Hi Olivier,
Any opinion on this patchset?
Regards,
Hemant
On 7/4/2017 5:52 PM, Hemant Agrawal wrote:
This patch is in addition to the patch series[1] submitted by
Santosh to allow application to set mempool handle.
The existing pktmbuf pool create api only support the internal use
of "
On Friday 22 September 2017 12:23 PM, Thomas Monjalon wrote:
22/09/2017 08:47, Shreyansh Jain:
On Friday 22 September 2017 03:26 AM, Thomas Monjalon wrote:
23/08/2017 16:11, Shreyansh Jain:
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -409,6 +409,7 @@ NXP dpaa
M: Hemant Agrawal
M: Shreyansh J
> -Original Message-
> From: Rybalchenko, Kirill
> Sent: Wednesday, September 20, 2017 10:33 PM
> To: dev@dpdk.org
> Cc: Rybalchenko, Kirill ; Chilikin, Andrey
> ; Xing, Beilei ; Wu,
> Jingjing
> Subject: [PATCH v3 4/6] net/i40e: add new functions to manipulate with
> pctype mapping tabl
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Kirill Rybalchenko
> Sent: Wednesday, September 20, 2017 10:33 PM
> To: dev@dpdk.org
> Cc: Rybalchenko, Kirill ; Chilikin, Andrey
> ; Xing, Beilei ; Wu,
> Jingjing
> Subject: [dpdk-dev] [PATCH v3 2/6] net/i40e: a
In func i40evf_dev_link_update(), "new_link.link_autoneg" is used in
func call i40evf_dev_atomic_write_link_status(), but is uninitialized.
Signed-off-by: Yong Wang
---
drivers/net/i40e/i40e_ethdev_vf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
b/driv
22/09/2017 09:37, Shreyansh Jain:
> On Friday 22 September 2017 12:23 PM, Thomas Monjalon wrote:
> > 22/09/2017 08:47, Shreyansh Jain:
> >> On Friday 22 September 2017 03:26 AM, Thomas Monjalon wrote:
> >>> 23/08/2017 16:11, Shreyansh Jain:
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @
Hi, Ferruh
> -Original Message-
> From: Yigit, Ferruh
> Sent: Friday, September 22, 2017 5:01 AM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Wu, Jingjing
> Subject: Re: [dpdk-dev] [PATCH v2 1/2] net/i40e: fix clear xstats bug in vf
> port
>
> On 9/21/2017 7:16 PM, Ferruh Yigit wrote:
> > On 9
From: Jerin Jacob
In ppc_64, rte_rdtsc() returns timebase register value which increments
at independent timebase frequency and hence not related to lcore cpu
frequency to derive TSC hz. Hence, we stick with master lcore frequency.
CC: Chao Zhu
Signed-off-by: Jerin Jacob
Signed-off-by: Gowrish
From: Gowrishankar Muthukrishnan
Some architecture like armv8 provides an architecture specific function
to get the rdtsc frequency. The existing rdtsc calibration scheme uses
OS serivce like sleep(1) to calibrate the frequency which may not
produce the accurate result. Introducing an architectur
From: Jerin Jacob
Use cntvct_el0 system register to get the system counter frequency.
If the system is configured with RTE_ARM_EAL_RDTSC_USE_PMU then
return 0(let the common code calibrate the tsc frequency).
CC: Jianbo Liu
Signed-off-by: Jerin Jacob
Acked-by: Jianbo Liu
---
.../common/incl
From: Jerin Jacob
When calibrating the tsc frequency, first, probe the architecture specific
rdtsc hz function. if not available, use the existing calibrate scheme
to calibrate the tsc frequency.
Signed-off-by: Jerin Jacob
---
lib/librte_eal/common/eal_common_timer.c | 5 -
1 file changed,
From: Jerin Jacob
CC: Jan Viktorin
CC: Jianbo Liu
Signed-off-by: Jerin Jacob
---
lib/librte_eal/common/include/arch/arm/rte_cycles_32.h | 13 +
1 file changed, 13 insertions(+)
diff --git a/lib/librte_eal/common/include/arch/arm/rte_cycles_32.h
b/lib/librte_eal/common/include/ar
From: Jerin Jacob
CC: Bruce Richardson
CC: Konstantin Ananyev
Signed-off-by: Jerin Jacob
Acked-by: Anatoly Burakov
---
lib/librte_eal/common/include/arch/x86/rte_cycles.h | 13 +
1 file changed, 13 insertions(+)
diff --git a/lib/librte_eal/common/include/arch/x86/rte_cycles.h
On Thu, 21 Sep 2017 17:59:53 +0200
Lukasz Majczak wrote:
> The assertion of return value from the open() function is done against
> 0, while it is a correct value - open() returns -1 in case of an error.
> It causes problems while trying to run as a daemon, in which case, this
> call to open() wi
On Thu, Sep 21, 2017 at 01:46:46PM +0100, Pablo de Lara wrote:
> When adding a new entry in a hash table, there is
> a maximum number of evictions that can be
> performed. When the counter of these evictions reaches
> this maximum, the entry cannot be added, as it is considered
> that the algorithm
Hi，Andrey
> -Original Message-
> From: Chilikin, Andrey
> Sent: Friday, September 22, 2017 3:53 AM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Zhao1, Wei ; Yigit, Ferruh
> ; Xing, Beilei ; Wu, Jingjing
>
> Subject: RE: [dpdk-dev] [PATCH v3 1/2] net/i40e: queue region set and flush
>
> > -O
-Original Message-
> Date: Fri, 22 Sep 2017 02:47:13 +0530
> From: Nikhil Rao
> To: jerin.ja...@caviumnetworks.com, bruce.richard...@intel.com
> CC: gage.e...@intel.com, dev@dpdk.org, tho...@monjalon.net,
> harry.van.haa...@intel.com, hemant.agra...@nxp.com, nipun.gu...@nxp.com,
> narend
Add support of GTP-C and GTP-U tunnels in rte_net_get_ptype().
Signed-off-by: Beilei Xing
---
lib/librte_mbuf/rte_mbuf_ptype.c | 2 ++
lib/librte_mbuf/rte_mbuf_ptype.h | 24
2 files changed, 26 insertions(+)
diff --git a/lib/librte_mbuf/rte_mbuf_ptype.c b/lib/librte_mb
This patch set enables RSS/FDIR/cloud filter for GPT-C and GTP-U.
It depends on Kirill's patch:
http://dpdk.org/ml/archives/dev/2017-September/076035.html
v3 changes:
- Rework implementation to support the new profile.
- Add GTPC and GTPU tunnel type in software packet type parser.
- Update pty
Enable RSS for new pctypes after downloading
new profile.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 28
1 file changed, 28 insertions(+)
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
index dcff8cc..a15d994 100644
Update new packet type and new pctype info when downloading
profile.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 312
drivers/net/i40e/i40e_ethdev.h | 24
drivers/net/i40e/rte_pmd_i40e.c | 6 +-
3 files changed, 341 insertion
This patch adds GTP, GTPC and GTPU items for
generic flow API, and also exposes item fields
through the flow command.
Signed-off-by: Beilei Xing
---
app/test-pmd/cmdline_flow.c | 52 +
app/test-pmd/config.c | 3 ++
doc/guides/pro
This patch adds i40e_flow_parse_gtp_filter parsing
function for GTP-C and GTP-U.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.h | 2 +
drivers/net/i40e/i40e_flow.c | 151 +
2 files changed, 153 insertions(+)
diff --git a/drivers/net/i40
rte_eth_fdir_* structures are still used in FDIR functions.
This patch adds i40e private FDIR related structures and
functions to finish integration FDIR with generic flow API.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.h | 94 +++-
drivers/net/i40e/i40e_fdir.c | 490
GTP-C & GTP-U are not supported by cloud filter due
to limited resource of HW, this patch enables GTP-C
and GTP-U cloud filter by replacing inner_mac and
TUNNEL_KEY.
This configuration will be set when adding GTP-C or
GTP-U filter rules, and it will be invalid only by
NIC core reset.
Signed-off-by
This patch adds FDIR support for GTP-C and GTP-U.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 1 +
drivers/net/i40e/i40e_ethdev.h | 37 ++
drivers/net/i40e/i40e_fdir.c | 198 ++--
drivers/net/i40e/i40e_flow.c | 253 ++
New API for cfgfile library allows to create a cfgfile at runtime, add new
section, add entry in a section, update existing entry and save cfgfile
structure to INI file - opens up the possibility to have applications
dynamically build up a proper DPDK configuration, rather than
having to have a pre
From: Jacek Piasecki
This patch removes the dependency to EAL in cfgfile library.
Signed-off-by: Jacek Piasecki
Acked-by: Bruce Richardson
---
lib/Makefile | 3 +--
lib/librte_cfgfile/Makefile | 1 +
lib/librte_cfgfile/rte_cfgfile.c | 29 +---
From: Jacek Piasecki
Extend existing cfgfile library with providing new API functions:
rte_cfgfile_create() - create new cfgfile object
rte_cfgfile_add_section() - add new section to existing cfgfile
object
rte_cfgfile_add_entry() - add new entry to existing cfgfile
object in specified section
r
From: Jacek Piasecki
Change to flat arrays in cfgfile struct force slightly
diffrent data access for most of cfgfile functions.
This patch provides necessary changes in existing API.
Signed-off-by: Jacek Piasecki
Acked-by: Bruce Richardson
---
lib/librte_cfgfile/rte_cfgfile.c | 121 ++
29/08/2017 15:03, Ananyev, Konstantin:
>
> Hi Dave,
>
> > This patchset adds the facility for a guest VM to send a policy down to
> > the host that will allow the host to scale up/down cpu frequencies
> > depending on the policy criteria independently of the DPDK app running in
> > the guest. Th
25/08/2017 18:02, David Hunt:
>
> +static inline uint64_t
> +vfid_to_pfid_direct(uint8_t port_id, uint64_t vfid)
> +{
> + struct rte_eth_dev *dev = &rte_eth_devices[port_id];
> + uint64_t pfid = (*dev->dev_ops->vfid_to_pfid)(dev, vfid);
> + return pfid;
> +}
I would like to com
From: Jacek Piasecki
New functions added to cfgfile library make it possible
to significantly simplify the code of rte_cfgfile_load_with_params()
This patch shows the new body of this function.
Signed-off-by: Jacek Piasecki
Acked-by: Bruce Richardson
---
lib/librte_cfgfile/rte_cfgfile.c | 15
From: Jacek Piasecki
Load huge realloc_sections.ini file to check malloc/realloc
ability of cfgfile library.
Signed-off-by: Jacek Piasecki
Acked-by: Bruce Richardson
---
test/test/test_cfgfile.c | 41
test/test/test_cfgfiles/etc/realloc_sections.ini | 128 +++
24/07/2017 11:27, Jerin Jacob:
> Documentation changes could move to different patch for better review.
Sorry for late reply,
I think it is better to have doc with code in the same patch.
I will merge them when applying.
On 22/9/2017 10:51 AM, Thomas Monjalon wrote:
29/08/2017 15:03, Ananyev, Konstantin:
Hi Dave,
This patchset adds the facility for a guest VM to send a policy down to
the host that will allow the host to scale up/down cpu frequencies
depending on the policy criteria independently of the DPDK
On 22 September 2017 at 14:21, Phil Yang wrote:
> In container, the process cannot be terminated by SIGINT/SIGTERM when
> execute with 'stats-period' option.
> Fixed by adding a flag to exit stats period loop after received either
> SIGINT or SIGTERM.
>
> Signed-off-by: Phil Yang
> ---
> app/tes
On 9/19/2017 12:39 PM, Matan Azrad wrote:
> Hi Ferruh
>
>> -Original Message-
>> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
>> Sent: Tuesday, September 19, 2017 2:00 PM
>> To: Matan Azrad ; Gaetan Rivet
>>
>> Cc: dev@dpdk.org; john.mcnam...@intel.com
>> Subject: Re: [dpdk-dev] [PA
> -Original Message-
> From: Richardson, Bruce
> Sent: Friday, September 22, 2017 9:36 AM
> To: De Lara Guarch, Pablo
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [PATCH] hash: fix incorrect eviction counter
>
> On Thu, Sep 21, 2017 at 01:46:46PM +0100, Pablo de Lara wrote:
> > Wh
08/09/2017 14:57, ilia.kura...@intel.com:
> + /* See rte_ethdev_profile.h to find comments on code below. */
> + __rte_eth_profile_rx_init(port_id, dev);
We can find easily where the function is defined.
Please replace this comment by something like that:
/* Initialize Rx profiling if enab
06/09/2017 01:59, Yipeng Wang:
> --- a/lib/librte_eal/common/eal_common_log.c
> +++ b/lib/librte_eal/common/eal_common_log.c
> @@ -279,6 +279,7 @@ static const struct logtype logtype_strings[] = {
> {RTE_LOGTYPE_CRYPTODEV, "cryptodev"},
> {RTE_LOGTYPE_EFD,"efd"},
>
Hi All,
As part of our ongoing efforts to improve DPDK, we'd like to hear your feedback!
We have created a number of DPDK-related questions here.
https://www.surveymonkey.com/r/DPDK_Community_Survey_2017
and want to hear your views!!
The survey will close at midnight GMT on Sunday October 1st,
06/09/2017 01:59, Yipeng Wang:
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -734,6 +734,13 @@ F: test/test/test_meter.c
> F: examples/qos_meter/
> F: doc/guides/sample_app_ug/qos_metering.rst
>
> +Membership - EXPERIMENTAL
> +M: Yipeng Wang
> +M: Sameh Gobriel
> +F: lib/librte_member/
> +F: d
This reverts commit a1e7c17555e8f77d520ba5f06ed26c00e77a2bd1.
Original commit assumes there is 1:1 mapping between physical device and
ethdev port, so that device name can be used per port instead of ethdev
name field.
But one physical device may have multiple ethdev ports and each port
needs its
Hi
On 9/17/2017 2:45 PM, Shahaf Shuler wrote:
Hi Declan,
Thursday, September 14, 2017 11:27 AM, Akhil Goyal:
From: Declan Doherty
rte_flow_action type and ethdev updated to support rte_security sessions
for crypto offload to ethernet device.
Signed-off-by: Boris Pismenny
Signed-off-by: Av
Hi,
On 9/18/2017 8:57 AM, Jerin Jacob wrote:
-Original Message-
Date: Thu, 14 Sep 2017 13:56:46 +0530
From: Akhil Goyal
To: dev@dpdk.org
CC: declan.dohe...@intel.com, pablo.de.lara.gua...@intel.com,
hemant.agra...@nxp.com, radu.nico...@intel.com, bor...@mellanox.com,
avia...@mella
Hi,
I will address most of the issues in the v2, except the one related to
the multiprocess issue - we may need more discussions on that.
Thanks for reviewing,
Radu
On 9/18/2017 2:13 PM, Jerin Jacob wrote:
-Original Message-
Date: Thu, 14 Sep 2017 13:56:41 +0530
From: Akhil Goyal
-Original Message-
> Date: Fri, 22 Sep 2017 02:47:14 +0530
> From: Nikhil Rao
> To: jerin.ja...@caviumnetworks.com, bruce.richard...@intel.com
> CC: gage.e...@intel.com, dev@dpdk.org, tho...@monjalon.net,
> harry.van.haa...@intel.com, hemant.agra...@nxp.com, nipun.gu...@nxp.com,
> narend
When adding a new entry in a hash table, there is
a maximum number of evictions that can be
performed. When the counter of these evictions reaches
this maximum, the entry cannot be added, as it is considered
that the algorithm has encountered an infinite loop.
The problem with the current implemen
Add return value check for poll() call.
Coverity issue: 140740
Fixes: 59317cef249c ("vhost: allow many vhost-user ports")
Cc: jan.wick...@ericsson.com
Cc: sta...@dpdk.org
Signed-off-by: Kuba Kozak
---
lib/librte_vhost/fd_man.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --gi
From: Tomasz Kulasek
mixed_enums: Mixing enum types enum i40e_vsi_type and enum
virtchnl_vsi_type for type
Coverity issue 158651
Fixes: a58860f68929 ("net/i40e/base: use new virtchnl header file")
Cc: jingjing...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Tomasz Kulasek
---
dri
From: Tomasz Kulasek
Coverity error:
check_after_deref: Null-checking rq suggests that it may be null, but it
has already been dereferenced on all paths leading to
the check.
This patch moves NULL checking of "rq" at the very beginning of the path
before an
Hi Thomas,
On 22/9/2017 10:56 AM, Thomas Monjalon wrote:
25/08/2017 18:02, David Hunt:
+static inline uint64_t
+vfid_to_pfid_direct(uint8_t port_id, uint64_t vfid)
+{
+ struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+ uint64_t pfid = (*dev->dev_ops->vfid_to_pfid)(dev, vfid);
On Friday 22 September 2017 03:40 AM, Thomas Monjalon wrote:
09/09/2017 13:20, Shreyansh Jain:
DPAA, or Datapath Acceleration Architecture [R2], is a set of hardware
components designed for high-speed network packet processing. This
architecture provides the infrastructure to support simplified
Tested-by: Hemant Agrawal
On 9/7/2017 9:00 PM, Santosh Shukla wrote:
Some mempool hw like octeontx/fpa block, demands block size
(/total_elem_sz) aligned object start address.
Introducing an MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS flag.
If this flag is set:
- Align object start address(vaddr) to a
Hi Ferruh,
-johnd
> -Original Message-
> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
> Sent: Tuesday, September 19, 2017 5:59 AM
> To: John Daley (johndale) ; Thomas Monjalon
>
> Cc: dev@dpdk.org; Sergio Gonzalez Monroy
> ; Adrien Mazarguil
> ; Nelio Laranjeiro
> ; Ananyev, Konstan
22/09/2017 12:28, Hunt, David:
>
> On 22/9/2017 10:51 AM, Thomas Monjalon wrote:
> > 29/08/2017 15:03, Ananyev, Konstantin:
> >> Hi Dave,
> >>
> >>> This patchset adds the facility for a guest VM to send a policy down to
> >>> the host that will allow the host to scale up/down cpu frequencies
> >>
From: Jacek Piasecki
Fix size of buffer in strcpy. There was possible to get
not terminated string after copy operation.
Coverity issue: 158631
Fixes: db75c7af19bb ("examples/vhost_scsi: introduce a new sample app")
Cc: changpeng@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Jacek Piasecki
From: Tomasz Kulasek
Coverity error:
check_after_deref: Null-checking rq suggests that it may be null, but it
has already been dereferenced on all paths leading to
the check.
This patch moves NULL checking of "rq" at the very beginning of the path
before an
From: Jacek Piasecki
Fix size of buffer in strcpy. There was possible to get
not terminated string after copy operation.
Coverity issue: 158631
Fixes: db75c7af19bb ("examples/vhost_scsi: introduce a new sample app")
Cc: changpeng@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Jacek Piasecki
From: Jacek Piasecki
Fix size of buffer in strcpy. There was possible to get
not terminated string after copy operation.
Coverity issue: 158629
Fixes: db75c7af19bb ("examples/vhost_scsi: introduce a new sample app")
Cc: changpeng@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Jacek Piasecki
On 22/9/2017 2:03 PM, Thomas Monjalon wrote:
22/09/2017 12:28, Hunt, David:
On 22/9/2017 10:51 AM, Thomas Monjalon wrote:
29/08/2017 15:03, Ananyev, Konstantin:
Hi Dave,
This patchset adds the facility for a guest VM to send a policy down to
the host that will allow the host to scale up/do
22/09/2017 15:06, Shreyansh Jain:
> On Friday 22 September 2017 03:40 AM, Thomas Monjalon wrote:
> > 09/09/2017 13:20, Shreyansh Jain:
> >> DPAA, or Datapath Acceleration Architecture [R2], is a set of hardware
> >> components designed for high-speed network packet processing. This
> >> architectur
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Michal Jastrzebski
> Sent: Friday, September 22, 2017 3:08 PM
> To: y...@fridaylinux.org; maxime.coque...@redhat.com
> Cc: dev@dpdk.org; Jain, Deepak K ; Kulasek,
> TomaszX ; yongw...@vmware.com;
> sta...@dpdk.org
>
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Michal Jastrzebski
> Sent: Friday, September 22, 2017 3:08 PM
> To: y...@fridaylinux.org; maxime.coque...@redhat.com
> Cc: dev@dpdk.org; Jain, Deepak K ; Piasecki,
> JacekX ; Liu, Changpeng
> ; sta...@dpdk.org
> Sub
On Sat, Sep 23, 2017 at 06:35:10AM +0800, Beilei Xing wrote:
> This patch adds GTP, GTPC and GTPU items for
> generic flow API, and also exposes item fields
> through the flow command.
>
> Signed-off-by: Beilei Xing
> diff --git a/app/test-pmd/cmdline_flow.c b/app/test-pmd/cmdline_flow.c
> +stat
15/09/2017 11:24, Nélio Laranjeiro:
> On Tue, Sep 05, 2017 at 12:05:32AM +0200, Thomas Monjalon wrote:
> > The script git-log-fixes.sh (used in check-git-log.sh) looks
> > for git tags to find the version where a bug is introduced.
> >
> > In DPDK 17.08, the script has been fixed to ignore tags fr
> Thomas Monjalon (3):
> maintainers: separate main tree and devtools maintenance
> maintainers: add Yuanhan for stable branches
> maintainers: add Ferruh for main branch
Applied
On Fri, Sep 22, 2017 at 05:25:43AM +0100, Pablo de Lara wrote:
> When adding a new entry in a hash table, there is
> a maximum number of evictions that can be
> performed. When the counter of these evictions reaches
> this maximum, the entry cannot be added, as it is considered
> that the algorithm
Hello Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Friday, September 22, 2017 6:43 PM
> To: Shreyansh Jain
> Cc: dev@dpdk.org; ferruh.yi...@intel.com; Hemant Agrawal
>
> Subject: Re: [PATCH v4 00/41] Introduce NXP DPAA Bus, Mempool and PMD
>
22/09/2017 16:00, Shreyansh Jain:
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > At the beginning of fslmc work, I had understood that every NXP SoC were
> > connecting components with the same principle which we could call the
> > "Freescale bus".
> > Then you came with this bus named bu
13/09/2017 12:44, David Hunt:
> Recent generations of the Intel® Xeon® family processors allow Turbo Boost
> to be enabled/disabled on a per-core basis.
>
> This patch set introduces additional API calls to the librte_power library
> to allow users to enable/disable Turbo Boost on particular cores
Memory allocated in strdup is not free.
Coverity issue: 143257
Fixes: d8a2bc71dfc2 ("log: remove app path from syslog id")
Cc: tho...@monjalon.net
Signed-off-by: Daniel Mrzyglod
---
v2:
* Fix due to compilation errors
lib/librte_eal/linuxapp/eal/eal.c | 18 +-
1 file changed, 1
From: Ilia Kurakin
The patch simplifies DPDK applications analysis for developers which use
Intel® VTune Amplifier.
The empty cycles are such iterations that yielded no RX packets. As far as
DPDK is running in poll mode, wasting cycles is equal to wasting CPU time.
Tracing such iterations can id
On Fri, Sep 22, 2017 at 12:30:07PM +0100, Ferruh Yigit wrote:
> This reverts commit a1e7c17555e8f77d520ba5f06ed26c00e77a2bd1.
>
> Original commit assumes there is 1:1 mapping between physical device and
> ethdev port, so that device name can be used per port instead of ethdev
> name field.
>
> Bu
Hi Jerin, et al.,
The following RFC patch contains enough of a skeleton implementation
for an event timer adapter to show how the API could call through an ops
structure to a plugin backend to provide different implementations.
In terms of differences from the original RFC, the most obvious one i
Signed-off-by: Erik Gabriel Carrillo
---
v2
- Added ops structure and stubbed out plugin for SW impl
- Added unit test stubs
- Replaced occurrences of "wheel" in API with "adapter"
- Replaced occurrences of pointer to struct rte_event_timer_adapter with ids
- Removed rte_event_timer_adapter_lookup
The unscrutinized value may be incorrectly assumed to be within a certain
range by later operations.
In vhost_user_read: An unscrutinized value from an untrusted source used
in a trusted context - the value of sz_payload may be harmfull and we need
limit them to the max value of payload.
Coverity
Hi,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vladimir
> Medvedkin
> Sent: Tuesday, August 22, 2017 4:57 PM
> To: Yangchao Zhou
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] hash: optimize the softrss computation
>
> Hi,
>
> 2017-08-22 15:02 GMT+
>
> Signed-off-by: Olivier Chirossel
> ---
> doc/guides/prog_guide/qos_framework.rst | 10 ++-
> lib/librte_sched/rte_sched.c| 124
> ++--
> 2 files changed, 112 insertions(+), 22 deletions(-)
>
> diff --git a/doc/guides/prog_guide/qos_framework.rst
> b/
Since DPDK 17.08, there is specific parameters
for AEAD algorithm, like AES-GCM. When verifying
crypto operations with test vectors, the parser
was not reading AEAD data (such as IV or key).
Fixes: 8a5b494a7f99 ("app/test-crypto-perf: add AEAD parameters")
Cc: sta...@dpdk.org
Signed-off-by: Pablo
This patchset includes some improvements in the Crypto performance
application, including app fixes and new parameter additions.
The last patch, in particular, introduces performance improvements.
Currently, crypto operations are allocated in a mempool and mbufs
in a different one. Then mbufs are
Instead of prepending the AAD (Additional Authenticated Data)
in the mbuf, it is easier to set after the crypto operation,
as it is a read-only value, like the IV, and then it is not
restricted to the size of the mbuf headroom.
Signed-off-by: Pablo de Lara
---
app/test-crypto-perf/cperf_ops.c
Instead of parsing number of segments, from the command line,
parse segment size, as it is a more usual case to have
the segment size fixed and then different packet sizes
will require different number of segments.
Signed-off-by: Pablo de Lara
---
app/test-crypto-perf/cperf_ops.c
When running the verify test, mbufs in the pool were
populated with the test vector loaded from a file.
To avoid limiting the number of operations to the pool size,
mbufs will be rewritten with the test vector, before
linking them to the crypto operations.
Signed-off-by: Pablo de Lara
---
app/te
For throughput and latency tests, it is not required
to populate the mbufs with any test vector.
For verify test, there is already a function that rewrites
the mbufs every time they are going to be used with
crypto operations.
Signed-off-by: Pablo de Lara
---
app/test-crypto-perf/cperf_test_late
Add parameter "qps" in crypto performance app,
to create multiple queue pairs per device.
This new parameter is useful to have multiple logical
cores using a single crypto device, without needing
to initialize a crypto device per core.
Signed-off-by: Pablo de Lara
---
app/test-crypto-perf/cperf
In order to improve memory utilization, a single mempool
is created, containing the crypto operation and mbufs
(one if operation is in-place, two if out-of-place).
This way, a single object is allocated and freed
per operation, reducing the amount of memory in cache,
which improves scalability.
Si
This commit extends the testpmd application with new forwarding engine
that demonstrates the use of ethdev traffic management APIs and softnic
PMD for QoS traffic management.
In this mode, 5-level hierarchical tree of the QoS scheduler is built
with the help of ethdev TM APIs such as shaper profil
Add following CLIs in testpmd application;
- commands to add/del shaper profile for TM hieraqrchy nodes.
- commands to add/update shared shapers
- commands to add/del WRED profiles for TM hiearchy leaf nodes.
Signed-off-by: Jasvinder Singh
---
v4 change:
- remove softnic specific checkes to make
Add following CLIs to testpmd application;
- commands to display TM capability information.
(per port, per hierarchy level and per hierarchy node)
- command to display hiearchy node type
- stats collection
Signed-off-by: Jasvinder Singh
---
v4 change:
- remove softnic specific checkes to make
Add following CLIs in testpmd application;
- commands to add TM hierarchy nodes (leaf and nonleaf).
- command for runtime update of node weight.
- command to commit the TM hierarchy
Signed-off-by: Jasvinder Singh
---
v4 change:
- remove softnic specific checkes to make it generic
app/test-pmd/
Add following CLIs in testpmd application;
- command to set the packet field mask and offset value for
classification.
- command to set traffic class translation table entry
Signed-off-by: Jasvinder Singh
---
app/test-pmd/cmdline.c | 13 ++
app/test-pmd/cmdline_tm.c | 309 +++
On 9/22/2017 1:39 PM, Michal Jastrzebski wrote:
> From: Tomasz Kulasek
>
> Coverity error:
>
> check_after_deref: Null-checking rq suggests that it may be null, but it
>has already been dereferenced on all paths leading to
>the check.
>
> This patch moves
On 9/22/2017 1:36 PM, Michal Jastrzebski wrote:
> From: Tomasz Kulasek
>
> mixed_enums: Mixing enum types enum i40e_vsi_type and enum
> virtchnl_vsi_type for type
>
> Coverity issue 158651
> Fixes: a58860f68929 ("net/i40e/base: use new virtchnl header file")
> Cc: jingjing...@intel.
On 9/11/2017 7:58 PM, John Daley wrote:
> - Use rte_malloc() instead of malloc() for the per device 'vdev' structure
> so that it can be shared across processes.
> - Only initialize the device if the process type is RTE_PROC_PRIMARY
> - Only allow the primary process to do queue setup, start/stop
22/09/2017 16:52, ilia.kura...@intel.com:
> From: Ilia Kurakin
>
> The patch simplifies DPDK applications analysis for developers which use
> Intel® VTune Amplifier.
>
> The empty cycles are such iterations that yielded no RX packets. As far as
> DPDK is running in poll mode, wasting cycles is e
On 9/21/2017 7:32 AM, Wei Zhao wrote:
> There is a bug in vf clear xstats command, it do not
> record the statics data in offset struct member.So, vf
> need to keep record of xstats data from pf and update
> the statics according to offset.
>
> Fixes: da61cd0849766 ("i40evf: add extended stats")
>
On 9/22/2017 6:13 PM, Ferruh Yigit wrote:
> On 9/21/2017 7:32 AM, Wei Zhao wrote:
>> There is a bug in vf clear xstats command, it do not
>> record the statics data in offset struct member.So, vf
>> need to keep record of xstats data from pf and update
>> the statics according to offset.
>>
>> Fixe
On 9/21/2017 3:43 PM, Ferruh Yigit wrote:
> On 9/21/2017 10:57 AM, Chas Williams wrote:
>> From: "Charles (Chas) Williams"
>>
>> In certain situations, low speed interfaces, it may be desirable to
>> have the flow control provided by the kernel queueing disciplines.
>>
>> Signed-off-by: Chas Willi
1 - 100 of 107 matches
Mail list logo
