Also CC netdev, this thread may interest network folks.
Le 06/11/2014 09:13, Alex Markuze a ?crit :
> Danny sums up the issue perfectly IMHO.
> While both verbs and DPDK aim to provide generic user space networking, the
> similarities end there.
> verbs and RDMA HW are closely coupled and behave d
Le 29/07/2013 14:44, Thomas Monjalon a ?crit :
> - timecompare has been removed.
> (see Linux commit 65f8f9a1c1db831e5159e3e3e50912d1f214cd0c)
All this code is between 'ifdef HAVE_HW_TIME_STAMP'. Maybe just deactivating it
will help to port patches on this driver in the future.
>
> - annotations
Le 29/07/2013 14:44, Thomas Monjalon a ?crit :
> hlist API has changes.
> See Linux commit b67bfe0d42cac56c512dd5da4b1b347a23f4b70a.
>
> Signed-off-by: Thomas Monjalon
Acked-by: Nicolas Dichtel
Le 29/07/2013 14:44, Thomas Monjalon a ?crit :
> GCC 4.8 was producing this error:
> argument to ?sizeof? in ?strncmp? call is the same expression as the
> second source; did you mean to provide an explicit length?
> [-Werror=sizeof-pointer-memaccess]
>
> Signed-off-by: Thomas Mon
bbb6d094c
> and 80d5c3689b886308247da295a228a54df49a44f6.
>
> Signed-off-by: Thomas Monjalon
Acked-by: Nicolas Dichtel
be included before testing for
> HAVE_HW_TIME_STAMP.
>
> - annotations __devinit and __devexit have been removed.
> (see Linux commit 54b956b903607f8f8878754dd4352da6a54a1da2)
>
> Signed-off-by: Thomas Monjalon
> Tested-by: David Nystr?m
Acked-by: Nicolas Dichtel
ned-off-by: Thomas Monjalon
Acked-by: Nicolas Dichtel
Le 01/12/2014 06:45, Hemant at freescale.com a ?crit :
>> 2014-11-21 12:10, Takayuki Usui:
>>> With this patch, KNI interface (e.g. vEth0) is created in the network
>>> namespace where the DPDK application is running.
>>> Otherwise, all interfaces are created in the default namespace in the
>>> hos
Le 02/12/2014 03:19, Takayuki Usui a ?crit :
> With this patch, KNI interface (e.g. vEth0) is created in the
> network namespace where the DPDK application is running.
> Otherwise, all interfaces are created in the default namespace
> in the host.
>
> put_net() is required, since get_net_ns_by_pid(
get_net_ns_by_pid() increments
> the reference counter of the network namespace with get_net().
>
> Signed-off-by: Takayuki Usui
Signed-off-by: Nicolas Dichtel
Le 12/12/2014 13:06, Sergio Gonzalez Monroy a ?crit :
> Known issue regarding iommu/VT-d and igb_uio on Linux kernel version
> 3.15 to 3.17 where unbinding the device from the driver removes the 1:1
Do you mean that the problem doesn't exist with a linux 3.18?
> mapping for the device on the iommu
Le 12/12/2014 14:20, Gonzalez Monroy, Sergio a ?crit :
>> From: Nicolas Dichtel [mailto:nicolas.dichtel at 6wind.com]
>> Sent: Friday, December 12, 2014 1:00 PM
>>
>> Le 12/12/2014 13:06, Sergio Gonzalez Monroy a ?crit :
>>> Known issue regarding iommu/VT-d an
Le 12/12/2014 14:38, Gonzalez Monroy, Sergio a ?crit :
>> From: Nicolas Dichtel [mailto:nicolas.dichtel at 6wind.com]
>> Sent: Friday, December 12, 2014 1:28 PM
>>
>> Le 12/12/2014 14:20, Gonzalez Monroy, Sergio a ?crit :
>>>> From: Nicolas Dichtel [mailto:nic
t/?id=4244de1c64de
Signed-off-by: Nicolas Dichtel
Reviewed-by: David Marchand
---
lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 11 +++
1 file changed, 11 insertions(+)
diff --git a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
index 192bd4a
t/?id=4244de1c64de
Signed-off-by: Nicolas Dichtel
Reviewed-by: David Marchand
---
v2: use compat.h and define HAVE_PCI_ENABLE_MSIX
limit commit log to 75 columns
lib/librte_eal/linuxapp/igb_uio/compat.h | 4
lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 11 +++
2 files change
Le 20/04/2017 à 13:59, Ferruh Yigit a écrit :
> On 4/20/2017 10:01 AM, Nicolas Dichtel wrote:
>> pci_enable_msix() will be removed in kernel 4.12. The new API is available
>> since linux 4.8, thus let's use it.
>>
>> Link:
>> https://git.kernel.org/pub/s
t/?id=4244de1c64de
Signed-off-by: Nicolas Dichtel
Reviewed-by: David Marchand
Acked-by: Ferruh Yigit
---
v3: move code in compat.h at the end of the file
v2: use compat.h and define HAVE_PCI_ENABLE_MSIX
limit commit log to 75 columns
lib/librte_eal/linuxapp/igb_uio/compat.h | 4
Le 03/05/2017 à 18:00, Ferruh Yigit a écrit :
> build error:
> .../build/build/lib/librte_eal/linuxapp/kni/igb_main.c:1034:10:
> error: implicit declaration of function ‘pci_enable_msix’
> [-Werror=implicit-function-declaration]
> err = pci_enable_msix(pdev,
> ^~~
>
>
Le 03/05/2017 à 18:43, Ferruh Yigit a écrit :
> On 5/3/2017 5:39 PM, Nicolas Dichtel wrote:
>> Le 03/05/2017 à 18:00, Ferruh Yigit a écrit :
>>> build error:
>>> .../build/build/lib/librte_eal/linuxapp/kni/igb_main.c:1034:10:
>>> error: implicit decl
Le 21/11/2014 04:10, Takayuki Usui a ?crit :
> With this patch, KNI interface (e.g. vEth0) is created in the
> network namespace where the DPDK application is running.
> Otherwise, all interfaces are created in the default namespace
> in the host.
>
> Signed-off-by: Takayuki Usui
> ---
> lib/lib
urned value of move_pages() was not checked, thus some
errors could be hidden (if the requested id was 0).
Signed-off-by: Nicolas Dichtel
Reviewed-by: Olivier Matz
Reviewed-by: Didier Pallard
---
lib/librte_eal/linux/eal/eal_memalloc.c | 10 +++---
1 file changed, 7 insertions(+), 3 dele
Le 22/05/2019 à 17:57, Burakov, Anatoly a écrit :
> On 22-May-19 4:41 PM, Nicolas Dichtel wrote:
>> move_pages() is only used to get the numa node id, but this function
>> is not allowed by default in docker (it needs CAP_SYS_NICE and an update of
>> the seccomp profile).
&g
urned value of move_pages() was not checked, thus some
errors could be hidden (if the requested id was 0).
Cc: sta...@dpdk.org
Fixes: 582bed1e1d1d ("mem: support mapping hugepages at runtime")
Signed-off-by: Nicolas Dichtel
Reviewed-by: Olivier Matz
Reviewed-by: Didier Pallard
Acked-by:
Le 05/08/2020 à 14:26, Nick Connolly a écrit :
> Running dpdk-helloworld on Linux with lib numa present,
> but no kernel support for NUMA (CONFIG_NUMA=n) causes
> ret_service_init() to fail with EAL: error allocating
> rte services array.
>
> alloc_seg() calls get_mempolicy to verify that the allo
Le 05/08/2020 à 16:20, Nick Connolly a écrit :
[snip]
>>> Fixes: 2a96c88be83e ("mem: ease init in a docker container")
>> I'm wondering if the bug existed before this commit.
>>
>> Before this commit, it was:
>> move_pages(getpid(), 1, &addr, NULL, &cur_socket_id, 0);
>> if (cur_soc
Le 05/08/2020 à 16:53, Nick Connolly a écrit :
[snip]
> + if (check_numa()) {
> + ret = get_mempolicy(&cur_socket_id, NULL, 0, addr,
> + MPOL_F_NODE | MPOL_F_ADDR);
> + if (ret < 0) {
> + RTE_LOG(DEBUG, EAL, "%s(): get_mempolicy: %s
ot;)
> Cc: nicolas.dich...@6wind.com
> Cc: sta...@dpdk.org
>
> Signed-off-by: Nick Connolly
Reviewed-by: Nicolas Dichtel
27 matches
Mail list logo
