Thanks Bruce so much! That perfectly solves my problem.
Tim
At 2015-05-25 18:28:48, "Bruce Richardson"
wrote:
>On Mon, May 25, 2015 at 06:15:23PM +0800, Tim Deng wrote:
>> Hi,
>>
>>
>> I am trying to use ixgbe tcp cksum h/w offload by following steps:
>> - populate pseudo cksum
>> - set l2_le
Any objections to this one? Otherwise I will rebase and propose a formal
patch
marc
On 12/05/15 01:45, Marc Sune wrote:
> The current rte_eth_dev_info abstraction does not provide any mechanism to
> know the supported speed(s) of an ethdev.
>
> For some drivers (e.g. ixgbe), an educated guess ca
In rte_mempool_obj_iter(), even when a single page is required per object,
a loop checks that the the next page is contiguous and drops the first one
otherwise. This commit checks subsequent pages only when several are
required per object.
Also a minor fix for the amount of remaining space that pr
rte_mempool_xmem_usage()'s return type is ssize_t which has the same
architecture-dependent width as size_t but is signed.
On 64-bit architectures, returning a negative uint32_t value without casting
to ssize_t first does not work as intended, the sign bit is lost and the
returned value is garbage
Hi Adrien,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Adrien Mazarguil
> Sent: Monday, May 25, 2015 5:28 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 2/2] mempool: fix pages computation to determine
> number of objects
>
> In rte_mempool_obj_i
Hi,
I am trying to use ixgbe tcp cksum h/w offload by following steps:
- populate pseudo cksum
- set l2_len, l3_len, l4_len
- set ol_flags
But I found the pkt doesn't get right h/w checksum by sniffing on recv side,
and TCP cksum still leave with the original pseudo cksum.
And I verified thos
On 5/19/2015 1:40 AM, Stephen Hemminger wrote:
> +/* enable MSI-X interrupts */
> +static int
> +uio_msix_enable(struct rte_intr_handle *intr_handle)
> +{
> + int i, max_intr;
> +
> + if (!intr_handle->max_intr ||
> + intr_handle->max_intr > RTE_MAX_RXTX_INTR_VEC_ID)
> +
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Monday, May 25, 2015 3:06 PM
> To: Mcnamara, John
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 0/3] doc: refactored fig and table nums
> into references
>
>
> Applied, thanks
> It will
2015-05-18 12:34, John McNamara:
> This patchset adds automatic figure and table references to the docs. The
> figure and table numbers in the generated Html and PDF docs can now be
> automatically numbered.
>
> It replaces all hardcoded figure/table numbers and references.
>
> The numfig/numref
On Mon, May 25, 2015 at 09:54:14AM -0300, Victor Detoni wrote:
> Hi Bruce,
>
> Thanks for your answer. The complete output is attached.
>
Thanks for that. It looks like the compiler itself is crashing or getting killed
by the OS. Are you running in a memory-constrained environment, by any chance?
On 5/19/2015 1:40 AM, Stephen Hemminger wrote:
> +
> +/* set the mapping between vector # and existing eventfd. */
> +static int set_irq_eventfd(struct uio_msi_pci_dev *udev, u32 vec, int fd)
> +{
> + struct uio_msi_irq_ctx *ctx;
> + struct eventfd_ctx *trigger;
> + int irq, err;
> +
Hi Stephen,
On 05/15/2015 06:37 PM, Stephen Hemminger wrote:
> 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
> initaili
Hi Adrien,
On 05/22/2015 07:03 PM, Adrien Mazarguil wrote:
> ICMP echo replies with invalid checksums may be dropped by network nodes or
> ignored by the ping utility.
>
> Signed-off-by: Adrien Mazarguil
> Acked-by: Ivan Boule
Acked-by: Olivier Matz
> ---
>
> v2:
> - Compute correct check
The file rte_kni.h depends upon a number of other headers, some of which
are missing from the #include lines. The following #includes are added:
* rte_memory.h - for the definition of phys_addr_t
* rte_mempool.h - for the definition of mempool struct and the mempool
create function.
Signed-of
rte_pci.h depends upon stdio.h for the definition of the FILE type. Add
in #include to the file to satisfy this dependency in cases
where the including C file does not already include stdio.
Signed-off-by: Bruce Richardson
---
lib/librte_eal/common/include/rte_pci.h | 1 +
1 file changed, 1 ins
The convention in DPDK is that each header file should include
any other headers on which it depends. This patch set adds in
some missing header dependencies.
Bruce Richardson (2):
eal: add missing include to rte_pci.h
kni: add missing include dependencies
lib/librte_eal/common/include/rt
2015-05-21 13:33, Dumitrescu, Cristian:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > 2015-05-20 23:41, Dumitrescu, Cristian:
> > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > > > I think that counting stats is a kind of logging.
> > > > Some stats are always
Fix NULL dereference if virtio control queue is not negotiated.
Signed-off-by: Damjan Marion
---
drivers/net/virtio/virtio_ethdev.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virtio/virtio_ethdev.c
index f74e413..363
On Mon, May 25, 2015 at 06:15:23PM +0800, Tim Deng wrote:
> Hi,
>
>
> I am trying to use ixgbe tcp cksum h/w offload by following steps:
> - populate pseudo cksum
> - set l2_len, l3_len, l4_len
> - set ol_flags
>
>
> But I found the pkt doesn't get right h/w checksum by sniffing on recv side,
On Sat, May 23, 2015 at 10:20:46PM -0300, Victor Detoni wrote:
> Hi,
>
> I'm trying to install dpdk through freebsd's ports and the error is shown
> bellow. Please, someone knows if it can install on FreeBSD 10.1? And what
> means these errors?
>
> If I compile with gcc48 it works fine.
Thanks f
On Tue, 12 May 2015 01:45:45 +0200
Marc Sune wrote:
> +/**
> + * Ethernet device information
> + */
> struct rte_eth_dev_info {
> struct rte_pci_device *pci_dev; /**< Device PCI information. */
> const char *driver_name; /**< Device Driver name. */
> @@ -924,6 +947,7 @@ struct rte_et
On Mon, 25 May 2015 16:55:23 +0800
"Liang, Cunming" wrote:
> > + irqs.fd = intr_handle->fd;
> > +
> > + if (ioctl(intr_handle->vfio_dev_fd, UIO_MSI_IRQ_SET, &irqs) <
> > 0) {
> It would be strange if using vfio_dev_fd in 'uio_msix_' related function.
Just minor var
On Mon, 25 May 2015 14:01:14 +0800
"Liang, Cunming" wrote:
>
>
> On 5/19/2015 1:40 AM, Stephen Hemminger wrote:
> > +
> > +/* set the mapping between vector # and existing eventfd. */
> > +static int set_irq_eventfd(struct uio_msi_pci_dev *udev, u32 vec, int fd)
> > +{
> > + struct uio_msi_ir
Hi Bruce,
Thanks for your answer. The complete output is attached.
On Mon, May 25, 2015 at 6:49 AM, Bruce Richardson <
bruce.richardson at intel.com> wrote:
> On Sat, May 23, 2015 at 10:20:46PM -0300, Victor Detoni wrote:
> > Hi,
> >
> > I'm trying to install dpdk through freebsd's ports and the
Much Thanks.
>Thank You Andriy, You are right
>Below I put tested KVM configuration that put packets into vhost dpdk plane
>space:
>export TLBFS_DIR=/mnt/huge
>export UVH_PREFIX=/home/ubuntu/esi_ee/dpdk/examples/vhost/usvhost
>export VM1_MAC=00:01:04:00:01:00
>kvm -cpu host -smp 2 -enable-kvm \
25 matches
Mail list logo
