When eth_virtio_dev_init is failed, the registered virtio user memory event
cb is not released and the backend created tap device is not destroyed.
It would cause some residual tap device existed in the host and creating
a new vdev could be failed because the new virtio_user_dev could use the
same
The problem this patch wants to solve can be reproduced by ovs-dpdk:
1. create a kni port in ovs:
ovs-vsctl add-port ovs-br0 kni0 -- set Interface kni0 type=dpdk
options:dpdk-devargs=net_kni0
2. change the mtu of the kni device in kernel:
ip link set kni0 mtu 1500
If we do not set rte_kni_conf
> -Original Message-
> From: Stephen Douthit
> Sent: Thursday, December 23, 2021 05:44
> To: Wang, Haiyue ; Morten Brørup
> ; Lu, Wenzhuo
> ; Zhang, Helin ; Zhang, Qi Z
>
> Cc: dev@dpdk.org; Wang, Wen ; sta...@dpdk.org
> Subject: Re: [PATCH v2 3/7] net/ixgbe: Check that SFF-8472 soft ra
From Steve's response:
ME: "I guess this is just in C3000 reference board SDK ?"
Steve: "It's the board covered by Intel Doc # 574437."
I check the doc "Last Updated: 11/07/2018" It should be some kind
of customer release, that's why
they are not in the official *open source*
> From: Robert Sanford [mailto:rsanfo...@gmail.com]
> Sent: Wednesday, 22 December 2021 17.20
>
> - Add RING_F_EXACT_SZ description to rte_ring_init and
> rte_ring_create param comments.
> - Fix ring size comments.
>
> Signed-off-by: Robert Sanford
> ---
> lib/ring/rte_ring.h | 24 ++
> From: Wang, Haiyue [mailto:haiyue.w...@intel.com]
> Sent: Wednesday, 22 December 2021 17.03
>
> > -Original Message-
> > From: Morten Brørup
> > Sent: Wednesday, December 22, 2021 18:44
> >
> > > From: Wang, Haiyue [mailto:haiyue.w...@intel.com]
> > > Sent: Wednesday, 22 December 2021 0
https://bugs.dpdk.org/show_bug.cgi?id=917
Bug ID: 917
Summary: [20.11.4-rc1][mlx5] application with MPRQ enabled
crashes when receiving a packet
Product: DPDK
Version: 20.11
Hardware: All
OS: All
https://bugs.dpdk.org/show_bug.cgi?id=916
Bug ID: 916
Summary: [20.11.4-rc1][mlx5] 2% single core packet forwarding
performance degradation
Product: DPDK
Version: 20.11
Hardware: All
OS: All
Stat
On Wed, 22 Dec 2021 08:25:49 +
Ruitao Gong wrote:
> hi DEVers,
>
> Send this mail for some help about VPP and DPDK.
> rte_eth_stats_get (xd->port_id, &xd->stats)
> rte_eth_xstats_get (xd->port_id, xd->xstats, len)
> APIs in dpdk_update_counters() node "dpdk_process" will cost about 140ms
https://bugs.dpdk.org/show_bug.cgi?id=915
Bug ID: 915
Summary: [20.11.4-rc1][mlx5] segfault when changing number of
rxqs
Product: DPDK
Version: 20.11
Hardware: All
OS: All
Status: UNCONFIRMED
On Wed, 22 Dec 2021 08:54:00 +0800
Yanling Song wrote:
> > If all you want is jiffie accuracy, you could use
> > CLOCK_MONOTONIC_COARSE.
> >
> I did not get your point: CLOCK_MONOTONIC is more accurate than
> CLOCK_MONOTONIC_COARSE, right?
CLOCK_MONOTONIC ends up using the TSC counter and va
- Add RING_F_EXACT_SZ description to rte_ring_init and
rte_ring_create param comments.
- Fix ring size comments.
Signed-off-by: Robert Sanford
---
lib/ring/rte_ring.h | 24
lib/ring/rte_ring_elem.h | 2 +-
2 files changed, 21 insertions(+), 5 deletions(-)
diff -
> -Original Message-
> From: Morten Brørup
> Sent: Wednesday, December 22, 2021 18:44
> To: Wang, Haiyue ; steph...@silicom-usa.com; Lu,
> Wenzhuo ;
> Zhang, Helin ; Zhang, Qi Z
> Cc: dev@dpdk.org; Wang, Wen ; sta...@dpdk.org
> Subject: RE: [PATCH v2 3/7] net/ixgbe: Check that SFF-8472 s
On Wed, Nov 17, 2021 at 11:20:17AM +0100, Thomas Monjalon wrote:
> 01/10/2021 17:41, Bruce Richardson:
> > On Fri, Oct 01, 2021 at 05:36:51PM +0200, Thomas Monjalon wrote:
> > > 01/10/2021 17:15, Bruce Richardson:
> > > > On Fri, Oct 01, 2021 at 05:03:11PM +0200, Thomas Monjalon wrote:
> > > > > 15
Standard "find" on BSD does not support the "-printf" so gfind from
findutils package was used to enable full doc builds. We can remove this
extra dependency by using "sed" and "tr" to adjust the output from
regular find instread.
Fixes: 8260f4f98cfe ("mk: use script to generate examples.dox")
Fix
> From: Zhiheng Chen [mailto:chenzhiheng0...@gmail.com]
> Sent: Wednesday, 22 December 2021 09.26
>
> Compared to patch version 1, this version updates the descriptions
> of underlying functions.
Some comments inline below, regarding the return value of success.
You should also update the descri
> -Original Message-
> From: Guo, Junfeng
> Sent: Wednesday, December 22, 2021 4:12 PM
> To: Zhang, Qi Z ; Wu, Jingjing ;
> Xing, Beilei
> Cc: dev@dpdk.org; sta...@dpdk.org; Yigit, Ferruh ;
> Guo, Junfeng
> Subject: [PATCH v3] net/ice: fix pattern check for FDIR parser
>
> FDIR rules
> From: Wang, Haiyue [mailto:haiyue.w...@intel.com]
> Sent: Wednesday, 22 December 2021 02.24
>
> > -Original Message-
> > From: Morten Brørup
> > Sent: Tuesday, December 21, 2021 16:58
> >
> > > From: Wang, Haiyue [mailto:haiyue.w...@intel.com]
> > > Sent: Tuesday, 21 December 2021 02.15
Compared to patch version 1, this version updates the descriptions
of underlying functions.
In rte_mempool_ring.c, the committer uses the symbol ENOBUFS to
describe the return value of function common_ring_sc_dequeue,
but in rte_mempool.h, the symbol ENOENT is used to describe
the return value of
hi DEVers,
Send this mail for some help about VPP and DPDK.
rte_eth_stats_get (xd->port_id, &xd->stats)
rte_eth_xstats_get (xd->port_id, xd->xstats, len)
APIs in dpdk_update_counters() node "dpdk_process" will cost about 140ms
each physical interface every 10s (DPDK_STATS_POLL_INTERVAL).
Thanks for your suggestions and time, I will update the underlying functions.
[Public]
Hi David Marchand,
I have submitted v2 patch with your suggestion in git log. Please review
changes.
Regards,
Chandu
-Original Message-
From: Namburu, Chandu-babu
Sent: Thursday, December 2, 2021 9:41 PM
To: dev@dpdk.org; david.march...@redhat.com
Cc: Sebastian, Selwin ; ars
When eth_virtio_dev_init is failed, the registered virtio user memory
event cb is not released and creating a new vdev could be failed
because the new virtio_user_dev could use the same address pointer and
register memory event cb to the same address is not allowed.
Signed-off-by: Harold Huang
--
FDIR rules with masks are not supported in current code. Thus add
pattern check for IPv4/UDP/TCP/SCTP addr/port to terminate the FDIR
programming stage.
Fixes: 1b71ed2cdd5d ("net/ice: refactor flow pattern parser")
Cc: sta...@dpdk.org
Signed-off-by: Junfeng Guo
---
drivers/net/ice/ice_fdir_filt
FDIR rules with masks are not supported in current code. Thus add
pattern check for IPv4/UDP/TCP/SCTP addr/port to terminate the FDIR
programming stage.
Fixes: 1b71ed2cdd5d ("net/ice: refactor flow pattern parser")
Cc: sta...@dpdk.org
Signed-off-by: Junfeng Guo
---
drivers/net/ice/ice_fdir_filt
FDIR rules with masks are not supported in current code. Thus add
pattern check for IPv4/UDP/TCP/SCTP addr/port to terminate the FDIR
programming stage.
Fixes: 1b71ed2cdd5d ("net/ice: refactor flow pattern parser")
Cc: sta...@dpdk.org
Signed-off-by: Junfeng Guo
---
drivers/net/ice/ice_fdir_filt
26 matches
Mail list logo
