(I am not reducing the thread as it contains quite interesting
discussion - so, you might have to fish for inline comments...)
On Thursday 12 July 2018 08:38 PM, Gaëtan Rivet wrote:
Hi Shreyansh,
On Thu, Jul 12, 2018 at 04:28:27PM +0530, Shreyansh Jain wrote:
On Thursday 12 July 2018 03:15 AM
On 12-Jul-18 11:36 PM, Thomas Monjalon wrote:
26/06/2018 12:53, Anatoly Burakov:
From: Jianfeng Tan
Next commit will make asynchronous IPC requests rely on alarm API,
which in turn relies on interrupts to work. Therefore, move the EAL
interrupt initialization before IPC initialization to avoid
Hi, Wenzhuo,
I'm sorry, but I have more even harder questions than the previous one.
This questions are rather generic and mainly to ethdev maintainers.
On 13.07.2018 05:42, Wenzhuo Lu wrote:
The device information cannot be gotten correctly before
the configuration is set. Because on some NICs
On Fri, Jul 13, 2018 at 12:36 AM, Thomas Monjalon wrote:
> I am almost sure it will bring regressions.
>
> Please think again about the consequences of initializing interrupt thread
> before affinity setting, memory init, device init.
Well, there was an issue vith virtio at one time (interrupt ha
Hi Thomas,
On 12/7/2018 8:13 PM, Thomas Monjalon wrote:
26/06/2018 11:23, David Hunt:
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#include
+#include
+#include
+#includ
Fixes: 4ed05fcd441b ("ethdev: add flow API to expand RSS flows")
Signed-off-by: Nelio Laranjeiro
Acked-by: Adrien Mazarguil
---
lib/librte_ethdev/rte_ethdev_version.map | 1 +
lib/librte_ethdev/rte_flow_driver.h | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/lib/libr
Hi Thomas,
On 12/7/2018 8:09 PM, Thomas Monjalon wrote:
26/06/2018 11:23, David Hunt:
This patch set adds the capability to do out-of-band power
monitoring on a system. It uses a thread to monitor the branch
counters in the targeted cores, and calculates the branch ratio
if the running code.
I
13/07/2018 10:31, Hunt, David:
> Hi Thomas,
>
> On 12/7/2018 8:09 PM, Thomas Monjalon wrote:
> > 26/06/2018 11:23, David Hunt:
> >> This patch set adds the capability to do out-of-band power
> >> monitoring on a system. It uses a thread to monitor the branch
> >> counters in the targeted cores, an
On 13/7/2018 9:33 AM, Thomas Monjalon wrote:
13/07/2018 10:31, Hunt, David:
Hi Thomas,
On 12/7/2018 8:09 PM, Thomas Monjalon wrote:
26/06/2018 11:23, David Hunt:
This patch set adds the capability to do out-of-band power
monitoring on a system. It uses a thread to monitor the branch
counter
Hi Nelio,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Nelio Laranjeiro
> Sent: Friday, July 13, 2018 9:25 AM
> To: dev@dpdk.org; Thomas Monjalon
> Subject: [dpdk-dev] [PATCH] ethdev: fix missing function in map file
>
> Fixes: 4ed05fcd441b ("ethdev: add fl
Previous modification to evt_service_setup() broke order_queue/atq
tests.
Fixes: b0333c55dfa5 ("app/eventdev: add service core configuration")
Cc: sta...@dpdk.org
Reported-by: Gage Eads
Signed-off-by: Pavan Nikhilesh
---
app/test-eventdev/test_order_atq.c | 12
app/test-eventdev
11/06/2018 22:55, Anatoly Burakov:
> This patchset is mostly dealing with changes fbarray, but it is
> actually about reducing fragmentation in Linuxapp memalloc.
>
> We allocate hugepages from lower VA to higher VA. However, our
> malloc heap allocates addresses from higher VA to lower VA. This
>
Hi Pablo,
On Fri, Jul 13, 2018 at 08:52:07AM +, De Lara Guarch, Pablo wrote:
> Hi Nelio,
>
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Nelio Laranjeiro
> > Sent: Friday, July 13, 2018 9:25 AM
> > To: dev@dpdk.org; Thomas Monjalon
> > Subject: [dpdk
On Fri, Jul 13, 2018 at 10:09:42AM +0200, David Marchand wrote:
[...]
> Well, there was an issue vith virtio at one time (interrupt handler
> did not have the right iopl for virtio callback).
> http://git.dpdk.org/dpdk/commit/lib/librte_eal/linuxapp/eal/eal.c?id=fd6949c55c9a48e81c625138679159829d51
Fixes: 4ed05fcd441b ("ethdev: add flow API to expand RSS flows")
Signed-off-by: Nelio Laranjeiro
Acked-by: Adrien Mazarguil
--
Changes in v2:
- add missing documentation.
- add missing __rte_experimental in source file.
- update the order in map file.
---
lib/librte_ethdev/rte_ethdev_version
31/05/2018 18:11, Anatoly Burakov:
> When rte_eal_cleanup() is called, it is expected that DPDK will be able to
> release all of its memory back to the system. However, if pages are marked
> as unfreeable, the pages will not be released back. Fix this to mark all
> pages as freeable on calling rte_
12/06/2018 11:46, Anatoly Burakov:
> Sometimes, user code needs to walk memseg list while being inside
> a memory-related callback. Rather than making everyone copy around
> the same iteration code and depending on DPDK internals, provide an
> official way to do memseg_contig_walk() inside callback
31/05/2018 19:05, Anatoly Burakov:
> Previously, when joining adjacent free elements, we were erasing
> trailer and header, but did not erase the padding. Fix this by
> accounting for padding on erase, and do not erase padding twice
> by adjusting data pointer and data len to not include padding.
>
31/05/2018 11:50, Anatoly Burakov:
> This patchset does two things. First, it enables reserving
> memzones of zero-length that are IOVA-contiguous. Second,
> it fixes a long-standing race condition in reserving
> zero-length memzones, where malloc heap is not locked between
> stats collection and r
31/05/2018 19:35, Anatoly Burakov:
> Previously, it was possible to limit maximum amount of memory
> allowed for allocation by creating validator callbacks. Although a
> powerful tool, it's a bit of a hassle and requires modifying the
> application for it to work with DPDK example applications.
>
This series adds support for switch flow rules, that is, rte_flow rules
applied to mlx5 devices at the switch level.
It allows applications to offload traffic redirection between DPDK ports in
hardware, while optionally modifying it (e.g. performing encap/decap).
For this to work, involved DPDK p
With mlx5, unlike normal flow rules implemented through Verbs for traffic
emitted and received by the application, those targeting different logical
ports of the device (VF representors for instance) are offloaded at the
switch level and must be configured through Netlink (TC interface).
This patc
Because mlx5 switch flow rules are configured through Netlink (TC
interface) and have little in common with Verbs, this patch adds a separate
parser function to handle them.
- mlx5_nl_flow_transpose() converts a rte_flow rule to its TC equivalent
and stores the result in a buffer.
- mlx5_nl_flo
This enables flow rules to explicitly match VLAN traffic (VLAN pattern
item) and perform various operations on VLAN headers at the switch level
(OF_POP_VLAN, OF_PUSH_VLAN, OF_SET_VLAN_VID and OF_SET_VLAN_PCP actions).
Testpmd examples:
- Directing all VLAN traffic received on port ID 1 to port ID
This enables flow rules to explicitly match supported combinations of
Ethernet, IPv4, IPv6, TCP and UDP headers at the switch level.
Testpmd example:
- Dropping TCPv4 traffic with a specific destination on port ID 2:
flow create 2 ingress transfer pattern eth / ipv4 / tcp dst is 42 / end
This patch enables creation of rte_flow rules that direct matching traffic
to a different port (e.g. another VF representor) or drop it directly at
the switch level (PORT_ID and DROP actions).
Testpmd examples:
- Directing all traffic to port ID 0:
flow create 1 ingress transfer pattern end ac
This enables flow rules to match traffic coming from a different DPDK port
ID associated with the device (PORT_ID pattern item), mainly for the
convenience of applications that want to deal with a single port ID for all
flow rules associated with some physical device.
Testpmd example:
- Creating
31/05/2018 17:35, Anatoly Burakov:
> As per deprecation notice [1], move DPDK runtime config to default
> DPDK runtime data location. Also, remove the deprecation notice.
>
> [1] http://dpdk.org/dev/patchwork/patch/40418/
>
> Signed-off-by: Anatoly Burakov
> ---
> doc/guides/rel_notes/deprecati
01/06/2018 11:08, Anatoly Burakov:
> Parentheses were missing. It worked because macro is enclosed in
> parentheses, so syntax was valid after macro expansion.
>
> Bugzilla ID: 58
> Fixes: 0a45657a6794 ("pci: rework interrupt handling")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Anatoly Burakov
S
The workaround of BAR0 mapping gives up and immediately returns an
error if it cannot map around the MSI-X. However, recent version
of VFIO allows MSIX mapping (*).
I fixed not to return immediately but try mapping. In old Linux, mmap
just fails and returns the same error as the code before my fix
This patchset adds a new command-line option "--in-memory",
which takes old debug options "--huge-unlink" and
"--no-shconf", and enhances them with additional
functionality. This will allow DPDK to reserve hugepages
anonymously instead of using hugetlbfs mountpoints. Coupled
with the fact that this
When using --no-shconf option, the expectation is that no multiprocess
will be supported as no shared files are created. However, fbarray still
creates some shared files that prevent multiple processes with the same
prefix from starting.
Fix this by avoiding creating shared files whenever noshconf
IPC is an inter-process communication mechanism. Since no secondaries
can ever be expected to run in no-shconf mode, IPC will be useless, so
do not enable it in the first place. In the interests of API usage
convenience, we will still allow registering callbacks, but obviously
they won't ever be tr
Do not create a shared hugepage data file if we were asked to
not create any shared files.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Use --no-shconf only
lib/librte_eal/linuxapp/eal/eal_memory.c | 13 -
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git
Options --no-shconf and --huge-unlink will be removed, and
replaced with --in-memory option, which will be a superset
of these two, and an offially support method to run DPDK
entirely in memory.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Add this patch
doc/guides/rel_notes/de
Implement the final piece of the in-memory mode puzzle - enable running
DPDK entirely in memory, without creating any files.
To do it, use mmap with MAP_HUGETLB and size flags to enable DPDK to work
without hugetlbfs mountpoints. In order to enable this, a few things needed
to be changed.
First o
Unlink hugepages after creating them, to honor the hugepage-unlink mode.
We cannot resize non-existing files, so make single file segments
explicitly unsupported.
Signed-off-by: Anatoly Burakov
---
Notes:
v1->v2:
- Move check for hugepage unlink into this patch, to be
consistent wi
Now that the rest of the EAL is adjusted to not create any shared
files, prevent runtime directory from ever being created.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Use --no-shconf only
lib/librte_eal/bsdapp/eal/eal.c | 3 ++-
lib/librte_eal/linuxapp/eal/eal.c | 3 ++-
2
Do not create any shared hugepage size info files if we were
asked to not create any shared files.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Use --no-shconf only
lib/librte_eal/bsdapp/eal/eal_hugepage_info.c | 4
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c | 4 +++
This command-line option will cause DPDK to operate entirely in
memory and not create any shared files at runtime, including any
shared configuration or hugetlbfs files. This is useful for debug
purposes, as well as for certain use cases like containers or
automatic memory cleanup.
Currently, this
Create compression PMD for Intel QuickAssist devices Currently only the C62x
and c3xxx devices are supported.
The qat comp PMD supports
- stateless compression and
decompression using the Deflate algorithm with Fixed Huffman
encoding. Dynamic huffman encoding is not supported, it
will b
From: Fiona Trahe
Updated to latest firmware headers files for QuickAssist devices.
Includes updates for symmetric crypto, PKE and Compression services.
Signed-off-by: Fiona Trahe
---
drivers/common/qat/qat_adf/icp_qat_fw.h | 69 +++-
drivers/common/qat/qat_adf/icp_qat_fw_comp.h | 482 ++
From: Fiona Trahe
Add Makefiles, directory and empty source files for compression PMD.
Handle cases for building either symmetric crypto PMD
or compression PMD or both and the common files both depend on.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
MAINTAINERS
From: Fiona Trahe
Add meson build files.
Signed-off-by: Tomasz Jozwiak
Signed-off-by: Fiona Trahe
---
drivers/common/qat/Makefile | 2 +-
drivers/compress/meson.build | 2 +-
drivers/compress/qat/meson.build | 18 ++
drivers/compr
From: Fiona Trahe
Add code to process compressdev rte_comp_xforms, creating
private qat_comp_xforms with prepared firmware message templates.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp.c | 239
drivers/co
From: Fiona Trahe
Setup and clear queue-pairs for handling compression
requests and responses.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp.h | 2 ++
drivers/compress/qat/qat_comp_pmd.c | 61 +
drivers/comp
From: Fiona Trahe
Add functions to create the request message to send to
firmware and to process the firmware response.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp.c | 101
drivers/compress/qat/qat_comp.h
From: Fiona Trahe
Add functions to configure and clear the qat comp device,
including the creation and freeing of the xform pool
and the freeing of queue-pairs.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp_pmd.c | 95 ++
From: Fiona Trahe
Add functions to get and clear compression queue-pair statistics.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp_pmd.c | 35 +++
drivers/compress/qat/qat_comp_pmd.h | 7 +++
2 files changed, 42
From: Fiona Trahe
Check bit in response message to verify that correct firmware
is in use for compression. If not return an error.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp.c | 16 +++-
drivers/compress/qat/qat_comp.h | 2 ++
2 fil
From: Fiona Trahe
Add capabilities pointer to internal qat comp device
and function to return this and other info.
C
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp_pmd.c | 19 +++
drivers/compress/qat/qat_comp_pmd.h | 6 ++
2 fi
From: Fiona Trahe
There are no specific actions needed to start/stop a QAT comp device
so these are just trivial fns to satisfy the pmd API.
Signed-off-by: Fiona Trahe
---
drivers/compress/qat/qat_comp_pmd.c | 11 +++
drivers/compress/qat/qat_comp_pmd.h | 6 ++
2 files changed, 17
From: Fiona Trahe
Wrap generic qat enqueue/dequeue functions with
compressdev enqueue and dequeue fns.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp_pmd.c | 14 ++
drivers/compress/qat/qat_comp_pmd.h | 8
2 files changed, 22 i
From: Fiona Trahe
Create an ops structure and populate it with the
qat-specific functions.
Signed-off-by: Fiona Trahe
Signed-off-by: Tomasz Jozwiak
---
drivers/compress/qat/qat_comp_pmd.c | 38 -
drivers/compress/qat/qat_comp_pmd.h | 30
From: Fiona Trahe
Previous check only causes op to fail on dequeue.
This extends so once first fail is detected, application can
no longer enqueue ops to the device and will also get an
appropriate error if trying to reconfigure or setup the device.
Signed-off-by: Tomasz Jozwiak
Signed-off-by:
From: Fiona Trahe
Now that all the device operations are available,
add the functions to create and destroy the pmd.
Called on probe and remove of the qat pci device, these
register the device with the compressdev API
and plug in all the device functionality.
Signed-off-by: Fiona Trahe
Signed-o
From: Fiona Trahe
Extend QAT guide to cover crypto and compression and common
information, particularly about kernel driver dependency.
Update release note.
Update compression feature list for qat.
Signed-off-by: Fiona Trahe
---
config/common_base | 2 +-
doc/guides/com
> Anatoly Burakov (4):
> eal/bsdapp: add interrupt thread
> eal/bsdapp: add alarm support
> ipc: remove IPC thread for async requests
> doc: document IPC callback limitations
>
> Jianfeng Tan (3):
> eal/linux: use glibc malloc in alarm
> eal/linux: use glibc malloc in interrupt handlin
As per deprecation notice [1], move DPDK runtime config to default
DPDK runtime data location. Also, remove the deprecation notice and
update release notes to indicate the changes.
[1] http://dpdk.org/dev/patchwork/patch/40418/
Signed-off-by: Anatoly Burakov
---
doc/guides/rel_notes/deprecation
On 13-Jul-18 11:11 AM, Takeshi Yoshimura wrote:
The workaround of BAR0 mapping gives up and immediately returns an
error if it cannot map around the MSI-X. However, recent version
of VFIO allows MSIX mapping (*).
I fixed not to return immediately but try mapping. In old Linux, mmap
just fails an
On 13-Jul-18 12:00 PM, Burakov, Anatoly wrote:
On 13-Jul-18 11:11 AM, Takeshi Yoshimura wrote:
The workaround of BAR0 mapping gives up and immediately returns an
error if it cannot map around the MSI-X. However, recent version
of VFIO allows MSIX mapping (*).
I fixed not to return immediately b
On Fri, Jul 13, 2018 at 11:10 AM, Tiwei Bie wrote:
> On Fri, Jul 13, 2018 at 10:09:42AM +0200, David Marchand wrote:
> [...]
>> Well, there was an issue vith virtio at one time (interrupt handler
>> did not have the right iopl for virtio callback).
>> http://git.dpdk.org/dpdk/commit/lib/librte_eal
13/07/2018 12:44, Anatoly Burakov:
> As per deprecation notice [1], move DPDK runtime config to default
> DPDK runtime data location. Also, remove the deprecation notice and
> update release notes to indicate the changes.
>
> [1] http://dpdk.org/dev/patchwork/patch/40418/
>
> Signed-off-by: Anato
13/07/2018 12:27, Anatoly Burakov:
> This command-line option will cause DPDK to operate entirely in
> memory and not create any shared files at runtime, including any
> shared configuration or hugetlbfs files. This is useful for debug
> purposes, as well as for certain use cases like containers or
13/07/2018 12:27, Anatoly Burakov:
> Options --no-shconf and --huge-unlink will be removed, and
> replaced with --in-memory option, which will be a superset
> of these two, and an offially support method to run DPDK
> entirely in memory.
>
> Signed-off-by: Anatoly Burakov
The deprecation notice
There is a compilation error:
../lib/librte_eal/linuxapp/eal/eal_memalloc.c: In function ‘alloc_seg’:
../lib/librte_eal/linuxapp/eal/eal_memalloc.c:619:3: error:
‘map_offset’ may be used uninitialized in this function
13/07/2018 12:27, Anatoly Burakov:
> Implement the final piece of the in-memor
Compilation issue:
test/test/test_power_acpi_cpufreq.c:556:31:
error: format ‘%lx’ expects argument of type ‘long unsigned int’,
but argument 2 has type ‘uint64_t {aka long long unsigned int}’
-Werror=format=]
printf("ACPI: Capabilities %lx\n", caps.capabilities);
~
On 13-Jul-18 1:13 PM, Thomas Monjalon wrote:
13/07/2018 12:27, Anatoly Burakov:
This command-line option will cause DPDK to operate entirely in
memory and not create any shared files at runtime, including any
shared configuration or hugetlbfs files. This is useful for debug
purposes, as well as
On 13-Jul-18 1:13 PM, Thomas Monjalon wrote:
13/07/2018 12:27, Anatoly Burakov:
Options --no-shconf and --huge-unlink will be removed, and
replaced with --in-memory option, which will be a superset
of these two, and an offially support method to run DPDK
entirely in memory.
Signed-off-by: Anato
On 7/13/2018 5:12 AM, Pablo de Lara wrote:
Compilation issue:
test/test/test_power_acpi_cpufreq.c:556:31:
error: format ‘%lx’ expects argument of type ‘long unsigned int’,
but argument 2 has type ‘uint64_t {aka long long unsigned int}’
-Werror=format=]
printf("ACPI: Capabilities %lx\n", c
When using --no-shconf option, the expectation is that no multiprocess
will be supported as no shared files are created. However, fbarray still
creates some shared files that prevent multiple processes with the same
prefix from starting.
Fix this by avoiding creating shared files whenever noshconf
IPC is an inter-process communication mechanism. Since no secondaries
can ever be expected to run in no-shconf mode, IPC will be useless, so
do not enable it in the first place. In the interests of API usage
convenience, we will still allow registering callbacks, but obviously
they won't ever be tr
Implement the final piece of the in-memory mode puzzle - enable running
DPDK entirely in memory, without creating any files.
To do it, use mmap with MAP_HUGETLB and size flags to enable DPDK to work
without hugetlbfs mountpoints. In order to enable this, a few things needed
to be changed.
First o
Do not create a shared hugepage data file if we were asked to
not create any shared files.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Use --no-shconf only
lib/librte_eal/linuxapp/eal/eal_memory.c | 13 -
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git
This patchset adds a new command-line option "--in-memory",
which takes old debug options "--huge-unlink" and
"--no-shconf", and enhances them with additional
functionality. This will allow DPDK to reserve hugepages
anonymously instead of using hugetlbfs mountpoints. Coupled
with the fact that this
This command-line option will cause DPDK to operate entirely in
memory and not create any shared files at runtime, including any
shared configuration or hugetlbfs files. This is useful for debug
purposes, as well as for certain use cases like containers or
automatic memory cleanup.
Currently, this
Do not create any shared hugepage size info files if we were
asked to not create any shared files.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Use --no-shconf only
lib/librte_eal/bsdapp/eal/eal_hugepage_info.c | 4
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c | 4 +++
Now that the rest of the EAL is adjusted to not create any shared
files, prevent runtime directory from ever being created.
Signed-off-by: Anatoly Burakov
---
Notes:
RFC->v1:
- Use --no-shconf only
lib/librte_eal/bsdapp/eal/eal.c | 3 ++-
lib/librte_eal/linuxapp/eal/eal.c | 3 ++-
2
Unlink hugepages after creating them, to honor the hugepage-unlink mode.
We cannot resize non-existing files, so make single file segments
explicitly unsupported.
Signed-off-by: Anatoly Burakov
---
Notes:
v1->v2:
- Move check for hugepage unlink into this patch, to be
consistent wi
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Friday, July 13, 2018 5:13 AM
> To: Nicolau, Radu ; Hunt, David
>
> Cc: dev@dpdk.org; De Lara Guarch, Pablo
> Subject: [PATCH] test/power: fix 32-bit build
>
> Compilation issue:
>
> test/test/test_power_acpi_cpufreq.c:556:31:
Compilation issue:
test/test/test_power_acpi_cpufreq.c:556:31:
error: format ‘%lx’ expects argument of type ‘long unsigned int’,
but argument 2 has type ‘uint64_t {aka long long unsigned int}’
-Werror=format=]
printf("ACPI: Capabilities %lx\n", caps.capabilities);
~
Hi Fiona,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Trahe, Fiona
> Sent: Wednesday, July 11, 2018 7:04 PM
> To: Dmitry Eremin-Solenikov ;
> dev@dpdk.org
> Cc: Trahe, Fiona
> Subject: Re: [dpdk-dev] [PATCH] qat: fix checks for 3gpp algorithms vs bit
> mod
Some blank lines and hyphens are missing, so lists were badly
interpreted and rendered.
Signed-off-by: Thomas Monjalon
---
Already applied.
---
doc/guides/rel_notes/release_18_08.rst | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/doc/guides/rel_notes/release_18
> Anatoly Burakov (8):
> fbarray: support no-shconf mode
> ipc: add support for no-shconf mode
> eal: add support for no-shconf for hugepage info
> eal: add support for no-shconf in hugepage data file
> eal: do not create runtime dir in no-shconf mode
> mem: add support for hugepage-unl
Hi all,
I just noticed that, because of the removal of the "register" keyword in C++17,
when I compile my DPDK-enabled code with -std=c++17 I get the following:
In file included from
../../../Third-Party/cpp-libs/dpdk/include/rte_ether.h:53:0,
from
../../../Third-Party/cpp-
On systems where the required Netlink commands are not supported but
Mellanox OFED is installed, representors information must be retrieved
through sysfs.
Fixes: 4c10141488fe ("net/mlx5: add port representor awareness")
Signed-off-by: Nelio Laranjeiro
Acked-by: Adrien Mazarguil
---
drivers/net
13/07/2018 11:11, Nelio Laranjeiro:
> Fixes: 4ed05fcd441b ("ethdev: add flow API to expand RSS flows")
>
> Signed-off-by: Nelio Laranjeiro
> Acked-by: Adrien Mazarguil
>
> --
>
> Changes in v2:
>
> - add missing documentation.
> - add missing __rte_experimental in source file.
> - update the
> -Original Message-
> From: Trahe, Fiona
> Sent: Wednesday, July 11, 2018 7:03 PM
> To: dev@dpdk.org; dmitry.ereminsoleni...@linaro.org
> Cc: De Lara Guarch, Pablo ; Trahe, Fiona
>
> Subject: [PATCH v2] crypto/qat: fix checks for 3gpp algo bit params
>
> QAT driver checks byte alignme
On 07/04/2018 11:06 PM, Ferruh Yigit wrote:
> External Email
>
> On 7/1/2018 5:46 PM, Pavan Nikhilesh wrote:
>> From: "Kudurumalla, Rakesh"
>>
>> This feature is used to offload stripping of vlan header from recevied
>> packets and update vlan_tci field in mbuf when
>> DEV_RX_OFFLOAD_VLAN_STRI
> -Original Message-
> From: Trahe, Fiona
> Sent: Tuesday, July 10, 2018 12:07 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo ; Trahe, Fiona
>
> Subject: [PATCH] test/compress: add trace with device name
>
> Print out name of device on which test is running at start of test suite.
>
> -Original Message-
> From: Daly, Lee
> Sent: Wednesday, July 11, 2018 3:22 PM
> To: De Lara Guarch, Pablo
> Cc: dev@dpdk.org; Daly, Lee ; sta...@dpdk.org
> Subject: [PATCH v2] compress/isal: fix offset usage
>
> This patch allows the ISA-L compression PMD, to be used with offsets in
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Friday, July 13, 2018 3:28 AM
> To: Trahe, Fiona ; Jozwiak, TomaszX
> ; Griffin, John ; Jain,
> Deepak K
> Cc: dev@dpdk.org; De Lara Guarch, Pablo
> Subject: [PATCH v7 00/16] compress/qat: add compression PMD
>
> Create compre
This patch set adds the capability to do out-of-band power
monitoring on a system. It uses a thread to monitor the branch
counters in the targeted cores, and calculates the branch ratio
if the running code.
If the branch ratio is low (0.01), then
the code is most likely running in a tight poll loo
If we don't pass any ports to the app, we don't need to create
any mempools, and we don't need to init any ports.
Signed-off-by: David Hunt
Acked-by: Radu Nicolau
---
examples/vm_power_manager/main.c | 81 +---
1 file changed, 43 insertions(+), 38 deletions(-)
diff
Add in the '-l' command line parameter (also --core-list)
So the user can now pass --corelist=4,6,8-10 and it will
expand out to 4,6,8,9,10 using the parse function provided
in parse.c (parse_set).
This list of cores is then used to enable out-of-band monitoring
to scale up and down these cores ba
This patch introduces the out-of-band (oob) core monitoring
functions.
The functions are similar to the channel manager functions.
There are function to add and remove cores from the
list of cores being monitored. There is a function to initialise
the monitor setup, run the monitor thread, and exi
To facilitate more info per core, change the global_cpu_mask
from a uint64_t to an array. This also removes the limit on
64 cores, allocing the aray at run-time based on the number of
cores found in the system.
Signed-off-by: David Hunt
Acked-by: Radu Nicolau
---
examples/vm_power_manager/power
Change the app to now require three cores, as the third core
will be used to run the oob montoring thread.
Signed-off-by: David Hunt
Acked-by: Radu Nicolau
---
examples/vm_power_manager/main.c | 37 +---
1 file changed, 34 insertions(+), 3 deletions(-)
diff --git a/
add in the long form of -p, which is --port-list
Signed-off-by: David Hunt
Acked-by: Radu Nicolau
---
examples/vm_power_manager/main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/examples/vm_power_manager/main.c b/examples/vm_power_manager/main.c
index aef97b9ae..f9990f153 100644
--- a/
Add the capability for the vm_power_manager to receive
a policy of type BRANCH_RATIO. This will add any vcpus
in the policy to the oob monitoring thread.
Signed-off-by: David Hunt
Acked-by: Radu Nicolau
---
examples/vm_power_manager/channel_monitor.c | 23 +++--
lib/librte_power
1 - 100 of 161 matches
Mail list logo
