2014-12-08 09:49, Neil Horman:
> On Tue, Oct 07, 2014 at 12:14:04AM +0100, stepan wrote:
> > Build of some of the test binaries fails when the following flags are
> > enabled:
> >
> > CONFIG_RTE_LIBRTE_PMD_PCAP=y
> > CONFIG_RTE_BUILD_SHARED_LIB=y
> > CONFIG_RTE_BUILD_COMBINE_LIBS=y
> >
> > The b
On Mon, Dec 15, 2014 at 10:33 PM, Thomas Monjalon wrote:
>
> 2014-12-15 21:11, Vladislav Zolotarov:
> > Hi,
> > I'm running an ixgbevf PMD on an AWS guests with extended networking
> > (SR-IOV functions of 82599 Intel's NIC) and noticed that even in the
> > current git tree there is no support for
Hi,
While working on TSO based solution I faced the following two questions:
1.
is there a maximum pkt_len to be used with TSO?, e.g. let's say if seg_sz
is 1400 can the entire segmented pkt be 256K (higer than 64K) ?, then the
driver gets a list of chanined mbufs while the first mbuf is set to T
2014-12-15 22:45, Dor Laor:
> On Mon, Dec 15, 2014 at 10:33 PM, Thomas Monjalon 6wind.com
> > wrote:
> > Does it mean DPDK is going to be supported in your system (OSv)?
>
> In general yes. It's premature to ask now since there are components
> that already implemented in OSv and won't be needed
2014-12-15 21:11, Vladislav Zolotarov:
> Hi,
> I'm running an ixgbevf PMD on an AWS guests with extended networking
> (SR-IOV functions of 82599 Intel's NIC) and noticed that even in the
> current git tree there is no support for a multi-queue in this PMD: reta
> size returned by rte_eth_dev_info_g
Hi,
I'm running an ixgbevf PMD on an AWS guests with extended networking
(SR-IOV functions of 82599 Intel's NIC) and noticed that even in the
current git tree there is no support for a multi-queue in this PMD: reta
size returned by rte_eth_dev_info_get() call is 0, while max_rx_queues and
max_tx_qu
2014-12-15 16:00, Ananyev, Konstantin:
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> > 2014-12-15 13:47, Wodkowski, PawelX:
> > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > > > 2014-12-15 11:27, Wodkowski, PawelX:
> > > > > Thomas, can you check bu
-v2:
Incorporates Pawel's comments regarding assertion's check on activate_slave
array indexing
Fixes for link bonding library identified by static analysis tool
- Overflow assert for active_slaves array in activate_slave function
- Allocation check of pci_id_table in rte_eth_bond_create
- Use o
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Monday, December 15, 2014 3:17 PM
> To: Wodkowski, PawelX
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] error: value computed is not used
>
> 2014-12-15 13:47, Wodkowski, PawelX:
> > Fr
From: Pawel Wodkowski
This change use statements in expressions C extension provided by gcc to avoid
'value computed is not used' warning/error when size is not known at compile
time.
Comments on possible side effects are welcome an tests are welcome.
Reported-by: Qiu, Michael
Signed-off-by: P
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Wodkowski, PawelX
> Sent: Monday, December 15, 2014 3:44 PM
> To: Thomas Monjalon
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] error: value computed is not used
>
> > > > > And something like this?
> > > >
Hi Neil,
> -Original Message-
> From: Neil Horman [mailto:nhorman at tuxdriver.com]
> Sent: Monday, December 15, 2014 4:00 PM
> To: Ananyev, Konstantin
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 10/17] librte_acl: add AVX2 as new
> rte_acl_classify() method
>
> On Sun, Dec 14
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Monday, December 15, 2014 2:17 PM
> To: Wodkowski, PawelX
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] error: value computed is not used
>
> 2014-12-15 13:47, Wodkowski, PawelX:
> >
As the fixes of below performance issues on X710 may not be integrated
in latest version of firmware, a workaround in software PMD is needed.
It is to re-configure 3 specific registers after being initialized.
- Cannot achieve line rate on X710.
- Performance reduction when promiscuous mode is disa
> > > > And something like this?
> > > >
> > > > #define rte_memcpy(dst, src, n) \
> > > > - ((__builtin_constant_p(n)) ? \
> > > > + ({ (__builtin_constant_p(n)) ? \
> > > > memcpy((dst), (src), (n)) : \
> > > > - rte_memcpy_func((
On Mon, Dec 15, 2014 at 04:33:47PM +, Ananyev, Konstantin wrote:
> Hi Neil,
>
> > -Original Message-
> > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > Sent: Monday, December 15, 2014 4:00 PM
> > To: Ananyev, Konstantin
> > Cc: dev at dpdk.org
> > Subject: Re: [dpdk-dev] [PATC
2014-12-15 13:47, Wodkowski, PawelX:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > 2014-12-15 11:27, Wodkowski, PawelX:
> > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > > > 2014-12-08 15:26, Wodkowski, PawelX:
> > > > > From: Qiu, Michael
> > > > > > On 2014
As the fixes of below performance issues on X710 may not be integrated
in latest version of firmware, a workaround in software PMD is needed.
It is to re-configure 3 specific registers after being initialized.
- Cannot achieve line rate on X710.
- Performance reduction when promiscuous mode is disa
Interestingly, in 64-bit mode the default size of operands on IA is still
32-bit. Instructions often need to have the REX prefix on them to actually use
64-bit data. The REX prefix is explained in section 2.2.1 of the "Intel? 64 and
IA-32 Architectures Software Developer?s Manual", Volume 2
Reg
2014-12-15 11:27, Wodkowski, PawelX:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > 2014-12-08 15:26, Wodkowski, PawelX:
> > > From: Qiu, Michael
> > > > On 2014/12/8 19:00, Wodkowski, PawelX wrote:
> > > > >> lib/librte_pmd_enic/enic_main.c: In function 'enic_set_rsskey':
> > >
Hi Xie,
I've got warnings from checkpatch.pl.
Mostly 'over 80 characters' warnings.
(But I know these are come from original vhost-example code sometimes.)
So far, your patches are RFC, so I haven't check these strictly.
Thanks,
Tetsuya
(2014/12/11 6:37), Huawei Xie wrote:
> This patchset refin
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Wodkowski, PawelX
> Sent: Monday, December 15, 2014 9:05 AM
> To: Jay Rolette; Dev
> Subject: Re: [dpdk-dev] [PATCH] replaced O(n^2) sort in sort_by_physaddr()
> with qsort() from standard library
>
> > -
(2014/12/11 6:37), Huawei Xie wrote:
> Signed-off-by: Huawei Xie
> ---
> lib/librte_vhost/vhost_user/fd_man.c | 205
> +++
> lib/librte_vhost/vhost_user/fd_man.h | 64 +++
> 2 files changed, 269 insertions(+)
> create mode 100644 lib/librte_vhost/vhost_u
(2014/12/11 6:37), Huawei Xie wrote:
> cuse_set_memory_table
>
> Signed-off-by: Huawei Xie
> ---
> lib/librte_vhost/Makefile | 2 +-
> lib/librte_vhost/vhost-net.h | 4 +-
> lib/librte_vhost/vhost_cuse/vhost-net-cdev.c | 7 +-
> lib/librte_vhost/vhost_c
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Monday, December 15, 2014 2:27 PM
> To: Wodkowski, PawelX
> Cc: Qiu, Michael; dev at dpdk.org
> Subject: Re: [dpdk-dev] error: value computed is not used
>
> 2014-12-15 11:27, Wodkowski, PawelX:
>
Enqueue and dequeue burst functions always return a positive
value (including 0), so return type should be unsigned,
instead of int.
Fixed also API doc for one of the functions.
Signed-off-by: Pablo de Lara
---
lib/librte_ring/rte_ring.h | 14 +++---
1 files changed, 7 insertions(+),
> Because it doesn't work correctly :-)
It should, what I am missing here? :P
Pawel
GCC 4.5.1 from SUSE throws this error:
lib/librte_pmd_enic/enic_main.c:862:2: error: value computed is not used
It seems to be a GCC bug.
Reported-by: Michael Qiu
Suggested-by: Pawel Wodkowski
Signed-off-by: Thomas Monjalon
---
lib/librte_pmd_enic/enic_main.c | 3 ++-
1 file changed,
2014-12-08 15:26, Wodkowski, PawelX:
> From: Qiu, Michael
> > On 2014/12/8 19:00, Wodkowski, PawelX wrote:
> > >> lib/librte_pmd_enic/enic_main.c: In function 'enic_set_rsskey':
> > >> lib/librte_pmd_enic/enic_main.c:862:2: error: value computed is not used
> > >>
> > >> I dig out that, it was ome
Hi Mirek,
That sounds great.
Looking forward to it.
-Cunming
> -Original Message-
> From: Walukiewicz, Miroslaw
> Sent: Monday, December 15, 2014 7:11 PM
> To: Liang, Cunming; dev at dpdk.org
> Subject: RE: [dpdk-dev] [RFC PATCH 0/7] support multi-phtread per lcore
>
> Hi Cunming,
>
>
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Monday, December 15, 2014 11:55 AM
> To: Wodkowski, PawelX; Qiu, Michael
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] error: value computed is not used
>
> 2014-12-08 15:26, Wodkowski, PawelX:
>
Hi Cunming,
The timers could be used by any application/library started as a standard
pthread.
Each pthread needs to have assigned some identifier same way as you are doing
it for mempools (the rte_linear_thread_id and rte_lcore_id are good examples)
I made series of patches extending the rte
On Sun, Dec 14, 2014 at 06:10:52PM +, Konstantin Ananyev wrote:
> Introduce new classify() method that uses AVX2 instructions.
> From my measurements:
> On HSW boards when processing >= 16 packets per call,
> AVX2 method outperforms it's SSE counterpart by 10-25%,
> (depending on the ruleset).
Set VMDq RSS mode if it has VF(VF number is more than 1) and has RSS
information.
Signed-off-by: Changchun Ouyang
---
app/test-pmd/testpmd.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 8c69756..90a3c64 100644
--- a/app/test-
It needs config RSS and IXGBE_MRQC and IXGBE_VFPSRTYPE to enable VF RSS.
Signed-off-by: Changchun Ouyang
---
lib/librte_pmd_ixgbe/ixgbe_pf.c | 15 +
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 66 +--
2 files changed, 71 insertions(+), 10 deletions(-)
diff
Check mq mode for VMDq RSS, handle it correctly instead of returning an error;
Also remove the limitation of per pool queue number has max value of 1, because
the per pool queue number could be 2 or 4 if it is VMDq RSS mode;
Signed-off-by: Changchun Ouyang
---
lib/librte_ether/rte_ethdev.c | 21
Get the available Rx and Tx queue number when receiving IXGBE_VF_GET_QUEUES
message from VF.
Signed-off-by: Changchun Ouyang
---
lib/librte_pmd_ixgbe/ixgbe_pf.c | 35 ++-
1 file changed, 34 insertions(+), 1 deletion(-)
diff --git a/lib/librte_pmd_ixgbe/ixgbe_pf.
Negotiate API version with VF when receiving the IXGBE_VF_API_NEGOTIATE message.
Signed-off-by: Changchun Ouyang
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.h | 1 +
lib/librte_pmd_ixgbe/ixgbe_pf.c | 25 +
2 files changed, 26 insertions(+)
diff --git a/lib/librte_pmd_ixgb
Put global register configuring out of loop for queue; also fix typo and indent.
Signed-off-by: Changchun Ouyang
---
lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 29 +++--
1 file changed, 15 insertions(+), 14 deletions(-)
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
b/lib/libr
This patch enables VF RSS for Niantic, which allow each VF having at most 4
queues.
The actual queue number per VF depends on the number of VF:
VF number from 1~32: 4 queues per VF;
VF number from 33~max vf num: 2 queues per VF;
On host, to enable VF RSS functionality, mq mode should be set as
E
On Sun, Dec 14, 2014 at 06:10:51PM +, Konstantin Ananyev wrote:
> New data type to manipulate 256 bit AVX values.
> Rename field in the rte_xmm to keep common naming accross SSE/AVX fields.
>
> Signed-off-by: Konstantin Ananyev
> ---
> examples/l3fwd/main.c | 2 +-
On Mon, Dec 15, 2014 at 10:56:59AM +0800, Ouyang Changchun wrote:
> This patch enables VF RSS for Niantic, which allow each VF having at most 4
> queues.
> The actual queue number per VF depends on the number of VF:
> VF number from 1~32: 4 queues per VF;
> VF number from 33~max vf num: 2 queues p
On Mon, Dec 15, 2014 at 10:47:40AM +, Bruce Richardson wrote:
> On Sat, Dec 13, 2014 at 01:44:36AM +, Anant Mudambi wrote:
> > Hi all,
> > I am using DPDK 1.7.0.
> > Qemu-KVM system with the Intel 10G X540 NIC; host has the Linux ixgbe PF
> > driver and a guest is using a VF with the DPDK
On Sat, Dec 13, 2014 at 01:44:36AM +, Anant Mudambi wrote:
> Hi all,
> I am using DPDK 1.7.0.
> Qemu-KVM system with the Intel 10G X540 NIC; host has the Linux ixgbe PF
> driver and a guest is using a VF with the DPDK ixgbevf PMD (uio).
> I am trying to configure multiple (2 for now) receive q
Hi Konstantin,
Thanks for the reply.
I was trying to find more intuitive one compare to rte_mempool_obj_iter().
Once mempool is created with objects, shouldn't we able to walk-through by just
passing 'mp' object and avoiding other params like vaddr, elt_size etc. For
now, I could use callbac
Known issue regarding iommu/VT-d and igb_uio in Linux kernel version 3.15
to 3.17 where unbinding the device from the driver removes the 1:1 mapping
in the iommu resulting in IOMMU/DMAR errors when the device tries to
access memory.
Signed-off-by: Sergio Gonzalez Monroy
---
v4:
Improve commit lo
Hi Vithal,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Vithal S Mohare
> Sent: Monday, December 15, 2014 5:08 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] Walk through a given mbuf-pool elements
>
> [Re-sending the mail after registering to dpdk.org]
>
Hi, Hiroshi,
Yes, the should be performance degradation, not only due to the mempool cache,
but also due to process scheduling overhead (lead by no CPU pin.)
I have not done the performance testing. In my project scenarios, those
SECONDARY processes only send/receive messages to/from the PRIMARY
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jay Rolette
> Sent: Thursday, December 11, 2014 5:06 PM
> To: Dev
> Subject: [dpdk-dev] [PATCH] replaced O(n^2) sort in sort_by_physaddr() with
> qsort() from standard library
>
> Signed-off-by: Jay Rolette
> -
FWIW, it surprised the heck out of me as well.
Turns out that even though I'm compiling in 64-bit mode, gcc has
sizeof(int) as 4 bytes rather than 8. Not really sure what the scoop is on
that, but the standard leaves that up to the compiler. I'm used to int
always being the "natural size" on the C
Because it doesn't work correctly :-)
On Mon, Dec 15, 2014 at 3:05 AM, Wodkowski, PawelX <
pawelx.wodkowski at intel.com> wrote:
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jay Rolette
> > Sent: Thursday, December 11, 2014 5:06 PM
> > To: Dev
> > Su
Hi Changchun,
Yes, we are trying add some startup parameter when we create VM. But
unfortunately our Guest OS kernel version is too low, it can't work.
# uname -r
2.6.34.13-WR4.3.fp_x86_64_standard-00027-g76285ab
Brs,
Fu Weiyi
-Original Message-
From: ext Ouyang, Changchun [mailto:chan
Hi,
I'm new to dpdk - played with execution_path, l2fwd and l3fwd examples.
I'm using 82599ES intel dual 10G interface on Xeon X5650 2.67GHz.
I got the following strange results with my tests:
1) Sending 10G in port 0 only - stand in line rate (no misses).
2) Sending 10G in port 1 only - stand i
[Re-sending the mail after registering to dpdk.org]
Team,
I am looking for a code/api to walk through a dpdk mbuf-pool elements (similar
to rte_mempool_walk() but for elements within mempool). Calling
pkt_mbuf_alloc for 'n' elements and then _free is not an option.
Rte_mempool_obj_itr() walk
Hi Weiyi,
Thanks for updating.
> -Original Message-
> From: Fu, Weiyi (NSN - CN/Hangzhou) [mailto:weiyi.fu at nsn.com]
> Sent: Monday, December 15, 2014 10:56 AM
> To: Fu, Weiyi (NSN - CN/Hangzhou); Ouyang, Changchun; dev at dpdk.org
> Cc: mmvijay at gmail.com
> Subject: RE: [dpdk-dev] In
Hi,
With follow changes, the link is UP and interface can receive and send traffic.
Thanks a lot:)
diff --git a/lib/librte_pmd_virtio/virtio_ethdev.c
b/lib/librte_pmd_virtio/virtio_ethdev.c
index 3344ffb..43d1c19 100644
--- a/lib/librte_pmd_virtio/virtio_ethdev.c
+++ b/lib/librte_pmd_virtio/virt
56 matches
Mail list logo