2015-07-09 14:15, Stephen Hemminger:
> On Thu, 09 Jul 2015 22:41:23 +0200
> Thomas Monjalon wrote:
>
> > REJECTED
> >
> > 2015-07-09 11:15, Stephen Hemminger:
> > > Changes in this version:
> > > - rebase for PCI uio changes
> > > - fix version map for 2.1
> > > - add BCM57840 support
> >
REJECTED
2015-07-09 11:15, Stephen Hemminger:
> Changes in this version:
> - rebase for PCI uio changes
> - fix version map for 2.1
> - add BCM57840 support
You ignore the comments which are done.
Examples for this series:
http://dpdk.org/ml/archives/dev/2015-June/019556.html
Big Thanks!
Sami.
From: Matt Laswell [mailto:lasw...@infiniteio.com]
Sent: Thursday, July 09, 2015 4:28 PM
To: Wiles, Keith
Cc: Assaad, Sami (Sami); dev at dpdk.org; Richardson, Bruce
Subject: Re: [dpdk-dev] DPDK Port Mirroring
Keith speaks truth. If I were going to do what you're describing, I
Hi Thomas,
On Tue, Jul 07, 2015 at 23:30:38 +0200, Thomas Monjalon wrote:
> 2015-07-07 22:42, Rahul Lakkireddy:
> > CXGBE PMD rx allocates a new mbuf everytime, which could lead to performance
> > hit. Instead, do bulk allocation of mbufs and re-use them.
> >
> > Also, simplify the overall rx-ha
On 7/9/15, 12:26 PM, "dev on behalf of Assaad, Sami (Sami)"
wrote:
>Hello,
>
>I want to build a DPDK app that is able to port-mirror all ingress
>traffic from two 10G interfaces.
>
>1. Is it possible in port-mirroring traffic consisting of 450byte
>packets at 20G without losing more than
On 7/9/15, 11:24 AM, "dev on behalf of stephen at networkplumber.org"
wrote:
>From: Stephen Hemminger
>
>These are update to earlier vmxnet3 driver changes. Mostly rebasing
>to current layout. I skipped the jumbo MTU stuff which works for me
>but reviewers seem to see problems with.
>
>Stephen H
Add new unit test for calculating the average table utilization,
using random keys, based on number of entries that can be added
until we encounter one that cannot be added (bucket if full).
Also, replace current hash_perf unit test to see performance more clear.
The current hash_perf unit test ta
This patch improves the unit tests for the hash library,
showing more readable results, in preparation for the new hash
implementation to show performance differences.
Changes in v4:
- Reduce test time, by reducing number of added keys/iterations,
as test was taking too long.
- Reduce number of
2015-07-08 14:10, Bruce Richardson:
> On Mon, Jul 06, 2015 at 03:16:01PM +0200, Thomas Monjalon wrote:
> > 2015-07-02 16:16, John McNamara:
> > > --- a/doc/guides/rel_notes/abi.rst
> > > +++ b/doc/guides/rel_notes/abi.rst
> > > Deprecation Notices
> > > ---
> > > +
> > > +* In DPD
2015-07-09 12:18, Bruce Richardson:
> On Thu, Jul 09, 2015 at 11:01:29AM +0200, Olivier Matz wrote:
> > In test application, the default size of allocated mempool is calculated
> > as following:
> >
> > (RTE_MAX_LCORE * (RTE_MEMPOOL_CACHE_MAX_SIZE + max_kept_objects)) - 1
> >
> > The objective
Thank you!
Best Regards,
Sami.
-Original Message-
From: Bruce Richardson [mailto:bruce.richard...@intel.com]
Sent: Thursday, July 09, 2015 6:10 AM
To: Assaad, Sami (Sami)
Cc: dev at dpdk.org
Subject: Re: dev Digest, Vol 45, Issue 9
On Wed, Jul 08, 2015 at 11:18:04PM +, Assaad, Sami
2015-07-07 09:23, Dumitrescu, Cristian:
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Maciej Gajdzica
> > Changes in v6:
> > - fixed build issues with icc 15
> > - fixed build issues with gcc 32bit
>
> Acked-by: Cristian Dumitrescu
Applied, thanks
> > Exported symbols for nodrop, fragmentation, reassembly ports
> >
> > Signed-off-by: Maciej Gajdzica
>
> Acked-by: Cristian Dumitrescu
Series applied, thanks
Hello,
I want to build a DPDK app that is able to port-mirror all ingress traffic from
two 10G interfaces.
1. Is it possible in port-mirroring traffic consisting of 450byte packets
at 20G without losing more than 5% of traffic?
2. Would you have any performance results due to packe
The patch fixes doxygen comments of below functions.
- rte_eth_dev_close()
Add description about when the function can be called and also about
what kind of resources will be freed.
- rte_eth_dev_detach()
Add description about when the function can be called.
Signed-off-by: Tetsuya Muka
Hi John,
Thank you for your review.
I will submit a v2 of the patch.
Klaus
Am 08.07.15 um 18:11 schrieb Mcnamara, John:
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Klaus Degner
>> Sent: Tuesday, June 30, 2015 12:40 PM
>> To: dev at dpdk.org
>> Subjec
On 2015/07/09 16:28, Thomas Monjalon wrote:
> 2015-07-09 14:46, Tetsuya Mukawa:
>> The patch fixes doxygen comments of below functions.
>> - rte_eth_dev_close()
>>Add description about what kind of resources will be freed.
>> - rte_eth_dev_detach()
>>Add description about when the functio
On Thu, Jul 09, 2015 at 05:51:16PM +0200, Thomas Monjalon wrote:
> 2015-07-08 14:10, Bruce Richardson:
> > On Mon, Jul 06, 2015 at 03:16:01PM +0200, Thomas Monjalon wrote:
> > > 2015-07-02 16:16, John McNamara:
> > > > --- a/doc/guides/rel_notes/abi.rst
> > > > +++ b/doc/guides/rel_notes/abi.rst
>
On Fri, 10 Jul 2015 01:27:25 +0200
Thomas Monjalon wrote:
> 2015-07-09 16:01, Stephen Hemminger:
> > From: Stephen Hemminger
> >
> > Customers often screen off info level messages, so raise log
> > level of significant events
> >
> > Signed-off-by: Stephen Hemminger
>
> It was acked by Bruce
From: Stephen Hemminger
For applications that use m->userdata the initialization can
be a signficant (10%) performance penalty.
Rather than taking the cache penalty of initializing userdata
in the receive handling, do it in the place where mbuf is
already cache hot and being setup.
Signed-off-b
From: Stephen Hemminger
Added rte_pktmbuf_copy() function since copying multi-part
segments is common issue and can be problematic.
Signed-off-by: Mike Davison
Reviewed-by: Stephen Hemminger
---
lib/librte_mbuf/rte_mbuf.h | 59 ++
1 file changed, 59
These are a couple of small patches we use to help
with mbuf handling.
Stephen Hemminger (2):
mbuf: Add rte_pktmbuf_copy
mbuf: make sure userdata is initialized
drivers/net/cxgbe/sge.c | 1 +
drivers/net/e1000/em_rxtx.c | 2 ++
drivers/net/e1000/igb_rxtx.c
From: Stephen Hemminger
If VFIO is configured, it is better to just not build the source
files (rather than generating empty object files).
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/linuxapp/eal/Makefile | 4 ++--
lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 3 -
From: Stephen Hemminger
The build of DPDK may be done on a system where Linux headers
in /usr/include (and therefore kernel version macro) are much
older than the target runtime system.
In order to work around this, one solution is to put in simplified
kernel header (this is what the compat stuf
In our environment we build on old system (2.6.32) but want
to have VFIO enabled. This was the best solution after many
different experiments. There was an earlier discussion and
the solution proposed then was significantly different.
Stephen Hemminger (2):
vfio: fix build if build envrionment
From: Cyril Chemparathy
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
---
MAINTAINERS | 4
1 file changed, 4 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 5476a73..6ffa01b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -114,6 +114,10 @@ M: Bruce Richardson
M: K
From: Cyril Chemparathy
This commit adds a poll mode driver for the mPIPE hardware present on
TILE-Gx SoCs.
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
---
config/defconfig_tile-tilegx-linuxapp-gcc |1 +
drivers/net/Makefile |1 +
drivers/net/mpipe/
From: Cyril Chemparathy
This commit adds support for the TILE-Gx platform, as well as the TILE
CPU architecture. This architecture port is fairly simple due to its
reliance on generics for most arch stuff.
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
---
config/defconfig_tile-t
From: Cyril Chemparathy
This patch adds a few new page sizes that are supported on the TILE-Gx
and TILE-Mx platforms.
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
---
lib/librte_eal/common/eal_common_memzone.c | 8 +
lib/librte_eal/common/include/rte_memory.h | 16 +--
From: Cyril Chemparathy
On TILE-Gx and TILE-Mx platforms, the buffers fed into the hardware
buffer manager require a 128-byte alignment. With this change, we
allow configuration based override of the element alignment, and
default to RTE_CACHE_LINE_SIZE if left unspecified.
Signed-off-by: Cyril
From: Cyril Chemparathy
This patch extends the memzone allocator to remove the restriction
that prevented callers from specifying multiple page sizes in the
flags argument.
In doing so, we also sanitize the free segment matching logic to get
rid of architecture specific disjunctions (2MB vs 1GB
From: Cyril Chemparathy
The definitions of rte_memzone_reserve_aligned() and
rte_memzone_reserve_bounded() were identical with the exception of the
bound argument passed into rte_memzone_reserve_thread_safe().
This patch removes this replication of code by unifying it into
rte_memzone_reserve_th
From: Cyril Chemparathy
The library name is now being pinned to "dpdk" instead of intel_dpdk,
powerpc_dpdk, etc. As a result, we no longer need this config item.
This patch removes it.
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
Acked-by: Bruce Richardson
---
config/common_bs
When RTE_COMPILE_TIME_CPUFLAGS is empty, the rte_cpu_check_supported()
code breaks with a "comparison is always false due to limited range of
data type". This is because the compile_time_flags[] array is empty.
Assigning the array dimension to a local variable apparently solves this.
Signed-off-b
From: Cyril Chemparathy
This is necessary because the required CPU flags may not be defined on
other architectures.
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
Acked-by: Bruce Richardson
---
lib/librte_hash/rte_hash_crc.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/l
From: Cyril Chemparathy
The original code mistakenly defaulted to X86 when RTE_ARCH_PPC_64 was
left undefined. This did not accomodate other non-PPC/non-X86
architectures. This patch fixes this issue.
Signed-off-by: Cyril Chemparathy
Signed-off-by: Zhigang Lu
Acked-by: Bruce Richardson
---
This series adds support for the EZchip TILE-Gx family of SoCs. The
architecture port in itself is fairly straight forward due to its
reliance on generics for the most part.
In addition to adding TILE-Gx architecture specific code, this series
includes a few cross-platform fixes for DPDK (cpuflag
On Thu, 9 Jul 2015 22:32:29 +
Thomas Monjalon wrote:
> 2015-07-09 18:46, Yong Wang:
> > On 7/9/15, 11:24 AM, "dev on behalf of stephen at networkplumber.org"
> > wrote:
> > >From: Stephen Hemminger
> > >
> > >These are update to earlier vmxnet3 driver changes. Mostly rebasing
> > >to curren
On Wed, 01 Apr 2015 09:45:02 +0200
Thomas Monjalon wrote:
> 2015-03-24 23:54, Ananyev, Konstantin:
> > From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> > > On Mon, 23 Mar 2015 16:45:44 +
> > > "Ananyev, Konstantin" wrote:
> > > > From: dev [mailto:dev-bounces at dpdk.org] On
From: Stephen Hemminger
Any message about incorrect API usage should be at NOTICE
level or above.
Signed-off-by: Stephen Hemminger
---
drivers/net/e1000/igb_ethdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_e
From: Stephen Hemminger
Any debug messages about hardware should be under debug (or removed)
and reduce customer visible log spam.
Signed-off-by: Stephen Hemminger
---
drivers/net/e1000/em_ethdev.c | 5 +++--
drivers/net/e1000/igb_ethdev.c | 5 +++--
2 files changed, 6 insertions(+), 4 deleti
From: Stephen Hemminger
Similar to ixgbe, allow log messages to be removed
by using RTE_LOG_LEVEL during the build process.
Signed-off-by: Stephen Hemminger
---
drivers/net/e1000/e1000_logs.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/e1000/e1000_logs.h b
From: Stephen Hemminger
The ixgbe driver was not following DPDK convention and
was leaving loggin always in even if LOG_LEVEL was configured
to disable debug logs.
Signed-off-by: Stephen Hemminger
---
drivers/net/ixgbe/ixgbe_logs.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff
From: Stephen Hemminger
Customers often screen off info level messages, so raise log
level of significant events
Signed-off-by: Stephen Hemminger
---
drivers/net/ixgbe/ixgbe_ethdev.c | 12 ++--
drivers/net/ixgbe/ixgbe_fdir.c | 2 +-
2 files changed, 7 insertions(+), 7 deletions(-)
From: Stephen Hemminger
All the debug chatter messages in the system log causes
complaints from users. Change the INFO messages to DEBUG
for normal startup kind of stuff.
Signed-off-by: Stephen Hemminger
---
drivers/net/ixgbe/ixgbe_ethdev.c | 14 +++---
drivers/net/ixgbe/ixgbe_rxtx.c
From: Stephen Hemminger
These patches were sent earlier, updated to current tree.
They make Intel drivers not spam the log with information
messages that cause questions in production.
Unfortunately, developers seem to get attached to log messages
which are not appropriate in a production produ
2015-07-09 14:22, Bruce Richardson:
> The comment for TX offload flags stated that those flags started at bit
> 55 and then were added to the right of that, leaving 8 bits reserved for
> generic mbuf (i.e. non-offload) use. This comment may not have been
> clear as 5 of the 8 flags which were reser
On Fri, Jun 19, 2015 at 6:00 AM, Cunming Liang
wrote:
> v13 changes
> - version map cleanup for v2.1
> - replace RTE_EAL_RX_INTR by RTE_NEXT_ABI for ABI compatibility
>
Please, this patchset ends with a patch that deals with ABI compatibility
while it should do so on a per-patch basis.
Besides
Keith speaks truth. If I were going to do what you're describing, I would
do the following:
1. Start with the l2fwd example application.
2. Remove the part where it modifies the ethernet MAC address of received
packets.
3. Add a call in to clone mbufs via rte_pktmbuf_clone() and send the cloned
p
-- Original --
From: "Tony Lu";;
Date: Jul 9, 2015
To: "'Thomas Monjalon'";
Cc: "dev";
Subject: Re: [dpdk-dev] [PATCH v3 04/12] eal: allow empty compile time flags
>-Original Message-
>From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
>Sen
The patch fixes doxygen comments of below functions.
- rte_eth_dev_close()
Add description about what kind of resources will be freed.
- rte_eth_dev_detach()
Add description about when the function can be called.
Signed-off-by: Tetsuya Mukawa
---
lib/librte_ether/rte_ethdev.h | 4
1
Document the optional ieee1588 forwarding mode.
Signed-off-by: John McNamara
---
doc/guides/testpmd_app_ug/run_app.rst | 2 +-
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 2 ++
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/doc/guides/testpmd_app_ug/run_app.rst
b/doc/guid
Refactor the ieee1588_fwd mode in testpmd to use the new ethdev
APIs to enable and read IEEE1588 PTP timestamps.
Signed-off-by: John McNamara
---
app/test-pmd/ieee1588fwd.c | 466 +++--
1 file changed, 27 insertions(+), 439 deletions(-)
diff --git a/app/t
Add ixgbe support for new ethdev APIs to enable and read IEEE1588/
802.1AS PTP timestamps.
Signed-off-by: John McNamara
---
drivers/net/i40e/i40e_ethdev.c | 143 +
drivers/net/i40e/i40e_rxtx.c | 40 +++-
2 files changed, 182 insertions(+), 1 del
Add ixgbe support for new ethdev APIs to enable and read IEEE1588
PTP timestamps.
Signed-off-by: John McNamara
---
drivers/net/ixgbe/ixgbe_ethdev.c | 122 +++
1 file changed, 122 insertions(+)
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/
Add e1000/igb support for new ethdev APIs to enable and read
IEEE1588 PTP timestamps.
Signed-off-by: John McNamara
---
drivers/net/e1000/igb_ethdev.c | 115 +
1 file changed, 115 insertions(+)
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e100
Add mbuf field to store the IEEE1588 RX register index and other flags.
Signed-off-by: John McNamara
---
lib/librte_mbuf/rte_mbuf.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 80419df..d5895ea 100644
--- a/lib/librte_mbuf/r
Add ethdev API to enable and read IEEE1588/802.1AS PTP timestamps
from devices that support it. The following functions are added:
rte_eth_timesync_enable()
rte_eth_timesync_disable()
rte_eth_timesync_read_rx_timestamp()
rte_eth_timesync_read_tx_timestamp()
Signed-off-by: John McN
This patchset adds ethdev API to enable and read IEEE1588/802.1AS PTP
timestamps from devices that support it. The following functions are added:
rte_eth_timesync_enable()
rte_eth_timesync_disable()
rte_eth_timesync_read_rx_timestamp()
rte_eth_timesync_read_tx_timestamp()
The "iee
The comment for TX offload flags stated that those flags started at bit
55 and then were added to the right of that, leaving 8 bits reserved for
generic mbuf (i.e. non-offload) use. This comment may not have been
clear as 5 of the 8 flags which were reserved have now been used for TX
offloads.
This
2015-07-09 11:19, David Marchand:
> Here is a little patchset cleaning eal_hugepage_info.c file and fixing a bug
> when having more than two hugepage sizes.
> No functional change to be expected.
>
> Changes since v1
> - fix build on 32 bits system
Applied, thanks
On Thu, 09 Jul 2015 22:41:23 +0200
Thomas Monjalon wrote:
> REJECTED
>
> 2015-07-09 11:15, Stephen Hemminger:
> > Changes in this version:
> > - rebase for PCI uio changes
> > - fix version map for 2.1
> > - add BCM57840 support
>
> You ignore the comments which are done.
> Examples for t
Issue: When calling the reset API to reset all the stats for i40e,
all the stats will be untracked before the next time calling get stats API.
Once calling the get stats API it will show all the stats equal zero.
Changes: Calling the get stats API in the reset API will force the stats_offset
upda
On Wed, 17 Jun 2015 14:44:31 +
David Marchand wrote:
> +? ? ? ?if (len == 3 || len > sizeof(pi.pi_data)) {
> +? ? ? ? ? ? ? ?RTE_LOG(ERR, EAL, "%s(): invalid pci read length\n",
> __func__);
> +? ? ? ? ? ? ? ?goto error;
> +? ? ? ?}
>
> A comment on length 3 would help to understand why it
You are right, I dint think of the rings. I guess if I keep the netdev
intact and release the rings and stuff as it does on a /dev/kni close,
that should be fine ? And when my app comes back up and opens dev/kni,
the rings etc.. can be recreated, and when my app tries to create the
netdevs, it rea
On Thu, Jul 09, 2015 at 09:12:23AM +0100, Bruce Richardson wrote:
> Thanks for the feedback Matthew. Can you suggest a function prototype for such
> a walk operation that would make it useful for you. While we can keep the
> hash structure public, I'd prefer if we could avoid it, as it makes making
Add new unit test for calculating the average table utilization,
using random keys, based on number of entries that can be added
until we encounter one that cannot be added (bucket if full)
Also, replace current hash_perf unit test to see performance more clear.
The current hash_perf unit test tak
This patch improves the unit tests for the hash library,
showing more readable results, in preparation for the new hash
implementation to show performance differences.
Changes in v3:
- Increase table utilization in performance unit tests
Changes in v2:
- Add missing error check
- Simplify avera
From: Cyril Chemparathy
Signed-off-by: Zhigang Lu
---
MAINTAINERS | 4
1 file changed, 4 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 5476a73..6ffa01b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -114,6 +114,10 @@ M: Bruce Richardson
M: Konstantin Ananyev
F: lib/librte_
From: Cyril Chemparathy
This commit adds a poll mode driver for the mPIPE hardware present on
TILE-Gx SoCs.
Signed-off-by: Zhigang Lu
---
config/defconfig_tile-tilegx-linuxapp-gcc |1 +
drivers/net/Makefile |1 +
drivers/net/mpipe/Makefile| 46 +
From: Cyril Chemparathy
This commit adds support for the TILE-Gx platform, as well as the TILE
CPU architecture. This architecture port is fairly simple due to its
reliance on generics for most arch stuff.
Signed-off-by: Zhigang Lu
---
config/defconfig_tile-tilegx-linuxapp-gcc | 69 +
From: Cyril Chemparathy
This patch adds a few new page sizes that are supported on the TILE-Gx
and TILE-Mx platforms.
Signed-off-by: Zhigang Lu
---
lib/librte_eal/common/eal_common_memzone.c | 8 +
lib/librte_eal/common/include/rte_memory.h | 16 +
lib/librte_eal/common/include/
From: Cyril Chemparathy
On TILE-Gx and TILE-Mx platforms, the buffers fed into the hardware
buffer manager require a 128-byte alignment. With this change, we
allow configuration based override of the element alignment, and
default to RTE_CACHE_LINE_SIZE if left unspecified.
Signed-off-by: Zhiga
From: Cyril Chemparathy
This patch extends the memzone allocator to remove the restriction
that prevented callers from specifying multiple page sizes in the
flags argument.
In doing so, we also sanitize the free segment matching logic to get
rid of architecture specific disjunctions (2MB vs 1GB
From: Cyril Chemparathy
The definitions of rte_memzone_reserve_aligned() and
rte_memzone_reserve_bounded() were identical with the exception of the
bound argument passed into rte_memzone_reserve_thread_safe().
This patch removes this replication of code by unifying it into
rte_memzone_reserve_th
From: Cyril Chemparathy
The library name is now being pinned to "dpdk" instead of intel_dpdk,
powerpc_dpdk, etc. As a result, we no longer need this config item.
This patch removes it.
Signed-off-by: Zhigang Lu
Acked-by: Bruce Richardson
---
config/common_bsdapp| 1 -
When RTE_COMPILE_TIME_CPUFLAGS is empty, the rte_cpu_check_supported()
code breaks with a "comparison is always false due to limited range of
data type". This is because the compile_time_flags[] array is empty.
Assigning the array dimension to a local variable apparently solves this.
Signed-off-b
From: Cyril Chemparathy
This is necessary because the required CPU flags may not be defined on
other architectures.
Signed-off-by: Zhigang Lu
Acked-by: Bruce Richardson
---
lib/librte_hash/rte_hash_crc.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/librte_hash/rte_hash_crc.h b/li
From: Cyril Chemparathy
The original code mistakenly defaulted to X86 when RTE_ARCH_PPC_64 was
left undefined. This did not accomodate other non-PPC/non-X86
architectures. This patch fixes this issue.
Signed-off-by: Zhigang Lu
Acked-by: Bruce Richardson
---
app/test/test_cpuflags.c | 6 +++-
This series adds support for the EZchip TILE-Gx family of SoCs. The
architecture port in itself is fairly straight forward due to its
reliance on generics for the most part.
In addition to adding TILE-Gx architecture specific code, this series
includes a few cross-platform fixes for DPDK (cpuflag
On 2015/07/08 18:59, Thomas Monjalon wrote:
> 2015-07-08 09:49, Iremonger, Bernard:
>> From: Tetsuya Mukawa [mailto:mukawa at igel.co.jp]
>>> On 2015/07/07 19:53, Iremonger, Bernard wrote:
From: Tetsuya Mukawa [mailto:mukawa at igel.co.jp]
> On 2015/07/06 20:35, Qiu, Michael wrote:
>>
Hi,
I have a DPDK based application where the core 0 is handling the exception
path and rest of the cores are bringing in the data from the NIC via the
PMD.
For the exception path handling I use the tun/tap interface.
So the flow is like this ?
Fast path cores bring in the data from NIC,
>-Original Message-
>From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
>Sent: Thursday, July 09, 2015 8:46 AM
>To: Zhigang Lu
>Cc: dev at dpdk.org
>Subject: Re: [dpdk-dev] [PATCH v3 04/12] eal: allow empty compile time
flags
>
>2015-07-06 16:51, Zhigang Lu:
>> The rte_cpu_check_
On Thu, Jul 09, 2015 at 11:01:29AM +0200, Olivier Matz wrote:
> In test application, the default size of allocated mempool is calculated
> as following:
>
> (RTE_MAX_LCORE * (RTE_MEMPOOL_CACHE_MAX_SIZE + max_kept_objects)) - 1
>
> The objective is to ensure that all cores can fill their cache a
2015-07-09 09:55, Kulasek, TomaszX:
> > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > Sent: Thursday, July 9, 2015 03:58
> > To: Kulasek, TomaszX
> > Cc: dev at dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH v3 5/8] ring: queue stats mapping set dummy
> > implementation
> >
> > 2015
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Maciej Gajdzica
> Sent: Thursday, July 9, 2015 11:17 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 2/2] pipeline: added missing symbols to map file
>
> Exported symbols for port in, port out and table
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Maciej Gajdzica
> Sent: Thursday, July 9, 2015 11:17 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH 1/2] port: added missing symbols to map file
>
> Exported symbols for nodrop, fragmentation, reassembl
From: Stephen Hemminger
No reason to inline large functions. Compiler will decide already
based on optimization level.
Also register array should be const.
Signed-off-by: Stephen Hemminger
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletions
From: Stephen Hemminger
By defining macro as a stub it is possible to get rid of #ifdef's
in the actual code. Always evaluate the argument (even in the stub)
so that there are no extra unused variable errors.
Signed-off-by: Stephen Hemminger
---
drivers/net/vmxnet3/vmxnet3_ethdev.h | 6 --
From: Stephen Hemminger
Refactor the logic to compute receive offload flags to a simpler
function. And add support for putting RSS flow hash into packet.
Signed-off-by: Stephen Hemminger
Signed-off-by: Bill Hong
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 69 ++---
From: Stephen Hemminger
The Intel version of VMXNET3 driver does not handle link state properly.
The VMXNET3 API returns 1 if connected and 0 if disconnected.
Also need to return correct value to indicate state change.
Signed-off-by: Stephen Hemminger
Acked-by: Yong Wang
---
drivers/net/vmxne
From: Stephen Hemminger
Change sending loop to support multi-segment mbufs.
The VMXNET3 api has start-of-packet and end-packet flags, so it
is not hard to send multi-segment mbuf's.
Also, update descriptor in 32 bit value rather than toggling
bitfields which is slower and error prone.
Based on c
From: Stephen Hemminger
There are several stats here which are never set, and have no way
to be displayed. Assume in future xstats could be used.
Signed-off-by: Stephen Hemminger
---
drivers/net/vmxnet3/vmxnet3_ring.h | 16 ++--
1 file changed, 6 insertions(+), 10 deletions(-)
di
From: Stephen Hemminger
Remove check for packets greater than MTU. No other driver does
this, it should be handled at higher layer
Signed-off-by: Stephen Hemminger
Acked-by: Yong Wang
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 2 --
drivers/net/vmxnet3/vmxnet3_ethdev.h | 1 -
drivers/net/vm
From: Stephen Hemminger
Support the VLAN filter functionality of the VMXNET3 interface.
Signed-off-by: Stephen Hemminger
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 105 ---
drivers/net/vmxnet3/vmxnet3_ethdev.h | 3 +-
drivers/net/vmxnet3/vmxnet3_rxtx.c | 31
From: Stephen Hemminger
These are update to earlier vmxnet3 driver changes. Mostly rebasing
to current layout. I skipped the jumbo MTU stuff which works for me
but reviewers seem to see problems with.
Stephen Hemminger (8):
vmxnet3: enable VLAN filtering
vmxnet3: remove mtu check
vmxnet3:
Using IBM advance toolchain on Ubuntu 14.04 (package 8.0-3), gcc is complaining
about out of bound accesses.
CC eal_hugepage_info.o
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c:
In function ?eal_hugepage_info_init?:
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c:350:35:
error: array subscrip
With this, we should be checkpatch compliant.
Signed-off-by: David Marchand
Acked-by: Sergio Gonzalez Monroy
---
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c | 73 ---
1 file changed, 39 insertions(+), 34 deletions(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_hugepa
Replace this while loop with a for loop and simplify error handling.
Indent is broken on purpose, fixed in next commit.
Signed-off-by: David Marchand
Acked-by: Sergio Gonzalez Monroy
---
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c | 28 ---
1 file changed, 15 insertion
Prepare for checkpatch compliance.
Signed-off-by: David Marchand
Acked-by: Sergio Gonzalez Monroy
---
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c | 28 +--
1 file changed, 16 insertions(+), 12 deletions(-)
diff --git a/lib/librte_eal/linuxapp/eal/eal_hugepage_info.c
1 - 100 of 159 matches
Mail list logo
