Hi,
We noticed 7% performance improvement by simply moving rte_mbuf.next field to
the 1st cache line.
Currently, it falls under /* second cache line - fields only used in slow path
or on TX */
but it is actually used at several places in rx fast path. (e.g.:
i40e_rx_alloc_bufs() is setting th
Hi,
As described in the roadmap (http://dpdk.org/dev/roadmap),
starting from this week,
every new feature submission will be postponed to release 2.2.
The below features, which were submitted earlier, will be accepted in
the release 2.1 if they are correctly reviewed and acknowledged before
the en
Add hotplug support for fm10k.
Signed-off-by: Michael Qiu
---
drivers/net/fm10k/fm10k_ethdev.c | 97 +++-
1 file changed, 96 insertions(+), 1 deletion(-)
diff --git a/drivers/net/fm10k/fm10k_ethdev.c b/drivers/net/fm10k/fm10k_ethdev.c
index e310698..0d3eaf1 1
When close a port, lots of memory should be released,
such as software rings, queues, etc.
Signed-off-by: Michael Qiu
---
drivers/net/fm10k/fm10k_ethdev.c | 37 +
1 file changed, 33 insertions(+), 4 deletions(-)
diff --git a/drivers/net/fm10k/fm10k_ethdev.c b
Hotplug feature is supported in EAL, this patch set is to enable
this feature in driver side.
Michael Qiu (2):
fm10k: Free queues when close port
fm10k: Add hotplug support for fm10k
drivers/net/fm10k/fm10k_ethdev.c | 134 +--
1 file changed, 129 insertion
On 6/10/15, 9:09 AM, "Stephen Hemminger"
wrote:
>From: Stephen Hemminger
>
>Fix spelling errors in strings and comments.
>
>Signed-off-by: Stephen Hemminger
Acked-by: Yong Wang
>---
> drivers/net/vmxnet3/vmxnet3_ethdev.c | 10 +-
> 1 file changed, 5 insertions(+), 5 deletions(-)
>
>di
2015-06-10 16:32, Olivier MATZ:
> On 06/02/2015 03:27 PM, O'Driscoll, Tim wrote:
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier MATZ
> >> On 06/01/2015 09:33 AM, Helin Zhang wrote:
> >>> In order to unify the packet type, the field of 'packet_type' in
> >>> 'struct rte_mbuf' ne
This patch adds a note to the README files in the
drivers/net/pmd/base dirs to highlight that the code should not
be modifed by the user apart from the pmd_osdep.[ch] files.
Signed-off-by: John McNamara
---
drivers/net/e1000/base/README | 13 +
drivers/net/ixgbe/base/README | 16
This patch updates the "Source Organisation" section of the
Programmers Guide to add an note that the code in the
drivers/net/pmd/base directories should not be modifed
by the user apart from the pmd_osdep.[ch] files.
Also fixes some grammar and rst issues in that section.
Signed-off-by: John McN
This patch updates the "Source Organisation" section of the Programmers Guide
to add an note that the code in the drivers/net/pmd/base directories should
not be modifed by the user apart from the pmd_osdep.[ch] files.
It also adds a note to the README files in the drivers/net/pmd/base dirs to
high
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen Hemminger
> Sent: Wednesday, June 10, 2015 5:10 PM
> To: dev at dpdk.org
> Cc: Stephen Hemminger
> Subject: [dpdk-dev] [PATCH] vmxnet3: fix spelling
>
> From: Stephen Hemminger
>
> Fix spelling errors
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Bernard Iremonger
> Sent: Wednesday, June 10, 2015 4:13 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 0/2] doc: kni command line fixes
>
> Several kni command lines did not work.
> The patches below fix
HI
Is there any document which explains the features that are planned for DPDK 2.1
I am just trying to understand the some features such as KNI optimization, KNI
multicast, etc.
Could you please point me to some documentation related to these features!
Thanks
Jaffar
-Original Message
Hi Tim, Helin,
On 06/02/2015 03:27 PM, O'Driscoll, Tim wrote:
>
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier MATZ
>> Sent: Monday, June 1, 2015 9:15 AM
>> To: Zhang, Helin; dev at dpdk.org
>> Subject: Re: [dpdk-dev] [PATCH v6 01/18] mbuf: redefin
Added new test that verifies that rte_jhash_1words,
rte_jhash_2words and rte_jhash_3words return the same
values as rte_jhash.
Note that this patch has been added after the update
of the jhash function because these 3 functions did not
return the same values as rte_jhash before
Signed-off-by: Pab
Changed name to something more meaningful,
and mark rte_jhash2 as deprecated.
Signed-off-by: Pablo de Lara
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_hash.c| 4 ++--
app/test/test_hash_functions.c | 6 +++---
lib/librte_hash/rte_jhash.h | 17 +++--
rte_jhash is basically like __rte_jhash_2hashes but
it returns only 1 hash, instead of 2.
In order to remove duplicated code, rte_jhash calls __rte_jhash_2hashes,
passing 0 as the second seed and returning just the first hash value.
(performance penalty is negligible)
The same is done with rte_jha
With the jhash update, two new functions were introduced:
- rte_jhash_2hashes: Same as rte_jhash, but takes two seeds
and return two hashes (uint32_ts)
- rte_jhash2_2hashes: Same as rte_jhash2, but takes two seeds
and return two hashes (uint32_ts)
Signed
Jenkins hash function was developed originally in 1996,
and was integrated in first versions of DPDK.
The function has been improved in 2006,
achieving up to 35% better performance, compared to the original one.
This patch integrates that code into the rte_jhash library.
It also updates the precal
In order to make sure that the hash functions are returning
the correct values, new tests have been added:
- First test compares precalculated hash values with values calculated
from the existing hash functions.
- Second test compares values returned from rte_jhash2 and rte_jhash,
expecting same r
In order to see more clearly the performance difference
between different hash functions, order of the loops
have been changed, so it iterates first through initial values,
then key sizes and then the hash functions.
Signed-off-by: Pablo de Lara
---
app/test/test_hash_functions.c | 16 --
Previous key sizes used for testing did not have much purpose.
This patch substitutes them with some more meaninful
(standard multiple of 2 key sizes, plus IPv4/v6 tuple and others)
Also an arbitrary initial value has been added to increase
the test coverage, and RTE_DIM macro is used to iterate t
Cycles per hash calculation were measured per single operation.
It is much more accurate to run several iterations between measurements
and divide by number of iterations.
Signed-off-by: Pablo de Lara
---
app/test/test_hash_functions.c | 18 +-
1 file changed, 9 insertions(+), 9
This patch moves hash function performance tests to a separate file,
so user can check performance of the existing hash functions quicker,
without having to run all the other hash operation performance tests,
which takes some time.
Signed-off-by: Pablo de Lara
---
app/test/Makefile
Jenkins hash function was developed originally in 1996,
and was integrated in first versions of DPDK.
The function has been improved in 2006,
achieving up to 35% better performance, compared to the original one.
This patchset updates the current jhash in DPDK,
including two new functions that gene
Signed-off-by: Bernard Iremonger
---
doc/guides/prog_guide/kernel_nic_interface.rst |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/prog_guide/kernel_nic_interface.rst
b/doc/guides/prog_guide/kernel_nic_interface.rst
index fb12d43..713d30b 100644
--- a/doc
Signed-off-by: Bernard Iremonger
---
doc/guides/nics/virtio.rst |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/nics/virtio.rst b/doc/guides/nics/virtio.rst
index 9f18b3a..200a8be 100644
--- a/doc/guides/nics/virtio.rst
+++ b/doc/guides/nics/virtio.rst
@@ -
Several kni command lines did not work.
The patches below fix the command lines.
Bernard Iremonger (2):
doc: correct kni command line in virtio chapter
doc: fix kni command line in Kernel NIC Interface chapter
doc/guides/nics/virtio.rst |4 ++--
doc/guides/prog_guide/
Hi Olivier,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier MATZ
> Sent: Wednesday, June 10, 2015 3:33 PM
> To: O'Driscoll, Tim; Zhang, Helin; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v6 01/18] mbuf: redefine packet_type in
> rte_mbuf
>
> Hi
2015-06-10 14:07, Bruce Richardson:
> Following on from the feedback received from the community about the pktdev
> idea,
> I've decided not to push this approach further for DPDK 2.1.
>
> Instead, for future releases, I'll look at taking some of what was
> investigated in
> this work and see i
Sorry for spam and providing feedback here again.
> -Original Message-
> From: Liang-Min Larry Wang [mailto:liang-min.wang at intel.com]
> Sent: Wednesday, June 10, 2015 11:10 AM
> To: dev at dpdk.org
> Cc: Andrew Harvey (agh); Roger Melton (rmelton); David Harton (dharton);
> Liang-Min La
Hello,
I submitted this question yesterday, when I did not belong to group.
Re-submitting now that I am a member!
I am working on a design where a dpdk/intel710 based switch will receive VXLAN
traffic (DPDK 2.0 with centos 7 and kvm).
Ideally we would like to have the NIC strip the VXLAN header
From: Stephen Hemminger
Cleanup the code in bonding that checks ports.
* Use standard rte_eth_dev_is_valid_port
* Change name of driver string to avoid variable namespace conflicts
* Get rid of unnecessary string comparison stuff. A simple pointer
check is enough here.
* Get rid of un
From: Stephen Hemminger
The function rte_eth_dev_is_valid_port is good way to have all
drivers using same function and solves several hotplug related
bugs from drivers not checking attached flag.
Signed-off-by: Stephen Hemminger
---
lib/librte_ether/rte_ethdev.c | 2 +-
lib/librte_et
From: Stephen Hemminger
These are a couple things found while doing code inspection for
some other bonding related issues.
Stephen Hemminger (2):
ethdev: make rte_eth_dev_is_valid_port public
bonding: fix name and port validation
drivers/net/bonding/rte_eth_bond_api.c | 47 ++--
Hi Oliver
> -Original Message-
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Wednesday, June 10, 2015 10:33 PM
> To: O'Driscoll, Tim; Zhang, Helin; dev at dpdk.org
> Cc: Thomas Monjalon
> Subject: Re: [dpdk-dev] [PATCH v6 01/18] mbuf: redefine packet_type in
> rte_mbuf
>
> From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> Sent: Wednesday, June 10, 2015 1:51 AM
> To: Tahhan, Maryam
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 1/4] ixgbe: expose extended error statistics
>
> On Fri, 5 Jun 2015 18:35:02 +0100
> Maryam Tahhan wrote:
>
> > I
Signed-off-by: Jingjing Wu
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 8 ++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
index 761172e..2cd3461 100644
--- a/doc/guides/testpmd_
enable mirror functionality in i40e driver
.mirror_rule_set
.mirror_rule_reset
Signed-off-by: Jingjing Wu
---
drivers/net/i40e/i40e_ethdev.c | 334 +
drivers/net/i40e/i40e_ethdev.h | 23 +++
2 files changed, 357 insertions(+)
diff --git a/drivers/net/i40
This path renames the mirror type in rte_eth_mirror_conf and macros,
and rework the mirror set in ixgbe dirvers by using new definition.
It also fixes some coding style.
Signed-off-by: Jingjing Wu
---
app/test-pmd/cmdline.c | 42 ++---
drivers/net/ixgbe/ixgb
rename rte_eth_vmdq_mirror_conf to rte_eth_mirror_conf and move
the maximum rule id check from ethdev level to driver
Signed-off-by: Jingjing Wu
---
app/test-pmd/cmdline.c | 22 +++---
drivers/net/ixgbe/ixgbe_ethdev.c | 11 +++
drivers/net/ixgbe/ixgbe_ethdev.h |
This patch set enables mirror functionality in i40e driver, and redefines
structure and macros used to configure mirror.
v2 changes:
- correct comments style
- add doc change
v3 changes:
- change the mirror rule type to support bit mask
- fix code style
v4 changes:
- correct the rule type
Add in some performance testing for the pktdev library. Looking at
cycles count for a ring-based implementation, based off the ring
performance tests.
Compares ring performance:
* native ring calls
* calls through pktdev to the ring
* calls through ring pmd wrapper to the ring
* calls through pktde
From: Marc Sune
Add a basic test for pktdev non-buffered API for pktdev types:
* ethdev
* ring
* kni
Signed-off-by: Marc Sune
Signed-off-by: Bruce Richardson
---
app/test/Makefile | 4 +
app/test/test_pktdev.c | 440 +
2 files changed, 4
This patch takes the existing l2fwd example application and modifies it
to use pktdevs instead of ethdevs directly. The code is shorter, as we are able
to take advantage of the TX buffering provided by pktdev.
Signed-off-by: Bruce Richardson
---
examples/pktdev-l2fwd/Makefile | 50
exampl
This is a trivial example showing code which is using ethdevs and rings
in a neutral manner, with the same piece of pipeline code passing mbufs
along a chain without ever having to query its source or destination
type.
Signed-off-by: Bruce Richardson
---
examples/pktdev-chain/Makefile | 57 ++
The pktdev API is a minimal API designed for runtime packet processing
use. It works by providing a common API for RX and TX across a range of
device and object types: namely SW rings, ethernet ports and KNI ports.
By using the pktdev abstraction, packet data-path code can be written
to accept pac
When a KNI object is created, a name is assigned to it which is stored
internally. There is also an API function to look up a KNI object by
name, but there is no API to query the current name of an existing
KNI object. This patch adds just such an API.
Signed-off-by: Bruce Richardson
---
lib/lib
Following on from the feedback received from the community about the pktdev
idea,
I've decided not to push this approach further for DPDK 2.1.
Instead, for future releases, I'll look at taking some of what was investigated
in
this work and see if it can be applied to the existing ethdev library
Add per queue stats info
Changes in v2
- fix the stats issue in tx_local
- dynamically alloc mem for queue pair stats info
- fix checkpatch errors
Signed-off-by: Changchun Ouyang
---
examples/vhost/main.c | 125 +++---
1 file changed, 78 inserti
Control queue can't work for vhost-user mulitple queue mode,
so introduce a counter to void the dead loop when polling the control queue.
Changes in v2:
- fix checkpatch errors
Signed-off-by: Changchun Ouyang
---
drivers/net/virtio/virtio_ethdev.c | 15 +--
1 file changed, 13 inse
Sample vhost leverage the VMDq+RSS in HW to receive packets and distribute them
into different queue in the pool according to 5 tuples.
And enable multiple queues mode in vhost/virtio layer.
HW queue numbers in pool exactly same with the queue number in virtio device,
e.g. rxq = 4, the queue numb
Sample vhost need know the queue number user want to enable for each virtio
device,
so add the new option '--rxq' into it.
Changes in v2
- refine help info
- check if rxq = 0
- fix checkpatch errors
Signed-off-by: Changchun Ouyang
---
examples/vhost/main.c | 50 ++
QEMU sends separate commands orderly to set the memory layout for each queue
in one virtio device, accordingly vhost need keep memory layout information
for each queue of the virtio device.
This also need adjust the interface a bit for function gpa_to_vva by
introducing the queue index to specify
Each virtio device could have multiple queues, say 2 or 4, at most 8.
Enabling this feature allows virtio device/port on guest has the ability to
use different vCPU to receive/transmit packets from/to each queue.
In multiple queues mode, virtio device readiness means all queues of
this virtio devi
In non-SRIOV environment, VMDq RSS could be enabled by MRQC register.
In theory, the queue number per pool could be 2 or 4, but only 2 queues are
available due to HW limitation, the same limit also exist in Linux ixgbe driver.
Changes in v2:
- fix checkpatch errors
Signed-off-by: Changchun Ouya
This patch set supports the multiple queues for each virtio device in vhost.
The vhost-user is used to enable the multiple queues feature, It's not ready
for vhost-cuse.
The QEMU patch of enabling vhost-use multiple queues has already merged into
upstream sub-tree in
QEMU community and it will b
I see from the Mellanox PMD release notes:
http://www.mellanox.com/related-docs/prod_software/Mellanox_ConnectX3_ConnectX3Pro_DPDK_PMD_Release_Notes_v1.7-8_2.8.4.pdf
that the primary and secondary multi-process model is not supported. Though
it's not noted as a limitation in the DPDK guide here:
This patch depends on the Port Hotplug Framework.
It implements the eth_dev_uninit functions for rte_em_pmd,
rte_igb_pmd and rte_igbvf_pmd.
Changes in V4:
Release rx and tx queues in eth_igbvf_dev_uninit.
Changes in V3:
Add igb_adapter_stopped and em_adapter_stopped booleans.
Release rx and tx qu
Compare with RFC patch:
1. split one patch to two, especially for free memory.
2. rework from lib/ to drivers/net
On 6/10/2015 8:21 PM, Qiu, Michael wrote:
> Hotplug feature is supported in EAL, this patch set is to enable
> this feature in driver side.
>
> Michael Qiu (2):
> fm10k: Free queues
2015-06-10 10:48, Li Wei:
> On 06/09/2015 05:37 PM, Sergio Gonzalez Monroy wrote:
> > The combined lib was being created after building the lib root dir.
> > With the new directory hierarchy, it should be created after the
> > drivers root dir instead.
> >
> > Fixes: 980ed498eb1dd0 ("drivers: crea
Hello,
since I updated from 2.0.0 released to the current git clone the i40e
doesn't 'init' anymore.
EAL: PCI device :82:00.0 on NUMA socket 1
EAL: probe driver: 8086:1572 rte_i40e_pmd
EAL: PCI memory mapped at 0x7ff8a23fd000
EAL: PCI memory mapped at 0x7ff9ae2ec000
PMD: et
On Fri, May 22, 2015 at 11:16:10AM +0100, Pablo de Lara wrote:
> Changed name to something more meaningful,
> and mark rte_jhash2 as deprecated.
>
> Signed-off-by: Pablo de Lara
> ---
> app/test/test_func_reentrancy.c |2 +-
> app/test/test_hash.c|4 ++--
> app/test/test_hash
Patch looks good for me. But in latest dpdk file path changed, but it
applies with small reject.
Reviewed-by: Maxim Uvarov
Maxim.
On 02/27/15 16:42, Tero Aho wrote:
> Extend eth_pcap_rx and eth_pcap_tx to support jumbo frames.
> On receive side read large packets into multiple mbufs and
> on t
On Fri, May 22, 2015 at 11:16:07AM +0100, Pablo de Lara wrote:
> Jenkins hash function was developed originally in 1996,
> and was integrated in first versions of DPDK.
> The function has been improved in 2006,
> achieving up to 60% better performance, compared to the original one.
>
> This patch
On Fri, May 22, 2015 at 11:16:05AM +0100, Pablo de Lara wrote:
> In order to see more clearly the performance difference
> between different hash functions, order of the loops
> have been changed, so it iterates first through initial values,
> then key sizes and then the hash functions.
>
> Signed
Hi,
This is an know issue, as I faced before.
One workaround: remove i40e kernel driver, power off server, then power
on. After that start dpdk, it should work.
Thanks,
Michael
On 6/10/2015 6:12 PM, Dirk-Holger Lenz wrote:
> Hello,
> since I updated from 2.0.0 released to the current git clone
Hello,
since the hardware specific library functions were put into a separate
folder 'drivers' the feature to build a combined library doesn't generate
a combined library including these hardware specific functions anymore.
The reason for this is that the combined library is built before the
'drive
---
.../common/include/rte_pci_dev_feature_defs.h | 26 ++
.../common/include/rte_pci_dev_features.h | 26 ++
2 files changed, 52 insertions(+)
diff --git a/lib/librte_eal/common/include/rte_pci_dev_feature_defs.h
b/lib/librte_eal/common/incl
The example includes an ethtool library and two applications:
one application is a non- DPDK process (nic-control)
and the other is a DPDK l2fwd applicaiton (l2fwd-app).
The nic-control process sends ethtool alike device management
requests to l2fwd-app through a named pipe IPC. This example
is des
add function to support ethtool ops:
- set_mac_addr
- get_reg_length
- get_regs
- get_eeprom_length
- get_eeprom
- set_eeprom
Signed-off-by: Liang-Min Larry Wang
---
drivers/net/e1000/igb_ethdev.c | 190
drivers/net/e1000/igb_regs.h | 212 ++
add function to support ethtool ops:
- set_mac_addr
- get_ringparam
- get_reg_length
- get_regs
- get_eeprom_length
- get_eeprom
- set_eeprom
Signed-off-by: Liang-Min Larry Wang
---
drivers/net/ixgbe/ixgbe_ethdev.c | 207 +++
drivers/net/ixgbe/ixgbe_regs.h | 357 +++
add new apis:
- rte_eth_dev_default_mac_addr_set
- rte_eth_dev_reg_leng
- rte_eth_dev_reg_info
- rte_eth_dev_eeprom_leng
- rte_eth_dev_get_eeprom
- rte_eth_dev_set_eeprom
- rte_eth_dev_get_ringparam
- rte_eth_dev_set_ringparam
to enable reading device parameters (mac-addr, register,
eeprom, ring)
This implementation is designed to provide a familar interface for applications
that rely on kernel-space driver to support ethtool_op and net_device_op for
device management. The initial implementation focuses on ops that can be
implemented through existing netdev APIs. More ops will be support
2015-06-10 09:01, Burakov, Anatoly:
> > 2015-06-10 01:20, Zhang, Helin:
> > > From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> > > > > > On Tue, Jun 09, 2015 at 12:40:57PM -0500, Miguel Bernal Marin wrote:
> > > > > > > Hi,
> > > > > > >
> > > > > > > I'm working on Clear Linux proj
2015-06-10 01:20, Zhang, Helin:
> From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> > > > On Tue, Jun 09, 2015 at 12:40:57PM -0500, Miguel Bernal Marin wrote:
> > > > > Hi,
> > > > >
> > > > > I'm working on Clear Linux project, and when I was integrating
> > > > > DPDK kernel module
On 06/09/2015 05:37 PM, Sergio Gonzalez Monroy wrote:
> The combined lib was being created after building the lib root dir.
> With the new directory hierarchy, it should be created after the
> drivers root dir instead.
>
> Fixes: 980ed498eb1dd0 ("drivers: create new directory")
>
> Signed-off-b
On 10/06/2015 10:38, Dirk-Holger Lenz wrote:
> Hello,
> since the hardware specific library functions were put into a separate
> folder 'drivers' the feature to build a combined library doesn't generate
> a combined library including these hardware specific functions anymore.
> The reason for this
On 2015/6/9 21:34, Xie, Huawei wrote:
> On 6/9/2015 4:47 PM, Michael S. Tsirkin wrote:
>> On Tue, Jun 09, 2015 at 03:04:02PM +0800, Linhaifeng wrote:
>>>
>>> On 2015/4/24 15:27, Luke Gorrie wrote:
On 24 April 2015 at 03:01, Linhaifeng wrote:
> If not add memory fence what would hap
On 9 June 2015 at 10:46, Michael S. Tsirkin wrote:
> By the way, similarly, host side must re-check avail idx after writing
> used flags. I don't see where snabbswitch does it - is that a bug
> in snabbswitch?
Good question.
Snabb Switch does not use interrupts from the guest. We always set
VR
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Maxim Uvarov
> Sent: Wednesday, June 10, 2015 10:08 AM
> To: Tero Aho; dev at dpdk.org
> Subject: Re: [dpdk-dev] [dpdk-dev,2/3] pcap: add support for jumbo frames
>
> Patch looks good for me. But in latest dpdk
Signed-off-by: Bernard Iremonger
---
drivers/net/i40e/i40e_ethdev_vf.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
b/drivers/net/i40e/i40e_ethdev_vf.c
index f5af186..a921b5b 100644
--- a/drivers/net/i40e/i40e_ethdev_vf.c
+++ b/driver
_clear_cmd() was not being called in failure situations,
resulting in the next command also failing.
Fix several typos.
Signed-off-by: Bernard Iremonger
---
drivers/net/i40e/i40e_ethdev_vf.c | 11 +++
1 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/net/i40e/i40e_
Increase delay to avoid i40evf_read_pfmsg() failures.
Signed-off-by: Bernard Iremonger
---
drivers/net/i40e/i40e_ethdev_vf.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
b/drivers/net/i40e/i40e_ethdev_vf.c
index 71740dc..3f29498 100
Signed-off-by: Bernard Iremonger
---
drivers/net/i40e/i40e_ethdev.c |9 +
1 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
index 7bf9532..55fee6b 100644
--- a/drivers/net/i40e/i40e_ethdev.c
+++ b/drivers/net
This patch depends on the Port Hotplug Framework.
It implements the eth_dev_uninit functions for rte_i40e_pmd and
rte_i40evf_pmd.
Changes in V3:
Release rx and tx queues in vf uninit function.
Rebase to use latest i40e code.
Changes in V2:
Rebase to use drivers/net/i40e directory.
Signed-off-by:
This patch set depends on the Port Hotplug Framework.
It implements the eth_dev_uninit functions for rte_i40e_pmd and
rte_i40evf_pmd.
It also includes fixes for several issues encountered.
Bernard Iremonger (5):
i40e: changes to support PCI Port Hotplug
i40e: release vmdq vsi's in dev_close
From: Stephen Hemminger
Fix spelling errors in strings and comments.
Signed-off-by: Stephen Hemminger
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c
b/drivers/net/vmxnet3/vmxnet3_ethd
> 2015-06-10 01:20, Zhang, Helin:
> > From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> > > > > On Tue, Jun 09, 2015 at 12:40:57PM -0500, Miguel Bernal Marin wrote:
> > > > > > Hi,
> > > > > >
> > > > > > I'm working on Clear Linux project, and when I was integrating
> > > > > > DPDK
Tested-by: Jiajia Sunx
- Tested Commit: 94ef2964148a4540db21034f5c3669ab81fbdc76
- OS: Fedora20 3.18.9
- GCC: gcc version 4.8.3 20140911
- CPU: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
- NIC: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection
[8086:10fb]
- NIC: Intel Corporation E
Acked-by: Huawei Xie
On 6/9/2015 9:03 AM, Ouyang, Changchun wrote:
> Fix enqueue/dequeue can't handle chained vring descriptors;
> Remove unnecessary vring descriptor length updating;
> Add support copying scattered mbuf to vring;
>
> Changchun Ouyang (4):
> lib_vhost: Fix enqueue/dequeue can't
> -Original Message-
> From: Qiu, Michael
> Sent: Tuesday, June 09, 2015 11:41 PM
> To: Chen, Jing D; He, Shaopeng; dev at dpdk.org
> Subject: Re: [PATCH 3/3] fm10k: update VLAN offload features
>
> On 2015/6/9 11:27, Chen, Jing D wrote:
> > Hi,
> >
> >
> >> -Original Message-
> >>
Hi, Michael,
> -Original Message-
> From: Qiu, Michael
> Sent: Tuesday, June 09, 2015 11:21 PM
> To: Chen, Jing D; dev at dpdk.org
> Cc: He, Shaopeng
> Subject: Re: [PATCH 1/3] fm10k: Add promiscuous mode support
>
> On 2015/6/5 17:03, Chen, Jing D wrote:
> > From: "Chen Jing D(Mark)"
>
> -Original Message-
> From: Qiu, Michael
> Sent: Tuesday, June 09, 2015 11:52 PM
> To: He, Shaopeng; dev at dpdk.org
> Cc: Chen, Jing D
> Subject: Re: [PATCH 1/3] fm10k: update VLAN filter
>
> On 2015/6/2 10:59, He, Shaopeng wrote:
> > VLAN filter was updated to add/delete one static entr
Hi, Michael,
> -Original Message-
> From: Qiu, Michael
> Sent: Wednesday, June 10, 2015 12:24 AM
> To: Chen, Jing D; dev at dpdk.org
> Cc: He, Shaopeng
> Subject: Re: [PATCH 4/6] fm10k: Fix issue that MAC addr can't be set to
> silicon
>
> On 2015/5/29 16:11, Chen, Jing D wrote:
> > From
Acked-by: Huawei Xie
On 6/9/2015 9:03 AM, Ouyang, Changchun wrote:
> Fix enqueue/dequeue can't handle chained vring descriptors;
> Remove unnecessary vring descriptor length updating;
> Add support copying scattered mbuf to vring;
>
> Changchun Ouyang (4):
> lib_vhost: Fix enqueue/dequeue can't
> -Original Message-
> From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> Sent: Wednesday, June 10, 2015 9:15 AM
> To: Zhang, Helin
> Cc: Miguel Bernal Marin; dev at dpdk.org; Bernal Marin, Miguel
> Subject: Re: [dpdk-dev] Headers files with BSD license in kernel
>
> On Wed
> -Original Message-
> From: Qiu, Michael
> Sent: Wednesday, June 10, 2015 12:00 AM
> To: He, Shaopeng; dev at dpdk.org
> Cc: Chen, Jing D
> Subject: Re: [PATCH 2/3] fm10k: add MAC filter
>
> On 2015/6/2 10:59, He, Shaopeng wrote:
> > MAC filter function was newly added, each PF and VF can
Hi Miguel
My thought is there might be something wrong. Let's see what comments from
other experts!
Thank you very much for the good catch!
Regards,
Helin
> -Original Message-
> From: Miguel Bernal Marin [mailto:miguel.bernal.marin at linux.intel.com]
> Sent: Wednesday, June 10, 2015 4:
99 matches
Mail list logo
