I think the base_virtadd will be carefully selected by user when they need it.
So maybe it's not a real problem. ?:>The real reason is I can't find a easy way
to get the end address of hugepages. Can you give me some?suggestions
?--
> > This patch set fix packet length issue in vhost app, and enhance code by
> > extracting a function to replace duplicated codes in one copy and zero copy
> > TX function.
> >
> > -v4 chang:
> > Check offset value and extra bytes inside packet buffer cross page
> > boundary.
> >
> > -v3 chang
2014-11-05 21:55, Xie, Huawei:
> > 2014-11-05 21:21, Xie, Huawei:
> Btw, for alignment in structure, I see different projects use different way,
> some use tab, and some use space(between type and var), do we have rules for
> this?
> {
> Typevar1
> Typevar2
> }
I prefer using
> > The set of patches split x86 architecture specific operations from DPDK and
> > put
> > them to x86 arch directory.
> > This will make the adoption of DPDK much easier on other computer
> > architecture.
> > For a new architecture, just add an architecture specific directory and
> > necessary
> > Signed-off-by: Matthew Hall
>
> Acked-by: Bruce Richardson
Applied
Thanks
--
Thomas
> On FreeBSD, when initializing a secondary process,
> EAL was complaining if there were ports not bound
> to nic_uio module, exiting the application, which
> should not happen, as this is expected behaviour,
> and not an error
>
> Signed-off-by: Pablo de Lara
Acked-by: Thomas Monjalon
Applied
> > When building shared libs (for both GCC and CLANG targets), -fPIC flag
> > has been added to CFLAGS and leaks to BSD module build system causing
> > the following error:
> >
> > fatal error: error in backend: Cannot select: 0x802ad8010: i64 =
> > X86ISD::WrapperRIP 0x802ade110
> > [ID=13
Hi Thomas,
Thanks for sharing the links to ibverbs, I will take a close look at it and
compare it to bifurcated driver. My take
after a rough review is that idea is very much similar, but bifurcated driver
implementation is generic for any
Ethernet device based on existing af_packet mechanism,
> When using Intel C++ compiler(icc) 14.0.1.106 or the older icc 13.x
> version, the mbuf initializer variable was not getting configured
> correctly, as the mb_def variable was not set correctly. This is due
> to an issue with icc (DPD200249565 which already been fixed in
> icc 14.0.2 and newer co
> > The commit 15dbb63ef9e9f108e7dcd837b88234f27a1ec258 didn't compile,
> > if CONFIG_RTE_LIBRTE_I40E_DEBUG_DRIVER is enabled.
> >
> > Signed-off-by: Choonho Son
>
> Acked-by: Pablo de Lara
Applied
Thanks
--
Thomas
> Since commit a155d430119 ("support link bonding device initialization"),
> rte_eal_pci_probe() is called in rte_eal_init().
> pci_autotest called it to bind devices to the test_driver and test_driver2.
> Therefore, the function is called twice and devices already allocated
> will cause the test f
2014-11-05 21:21, Xie, Huawei:
> Thomas:
> I checked before. checkpatch reports 9 warnings, "over 80 characters" and
> "prefer pr_deubg".
> This code style fixes code style issue only, not the pr_debug/printk issue.
> Thoughts?
Using pr_debug is a code style fix.
> Besides, I don't understand
From: Alex Markuze [mailto:a...@weka.io]
Sent: Wednesday, November 05, 2014 11:19 PM
To: Thomas Monjalon
Cc: Zhou, Danny; dev at dpdk.org; Fastabend, John R
Subject: Re: [dpdk-dev] bifurcated driver
On Wed, Nov 5, 2014 at 5:14 PM, Alex Markuze mailto:alex at
weka.io>> wrote:
On Wed, Nov 5, 20
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, November 05, 2014 2:25 PM
> To: Xie, Huawei
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] lib/librte_vhost: code style fixes
>
> 2014-11-05 21:21, Xie, Huawei:
> > Thomas:
> > I
2014-10-31 17:03, Helin Zhang:
> #define ETH_RSS_RETA_SIZE_64 64
> #define ETH_RSS_RETA_SIZE_128 128
> #define ETH_RSS_RETA_SIZE_512 512
Are these values still needed?
Why 256 is forbidden?
Maybe that some comments are needed here.
> +#define RTE_RETA_GROUP_SIZE 64
Hi Huawei,
checkpatch.pl reports some errors of types PREFER_PR_LEVEL
and MISORDERED_TYPE.
--
Thomas
---
lib/librte_eal/linuxapp/eal/eal_pci_uio.c | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c
b/lib/librte_eal/linuxapp/eal/eal_pci_uio.c
index 7e62266..bc7ed3a 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c
+++ b/lib/l
Thomas:
I checked before. checkpatch reports 9 warnings, "over 80 characters" and
"prefer pr_deubg".
This code style fixes code style issue only, not the pr_debug/printk issue.
Thoughts?
Besides, I don't understand the MISORDERED_TYPE.
> -Original Message-
> From: Thomas Monjalon [mai
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jingjing Wu
> Sent: Thursday, October 30, 2014 7:27 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v5 05/21] i40e: implement operations to
> add/delete flow director
>
> Deal with two operations for flo
Hi Bruce,
OK understood. Then there's no real need to make any change.
But the question remains about this line:
http://dpdk.org/browse/dpdk/tree/lib/librte_distributor/rte_distributor.c#n285
new_tag = (next_mb->hash.rss | 1);
Why the logical OR is needed?
thx &
rgds,
-qinglai
On Wed
> Since release 1.7.1 and patchset "tailq fully local", the test
> eal_flags_autotest doesn't work anymore. It fails because it doesn't
> find any free hugepage (rte_memzone_reserve).
>
> The interesting commits are:
> http://dpdk.org/browse/dpdk/commit/?id=e3f3b68c6e42
> http://dpdk.o
2014-11-05 13:24, De Lara Guarch, Pablo:
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Anatoly Burakov
> > Sent: Wednesday, November 05, 2014 12:11 PM
> > To: dev at dpdk.org
> > Subject: [dpdk-dev] [PATCH] Fix regression for eal_flags_autotest
> > in
2014-11-05 16:52, Xie, Huawei:
> Why don't we merge 1,2,3 patches?
Because it's simpler to understand small patches with a dedicated
explanation in the commit log of each patch.
Why do you want to merge them?
--
Thomas
2014-11-05 11:54, Ananyev, Konstantin:
> From: Thomas Monjalon
> > + long master_lcore;
> > + char *parsing_end;
> > + struct rte_config *cfg = rte_eal_get_configuration();
> > +
> > + errno = 0;
> > + master_lcore = strtol(arg, &parsing_end, 0);
> > + if (errno || parsing_end == arg)
>
When start a secondary process, we got error message "EAL: pci_map_resource():
cannot mmap(11, 0x77fba000, 0x2, 0x0): Bad file descriptor
(0x77fb9000)"
The secondary process link difference shared libraries, so the 0x77fba000
is used.
We know the --base_virtaddr is designed f
Hi Konstantin,
I agree with you. A callback is not necessary. Pls refer to my previous
mail, which proposed a not-at-all-intrusive patch.
Pls let me know your concern.
thx &
rgds,
-qinglai
On Wed, Nov 5, 2014 at 5:13 PM, Ananyev, Konstantin <
konstantin.ananyev at intel.com> wrote:
>
>
> >
On Wed, Nov 5, 2014 at 5:14 PM, Alex Markuze wrote:
> On Wed, Nov 5, 2014 at 3:00 PM, Thomas Monjalon > wrote:
>
>> Hi Danny,
>>
>> 2014-10-31 17:36, O'driscoll, Tim:
>> > Bifurcated Driver (Danny.Zhou at intel.com)
>>
>> Thanks for the presentation of bifurcated driver during the community
>> c
On Wed, Nov 5, 2014 at 3:00 PM, Thomas Monjalon
wrote:
> Hi Danny,
>
> 2014-10-31 17:36, O'driscoll, Tim:
> > Bifurcated Driver (Danny.Zhou at intel.com)
>
> Thanks for the presentation of bifurcated driver during the community call.
> I asked if you looked at ibverbs and you wanted a link to che
Hi Bruce,
Thanks for reply.
The idea is triggered by real life use case, where the flow id is buried in
L3 payload. Deep packet inspection is one of the scenarios, tunneled pkts
is another.
However, only functionality is verified. Performance impact has not been
checked yet.
To add distributor an
:(.
Resent done. Please drop this patch.
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, November 05, 2014 2:10 AM
> To: Xie, Huawei
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] lib/librte_vhost: code style fixes
>
> Hi Huaw
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, November 05, 2014 10:01 AM
> To: Xie, Huawei
> Cc: dev at dpdk.org; Ouyang, Changchun
> Subject: Re: [dpdk-dev] [PATCH v4 3/3] vhost: Check offset value
>
> 2014-11-05 16:52, Xie, Huawei
> -Original Message-
> From: Ouyang, Changchun
> Sent: Wednesday, November 05, 2014 12:11 AM
> To: dev at dpdk.org
> Cc: Xie, Huawei; Ananyev, Konstantin; Cao, Waterman; Ouyang, Changchun
> Subject: [PATCH v4 3/3] vhost: Check offset value
>
> This patch checks the packet length offset v
> -Original Message-
> From: Ouyang, Changchun
> Sent: Wednesday, November 05, 2014 12:11 AM
> To: dev at dpdk.org
> Cc: Xie, Huawei; Ananyev, Konstantin; Cao, Waterman; Ouyang, Changchun
> Subject: [PATCH v4 1/3] vhost: Fix packet length issue
>
> As HW vlan strip will reduce the packet l
On Wed, Nov 05, 2014 at 05:11:51PM +0200, jigsaw wrote:
> Hi Bruce,
>
> Thanks for reply.
> The idea is triggered by real life use case, where the flow id is buried in
> L3 payload. Deep packet inspection is one of the scenarios, tunneled pkts
> is another.
> However, only functionality is verifie
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Choonho Son
> Sent: Wednesday, November 05, 2014 3:16 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] i40e: fix build of VXLAN packet identification
> debug
>
> The commit 15dbb63ef9e9f108e7dcd837b88234
Ah, that makes sense. So you?re actually hitting the very issue I?m concerned
about when mapping purely with base-virtaddr (a library is mapped into where
you?re trying to map your UIO resources).
Well, as I said, you can try and walk the memsegs and work out the biggest
end-address of hugepage
Hi Liang
Yes it is a problem. Even if it was carefully selected by user, nothing stops
the DPDK application from mapping something into where you?re trying to map
your UIO devices. Plus, this changes the default behavior where a wrong
base-virtaddr leads to a failure to initialize, rather than
User defined tag calculation has access to mbuf.
Default tag is RSS hash result.
Signed-off-by: Qinglai Xiao
---
app/test/test_distributor.c |6 +++---
app/test/test_distributor_perf.c |2 +-
lib/librte_distributor/rte_distributor.c | 12 ++--
lib/librte_di
Hi,
I have a DPDK application running on QEMU-KVM environment using DPDK 1.6.0.
I am trying to port the same to DPDK version 1.7.1.
I am using Virt-manager GUI to assign e1000 emulated port to the VM. This
works fine in DPDK 1.6.0. The device is identified by IGB_UIO and
initialized by my applica
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Bruce Richardson
> Sent: Wednesday, November 05, 2014 2:28 PM
> To: Qinglai Xiao
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] Add user defined tag calculation callback to
> librte_distributor.
>
>
This patch checks the packet length offset value, and checks if the extra bytes
inside buffer
cross page boundary.
Signed-off-by: Changchun Ouyang
---
examples/vhost/main.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/examples/vhost/main.c b/examples/vhost/main.c
i
Extract a function to replace duplicated codes in one copy and zero copy TX
function.
Signed-off-by: Changchun Ouyang
---
examples/vhost/main.c | 139 +-
1 file changed, 58 insertions(+), 81 deletions(-)
diff --git a/examples/vhost/main.c b/examp
As HW vlan strip will reduce the packet length by minus length of vlan tag,
so it need restore the packet length by plus it.
Signed-off-by: Changchun Ouyang
---
examples/vhost/main.c | 12 ++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/examples/vhost/main.c b/example
This patch set fix packet length issue in vhost app, and enhance code by
extracting a function to replace duplicated codes in one copy and zero copy
TX function.
-v4 chang:
Check offset value and extra bytes inside packet buffer cross page boundary.
-v3 change:
Extract a function to replace dup
I have a slight problems with this patch.
The base_virtaddr doesn't necessarily correspond to an address that everything
gets mapped to. It's a "hint" of sorts, that may or may not be taken into
account by mmap. Therefore we can't simply assume that if we requested a
base-virtaddr, everything w
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Sergio Gonzalez
> Monroy
> Sent: Thursday, October 30, 2014 10:58 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] mk: --no-as-needed by default for linux exec-
> env
>
> Ubuntu/Debian toolchain passes -
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Sergio Gonzalez
> Monroy
> Sent: Thursday, October 30, 2014 4:59 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] mk: pass MODULE_CFLAGS to BSD module
> build system
>
> When building shared libs (for bo
On Wed, Nov 05, 2014 at 03:30:37PM +0200, Qinglai Xiao wrote:
> User defined tag calculation has access to mbuf.
> Default tag is RSS hash result.
>
Interesting idea.
Did you investigate was there any performance improvement or regression
comparing
whether the callback was called per-packet as
Hi Danny,
2014-10-31 17:36, O'driscoll, Tim:
> Bifurcated Driver (Danny.Zhou at intel.com)
Thanks for the presentation of bifurcated driver during the community call.
I asked if you looked at ibverbs and you wanted a link to check.
The kernel module is here:
http://git.kernel.org/cgit/li
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Anatoly Burakov
> Sent: Wednesday, November 05, 2014 12:11 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] Fix regression for eal_flags_autotest
> introduced by tailq rework
>
> As a result of moving ta
This patch fixes code style issues and refines some comments in vhost library.
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 244 ++---
lib/librte_vhost/eventfd_link/eventfd_link.h | 127 ++-
lib/librte_vhost/rte_virtio_net.h| 3 +-
lib/librte_vhost/vho
This patch fixes code style issues and refines some comments in vhost library.
---
lib/librte_vhost/eventfd_link/eventfd_link.c | 244 ++---
lib/librte_vhost/eventfd_link/eventfd_link.h | 127 ++-
lib/librte_vhost/rte_virtio_net.h| 3 +-
lib/librte_vhost/vho
As a result of moving tailq's into local memory, some tailq data
is now reserved in rte_malloc heaps (because it needs to be
shared across DPDK processes). The first thing DPDK initializes
is a log mempool, and since it creates a tailq, it reserves
space in rte_malloc heap before allocating the mem
As a result of moving tailq's into local memory, some tailq data
is now reserved in rte_malloc heaps (because it needs to be
shared across DPDK processes). The first thing DPDK initializes
is a log mempool, and since it creates a tailq, it reserves
space in rte_malloc heap before allocating the mem
Hi Thomas,
Few questions/comments below.
Konstantin
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Tuesday, November 04, 2014 9:41 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v2] eal: add option --master-lcore
>
> From: Simon Kuenzer
>
> Enable users
The patch was attached and automatically dropped.
Please follow these guidelines:
http://dpdk.org/dev#send
2014-11-05 09:58, De Lara Guarch, Pablo:
> Patch is missing.
>
> Thanks,
> Pablo
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of XU Lia
Acked-by: Aaron Campbell mailto:aaron at arbor.net>>
Minor comments inline below, I don?t need to see another patch.
Thanks,
-Aaron
> On Nov 4, 2014, at 5:40 PM, Thomas Monjalon
> wrote:
>
> + RTE_LOG(ERR, EAL, "please specify the master lcore id"
> +
> On Nov 4, 2014, at 3:00 PM, Thomas Monjalon
> wrote:
>
> 2014-11-03 13:02, Aaron Campbell:
>>> On Jul 8, 2014, at 5:28 AM, Simon Kuenzer
>>> wrote:
>>>
>>> + else if (!strcmp(lgopts[option_index].name,
>>> OPT_MASTER_LCORE)) {
>>> + if (!coremask
Hi Jijiang,
Thank you for your answer. Please find some comments below.
On 11/05/2014 07:02 AM, Liu, Jijiang wrote:
>> First, the code checks if the mbuf has the flag PKT_RX_TUNNEL_IPV4_HDR.
>> What is the meaning of this flag? It was added by [3], but there is no
>> description
>> in comments o
> The set of patches split x86 architecture specific operations from DPDK and
> put
> them to x86 arch directory.
> This will make the adoption of DPDK much easier on other computer
> architecture.
> For a new architecture, just add an architecture specific directory and
> necessary building con
On Wed, Nov 05, 2014 at 03:28:13PM +0530, Manoj Viswanath wrote:
> Hi,
>
> I have a DPDK application running on QEMU-KVM environment using DPDK 1.6.0.
> I am trying to port the same to DPDK version 1.7.1.
>
> I am using Virt-manager GUI to assign e1000 emulated port to the VM. This
> works fine i
On Tue, Nov 04, 2014 at 08:45:53PM +, Wiles, Roger Keith wrote:
>
> >>
> > Can you provide a real example here? usnig vague terms like "huge" really
> > makes
> > more of an emotional argument than a factual one. To cite an example the
> > cmdline_test program adds a command line paramter
Hi Huawei,
Please set a Signed-off in your patch.
2014-11-05 12:42, Huawei Xie:
> This patch fixes code style issues and refines some comments in vhost library.
>
>
> ---
> lib/librte_vhost/eventfd_link/eventfd_link.c | 244 ++---
> lib/librte_vhost/eventfd_link/eventfd_link.h
Patch is missing.
Thanks,
Pablo
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of XU Liang
> Sent: Wednesday, November 05, 2014 9:50 AM
> To: dev
> Subject: [dpdk-dev] [PATCH] eal: map uio resources after hugepages when --
> base_virtaddr is configured
>
>
Hi
I've read the Intel 82599 official manual and I found that optimal
PTHRESH is the tx descriptor buffer size - N (N is CPU cache line
divided by 16).
1. I guess the size of the tx descriptor buffer is 128. Isn't it right?
Where is the size of the tx descriptor buffer in the official manual
> From: Ouyang, Changchun
> Sent: Wednesday, November 05, 2014 7:11 AM
> To: dev at dpdk.org
> Cc: Xie, Huawei; Ananyev, Konstantin; Cao, Waterman; Ouyang, Changchun
> Subject: [PATCH v4 0/3] Fix packet length issue
>
> This patch set fix packet length issue in vhost app, and enhance code by
> ext
Hey Folks,
I ran into the same issue that Alex is describing here, and I wanted to
expand just a little bit on his comments, as the documentation isn't very
clear.
Per the documentation, the two arguments to rte_pktmbuf_pool_init() are a
pointer to the memory pool that contains the newly-allocate
On Wed, Nov 05, 2014 at 09:43:43AM +0900, Gyumin wrote:
> Hi
>
> I've read the Intel 82599 official manual and I found that optimal
> PTHRESH is the tx descriptor buffer size - N (N is CPU cache line
> divided by 16).
This is sometimes true, but not always. I believe you are referring
to secti
Hi Olivier,
> -Original Message-
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Tuesday, November 4, 2014 4:19 PM
> To: Liu, Jijiang
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v8 10/10] app/testpmd:test VxLAN Tx checksum
> offload
>
> Hello Jijiang,
>
> On 1
Hi Thomas,
Yes. Xiaonan just want to confirm if yong's patch doesn't impact
original functionality and regression test cases under VMware.
Xiaonan will check with yong and see if we can add some test in the
regression to new changes.
Waterman
-Original Message-
Tested-by: Jiajia, SunX
- Tested Commit: f7aaae2fe6f7f9a78eab7313d77e92b934693b5d
- OS: Fedora20 3.11.10-301.fc20.x86_64 and 3.16.6-200.fc20.x86_64
- GCC: gcc version 4.8.2
- CPU: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
- NIC: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection
[8
Hi Yong,
We tested your patch with VMWare ESX 5.5.
It works fine with R1.8 RC1.
You can find more details from Xiaonan's reports.
Regards
Waterman
>-Original Message-
>From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Yong Wang
>Sent: Tuesday, October 14,
This patch introduces CONFIG_RTE_KNI_PREEMPT flag. When set to 'no', KNI
kernel thread(s) do not call schedule_timeout_interruptible(), which improves
overall KNI performance at the expense of CPU cycles (polling).
Default values is 'yes', maintaining the same behaviour as of now.
Note: this RFC
2014-10-12 23:23, Yong Wang:
> Signed-off-by: Yong Wang
Please, could you give some explanations to put in the commit log?
Thanks
--
Thomas
> > v3:
> > - Fix comments style.
> > - Simplify words in comments.
> > - Add variable defintion for BSD config file.
> > - Code rebase to latest DPDK repo.
> >
> > v2:
> > - Fix a few typos.
> > - Add comments for RX mq mode flags.
> > - Remove '\n' from some log messages.
> > - Remove 'Acked-by'
75 matches
Mail list logo
