The rx function used was ixgbe_recv_pkts_bulk_alloc.
the problem seems that the rx desc ring not full, but nic don't write
data to ring and inc the missed error counter.
2016-09-01 21:48 GMT+08:00 wei wang :
> my enviroment:
> NIC:X540
> DPDK version:2.2.0
>
> problems:
> start dpdk app with tr
From: ???
chagne atomic ref update to always call atomic_add
when mbuf is allocated by cpu1 and freed by cpu2. cpu1 cache may not be updated
by such a set operation.
causes refcnt reads incorrect values.
---
lib/librte_mbuf/rte_mbuf.h | 16 ++--
1 file changed, 6 insertions(+), 10
Hi Jan,
> -Original Message-
> From: Jan Viktorin [mailto:viktorin at rehivetech.com]
> Sent: Thursday, September 01, 2016 11:59 PM
> To: Shreyansh Jain
> Cc: dev at dpdk.org; david.marchand at 6wind.com; thomas.monjalon at
> 6wind.com; Hemant
> Agrawal
> Subject: Re: [PATCH v8 00/25] I
Spec said "The PCI Device ID is calculated by adding 0x1040 to the
Virtio Device ID". So this patch makes pmd can recognize modern virtio
net id.
Signed-off-by: Jason Wang
---
drivers/net/virtio/virtio_ethdev.c | 1 +
drivers/net/virtio/virtio_pci.h| 1 +
2 files changed, 2 insertions(+)
di
Virtio pmd doesn't support VFIO in the past since devices bypass IOMMU
completely. But recently, the work of making virtio device work with
IOMMU is near to complete. So this patch make pmd support IOMMU by:
- Allow VFIO mapping by setting RTE_PCI_DRV_NEED_MAPPING flag
- Negotiate feature VIRTIO_F
Hi Kyle,
On 9/2/2016 4:53 AM, Kyle Larose wrote:
> Hello everyone,
>
> In my own testing, I recently stumbled across an issue where I could get qemu
> to exit when sending traffic to my application. To do this, I simply needed
> to do the following:
>
> 1) Start my virtio interfaces
> 2) Send s
Hi Souvik,
On 09/02/2016 12:20 AM, Dey, Souvik wrote:
> Hi Maxime,
> When is patches or new implementation going to come in the release ? if
> it is not 16.11 then, can we keep this change till the new virtio changes
> come in the release. And if it is already planned for 16.11, then can I
This patch ensure not overwrite device data in the multiprocess application.
1)Changes in the library introduces continuity in array rte_eth_dev_data[]
shared between all processes. Secondary process adds new entries in free
space instead of overwriting existing entries.
2)Changes in application
Added prevention not overwrite device data in array rte_eth_dev_data[].
Secondary process appends in the first free place rather than at the
beginning. This behavior prevents overwriting devices of primary process
by secondary process.
Signed-off-by: Marcin Kerlin
---
lib/librte_ether/rte_ethdev
Added lookup for pool name because secondary process should attach to
mempool created by primary process rather than create new one.
Added function free_shared_dev_data() used at the exit of the testpmd.
This causes detach devices data from array rte_eth_dev_data[] shared
between all processes. Th
> -Original Message-
> From: Neil Horman [mailto:nhorman at tuxdriver.com]
> Sent: Thursday, September 1, 2016 8:16 PM
> To: Stephen Hemminger
> Cc: Trahe, Fiona ; dev at dpdk.org; Olivier Matz
> ; Thomas Monjalon
>
> Subject: Re: [dpdk-dev] [dpdk-dev, RFC] drivers: advertise kmod depen
This also helps to remove stack backtrace when kernel module is not
inserted.
Signed-off-by: Ferruh Yigit
---
lib/librte_kni/rte_kni.c | 20 +---
1 file changed, 13 insertions(+), 7 deletions(-)
diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
index f48b72b..d88a
The issue can be reproduced with example program l2fwd by modifying it
to sleep 1 second before launching thread.
code like this:
check_all_ports_link_status(nb_ports, l2fwd_enabled_port_mask);
sleep(1);
/* launch per-lcore init on every lcore */
rte_
Fix pernet calls when HAVE_SIMPLIFIED_PERNET_OPERATIONS is not set.
Fixes: e6734d21b4e1 ("kni: fix build with kernel 2.6.32")
Signed-off-by: Vincent Guo
---
lib/librte_eal/linuxapp/kni/kni_misc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/librte_eal/linuxapp/kni
Hi folks!
Many groups have flag -Werror=declaration-after-statement in the
their coding conventions. Dpdk have many code as static inline
function in the headers files and have trouble with it.
For example:
* lib/librte_ether/rte_ether.h, function rte_vlan_strip
* lib/librte_eal/common/include/r
2016-09-01 10:41, Stephen Hemminger:
> Neil Horman wrote:
> > On Thu, Sep 01, 2016 at 12:55:27PM +, Trahe, Fiona wrote:
> > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> > > > On 08/31/2016 03:27 PM, Neil Horman wrote:
> > > > > Oh, I see, so your list is a colon d
Previous patch updated the functions without updating all the comments.
Fixes: 591a9d7985c1 ("add FILE argument to debug functions")
Signed-off-by: Mauricio Vasquez B
---
lib/librte_eal/common/include/rte_malloc.h | 2 +-
lib/librte_eal/common/include/rte_memory.h | 2 +-
lib/librte_eal/commo
On 9/1/2016 3:16 AM, Jianfeng Tan wrote:
> Previously in igb_uio, iomem is mapped, and both ioport and io mem
> are recorded into uio framework, which is duplicated and makes the
> code too complex.
>
> For iomem, DPDK user space code never opens or reads files under
> /sys/pci/bus/devices/:xx
> -Original Message-
> From: Tan, Jianfeng [mailto:jianfeng.tan at intel.com]
> Sent: Friday, September 02, 2016 2:56 AM
> To: Kyle Larose; dev at dpdk.org
> Cc: huawei.xie at intel.com; yuanhan.liu at linux.intel.com
> Subject: Re: virtio kills qemu VM after stopping/starting ports
>
>
Hi Kyle,
On 9/2/2016 8:35 PM, Kyle Larose wrote:
>
>> -Original Message-
>> From: Tan, Jianfeng [mailto:jianfeng.tan at intel.com]
>> Sent: Friday, September 02, 2016 2:56 AM
>> To: Kyle Larose; dev at dpdk.org
>> Cc: huawei.xie at intel.com; yuanhan.liu at linux.intel.com
>> Subject: Re:
I will get a proper patch sent hopefully today.
Gary
-Original Message-
From: Mcnamara, John [mailto:john.mcnam...@intel.com]
Sent: Thursday, September 01, 2016 7:00 AM
To: Mussar, Gary; Dey, Souvik; Stephen Hemminger
Cc: nhorman at tuxdriver.com; dev at dpdk.org
Subject: RE: [dpdk-dev]
2016-09-02 14:36, Jason Wang:
> Spec said "The PCI Device ID is calculated by adding 0x1040 to the
> Virtio Device ID". So this patch makes pmd can recognize modern virtio
> net id.
Please could you describe what is a modern virtio-net?
> #define VIRTIO_PCI_DEVICEID_MIN 0x1000
> #define VIRTIO_
On 9/2/2016 8:31 PM, Ferruh Yigit wrote:
> On 9/1/2016 3:16 AM, Jianfeng Tan wrote:
>> Previously in igb_uio, iomem is mapped, and both ioport and io mem
>> are recorded into uio framework, which is duplicated and makes the
>> code too complex.
>>
>> For iomem, DPDK user space code never opens or
2016-09-02 14:37, Jason Wang:
> Virtio pmd doesn't support VFIO in the past since devices bypass IOMMU
> completely. But recently, the work of making virtio device work with
> IOMMU is near to complete.
Good news!
What are the requirements for Qemu and Linux version numbers please?
2016-09-02 13:49, ASM:
> Hi folks!
>
> Many groups have flag -Werror=declaration-after-statement in the
> their coding conventions. Dpdk have many code as static inline
> function in the headers files and have trouble with it.
>
> For example:
> * lib/librte_ether/rte_ether.h, function rte_vlan_
The dpdk-devbind.py script does not find/display the ifname for virtio
interfaces since the "net" directory is not directly under the device
directory but rather under a subdirectory.
eg.
> dpdk-devbind.py --status
:00:03.0 'Virtio network device' if= drv=virtio-pci unused=
This change searche
On Fri, Sep 02, 2016 at 09:19:26AM +, Trahe, Fiona wrote:
>
>
> > -Original Message-
> > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > Sent: Thursday, September 1, 2016 8:16 PM
> > To: Stephen Hemminger
> > Cc: Trahe, Fiona ; dev at dpdk.org; Olivier Matz
> > ; Thomas Monja
The pktgen docs state that the rte_kni.ko should be loaded with
lo_mode=lo_mode_ring however the source in dpdk master does not appear to
understand this value. This wasn't an issue in the past since the kni code
would simply disable lo_mode if you passed in an unknown value.
The Ubuntu 4.4.0-3
Hello all,
I think http://dpdk.org/dev/patchwork/patch/5389/ disabled support of indirect
buffers by accident.
Am I missing something ? Is there a reason why this was disabled ?
I tested it today and it seems to work fine.
If you have no objection, could we re-enable it ?
It is a very useful fe
Hi Pierre,
On 09/02/2016 03:41 PM, Pierre Pfister (ppfister) wrote:
> Hello all,
>
> I think http://dpdk.org/dev/patchwork/patch/5389/ disabled support of
> indirect buffers by accident.
> Am I missing something ? Is there a reason why this was disabled ?
>
> I tested it today and it seems to wor
> -Original Message-
> From: Neil Horman [mailto:nhorman at tuxdriver.com]
> Sent: Friday, September 2, 2016 2:33 PM
> To: Trahe, Fiona
> Cc: Stephen Hemminger ; dev at dpdk.org;
> Olivier Matz ; Thomas Monjalon
>
> Subject: Re: [dpdk-dev] [dpdk-dev, RFC] drivers: advertise kmod depende
HI Gary,
Regards,
Keith
> On Sep 2, 2016, at 8:39 AM, Mussar, Gary wrote:
>
> The pktgen docs state that the rte_kni.ko should be loaded with
> lo_mode=lo_mode_ring however the source in dpdk master does not appear to
> understand this value. This wasn't an issue in the past since the kni cod
On Fri, Sep 02, 2016 at 01:52:46PM +, Trahe, Fiona wrote:
>
>
> > -Original Message-
> > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > Sent: Friday, September 2, 2016 2:33 PM
> > To: Trahe, Fiona
> > Cc: Stephen Hemminger ; dev at dpdk.org;
> > Olivier Matz ; Thomas Monjalo
Hi Pankaj,
Sorry for the late review.
On 08/27/2016 06:26 PM, Pankaj Chauhan wrote:
> Indroduce support for a generic framework for handling of switching between
s/Indroduce/Introduce/
> physical and virtio devices. The vswitch framework introduces the following
> concept:
Shouldn't you use v
Hi,
Gentle remainder for review.
Thanks,
Reshma
Starting with DPDK 16.04, performing a start, then stop followed by a
start on a virtio NIC sending traffic can cause qemu to exit.
Qemu exits with a message like:
2016-09-01T15:45:32.119059Z qemu-kvm: Guest moved used index from 5
to 1
This appears to occur because virtio_dev_start will
On 08/27/2016 06:26 PM, Pankaj Chauhan wrote:
> Add command line options for selecting switch implementation
> and maximum ports for the vswitch.following are two new command
> line options:
>
> --switch [char string, Selects the switch imlementation]
> --max-ports [int, selects maximum number o
On 9/2/2016 3:16 PM, Wiles, Keith wrote:
> HI Gary,
>
> Regards,
> Keith
>
>> On Sep 2, 2016, at 8:39 AM, Mussar, Gary wrote:
>>
>> The pktgen docs state that the rte_kni.ko should be loaded with
>> lo_mode=lo_mode_ring however the source in dpdk master does not appear to
>> understand this va
As new_device and destroy_device use an int instead of a "struct virtio_net *",
The comment about setting VIRTIO_DEV_RUNNING doesn't make sense anymore, plus
If I've correctly understand the code, the drivers take care of
setting the flag before calling the callbacks, so I guess that this comment
i
Allow binding KNI thread to specific core in single threaded mode
by setting core_id and force_bind config parameters.
Signed-off-by: Vladyslav Buslov
---
lib/librte_eal/linuxapp/kni/kni_misc.c | 48 ++
1 file changed, 32 insertions(+), 16 deletions(-)
diff --git
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Gary Mussar
> Sent: Friday, September 2, 2016 2:17 PM
> To: dev at dpdk.org
> Cc: Gary Mussar
> Subject: [dpdk-dev] [PATCH] Tools: Fix issue with virtio interface names
>
> The dpdk-devbind.py script does not
> -Original Message-
> From: Ferruh Yigit [mailto:ferruh.yigit at intel.com]
> Sent: Friday, September 02, 2016 10:55 AM
> To: Wiles, Keith; Mussar, Gary
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] rte_kni.ko with lo_mode=lo_mode_ring
>
> On 9/2/2016 3:16 PM, Wiles, Keith wrote:
> > HI
Indirect descriptors support was disabled by commit 59d593f472a7,
presumably by accident as it was correctly supported.
This patch simply adds VIRTIO_RING_F_INDIRECT_DESC back to
the supported features bit mask, hence enabling the use of
indirect descriptors when the feature is negociated with the
On Fri, 2 Sep 2016 13:25:06 +0800
lilinzhe wrote:
> From: ???
>
> chagne atomic ref update to always call atomic_add
>
> when mbuf is allocated by cpu1 and freed by cpu2. cpu1 cache may not be
> updated by such a set operation.
> causes refcnt reads incorrect values.
What architecture are y
Hi,
Thank you everyone for all these comments. I'll try to summarize them here:
a- the kmod information should be per-device instead of per-driver
(modalias-like)
b- there is no need to specify kmod dependencies (i.e. "uio_pci_generic"
is enough, not "uio & uio_pci_generic") since it is available
On Sat, 3 Sep 2016 00:31:50 +0800
Linzhe Lee wrote:
> Thanks for reply, Stephen.
>
>
>
> I'm in x86-64, my cpu is `Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz`.
>
>
>
> When allocation mbuf in program1, and transfer it to program2 for free
> via ring, the program1 might meet assert in allocat
On Thu, Sep 01, 2016 at 01:31:47AM +, Jianfeng Tan wrote:
> This patch uses pthread_getaffinity_np() to narrow down detected
> cores before parsing coremask (-c), corelist (-l), and coremap
> (--lcores).
>
> The purpose of this patch is to leave out these core related options
> when DPDK appli
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Saturday, August 27, 2016 1:58 AM
> To: De Lara Guarch, Pablo; Marohn, Byron
> Cc: dev at dpdk.org; Richardson, Bruce; Edupuganti, Saikrishna;
> jianbo.liu at linaro.org; chaozhu at linux.vnet.ibm.c
On Fri, Sep 02, 2016 at 03:04:56PM +0200, Thomas Monjalon wrote:
> 2016-09-02 14:37, Jason Wang:
> > Virtio pmd doesn't support VFIO in the past since devices bypass IOMMU
> > completely. But recently, the work of making virtio device work with
> > IOMMU is near to complete.
>
> Good news!
> What
This patchset improves lookup performance on the current hash library
by changing the existing lookup bulk pipeline, with an improved pipeline,
based on a loop-and-jump model, instead of the current 4-stage 2-entry pipeline.
Also, x86 vectorized intrinsics are used to improve performance when compa
In order to optimize lookup performance, hash structure
is reordered, so all fields used for lookup will be
in the first cache line.
Signed-off-by: Pablo de Lara
---
lib/librte_hash/rte_cuckoo_hash.h | 12 +++-
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/lib/librte_hash
From: Byron Marohn
Move current signatures of all entries together in the bucket
and same with all alternative signatures, instead of having
current and alternative signatures together per entry in the bucket.
This will be benefitial in the next commits, where a vectorized
comparison will be perf
From: Byron Marohn
In lookup bulk function, the signatures of all entries
are compared against the signature of the key that is being looked up.
Now that all the signatures are together, they can be compared
with vector instructions (SSE, AVX2), achieving higher lookup performance.
Also, entries
From: Byron Marohn
This patch replaces the pipelined rte_hash lookup mechanism with a
loop-and-jump model, which performs significantly better,
especially for smaller table sizes and smaller table occupancies.
Signed-off-by: Byron Marohn
Signed-off-by: Saikrishna Edupuganti
Signed-off-by: Pabl
54 matches
Mail list logo
