-Original Message-
From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com]
Sent: Wednesday, January 11, 2017 6:55 PM
To: Shahaf Shuler
Cc: dev@dpdk.org; Elad Persiko; Hanoch Haim (hhaim)
Subject: Re: [PATCH] net/mlx5: support extended statistics
Hi Shahaf,
Thanks, I have a few comments, most
Hi Tim,
It's great that you are going to expose the i40E Qos capability, would it be
possible to expose the low-latency configuration too?
Thanks,
Hanoh
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of O'Driscoll, Tim
Sent: Friday, January 13, 2017 12:24 PM
To: de
Hi,
We (trex traffic generator project) upgrade DPDK version from 16.07 to
17.02arc-3 and we experienced a performance degradation on the following NICS:
XL710 : 10-15%
ixgbe : 8% in one case
mlx5: 8% 2 case
X710: no impact (same driver as XL710)
VIC : no impact
It might be r
ion
Thanks,
Hanoh
-Original Message-
From: Mcnamara, John [mailto:john.mcnam...@intel.com]
Sent: Tuesday, February 14, 2017 2:19 PM
To: Hanoch Haim (hhaim); dev@dpdk.org
Cc: Ido Barnea (ibarnea)
Subject: RE: [dpdk-dev] DPDK 17.02 RC-3 performance degradation of ~10%
> -Original M
don't fully understand
that).
Mlx5 small degradation wasn't solved yet.
Thanks,
Hanoh
-Original Message-
From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
Sent: Tuesday, February 14, 2017 3:05 PM
To: Hanoch Haim (hhaim)
Cc: dev@dpdk.org; Mcnamara, John; Ido Barne
Hi Bruce,
I'm Hanoch from Cisco Systems works for the
https://github.com/cisco-system-traffic-generator/trex-core traffic generator
project.
While upgrading from DPDK 1.8 to 2.2 Ido found that the following commit
creates a mbuf corruption and result in Tx hang
commit f20b50b946da9070d21e3
Hi All,
DPDK:17.11
When i40e is configured with RSS enabled and hash.type=toeplitz
m->hash.rss = some weird number
((m->ol_flags&PKT_RX_RSS_HASH) == PKT_RX_RSS_HASH
The hash value is correct and match the MS Toeplitz standard.
Is this expected?
The above works fine with ixgbe/mlx5
Thanks,
Hano
Hi mlx5 driver expert,
DPDK: 17.11
Any reason mlx5 driver change the rate table size dynamically based on the rx-
queues# ?
There is a hidden assumption that the user wants to distribute the packets
evenly which is not always correct.
/* If the requested number of RX queues is not a power of tw
: Wednesday, March 21, 2018 11:48 PM
To: Hanoch Haim (hhaim)
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] mlx5 reta size is dynamic
On Wed, Mar 21, 2018 at 06:56:33PM +, Hanoch Haim (hhaim) wrote:
> Hi mlx5 driver expert,
>
> DPDK: 17.11
> Any reason mlx5 driver change the rate table size dynam
018 10:55 AM
To: Hanoch Haim (hhaim)
Cc: Yongseok Koh; dev@dpdk.org
Subject: Re: [dpdk-dev] mlx5 reta size is dynamic
On Thu, Mar 22, 2018 at 06:52:53AM +0000, Hanoch Haim (hhaim) wrote:
> Hi Yongseok,
>
>
> RSS has a DPDK API,application can ask for the reta table size and
> conf
< not round of 64 , depends on the number of rx queues
Hanoh
-Original Message-
From: Nélio Laranjeiro [mailto:nelio.laranje...@6wind.com]
Sent: Thursday, March 22, 2018 11:28 AM
To: Hanoch Haim (hhaim)
Cc: Yongseok Koh; dev@dpdk.org
Subject: Re: [dpdk-dev] mlx5 reta size is dynamic
Hi
nge it under traffic and it works
>without issue.
Drivers tested are: igbe/i40e/mlx5
Thanks,
Hanoh
-Original Message-
From: Nélio Laranjeiro [mailto:nelio.laranje...@6wind.com]
Sent: Thursday, March 22, 2018 12:46 PM
To: Hanoch Haim (hhaim)
Cc: Yongseok Koh; dev@dpdk.org
Subject: Re: [dpd
ng TRex
Thanks,
Hanoh
-Original Message-
From: Bruce Richardson [mailto:bruce.richard...@intel.com]
Sent: Thursday, March 22, 2018 1:35 PM
To: Hanoch Haim (hhaim)
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] i40e mbuf->rss indication
On Wed, Mar 21, 2018 at 06:47:22PM +, Hanoch Ha
élio Laranjeiro [mailto:nelio.laranje...@6wind.com]
Sent: Thursday, March 22, 2018 2:29 PM
To: Hanoch Haim (hhaim)
Cc: Yongseok Koh; dev@dpdk.org
Subject: Re: [dpdk-dev] mlx5 reta size is dynamic
Hi,
On Thu, Mar 22, 2018 at 10:59:36AM +0000, Hanoch Haim (hhaim) wrote:
> Hi,
>
> 1) Regarding this sent
Hi,
I think this is not the vector driver because I'm user scatter/gather
Thanks,
Hanoh
-Original Message-
From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
Sent: Thursday, March 22, 2018 2:18 PM
To: Hanoch Haim (hhaim); Bruce Richardson
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev]
iginal Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
Sent: Thursday, March 22, 2018 2:22 PM
To: Hanoch Haim (hhaim) mailto:hh...@cisco.com>>
Cc: Yigit, Ferruh mailto:ferruh.yi...@intel.com>>;
dev@dpdk.org<mailto:dev@dpdk.org>
Subject: Re: [
Hi All,
I've found a minor issue in the function "rte_pktmbuf_prefree_seg"
This code is located here :
/dpdk/lib/librte_mbuf/rte_mbuf.h
- } else if (rte_atomic16_add_return(&m->refcnt_atomic, -1) == 0)
Should be :
+ } else if (likely(rte_mbuf_refcnt_update(m, -1) == 0)) {
This depends on
I would add this too
- } else if (rte_atomic16_add_return(&m->refcnt_atomic, -1) == 0)
Should be :
+ } else if (likely(rte_mbuf_refcnt_update(m, -1) == 0)) {
Hanoh
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ilya Matveychikov
Sent: Tuesday, November 14,
will run faster.
Thanks,
Hanoh
-Original Message-
From: Ilya Matveychikov [mailto:matvejchi...@gmail.com]
Sent: Wednesday, November 15, 2017 1:14 PM
To: Hanoch Haim (hhaim)
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH v3] mbuf: cleanup rte_pktmbuf_lastseg(), fix
atomic usage
> O
return NULL;
Hanoh
-Original Message-
From: Olivier MATZ [mailto:olivier.m...@6wind.com]
Sent: Wednesday, November 15, 2017 7:31 PM
To: Hanoch Haim (hhaim)
Cc: Ilya Matveychikov; dev@dpdk.org; Konstantin Ananyev
Subject: Re: [dpdk-dev] [PATCH v3] mbuf: cleanup rte
Understood
rte_mbuf_refcnt_update_blind()
should be good., it will take care the RTE_MBUF_REFCNT_ATOMIC
Hanoh
-Original Message-
From: Olivier MATZ [mailto:olivier.m...@6wind.com]
Sent: Thursday, November 16, 2017 10:42 AM
To: Hanoch Haim (hhaim)
Cc: Konstantin Ananyev; Ilya
Hi All,
While integrating dpdk17.11 into TRex latest code a new latency issue is
observed (i40e is very sensitive because it has very good resolution due to
Qos configuration).
git bitsec found the following commit.
With this commit we observe high spikes of Rx latency (~40usec) vs (~8usec).
Any
Re-sending
Hanoh
From: Hanoch Haim (hhaim)
Sent: Monday, November 20, 2017 5:19 PM
To: dev@dpdk.org
Cc: Wu, Jingjing (jingjing...@intel.com); Hanoch Haim (hhaim)
Subject: [dpdk-dev] net/i40e: latency issue due fix interrupt throttling
setting in PF
Hi All,
While integrating dpdk17.11 into TRex
Hi All,
Significant performance degradation observed with DPDK 17.11
The Scenario is with TRex traffic generator
(https://github.com/cisco-system-traffic-generator/trex-core)
1. Stateless mode, 64B packet stream (multi-core/single core)
DPDK 17.02 - 37-39MPPS/core
DPDK 17.11 - 33.5MPPS/c
patch and fix this latency issue in the different way?
Thanks,
Hanoh
From: Wu, Jingjing [mailto:jingjing...@intel.com]
Sent: Tuesday, November 28, 2017 2:50 PM
To: Hanoch Haim (hhaim); dev@dpdk.org
Subject: RE: [dpdk-dev] net/i40e: latency issue due fix interrupt throttling
setting in PF
Hi, Ha
From: Wu, Jingjing [mailto:jingjing...@intel.com]
Sent: Tuesday, November 28, 2017 5:01 PM
To: Hanoch Haim (hhaim)
Cc: dev@dpdk.org
Subject: RE: [dpdk-dev] net/i40e: latency issue due fix interrupt throttling
setting in PF
Hi, Hanoch
If DPDK PF, the commit affects that because it introduces an argumen
...@intel.com]
Sent: Tuesday, November 28, 2017 5:01 PM
To: Hanoch Haim (hhaim)
Cc: dev@dpdk.org
Subject: RE: [dpdk-dev] net/i40e: latency issue due fix interrupt throttling
setting in PF
Hi, Hanoch
If DPDK PF, the commit affects that because it introduces an argument (itr_idx)
for i40e_vsi_ena
device?
I guess it would be because that fix is not complete, the overlap with Rx
interrupt mode is not considered. We will look into it.
And it would be great if you can have a try on vfio_pci cases.
Thanks
Jingjing
From: Hanoch Haim (hhaim) [mailto:hh...@cisco.com]
Sent: Friday, December 1, 2
Hi All,
I want to configure 4 RX queues when rx-queue=1 is masked by RSS
So in case I have 4 rx-queues 0,1,2,3 I want to get packets only from 0,2,3 by
RSS. Not so complex.
1) Enable RSS
port_conf.rxmode.mq_mode = ETH_MQ_RX_RSS;
port_conf.rx_adv_conf.rss_conf.rss_hf = E
ency is measured betwean Tx1 to Rx1
Thanks,
Hanoh
-Original Message-
From: Xing, Beilei [mailto:beilei.x...@intel.com]
Sent: Wednesday, December 06, 2017 1:00 PM
To: Wu, Jingjing; Hanoch Haim (hhaim)
Cc: dev@dpdk.org
Subject: RE: [dpdk-dev] net/i40e: latency issue due fix interrupt thrott
Oliver, Looks great.
Thanks,
Hanoh
-Original Message-
From: Olivier Matz [mailto:olivier.m...@6wind.com]
Sent: Friday, December 08, 2017 5:47 PM
To: dev@dpdk.org; Hanoch Haim (hhaim)
Cc: matvejchi...@gmail.com; konstantin.anan...@intel.com
Subject: [PATCH v4] mbuf: fix mbuf free
f_attach(m1, m_const)
tx_burst(m1) |tx_burst(m2)
thanks,
Hanoh
-Original Message-
From: Olivier MATZ [mailto:olivier.m...@6wind.com]
Sent: Monday, January 04, 2016 3:53 PM
To: Hanoch Haim (hhaim); bruce.richardson at intel.com
Cc: dev at dpdk.org;
ter to the documentation that state that that you can't call
the atomic ref counter from more than one thread?
Thanks,
Hanoh
-Original Message-
From: Olivier MATZ [mailto:olivier.m...@6wind.com]
Sent: Tuesday, January 05, 2016 12:58 PM
To: Hanoch Haim (hhaim); bruce.richardson at in
, 2016 1:48 PM
To: Hanoch Haim (hhaim)
Cc: Olivier MATZ; dev at dpdk.org; Ido Barnea (ibarnea); Itay Marom (imarom)
Subject: Re: [dpdk-dev] [PATCH v2] mbuf: optimize rte_mbuf_refcnt_update
On Tue, Jan 05, 2016 at 11:11:24AM +, Hanoch Haim (hhaim) wrote:
> Hi Oliver,
> Thank you for th
Hi,
We have a DPDK 2.2 application and on specific server types with ix40e driver
we have an issue that we can't push more 20MPPS on Tx. (SW gets back pressure
from software queue, in other words the NIC is not happy)
Moving to 16.4 fix the issue.
Wanted to identify this specific issue throw
35 matches
Mail list logo
