Hello Ferruh, thanks for the reply and please see my below comments.
Regards,
Asaf Penso
>-Original Message-
>From: Ferruh Yigit
>Sent: Tuesday, February 16, 2021 3:14 PM
>To: Asaf Penso ; dev@dpdk.org
>Cc: NBU-Contact-Thomas Monjalon ; Andrew
>Rybchenko
>Subject: Re: [dpdk-dev] [PATCH
Add the widlcard match/ACL table type for the SWX pipeline, which is
used under the hood by the table instruction.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Churchill Khangar
---
doc/api/doxy-api-index.md | 1 +
examples/pipeline/obj.c | 8 +
lib/librte_table/m
Add support for table entry priority, which is required for the
wildcard match/ACL table type.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_ctl.c | 27 +++
lib/librte_table/rte_swx_table.h | 9 +
2 files changed, 36 insertions(+)
diff --gi
Some table types (e.g. exact match/hash) allow for incremental table
updates, while others (e.g. wildcard match/ACL) do not. The former is
already supported, the latter is enabled by this patch.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_ctl.c | 315 ++
Improve the table entry parsing: better code structure, enable parsing
for the key field masks, allow comments and empty lines in the table
entry files.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Venkata Suresh Kumar P
Signed-off-by: Churchill Khangar
---
examples/pipeline/cli.c
Improve the internal table entry helper routines for key comparison,
entry duplication and checks.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_ctl.c | 120 --
1 file changed, 65 insertions(+), 55 deletions(-)
diff --git a/lib/librte_pipeline/rt
The completion type was wrong.
Don't check the completion if the wait timed out.
Fixes: 669c8de67c88 ("net/ionic: support basic LIF")
Cc: cardigli...@ntop.org
Cc: sta...@dpdk.org
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions
A future patch will allow Tx scatter/gather to be disabled. Store the value
in the queue so it can be changed at runtime based on the configuration.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 6 +-
drivers/net/ionic/ionic_lif.h | 1 +
drivers/net/ionic/ionic_rxtx.c | 6
Rather than dropping the whole burst if some don't fit.
This improves performance.
Signed-off-by: Andrew Boyer
Signed-off-by: Vishwas Danivas
---
drivers/net/ionic/ionic_rxtx.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ionic/ionic_rxtx.c b/drivers/
This improves performance.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 41 +++---
1 file changed, 13 insertions(+), 28 deletions(-)
diff --git a/drivers/net/ionic/ionic_rxtx.c b/drivers/net/ionic/ionic_rxtx.c
index 5236cae211..bb67c497a1 100644
-
Break it up rather than inlining it, so that we can remove
branches from the hot path.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 11 --
drivers/net/ionic/ionic_dev.h | 1 -
drivers/net/ionic/ionic_main.c | 10 -
drivers/net/ionic/ionic_rxtx.c | 37 +++
This improves debuggability.
To see the logs, use EAL arg: --log-level=pmd.net.ionic,debug
While here, stop counting fragments, but start counting mtods.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.h | 2 +-
drivers/net/ionic/ionic_rxtx.c | 13 +++--
2 files changed,
This will conserve resources.
Rename ionic_qcq_alloc() arg from 'base' to 'type_name' for clarity.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 14 +++---
drivers/net/ionic/ionic_dev.h | 34 ++-
drivers/net/ionic/ionic_lif.c | 49 +++
Pipe the value from the queue setup routines through to
ionic_qcq_alloc().
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 10 +++---
drivers/net/ionic/ionic_lif.h | 10 ++
drivers/net/ionic/ionic_rxtx.c | 4 ++--
3 files changed, 15 insertions(+), 9 deletions(-)
This will conserve resources.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 7 ---
drivers/net/ionic/ionic_lif.h | 1 -
2 files changed, 8 deletions(-)
diff --git a/drivers/net/ionic/ionic_lif.c b/drivers/net/ionic/ionic_lif.c
index 1ca6e050ad..462a526935 100644
--- a/driv
Create a unique Q-CQ struct for adminq, notifyq, rxq, and txq to
reduce the size of each object.
Minimize the size of each field to squeeze into as few cachelines
as possible.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 153 ++---
drivers/net/ion
This will conserve resources.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 6 --
drivers/net/ionic/ionic_dev.h | 2 --
drivers/net/ionic/ionic_lif.c | 1 -
drivers/net/ionic/ionic_rxtx.c | 9 +
4 files changed, 5 insertions(+), 13 deletions(-)
diff --git a/driv
Drop the callback part of the object and store only the pointers.
This saves a bit of space and simplifies the code.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 8 ++--
drivers/net/ionic/ionic_dev.h | 21 +--
drivers/net/ionic/ionic_main.c | 8
The adminq is the only caller of ionic_q_service(), so absorb it
into ionic_adminq_service().
Move all of the adminq code together into ionic_main.c.
Staticize a few things.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic.h | 13 -
drivers/net/ionic/ionic_dev.c | 85 -
This function is unused.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.h | 1 -
drivers/net/ionic/ionic_rx_filter.c | 14 --
drivers/net/ionic/ionic_rx_filter.h | 1 -
3 files changed, 16 deletions(-)
diff --git a/drivers/net/ionic/ionic_dev.h b/drivers/net/io
Add Q_NEXT_TO_POST() and Q_NEXT_TO_SRVC() macros.
Use a precomputed size mask.
This will conserve resources.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 14 +++---
drivers/net/ionic/ionic_dev.h | 14 +++---
drivers/net/ionic/ionic_lif.c | 5 +++--
drivers
This patch series reorganizes the main datastructure for each
queue, struct ionic_qcq. Its constituent struct ionic_queue and
struct ionic_cq are stripped down first. Then the generic struct
ionic_qcq is stripped down, and a unique struct is created for
each queue type.
The adminq code is consolid
Improve the internal table entry helper routines for key comparison,
entry duplication and checks.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_ctl.c | 120 --
1 file changed, 65 insertions(+), 55 deletions(-)
diff --git a/lib/librte_pipeline/rt
Some table types (e.g. exact match/hash) allow for incremental table
updates, while others (e.g. wildcard match/ACL) do not. The former is
already supported, the latter is enabled by this patch.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_ctl.c | 320 ++
Improve the table entry parsing: better code structure, enable parsing
for the key field masks, allow comments and empty lines in the table
entry files.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Venkata Suresh Kumar P
Signed-off-by: Churchill Khangar
---
examples/pipeline/cli.c
Add the widlcard match/ACL table type for the SWX pipeline, which is
used under the hood by the table instruction.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Churchill Khangar
---
doc/api/doxy-api-index.md | 1 +
examples/pipeline/obj.c | 8 +
lib/librte_table/m
Add support for table entry priority, which is required for the
wildcard match/ACL table type.
Signed-off-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_ctl.c | 27 +++
lib/librte_table/rte_swx_table.h | 9 +
2 files changed, 36 insertions(+)
diff --gi
> -Original Message-
> From: Bruce Richardson
> Sent: Tuesday, February 16, 2021 5:31 PM
> To: Van Haaren, Harry
> Cc: Burakov, Anatoly ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] eal: support using 0 as coremask for no-
> affinitization
>
> On Tue, Feb 16, 2021 at 05:22:25PM +,
On Tue, Feb 16, 2021 at 05:22:25PM +, Van Haaren, Harry wrote:
> > -Original Message-
> > From: Burakov, Anatoly
> > Sent: Tuesday, February 16, 2021 10:53 AM
> > To: Richardson, Bruce ; Van Haaren, Harry
> >
> > Cc: dev@dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH] eal: support using
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, February 16, 2021 10:53 AM
> To: Richardson, Bruce ; Van Haaren, Harry
>
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] eal: support using 0 as coremask for no-
> affinitization
>
> On 16-Feb-21 10:46 AM, Bruce Richards
>-Original Message-
>From: Andrew Rybchenko
>Sent: Monday, February 15, 2021 5:32 PM
>To: Xueming(Steven) Li
>Cc: dev@dpdk.org; Slava Ovsiienko ; Asaf Penso
>; NBU-Contact-Thomas Monjalon
>; Ferruh Yigit ; Ray Kinsella
>; Neil Horman
>
>Subject: Re: [PATCH v6 8/9] ethdev: representor i
For using a DPDK application, such as OVS, which is dynamically linked, the
DPDK version in use should always report the actual version, not the
version used at build time. This incorrect behaviour can be seen by
building OVS against one version of DPDK and running it against a later
one. Using "ov
>-Original Message-
>From: Andrew Rybchenko
>Sent: Monday, February 15, 2021 4:50 PM
>To: Xueming(Steven) Li
>Cc: dev@dpdk.org; Slava Ovsiienko ; Asaf Penso
>; NBU-Contact-Thomas Monjalon
>; Ferruh Yigit ; Ray Kinsella
>; Neil Horman
>
>Subject: Re: [PATCH v6 7/9] ethdev: new API to ge
>-Original Message-
>From: Andrew Rybchenko
>Sent: Monday, February 15, 2021 4:35 PM
>To: Xueming(Steven) Li
>Cc: dev@dpdk.org; Slava Ovsiienko ; Asaf Penso
>; NBU-Contact-Thomas Monjalon
>; Ferruh Yigit
>Subject: Re: [PATCH v6 5/9] ethdev: support PF index in representor
>
>On 2/14/21
On 15-Jan-21 7:32 AM, Nithin Dabilpuram wrote:
Partial DMA unmap is not supported by VFIO type1 IOMMU
in Linux. Though the return value is zero, the returned
DMA unmap size is not same as expected size.
So add test case and fix to both heap triggered DMA
mapping and user triggered DMA mapping/unm
On 2/7/2021 10:52 AM, Asaf Penso wrote:
In http://doc.dpdk.org/guides/nics/overview.html, table 1.1 lists all
supported features.
It has a single line for "Flow API" that refers to rte_flow support.
rte_flow is composed of many items and actions that are not expressed in
this single line.
The fo
On 16-Feb-21 11:39 AM, Bruce Richardson wrote:
When the dpdk-telemetry client connects to a DPDK instance, we can use the
PID provided in the initial connection message to query from /proc the name
of the process we are connected to, and display that to the user. We use
the "cmdline" procfs entry
Currently the dpdk-telemetry.py script connects to all running DPDK apps
consecutively. With the addition of this file-prefix argument, we can limit
the amount of information returned providing improved consumability and
precision to the user.
Signed-off-by: Kevin Laatz
Reviewed-by: Bruce Richar
When the dpdk-telemetry client connects to a DPDK instance, we can use the
PID provided in the initial connection message to query from /proc the name
of the process we are connected to, and display that to the user. We use
the "cmdline" procfs entry for the query since that is available on both
Li
On 16-Feb-21 11:02 AM, Bruce Richardson wrote:
On Tue, Feb 16, 2021 at 10:40:36AM +, Burakov, Anatoly wrote:
On 16-Feb-21 9:44 AM, Bruce Richardson wrote:
When the dpdk-telemetry client connects to a DPDK instance, we can use the
PID provided in the initial connection message to query from
Currently the dpdk-telemetry.py script connects to all running DPDK apps
consecutively. With the addition of this file-prefix argument, we can limit
the amount of information returned providing improved consumability and
precision to the user.
Signed-off-by: Kevin Laatz
Reviewed-by: Bruce Richar
On Tue, Feb 16, 2021 at 10:40:36AM +, Burakov, Anatoly wrote:
> On 16-Feb-21 9:44 AM, Bruce Richardson wrote:
> > When the dpdk-telemetry client connects to a DPDK instance, we can use the
> > PID provided in the initial connection message to query from /proc the name
> > of the process we are
On 16-Feb-21 10:46 AM, Bruce Richardson wrote:
On Tue, Feb 16, 2021 at 10:36:13AM +, Burakov, Anatoly wrote:
On 16-Feb-21 9:43 AM, Bruce Richardson wrote:
Allow the user to specify that they don't want any core pinning from DPDK
by passing in the coremask of 0.
---
I haven't checked what
On Tue, Feb 16, 2021 at 10:36:13AM +, Burakov, Anatoly wrote:
> On 16-Feb-21 9:43 AM, Bruce Richardson wrote:
> > Allow the user to specify that they don't want any core pinning from DPDK
> > by passing in the coremask of 0.
> > ---
>
> I haven't checked what happens yet, but down the line we
On 15-Feb-21 3:50 PM, Kevin Laatz wrote:
Currently the dpdk-telemetry.py script connects to all running DPDK apps
consecutively. With the addition of this file-prefix argument, we can limit
the amount of information returned providing improved consumability and
precision to the user.
Signed-off
On 16-Feb-21 9:44 AM, Bruce Richardson wrote:
When the dpdk-telemetry client connects to a DPDK instance, we can use the
PID provided in the initial connection message to query from /proc the name
of the process we are connected to, and display that to the user. We use
the "cmdline" procfs entry
15/02/2021 10:33, David Marchand:
> On Mon, Feb 15, 2021 at 10:14 AM Thomas Monjalon wrote:
> >
> > Start a new release cycle with empty release notes.
> >
> > Signed-off-by: Thomas Monjalon
>
> Acked-by: David Marchand
Applied
On 16-Feb-21 9:43 AM, Bruce Richardson wrote:
Allow the user to specify that they don't want any core pinning from DPDK
by passing in the coremask of 0.
---
I haven't checked what happens yet, but down the line we also set
affinity for service cores as well as interrupt thread. what would be
On Tue, Feb 16, 2021 at 09:43:00AM +, Bruce Richardson wrote:
> Allow the user to specify that they don't want any core pinning from DPDK
> by passing in the coremask of 0.
> ---
Apologies, missed my signoff, will add in V2, but will wait for feedback on
this V1 first.
/Bruce
When the dpdk-telemetry client connects to a DPDK instance, we can use the
PID provided in the initial connection message to query from /proc the name
of the process we are connected to, and display that to the user. We use
the "cmdline" procfs entry for the query since that is available on both
Li
Allow the user to specify that they don't want any core pinning from DPDK
by passing in the coremask of 0.
---
lib/librte_eal/common/eal_common_options.c | 18 +++---
lib/librte_eal/common/eal_internal_cfg.h | 1 +
lib/librte_eal/freebsd/eal.c | 5 +++--
lib/librte_ea
>-Original Message-
>From: Andrew Rybchenko
>Sent: Monday, February 15, 2021 4:26 PM
>To: Xueming(Steven) Li
>Cc: dev@dpdk.org; Slava Ovsiienko ; Asaf Penso
>; NBU-Contact-Thomas Monjalon
>; Ferruh Yigit
>Subject: Re: [PATCH v6 4/9] ethdev: support sub function representor
>
>Hi,
>
>O
52 matches
Mail list logo
