On 09/21/2015 05:06 AM, Yuanhan Liu wrote:
> On Sun, Sep 20, 2015 at 04:58:42PM +0300, Marcel Apfelbaum wrote:
>> On 09/18/2015 06:10 PM, Yuanhan Liu wrote:
>>> All queue pairs, including the default (the first) queue pair,
>>> are allocated dynamically, when a vring_call message is received
>>>
Hello Shaham:
> I upgraded from dpdk 1.8.0 to 2.1.0 and my compilation now fails with the
> following errors:
I don't have an immediate solution, but may I suggest you check (and perhaps
post) what compiler you are using and what version.
I am aware of Linux source code bundles that failed
Hello All,
I'm DPDK extensible bucket hash in the rte_table library of packet framework.
My question is related to the actual hash function that computes the hash
signature.
All the available examples have initialized it to test_hash. I do not see any
hash function available in rte_table
Hi, Harry.
Sorry, but minimum size of packets we can generate is 64 bytes long.
Best regards,
Igor
> 21 . 2015 ?., ? 16:45, Van Haaren, Harry
> ???(?):
>
>> From: Igor Ryzhov [mailto:iryzhov at arccn.ru]
>> Thank you, I'll wait for result of mspdc testing.
>
> Hi Igor,
>
>
Free the memory allocated by the backtrace_symbols
to prevent the memory leak
Signed-off-by: Zhe Tao
---
lib/librte_eal/bsdapp/eal/eal_debug.c | 6 ++
lib/librte_eal/linuxapp/eal/eal_debug.c | 6 ++
2 files changed, 12 insertions(+)
diff --git a/lib/librte_eal/bsdapp/eal/eal_debug.c
Hi,
I have a hard time understanding the configuration of multiple pthreads
in eal initialization.
Let's say I have a 4 lcore machine (2 phys. cores with HT) and I want to
run 7 threads on it.
I thought that these options would help me:
-c 0xf -l 0-6 --lcores='0,(1,3)@2,(2,4)@3,(5,6)@1'
But
In merge-able RX path, vhost injects interrupts to guest for each packet.
This should degrade performance a lot.
This patch fixes this issue by injecting one interrupt for a batch of packets.
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_rxtx.c | 7 +--
1 file changed, 5
On Fri, 18 Sep 2015 11:33:36 +0100
Alejandro Lucero wrote:
> I have seen the API definition says nothing about accuracy but some PMD
> implementations sacrifice accuracy for the sake of performance. If I'm not
> understanding the code wrongly i40e and ixgbe check DD bit just for the
> first
On Wed, 16 Sep 2015 22:51:24 +0100
Pablo de Lara wrote:
> This is important to avoid trying to start/stop twice a queue,
> which will result in undefined behaviour
> (which may cause RX/TX disruption).
>
> Mind that only the PMDs which have queue_start/stop functions
> have been changed to
On Tue, 15 Sep 2015 15:06:33 +0200
Piotr Azarewicz wrote:
> + /*
> + * If we didnt manage to send all packets in single burst, move
Checkpatch complains:
WARNING: 'didnt' may be misspelled - perhaps 'didn't'?
#413: FILE: lib/librte_port/rte_port_ring.c:827:
+
On Tue, 15 Sep 2015 15:06:33 +0200
Piotr Azarewicz wrote:
> +static inline void
> +send_burst_mp(struct rte_port_ring_writer *p)
> +{
compiler will inline static functions anyway. No need to add inline qualifier
On Tue, 15 Sep 2015 15:06:33 +0200
Piotr Azarewicz wrote:
> +static int
> +rte_port_ring_multi_reader_rx(void *port, struct rte_mbuf **pkts, uint32_t
> n_pkts)
> +{
Please break arguments on line so that line length is not over 80 characters.
Old flow director APIs have been replaced by rte_eth_dev_filter_ctrl
since release 2.0. And no drivers in current code support these APIs.
All the removed APIs are list below:
- rte_eth_dev_fdir_add_perfect_filter;
- rte_eth_dev_fdir_add_signature_filter;
- rte_eth_dev_fdir_get_infos;
-
> -Original Message-
> From: Serguei Bezverkhi (sbezverk) [mailto:sbezverk at cisco.com]
> Sent: Monday, September 21, 2015 3:53 PM
> To: Ananyev, Konstantin; Van Haaren, Harry; dev at dpdk.org
> Subject: RE: getting pointer for struct ixgbe_hw
>
> Hi Konstantin,
>
> I need to setup
Hi Konstantin,
I need to setup certain parameters per VF from guest VM.
Here is the list:
#define IXGBE_VF_RESET0x01 /* VF requests reset */
#define IXGBE_VF_SET_MAC_ADDR 0x02 /* VF requests PF to set MAC addr */
#define IXGBE_VF_SET_MULTICAST 0x03 /* VF
Hi Serguei,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Serguei Bezverkhi
> (sbezverk)
> Sent: Monday, September 21, 2015 3:12 PM
> To: Van Haaren, Harry; dev at dpdk.org
> Subject: Re: [dpdk-dev] getting pointer for struct ixgbe_hw
>
> Hi Harry,
>
>
On Sun, Sep 20, 2015 at 12:21:14PM +0300, Michael S. Tsirkin wrote:
> On Fri, Sep 18, 2015 at 11:10:56PM +0800, Yuanhan Liu wrote:
> > From: Changchun Ouyang
> >
> > Fix the max virtio queue pair read issue.
> >
> > Control queue can't work for vhost-user mulitple queue mode,
> > so introduce a
> From: Kyle Larose [mailto:eomereadig at gmail.com]
> Can you disable the MAC padding on the NIC through a backdoor register
> access?
Good idea - yes it looks like that's possible, TXPADEN register.
I'll look into it, and post back later. Thanks, -Harry
Hi Harry,
Thank you for your reply. The reason I was looking for specifically ixgbe_hw
because I needed access to ixgbe PF/VF mailbox facility. I am not sure if it is
exposed via rte_eth api. Please advise.
Best regards
Serguei
Serguei Bezverkhi,
TECHNICAL LEADER.SERVICES
Global SP
Hi Serguei,
> From: Serguei Bezverkhi
> I would appreciate if somebody could share an example of getting access to
> ixgbe_hw structure for already initialized ixgbe nic. I tried to find any
> references but could not find any API returning pointer for this structure.
The ixgbe_hw struct is part
Hello,
I would appreciate if somebody could share an example of getting access to
ixgbe_hw structure for already initialized ixgbe nic. I tried to find any
references but could not find any API returning pointer for this structure.
Thank you
Serguei
Hey all,
I upgraded from dpdk 1.8.0 to 2.1.0 and my compilation now fails with the
following errors:
rte_memcpy.h:625:2: error: incompatible type for argument 2 of _mm_storeu_si128
emmintrin.h:701:1: note: expected __m128i but argument is of type int
Did anyone bounced into this issue? Any
> From: Igor Ryzhov [mailto:iryzhov at arccn.ru]
> Thank you, I'll wait for result of mspdc testing.
Hi Igor,
Regarding your original question:
The datasheet says that a packet with total size < 32 bytes is
discarded by MAC layer and counted in the mspdc register.
If possible, I would like to
On Sun, Sep 20, 2015 at 04:58:42PM +0300, Marcel Apfelbaum wrote:
> On 09/18/2015 06:10 PM, Yuanhan Liu wrote:
> >All queue pairs, including the default (the first) queue pair,
> >are allocated dynamically, when a vring_call message is received
> >first time for a specific queue pair.
> >
> >This
On Mon, Sep 21, 2015 at 10:25:18AM +0800, Yuanhan Liu wrote:
> On Sun, Sep 20, 2015 at 12:29:17PM +0300, Michael S. Tsirkin wrote:
> > On Fri, Sep 18, 2015 at 11:10:53PM +0800, Yuanhan Liu wrote:
> > > From: Changchun Ouyang
> > >
> > > Do not use VIRTIO_RXQ or VIRTIO_TXQ anymore; use the
On Mon, Sep 21, 2015 at 10:22:52AM +0800, Yuanhan Liu wrote:
> On Sun, Sep 20, 2015 at 12:37:35PM +0300, Michael S. Tsirkin wrote:
> > On Fri, Sep 18, 2015 at 11:10:54PM +0800, Yuanhan Liu wrote:
> > > From: Changchun Ouyang
> > >
> > > This message is used to enable/disable a specific vring
used event idx is put at the end of available ring. It isn't taken into account
when we calculate the address of used ring. Fortunately, it doesn't introduce
the bug with fixed queue number 256 and 4KB alignment.
Signed-off-by: hxie5
---
drivers/net/virtio/virtio_ring.h | 2 +-
1 file changed,
On Sun, Sep 20, 2015 at 12:29:17PM +0300, Michael S. Tsirkin wrote:
> On Fri, Sep 18, 2015 at 11:10:53PM +0800, Yuanhan Liu wrote:
> > From: Changchun Ouyang
> >
> > Do not use VIRTIO_RXQ or VIRTIO_TXQ anymore; use the queue_id,
> > instead, which will be set to a proper value for a specific
On Sun, Sep 20, 2015 at 12:37:35PM +0300, Michael S. Tsirkin wrote:
> On Fri, Sep 18, 2015 at 11:10:54PM +0800, Yuanhan Liu wrote:
> > From: Changchun Ouyang
> >
> > This message is used to enable/disable a specific vring queue pair.
> > The first queue pair is enabled by default.
> >
> >
On Mon, Sep 21, 2015 at 9:45 AM, Van Haaren, Harry
wrote:
>> From: Igor Ryzhov [mailto:iryzhov at arccn.ru]
>> Thank you, I'll wait for result of mspdc testing.
>
> Hi Igor,
>
> Regarding your original question:
> The datasheet says that a packet with total size < 32 bytes is
> discarded by MAC
Hi Reza,
As your log displays below, you have an error in EAL initialization:
EAL: Error - exiting with code: 1
I suggest you try to dig up the source code to understand which is the line of
code triggering this error in your system and why.
Regards,
Cristian
> -Original Message-
>
On Sun, Sep 20, 2015 at 04:58:42PM +0300, Marcel Apfelbaum wrote:
> On 09/18/2015 06:10 PM, Yuanhan Liu wrote:
> >All queue pairs, including the default (the first) queue pair,
> >are allocated dynamically, when a vring_call message is received
> >first time for a specific queue pair.
> >
> >This
Hello Helin, Bruce,
On Sun, Sep 20, 2015 at 4:51 PM, Helin Zhang wrote:
> It enlarges the number of supported queues to hardware allowed
> maximum. There was a software limitation of 64 per physical port
> which is not reasonable.
>
I looked at the commit that introduced this limitation, can't
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Huawei Xie
> Sent: Monday, September 21, 2015 4:16 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] vhost: vhost injects interrupts to guest for each
> packet
>
> In merge-able RX path, vhost injects
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Huawei Xie
Sent: Monday, September 21, 2015 11:39 AM
To: dev at dpdk.org
Subject: [dpdk-dev] [PATCH] virtio: fix used ring address calculation
used event idx is put at the end of available ring. It isn't taken into
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Remy Horton
> Sent: Thursday, September 17, 2015 2:47 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v3] ixgbe: fix access to last byte of EEPROM
>
> Incorrect operator in ixgbe_get_eeprom &
Hi David
PF, VFs VMDq, FD on the same port share the queues, actually we can know the
total number of the queues, the maximum number of queues may vary depends on
how they will be used with PF, VF, VMDq AND FD.
So the users will define the number for each, the code will just check the
total
Hi,
> -Original Message-
> From: Wu, Jingjing
> Sent: Monday, September 21, 2015 3:34 PM
> To: dev at dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Lu, Wenzhuo
> Subject: [PATCH] ethdev: remove old flow director APIs
>
> Old flow director APIs have been replaced by rte_eth_dev_filter_ctrl
Tested-by: Qian Xu
Commit: c36a82f045ae362b76af4f2a53af10a2a4d2d20f
Test platform: HSW server
OS: Fedora 20
Kernel : 3.18
1. Bind 2ports to igb_uio
2. Run vmdq sample : ./examples/vmdq/build/vmdq_app -n 4 -c 0x1e -- -p 0x3
--nb-pools 63
3. Send 63 flows with different MAC/VLAN and see the output.
> -Original Message-
> From: Sun, Xutao
> Sent: Monday, September 21, 2015 1:45 PM
> To: dev at dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Sun, Xutao
> Subject: [PATCH] examples/vmdq: Fix the core dump issue when mem_pool
> is more than 34
>
> Macro MAX_QUEUES was defined to 128, only
40 matches
Mail list logo