ipc: handle unsupported IPC in action register")
Cc: anatoly.bura...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
Acked-by: Anatoly Burakov
---
lib/librte_eal/linux/eal.c
When rte_eal_cleanup is called, hotplug should unregister the
resources associated with the multi-process server.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/hotplug_mp.c | 5 +
lib/librte_eal/common/hotplug_mp.h | 6 ++
lib/librte_eal/linux/eal.c | 1 +
3 files ch
When rte_eal_cleanup is called, free all the memory
associated with dynamic log levels and types.
Fixes: c1b5fa94a46f ("eal: support dynamic log types")
Cc: olivier.m...@6wind.com
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_log.c | 21 -
1 file chang
When rte_eal_cleanup is called, free all the memory
associated with dynamic log levels and types.
Fixes: c1b5fa94a46f ("eal: support dynamic log types")
Cc: olivier.m...@6wind.com
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/eal_private.h | 7 +++
lib/librte_eal/freebsd/eal.c
When rte_eal_cleanup is called it should stop all the child threads
and close the pipes between threads.
Signed-off-by: Stephen Hemminger
Acked-by: Aaron Conole
---
lib/librte_eal/linux/eal.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/lib/librte_eal/linux/eal.c b/lib/lib
When application calls rte_eal_cleanup on shutdown,
the DPDK log should be closed and cleaned up.
Fixes: af75078fece3 ("first public release")
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/eal_common_log.c | 12
lib/librte_eal/common/eal_private.h| 13 +
When rte_eal_cleanup is called, all control threads should exit.
For the mp thread, this best handled by closing the mp_socket
and letting the thread see that.
This also fixes potential problems where the mp_socket gets
another hard error, and the thread runs away repeating itself
by reading the s
Started using valgrind with DPDK, and there are lots of leftover
memory and file descriptors. This makes it hard to find application
leaks versus DPDK leaks.
The DPDK has a function that applications can use to tell it
to cleanup resources on shutdown (rte_eal_cleanup). But the
current coverage of
Please, ignore this patch and pull the patches from Ori Kam and David
Christensen
https://mails.dpdk.org/archives/dev/2020-April/165783.html
Thanks,
Thinh Tran
On 4/28/2020 11:52 AM, Thinh Tran wrote:
The altivec.h on PPC64 breaks boolean type:
In file included from ../lib/librte_mempool/rte_
Hi Jerry,
Few questions inline.
> Subject: [dpdk-dev] [PATCH] lib/librte_hash: add rte_hash_del_key_fixed
> without compact
>
> The keys idx are stored in rte_hash main bucket key slots and extend bucket
> key stots.
> We iterate every no empty Keys in h->buckets and h->buckets_ext from
On Mon, 24 Feb 2020 13:01:30 -0800
Stephen Hemminger wrote:
> Simple script to look for drivers and scripts that
> are missing requires SPDX header.
>
> Update the contribution guidelines to indicate that SPDX license
> identfier is required for this project.
>
> Signed-off-by: Stephen Hemminge
On Tue, 28 Apr 2020 17:39:24 +0100
Ray Kinsella wrote:
> > +
> > /* The last item */
> > RTE_CPUFLAG_NUMFLAGS, /**< This should always be the
> > last! */
> > };
These kind of enums break API's. We should remove them all in 20.11.
28/04/2020 20:11, Laatz, Kevin:
> > > --- a/devtools/libabigail.abignore
> > > +++ b/devtools/libabigail.abignore
> >
> > Kevin - you still have the surpession.
> > I am testing locally with 1.7.1, and it doesn't complain when I disable the
> > supression.
> > Are you seeing something different?
>
Fixes: 725f5dd0bfb5 ("net/mlx5: fix build on PPC64")
Signed-off-by: Ori Kam
---
There are a couple of other uses that should be covered in the patch:
diff --git a/drivers/net/i40e/i40e_rxtx_vec_altivec.c
b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
index 5fa92bf92..72bd410fc 100644
--- a/driv
> > ---
> > devtools/libabigail.abignore | 5 +
> > lib/librte_eal/x86/include/rte_cpuflags.h | 19 +++
> > lib/librte_eal/x86/rte_cpuflags.c | 18 ++
> > 3 files changed, 42 insertions(+)
> >
> > diff --git a/devtools/libabigail.abignore
> -Original Message-
> From: Thomas Monjalon
> Sent: Tuesday, April 28, 2020 4:30 PM
> To: Dumitrescu, Cristian
> Cc: Yigit, Ferruh ; Nithin Dabilpuram
> ; Singh, Jasvinder ;
> Andrew Rybchenko ; dev@dpdk.org;
> jer...@marvell.com; kka...@marvell.com; Nithin Dabilpuram
> ; Kinsella, Ra
> -Original Message-
> From: Liu, Yong
> Sent: Tuesday, April 28, 2020 9:01 PM
> To: 'Maxime Coquelin' ; Ye, Xiaolong
> ; Wang, Zhihong
> Cc: dev@dpdk.org
> Subject: RE: [PATCH v10 6/9] net/virtio: add vectorized packed ring Rx path
>
>
>
> > -Original Message-
> > From: Maxi
The altivec.h on PPC64 breaks boolean type:
In file included from ../lib/librte_mempool/rte_mempool_trace_fp.h:18:0,
from ../lib/librte_mempool/rte_mempool.h:54,
from ../lib/librte_mbuf/rte_mbuf.h:38,
from ../lib/librte_net/rte_ether.h:23,
On 28/04/2020 13:40, Kevin Laatz wrote:
> This patch adds CPU flags which will enable the detection of ISA
> features available on more recent x86 based CPUs.
>
> The CPUID leaf information can be found in
> Table 1-2. "Information Returned by CPUID Instruction" of this document:
> https://soft
On 4/26/20 2:07 PM, Matan Azrad wrote:
> Since a virtq configuration may be changed in disable state it is better to
> recreate a virtq becoming enabled.
> This series adding this behaviour to the mlx5 driver for vDPA.
>
> v2:
> 1. Address Maxime comments:
> - returning -1 for out of r
On 4/24/20 5:39 AM, Joyce Kong wrote:
> This patchset replaces the two-way barriers with C11 one-way barriers
> for split vring idx, when the frontend and backend are implemented
> in software.
>
> By doing PVP benchmarking, the test result of 2c1q showed the throughput
> increased 20% with the
On 4/23/20 6:54 PM, Phil Yang wrote:
> The rarp packet broadcast flag is synchronized with rte_atomic_XX APIs
> which is a full barrier, DMB, on aarch64. This patch optimized it with
> c11 atomic one-way barrier.
>
> Signed-off-by: Phil Yang
> Reviewed-by: Gavin Hu
> Reviewed-by: Honnappa Nag
On 4/21/20 10:59 AM, Roland Qi wrote:
> In process_slave_message_reply(), there is a
> possibility that receiving a peer close
> message instead of a real message response.
>
> this patch targeting to handle the peer close
> scenario and report the correct error message.
>
> Signed-off-by: Rol
On 4/20/20 9:53 AM, Maxime Coquelin wrote:
> The goal is to make the table more readable.
>
> Mark as partially supported features that are supported in
> the genric Virtio driver but not in the vectorized ones.
>
> Suggested-by: Thomas Monjalon
> Signed-off-by: Maxime Coquelin
> ---
> doc/
On 2/28/20 4:32 PM, Jin Yu wrote:
> Decrease the code and make it easier to read. It's
> useful for understanding the inflight APIs and how
> packed ring works. Update the RST because the packed
> ring patch has been merged to QEMU master and ring_packed
> parameter changes to packed.
>
> Fixes
> -Original Message-
> From: Maxime Coquelin
> Sent: Tuesday, April 28, 2020 11:40 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Honnappa Nagarahalli
> ; jer...@marvell.com
> Subject: Re: [PATCH v10 6/9] net/virtio: add vectorized packed ring Rx path
>
>
>
28/04/2020 17:04, Luca Boccassi:
> On Tue, 2020-04-28 at 15:45 +0100, Bruce Richardson wrote:
> > On Tue, Apr 28, 2020 at 03:06:20PM +0100, Ferruh Yigit wrote:
> > > On 4/27/2020 5:59 PM, Jerin Jacob wrote:
> > > > On Mon, Apr 27, 2020 at 10:19 PM Ferruh Yigit
> > > > wrote:
> > > > > On 4/27/202
On 28/04/2020 15:45, Bruce Richardson wrote:
> On Tue, Apr 28, 2020 at 03:06:20PM +0100, Ferruh Yigit wrote:
>> On 4/27/2020 5:59 PM, Jerin Jacob wrote:
>>> On Mon, Apr 27, 2020 at 10:19 PM Ferruh Yigit
>>> wrote:
On 4/27/2020 5:29 PM, Jerin Jacob wrote:
> On Mon, Apr 27, 2020 at
On 4/28/20 5:35 PM, Liu, Yong wrote:
>
>
>> -Original Message-
>> From: Maxime Coquelin
>> Sent: Tuesday, April 28, 2020 10:50 PM
>> To: Liu, Yong ; Ye, Xiaolong ;
>> Wang, Zhihong
>> Cc: dev@dpdk.org; Honnappa Nagarahalli
>> ; jer...@marvell.com
>> Subject: Re: [PATCH v10 6/9] net/v
> -Original Message-
> From: Maxime Coquelin
> Sent: Tuesday, April 28, 2020 11:28 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org
> Subject: Re: [PATCH v3 2/2] vhost: binary search address mapping table
>
>
>
> On 4/28/20 11:13 AM, Marvin Liu wrote:
> > If Tx
> -Original Message-
> From: Maxime Coquelin
> Sent: Tuesday, April 28, 2020 10:50 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Honnappa Nagarahalli
> ; jer...@marvell.com
> Subject: Re: [PATCH v10 6/9] net/virtio: add vectorized packed ring Rx path
>
>
>
27/04/2020 18:28, Dumitrescu, Cristian:
> From: Yigit, Ferruh
> > On 4/27/2020 10:19 AM, Dumitrescu, Cristian wrote:
> > > From: Yigit, Ferruh
> > >> Hi Nithin,
> > >>
> > >> It looks like patch is causing ABI break, I am getting following warning
> > >> [1],
> > >> can you please check?
> > >>
On 4/28/20 11:13 AM, Marvin Liu wrote:
> If Tx zero copy enabled, gpa to hpa mapping table is updated one by
> one. This will harm performance when guest memory backend using 2M
> hugepages. Now utilize binary search to find the entry in mapping
> table, meanwhile set threshold to 256 entries fo
I looked at it, but I have a simpler patch below that can resolve the
conflict, including after removing previous patches in mlx4/mlx5
Thanks,
Thinh Tran
diff --git a/lib/librte_eal/ppc/include/rte_memcpy.h
b/lib/librte_eal/ppc/include/rte_memcpy.h
index 25311ba1d..abeede231 100644
--- a/lib
On Tue, 2020-04-28 at 15:45 +0100, Bruce Richardson wrote:
> On Tue, Apr 28, 2020 at 03:06:20PM +0100, Ferruh Yigit wrote:
> > On 4/27/2020 5:59 PM, Jerin Jacob wrote:
> > > On Mon, Apr 27, 2020 at 10:19 PM Ferruh Yigit
> > > wrote:
> > > > On 4/27/2020 5:29 PM, Jerin Jacob wrote:
> > > > > On Mo
On Tue, Apr 28, 2020 at 5:02 PM Thinh Tran wrote:
>
> Agreed, this is not rte_trace issue. Moving to rte_common.h does not
> work neither, because altivec.h is included after and redefine bool
> This conflict happens on PPC64, I'll create a different patch.
Please look at Ori patch.
Thanks.
http
Agreed, this is not rte_trace issue. Moving to rte_common.h does not
work neither, because altivec.h is included after and redefine bool
This conflict happens on PPC64, I'll create a different patch.
Thanks,
Thinh Tran
On 4/28/2020 2:57 AM, Jerin Jacob wrote:
On Tue, Apr 28, 2020 at 3:29 AM Th
On 4/28/20 4:43 PM, Liu, Yong wrote:
>
>
>> -Original Message-
>> From: Maxime Coquelin
>> Sent: Tuesday, April 28, 2020 9:46 PM
>> To: Liu, Yong ; Ye, Xiaolong ;
>> Wang, Zhihong
>> Cc: dev@dpdk.org; Honnappa Nagarahalli
>> ; jer...@marvell.com
>> Subject: Re: [PATCH v10 6/9] net/vi
On Tue, Apr 28, 2020 at 03:06:20PM +0100, Ferruh Yigit wrote:
> On 4/27/2020 5:59 PM, Jerin Jacob wrote:
> > On Mon, Apr 27, 2020 at 10:19 PM Ferruh Yigit
> > wrote:
> >>
> >> On 4/27/2020 5:29 PM, Jerin Jacob wrote:
> >>> On Mon, Apr 27, 2020 at 9:42 PM Ferruh Yigit
> >>> wrote:
>
>
> -Original Message-
> From: Maxime Coquelin
> Sent: Tuesday, April 28, 2020 9:46 PM
> To: Liu, Yong ; Ye, Xiaolong ;
> Wang, Zhihong
> Cc: dev@dpdk.org; Honnappa Nagarahalli
> ; jer...@marvell.com
> Subject: Re: [PATCH v10 6/9] net/virtio: add vectorized packed ring Rx path
>
>
>
>
Prevent from writing beyond the allocated memory.
GCC 10 compiling output:
eal_common_trace_utils.c: In function 'eal_trace_dir_args_save':
eal_common_trace_utils.c:290:24: error: '__builtin___sprintf_chk' \
may write a terminating nul past the end of the destination \
[-Werror=f
On Thu, Apr 9, 2020 at 6:44 PM Wisam Jaddo wrote:
>
> Introduce packet forwarding support to the app to do
> some performance measurements.
>
> The measurements are reported in term of packet per
> second unit. The forwarding will start after the end
> of insertion/deletion operations.
>
> The sup
On 4/27/2020 5:59 PM, Jerin Jacob wrote:
> On Mon, Apr 27, 2020 at 10:19 PM Ferruh Yigit wrote:
>>
>> On 4/27/2020 5:29 PM, Jerin Jacob wrote:
>>> On Mon, Apr 27, 2020 at 9:42 PM Ferruh Yigit wrote:
On 4/27/2020 10:19 AM, Dumitrescu, Cristian wrote:
>
>
>> -Original Mess
On 4/28/2020 12:51 PM, Nithin Dabilpuram wrote:
> On Mon, Apr 27, 2020 at 10:29:48PM +0530, Jerin Jacob wrote:
>> External Email
>>
>> --
>> On Mon, Apr 27, 2020 at 10:19 PM Ferruh Yigit wrote:
>>>
>>> On 4/27/2020 5:29 PM, Jerin
Olivier (maintainer of the Ring),
I would like to suggest a couple of minor optimizations to the ring library.
1. Testing if the ring is empty is as simple as comparing the producer and
consumer pointers:
static inline int
rte_ring_empty(const struct rte_ring *r)
{
- return rte_ring_coun
>-Original Message-
>From: Gaëtan Rivet
>Sent: Tuesday, April 28, 2020 12:14 AM
>To: Sunil Kumar Kori
>Cc: step...@networkplumber.org; david.march...@redhat.com; Jerin Jacob
>Kollanukkaran ; dev@dpdk.org
>Subject: [EXT] Re: [dpdk-dev] [PATCH v3 1/1] bus/pci: optimise scanning with
>whitel
> -Original Message-
> From: Sunil Kumar Kori
> Sent: Tuesday, April 28, 2020 6:52 PM
> To: Phil Yang ; jer...@marvell.com; dev@dpdk.org
> Cc: David Marchand ; Ruifeng Wang
> ; Lijian Zhang ; nd
> ; nd
> Subject: RE: [EXT] [PATCH] trace: fix build with gcc 10
>
> >>
> >Hello, there is
On 4/28/20 3:01 PM, Liu, Yong wrote:
>>> Maxime,
>>> Thanks for point it out, it will add extra cache miss in datapath.
>>> And its impact on performance is around 1% in loopback case.
>> Ok, thanks for doing the test. I'll try to run some PVP benchmarks
>> on my side because when doing IO loopb
Fixes: 4f12e20c85dc ("net/sfc/base: introduce EVB module for SR-IOV")
Fixes: 18c8e84d7726 ("net/sfc/base: support proxy auth operations for SR-IOV")
Cc: sta...@dpdk.org
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_evb.c | 4 ++--
drivers/net/sfc/base/efx_evb.c | 4 ++--
drive
1 - 100 of 183 matches
Mail list logo
