On Fri, May 15, 2015 at 12:54:19PM +, Assaad, Sami (Sami) wrote:
> Thanks Bruce for your reply.
>
> Yes, your idea of bringing the PF into the VM looks like an option. However,
> how do you configure the physical interfaces within the VM supporting SRIOV?
> I always believed that the VM neede
Hi,
I have a query-why Linux top command does not show the NUMA pages allocated by
a DPDK process in Resident Memory? Is it a missing functionality in Linux top
command or some limitation, Please excuse my ignorance if I missed something
very obvious?
As an example if I allocated 512 NUMA page
Hi ,
If do not enable dpdk, plian ovs can pass about 120,000 pps but once I make
ovs to use dpdk the main reason in doing this is to get more performance I am
seeing that it is passing only 1000 pps.
So I guess the drop from 120,000 to just 1000 means I am missing something.
Regards,
Ravi
---
On Fri, May 15, 2015 at 04:43:33PM +0300, Nikita Kalyazin wrote:
> Hi,
>
>
> Maybe I missed a part of the discussion, but is there any special purpose for
> using rte_mb (both read and write fence) here rather than rte_wmb (write
> fence only)?
The fence is between write of used->idx and read
Added optional ip version check to l3fwd app to allow to detect
the ip version if mbuf ol_flags are not set in case of running
in a VM with emulated network controllers
Signed-off-by: Andrey Chilikin
---
examples/l3fwd/main.c | 22 ++
1 files changed, 22 insertions(+), 0 de
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ravi Rao
> Sent: Friday, May 15, 2015 5:12 PM
> To: therbert at redhat.com; dev at dpdk.org
> Subject: Re: [dpdk-dev] performance issue with ovs + dpdk2.0 with vhost
>
> Hi,
> This is what I am trying to Do
On Fri, 15 May 2015 16:56:02 +0800
Shaopeng He wrote:
> fm10k was failing to run in XEN domain0, as the physical
> memory for DMA should be allocated and translated
> in a different way for XEN domain0. So
> rte_memzone_reserve_bounded() should be used for DMA
> memory allocation, and rte_mem_phy
Since the PMDs have moved to the drivers directory, update the docs that
cover the source code organisation of DPDK
Signed-off-by: Bruce Richardson
---
doc/guides/prog_guide/source_org.rst | 37 +---
1 file changed, 26 insertions(+), 11 deletions(-)
diff --git a/
Update the directory list in the GSG to reflect recent changes of PMDs
to the drivers directory
Signed-off-by: Bruce Richardson
---
doc/guides/linux_gsg/build_dpdk.rst | 8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/doc/guides/linux_gsg/build_dpdk.rst
b/doc/guides/li
Following the move of the PMDs to the drivers directory, update the
maintainers file appropriately.
Signed-off-by: Bruce Richardson
---
MAINTAINERS | 28 ++--
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 0477e7d..9362c19
Move xenvirt PMD to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile | 2 +-
drivers/net/xenvirt/Makefile | 62 ++
drivers/net/xenvirt/rte_eth_xenvirt.c | 714 +
drivers/net/xenv
Move vmxnet3 PMD to drivers/net directory.
As part of the move, rename the "vmxnet3" subdirectory, containing the
original FreeBSD drivers, from "vmxnet3" to the more standard name
"base", to indicate it contains the base drivers used for the
implementation.
Signed-off-by: Bruce Richardson
---
d
Move virtio PMD to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/virtio/Makefile | 60 +
drivers/net/virtio/rte_pmd_virtio_version.map|4 +
drivers/net/virtio/virtio_ethdev.c
Move ring PMD to drivers directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile | 2 +-
drivers/net/ring/Makefile| 61 +++
drivers/net/ring/rte_eth_ring.c | 579 +++
drivers/net/ring/rte_eth_ring.h
Move pcap pmd to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile | 2 +-
drivers/net/pcap/Makefile| 63 ++
drivers/net/pcap/rte_eth_pcap.c | 994 +++
drivers/net/pcap/rte_pmd_pcap_v
Move null PMD to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile | 2 +-
drivers/net/null/Makefile| 62 +++
drivers/net/null/rte_eth_null.c | 585 +++
drivers/net/null/rte_pmd_null_
move mlx4 PMD to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/mlx4/Makefile| 121 +
drivers/net/mlx4/mlx4.c | 4686 ++
drivers/net/mlx4/mlx4.h
move ixgbe PMD to drivers/net directory.
As part of the move, we rename the ixgbe directory, containing the
ixgbe "base driver" code, from "ixgbe" to "base".
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/ixgbe/Makefile
Move i40e PMD to drivers/net directory.
As part of the move, rename the "i40e" directory, containing the "base
driver" code, from "i40e" to "base".
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/i40e/Makefile| 105 +
d
move fm10k PMD to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/fm10k/Makefile | 102 ++
drivers/net/fm10k/base/fm10k_api.c | 341
drivers/net/fm10k/base/fm10k_api.h
move enic PMD to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/enic/LICENSE | 27 +
drivers/net/enic/Makefile| 71 ++
drivers/net/enic/enic.h | 200 ++
Move e1000 pmd to drivers/net directory
As part of move, rename "e1000" subdirectory, which contains the code
from the "base driver", to "base".
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile |2 +-
drivers/net/e1000/Makefile | 99 +
Move bonded ethdev pmd to drivers/net
Signed-off-by: Bruce Richardson
---
doc/api/doxy-api.conf |2 +-
drivers/net/Makefile |2 +-
drivers/net/bonding/Makefile | 68 +
drivers/net/bonding/rte_eth_bond.h
move af_packet pmd to drivers/net directory
Signed-off-by: Bruce Richardson
---
drivers/net/Makefile | 2 +-
drivers/net/af_packet/Makefile | 64 ++
drivers/net/af_packet/rte_eth_af_packet.c | 847 +
drivers/net/af
Add a new top-level "drivers" directory to which all PMDs will be moved
for easier maintenance of both lib folder and drivers themselves. This
new directory is a dependency of all the apps in the app folder, so
the makefiles for each app are updated.
To the new top-level directory add a "net" subdi
In the Makefiles for the PMDs, the paths to the files are often
specified using the full path from $(RTE_SDK) variable. These paths can
be shortened, and make more flexible in case of a future path change by
specifying the paths using $(SRCDIR) instead.
Signed-off-by: Bruce Richardson
---
lib/li
As covered previously in an RFC, this patchset creates a new top-level drivers
folder and moves the PMDs into it. Moving the drivers involves a lot of code -
too big for a single patch, so each driver is moved separately in its own
patchset.
Some doc updates are done as part of this patchset - ba
fm10k was failing to run in XEN domain0, as the physical
memory for DMA should be allocated and translated
in a different way for XEN domain0. So
rte_memzone_reserve_bounded() should be used for DMA
memory allocation, and rte_mem_phy2mch() should be used
for DMA memory address translation to suppor
On Fri, 15 May 2015 14:08:52 +0800
Jijiang Liu wrote:
> + while (dev_ll != NULL) {
> + /*get virtio device ID*/
Really minor style nit. Please put whitespace in comments.
Do this instead.
/* get virtio device ID */
Also, the name virtio is confusing since
I agree that this is great to see a real example of this
On Fri, 15 May 2015 14:08:52 +0800
Jijiang Liu wrote:
> +static unsigned
> +check_ports_num(unsigned nb_ports)
> +{
> + unsigned valid_nb_ports = nb_ports;
> + unsigned portid;
> +
> + if (nb_ports > nb_ports) {
> +
Hi,
Maybe I missed a part of the discussion, but is there any special purpose for
using rte_mb (both read and write fence) here rather than rte_wmb (write fence
only)?
--
Best regards,
Nikita Kalyazin,
n.kalyazin at samsung.com
Software Engineer
CE OS Group
Samsung R&D Institute Russia
Tel
Hey guys,
Can we in function bond_mode_8023ad_activate_slave() try to add to the
slave bond and LACP multicast MACs first? And then we would fall back
into promiscuous mode if the adding has failed.
In other words:
if (rte_eth_dev_mac_addr_add(slave_id, bond_mac) != 0
|| rte_eth_dev_mac_addr_
2015-05-13 16:58, Bruce Richardson:
> On Wed, May 13, 2015 at 02:40:48PM +0100, Bruce Richardson wrote:
> > On Wed, May 13, 2015 at 03:33:27PM +0200, Thomas Monjalon wrote:
> > > 2015-05-13 11:01, Bruce Richardson:
> > > > On Tue, May 12, 2015 at 09:30:45PM +0200, Thomas Monjalon wrote:
> > > >> 20
2015-05-15 13:36, Bruce Richardson:
> On Wed, May 13, 2015 at 02:40:48PM +0100, Bruce Richardson wrote:
> > On Wed, May 13, 2015 at 03:33:27PM +0200, Thomas Monjalon wrote:
> > > 2015-05-13 11:01, Bruce Richardson:
> > > > On Tue, May 12, 2015 at 09:30:45PM +0200, Thomas Monjalon wrote:
> > > >> 20
On Fri, May 15, 2015 at 02:54:50PM +0200, Thomas Monjalon wrote:
> 2015-05-13 16:58, Bruce Richardson:
> > On Wed, May 13, 2015 at 02:40:48PM +0100, Bruce Richardson wrote:
> > > On Wed, May 13, 2015 at 03:33:27PM +0200, Thomas Monjalon wrote:
> > > > 2015-05-13 11:01, Bruce Richardson:
> > > > > O
The two flags are enabled by default, but sometimes we want to know the
performance influence of the encapsulation and decapsulation operations, and
I think we should add the two options.
Signed-off-by: Jijiang Liu
---
examples/tep_termination/main.c| 36 +
The number of packets with bad RX IP and L4 checksum in inner header is
recorded.
Signed-off-by: Jijiang Liu
---
examples/tep_termination/main.c| 10 +-
examples/tep_termination/main.h|4
examples/tep_termination/vxlan_setup.c |8
3 files changed,
If the 'tso-segsz' is not 0, which means TSO offload is enabled.
Signed-off-by: Jijiang Liu
---
examples/tep_termination/main.c| 17 +
examples/tep_termination/vxlan.c |6 ++
examples/tep_termination/vxlan.h |1 +
examples/tep_termination/vxlan_s
For VXLAN packet, the inner Tx checksum offload means inner IPv4 and inner
L4(TCP/UDP/SCTP).
Signed-off-by: Jijiang Liu
---
examples/tep_termination/main.c | 17
examples/tep_termination/vxlan.c | 80 ++
2 files changed, 97 insertions(+), 0 dele
The follwoing filter types are supported for VXLAN,
1> Inner MAC&VLAN and tenent ID
2> Inner MAC and tenent ID, and Outer MAC
3> Inner MAC and tenent ID
Signed-off-by: Jijiang Liu
---
examples/tep_termination/main.c| 20
examples/tep_termination/vxlan_setup.c | 52 +++
The port number of UDP tunneling packet is configurable, which has 16 entries
in total for i40e.
Signed-off-by: Jijiang Liu
---
examples/tep_termination/main.c| 18 +-
examples/tep_termination/vxlan_setup.c | 13 -
2 files changed, 29 insertions(+), 2 del
Implement the following functions:
1> VXLAN port configuration
2> VXLAN tunnel setup
3> VXLAN tunnel destroying
4> VXLAN packet processing for Rx side
5> VXLAN packet processing for Tx side
Signed-off-by: Jijiang Liu
Signed-off-by: Thomas Long
---
examples/tep_termination/Makefile |
We are trying to create a framework for tunneling packet processing, so some
common APIs are added here, which includes
1> tunnel port configuration
2> tunnel setup
3> tunnel destroying
4> tunneling packet processing for Rx side
5> tunneling packet processing for Tx side
6> tunnel parameter
Some basic VXLAN definations are added in this file, which includes VXLAN port
information and VXLAN device structures.
Signed-off-by: Jijiang Liu
Signed-off-by: Thomas Long
---
examples/tep_termination/main.c |1 +
examples/tep_termination/vxlan.h | 60
This sample uses the basic virtio devices management function from the vHost
example, which includes virtio device creation, destroying and maintenance.
Signed-off-by: Jijiang Liu
---
examples/Makefile |1 +
examples/tep_termination/Makefile | 55 ++
examples/tep_terminati
This VXLAN sample simulates a VXLAN Tunnel Endpoint (VTEP) termination in DPDK,
which is used to demonstrate the offload and filtering capabilities of i40 NIC
for VXLAN packet.
And this sample uses the basic virtio devices management function from vHOST
example, and the US-vHost interface and t
On Fri, May 15, 2015 at 12:54:19PM +, Assaad, Sami (Sami) wrote:
> Thanks Bruce for your reply.
>
> Yes, your idea of bringing the PF into the VM looks like an option. However,
> how do you configure the physical interfaces within the VM supporting SRIOV?
> I always believed that the VM neede
On Fri, May 15, 2015 at 02:50:37PM +0200, Thomas Monjalon wrote:
> 2015-05-15 13:36, Bruce Richardson:
> > On Wed, May 13, 2015 at 02:40:48PM +0100, Bruce Richardson wrote:
> > > On Wed, May 13, 2015 at 03:33:27PM +0200, Thomas Monjalon wrote:
> > > > 2015-05-13 11:01, Bruce Richardson:
> > > > > O
> -Original Message-
> From: Assaad, Sami (Sami) [mailto:sami.assaad at alcatel-lucent.com]
> Sent: Friday, May 15, 2015 2:00 PM
> To: Ananyev, Konstantin; Richardson, Bruce; Stephen Hemminger
> Cc: dev at dpdk.org
> Subject: RE: [dpdk-dev] How do you setup a VM in Promiscuous Mode using
Hi All,
I am trying to get a Guest VM connected to the dpdkvhost interface on a host
which has the ovs running from the latest ovs git and dpdk2.0. Looks like I am
missing something as 95% of traffic is not getting to the VM. Can one of you
please let me know which mailing list I should be po
On Wed, May 13, 2015 at 02:40:48PM +0100, Bruce Richardson wrote:
> On Wed, May 13, 2015 at 03:33:27PM +0200, Thomas Monjalon wrote:
> > 2015-05-13 11:01, Bruce Richardson:
> > > On Tue, May 12, 2015 at 09:30:45PM +0200, Thomas Monjalon wrote:
> > >> 2015-05-12 19:04, Bruce Richardson:
> > >>> dri
Thanks Konstantin for your reply.
Konstantin,
Would you be able in providing more details as to ixgbe VF mirroring?
Would you have any valuable URL's or documentation that explain this in detail
and/or provide examples?
Thanks in advance.
Best Regards,
Sami.
-Original Message-
From:
Thanks Bruce for your reply.
Yes, your idea of bringing the PF into the VM looks like an option. However,
how do you configure the physical interfaces within the VM supporting SRIOV?
I always believed that the VM needed to be associated with a virtual/emulated
interface card. With your suggestio
Hi,
2015-05-15 16:56, Shaopeng He:
> +#ifdef RTE_LIBRTE_XEN_DOM0
> + q->hw_ring_phys_addr = rte_mem_phy2mch(mz->memseg_id, mz->phys_addr);
> +#else
> q->hw_ring_phys_addr = mz->phys_addr;
> +#endif
I know this is already done this way in other drivers, but don't you think
it's time to c
Hello, I have strange issue with example/vhost app.
I had compiled DPDK to run a vhost example app with followed flags
CONFIG_RTE_LIBRTE_VHOST=y
CONFIG_RTE_LIBRTE_VHOST_USER=y
CONFIG_RTE_LIBRTE_VHOST_DEBUG=n
then I run vhost app based on documentation:
./build/app/vhost-switch -c f -n 4 --hug
Hi,
This is what I am trying to Do.
Below is the setup..
| +--+ |
| guest| |
| | |
| | | guest
| eth0 L3fwd e
On 5/15/15 9:55 AM, Rao, Ravi wrote:
> Hi All,
> I am trying to get a Guest VM connected to the dpdkvhost interface on a
> host which has the ovs running from the latest ovs git and dpdk2.0. Looks
> like I am missing something as 95% of traffic is not getting to the VM. Can
> one of you plea
On Thu, May 14, 2015 at 04:47:19PM -0700, Stephen Hemminger wrote:
> On Thu, 14 May 2015 21:38:24 +
> "Assaad, Sami (Sami)" wrote:
>
> > Hello,
> >
> > My Hardware consists of the following:
> > - DL380 Gen 9 Server supporting two Haswell Processors (Xeon CPU E5-2680
> > v3 @ 2.50GHz)
> >
Change the log level of startup messages. Anything that is
just normal activity (like getting virtual areas) is changed
to debug level. Anything that is a failure should be NOTICE
or ERR severity.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/linuxapp/eal/eal.c | 2 +-
lib/l
Hi Zi,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zi Hu
> Sent: Friday, May 15, 2015 1:27 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] DPDK ACL bug? pkt matches the wrong ACL rule.
>
> Hi, there,
>
> I recently noticed that sometimes packets are matc
The ixgbe driver likes to be far to chatty in the system log
which is good for the original developer but not good for a production
product. All the normal messages should be changed from INFO to DEBUG.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.c | 14 +++---
This driver should follow standard DPDK practice and use
RTE_LOG macro which allows setting config option to remove
the debug log messages.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_logs.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/lib/librte_pmd_
The driver does lots of logging at INFO level, but some setup
events are significant and should be at NOTICE or ERR level
since they are problems that user should see.
Also never put tabs in log messages because they get mangled
by syslog processing.
Signed-off-by: Stephen Hemminger
---
lib/lib
Printing PCI information on link state change is unnecessary since
the same information has already been displayed earlier in the log.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.c | 5 -
1 file changed, 5 deletions(-)
diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethde
Don't do unnecessary casts when logging messages. Better to use
the correct printf format code.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_ixgbe/ixgbe_ethdev.c | 25 -
1 file changed, 12 insertions(+), 13 deletions(-)
diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethd
This set of patches is breakout of earlier set of patches to
get rid of the log spam from ixgbe driver.
Stephen Hemminger (5):
ixgbe: remove unnecessary casts
ixgbe: don't print PCI address on link change
ixgbe: raise priority of significant events
ixgbe: use RTE_LOG not rte_log
ixgbe: s
On 5/15/15 9:55 AM, Rao, Ravi wrote:
> Hi All,
> I am trying to get a Guest VM connected to the dpdkvhost interface on a
> host which has the ovs running from the latest ovs git and dpdk2.0. Looks
> like I am missing something as 95% of traffic is not getting to the VM. Can
> one of you plea
This problem was discovered when passing invalid PCI id to the
blacklist API in devargs.
Any failures in rte_devargs_add would cause a core dump because
it would call rte_log() before the the EAL log environment was
initailized. Rather than try and log just remove the messages
and leave it up to
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Bruce Richardson
> Sent: Friday, May 15, 2015 10:27 AM
> To: Stephen Hemminger
> Cc: dev at dpdk.org; Assaad, Sami (Sami)
> Subject: Re: [dpdk-dev] How do you setup a VM in Promiscuous Mode using PCI
> Pass-Th
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jijiang Liu
> Sent: Friday, May 15, 2015 7:09 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 00/10] Add a VXLAN sample
Hi,
There are multiple changes on the same (new) files within the patchset. These
70 matches
Mail list logo
