> > Zero packets can be returned by rte_eth_rx_burst() and
> > rte_distributor_returned_pkts() inside lcore_rx(), so
> > for zero packet scenario instead of proceeding to
> > next operations we should continue to the next iteration of the
> > loop to avoid unnecessary processing overhead which is c
> > Inside flush_fwd_rx_queues removed redundant prev_tsc update with
> > cur_tsc,
> > as prev_tsc value is always updated with rte_rdtsc() in for loop.
> >
> > Coverity issue: 127797
> >
> > Fixes: f487715f36f5 ("app/testpmd: add timeout in Rx queue flushing")
> >
> > Signed-off-by: Reshma Patt
2016-07-15 12:34, John Daley:
> The enic PMD code has diverged from code that was once
> shared with the enic kernel mode driver for performance
> reasons. It is confusing and misleading to print the
> internal version number. Remove it.
>
> Fixes: fefed3d1e62c ("enic: new driver")
> Signed-off-by
2016-07-13 18:09, Nelson Escobar:
> When enic's interrupt handler is called indicating an error, it scans
> through the receive queues (RQs) on the adapter looking for errors.
> But since the inclusion of rx scatter, some of the RQs may not be in
> use, and you shouldn't check them for errors.
>
>
2016-07-13 09:52, Nelson Escobar:
> The calculation of truncated packets didn't take into account packet
> errors due to the adapter not having buffers, causing both the
> ipackets, and imissed counts to be wrong if such errors occurred. In
> order to properly calculate the number of packets trunc
2016-07-12 12:24, John Daley:
> The exported device start and stop functions where not setting the queue
> states to RTE_ETH_QUEUE_STATE_STARTED and RTE_ETH_QUEUE_STATE_STOPPED.
> After starting the device, the RTE queue stop function would not call
> the enic queue stop function since queue was al
2016-07-10 14:15, John Daley:
> The check that all Tx and Rx queues were set up was not
> adequate when reconfiguring with a different number of
> queues. Only the number of completion queues (CQs) was
> being used to make the determination, but the CQ array
> is shared between the underlying Rx an
2016-07-11 12:45, John Daley:
> In the burst Tx cleanup function, the reference count in mbufs
> returned to the pool should to be decremented before they are
> returned. Decrementing is not done by rte_mempool_put_bulk()
> so it must be done separately using __rte_pktmbuf_prefree_seg().
>
> Also
2016-07-08 15:22, John Daley:
> One instance of a filter add failure was not incrementing the
> the fail counter.
>
> Fixes: 4c2c7bf41f5a ("net/enic: fix negative array index write")
> Signed-off-by: John Daley
Applied, thanks
2016-07-13 16:33, Adrien Mazarguil:
> From: Olga Shern
>
> RHEL 7.1's GCC for POWER8 reports the following error in one rte_memcpy()
> macro call by mlx5:
>
> error: array subscript is above array bounds [-Werror=array-bounds]
>
> It appears to be a GCC bug which can be worked around by making
2016-07-15 18:38, Xiao Wang:
> In multi-queue + FTAG use case, we need to turn tx_ftag_en on for all
> the Tx queues.
>
> Fixes: 7958b1310d5e ("fm10k: enable FTAG based forwarding")
>
> Reported-by: Ricky Li
> Signed-off-by: Xiao Wang
Applied, thanks
> > This reverts commit 4761f57d58c6f52543738dbe299f846d62d75895.
> > Introducing VLAN table by adding VLAN adminq command will cause NIC's
> > throughput drop obviously. It's a hardware issue.
> > With this revert, VLAN filtering can only work when promiscuous mode is
> > disabled.
> >
> > Revert
2016-07-14 09:59, Jeff Shaw:
> Our testing suggests minimal (in some cases zero) impact to core-bound
> forwarding throughput as measured by testpmd. Throughput increase is
> observed in l3fwd as now the vpmd can be used with hw_ip_checksum
> enabled and without needing '--parse-ptype'.
>
> The be
2016-07-12 20:11, Yuanhan Liu:
> On Tue, Jul 12, 2016 at 11:30:25AM +0200, Maxime Coquelin wrote:
> > The error is reported using test build script:
> >
> > $ scripts/test-build.sh x86_64-native-linuxapp-gcc
> > ...
> > drivers/net/virtio/virtio_user_ethdev.c: In function
> > ?virtio_user_pmd_dev
On Wed, Jul 13, 2016 at 03:02:37PM +0200, Adrien Mazarguil wrote:
> DPDK uses GNU C language extensions in most of its code base. This is fine
> for internal source files whose compilation flags are controlled by DPDK,
> however user applications that use exported "public" headers may experience
>
2016-07-12 16:37, Yuanhan Liu:
> On Wed, Jul 06, 2016 at 02:24:58PM +0200, Christian Ehrhardt wrote:
> > *update in v2*
> > - refreshing for DPDK 16.07
> > - Close fd on vserver->listenfd as suggested in discussion
> >
> > Original From:
> > From: Patrik Andersson
> >
> > Protect against DPDK cr
2016-07-15 20:14, Yuanhan Liu:
> On Fri, Jul 15, 2016 at 02:15:03PM +0300, Ilya Maximets wrote:
> > Version 3:
> > * Patch splitted in two.
> > * Applied workaround from Rich Lane and added comment about
> > performance issue with some compilers and 'unlikely' macro.
>
> Thanks a lot
On Fri, Jul 15, 2016 at 11:14:52AM +0200, Thomas Monjalon wrote:
> 2016-07-15 16:42, Yuanhan Liu:
> > You see that no body cares it :)
> >
> > So I will make a patch to mark vhost-cuse as deprecated shortly.
> > Thomas, works to you?
>
> Perfect. Thanks Yuanhan
Great! deprecate note has been sen
Vhost-cuse was invented before vhost-user exist. The both are actually
doing the same thing: a vhost-net implementation in user space. But they
are not exactly the same thing.
Firstly, vhost-cuse is harder for use; no one seems to care it, either.
Furthermore, since v2.1, a large majority of devel
On Fri, Jul 15, 2016 at 02:15:03PM +0300, Ilya Maximets wrote:
> Version 3:
> * Patch splitted in two.
> * Applied workaround from Rich Lane and added comment about
> performance issue with some compilers and 'unlikely' macro.
Thanks a lot for the patches.
Acked-by: Yuanhan Li
>
>it is fixed in 16.07-rc2 that I checked
Great, thanks.
>
>Vincent
>
>On Fri, Jul 15, 2016 at 11:48 AM, Harish Patil
>wrote:
>> Hi Huawie/Yuanhan,
>> I encounter segfault issue in virtio PMD driver when I run any DPDK
>> application in the VM. The virtio devices should not have been probed in
2016-07-15 18:42, Thomas Monjalon:
> 2016-07-15 17:32, Thomas Monjalon:
> > 2016-07-14 17:15, Yong Wang:
> > > - void *second_addr = RTE_PTR_ADD(bar_addr,
> > > memreg[1].offset);
> > > + void *second_addr = RTE_PTR_ADD(bar_addr,
> > > +
Hi Huawie/Yuanhan,
I encounter segfault issue in virtio PMD driver when I run any DPDK
application in the VM. The virtio devices should not have been probed in
the first place since they are not attached to igb_uio driver (and managed
by kernel driver).
Network devices using DPDK-compatible drive
On Friday 15 July 2016 03:09 PM, Shreyansh jain wrote:
> On Thursday 14 July 2016 10:25 PM, Jan Viktorin wrote:
>> On Tue, 12 Jul 2016 11:31:17 +0530
>> Shreyansh Jain wrote:
>>
>>> eal is a better place than crypto / ethdev for naming resources.
>>
>> s/for naming/to name/
>
> OK.
>
>>
>> What
2016-07-15 17:32, Thomas Monjalon:
> 2016-07-14 17:15, Yong Wang:
> > - void *second_addr = RTE_PTR_ADD(bar_addr,
> > memreg[1].offset);
> > + void *second_addr = RTE_PTR_ADD(bar_addr,
> > +
In multi-queue + FTAG use case, we need to turn tx_ftag_en on for all
the Tx queues.
Fixes: 7958b1310d5e ("fm10k: enable FTAG based forwarding")
Reported-by: Ricky Li
Signed-off-by: Xiao Wang
---
drivers/net/fm10k/fm10k_ethdev.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --
On Fri, 15 Jul 2016 15:19:14 +0200
Thomas Monjalon wrote:
> 2016-07-08 21:09, Jan Viktorin:
> > Hello,
> >
> > based on the discussions with Shreyansh, I propose a patchset with
> > the important EAL changes. It is incomplete and I suppose to extend
> > and change certain things in the foreseeab
2016-07-14 17:15, Yong Wang:
> - void *second_addr = RTE_PTR_ADD(bar_addr,
> memreg[1].offset);
> + void *second_addr = RTE_PTR_ADD(bar_addr,
> +
> memreg[1].offset - reg.offset);
> > Some tests can fail to run because they are not compiled.
> > It has been more visible recently when the PCI test became disabled
> > in the default configuration because of dependency on libarchive:
> > PCI autotest:Fail [Not found]
> >
> > The autotest script catch them and do not cou
> > When using "make -C app/test" (with RTE_SDK/RTE_TARGET adjusted) without
> > specifying the rule (all), the build is not done.
> > Indeed the default rule is not "all" anymore since there are some rules
> > added for
> > external resources link.
> >
> > It is fixed by adding a reference to "a
2016-07-13 09:42, Thomas Monjalon:
> The -l options specifying libraries to link with are in LDLIBS.
> But it can happen to have some libraries in other variables.
> In case of a low level dependency specified in some environments
> via EXTRA_LDFLAGS, there can be an unresolved issue due to a
> wro
2016-07-12 17:55, Thomas Monjalon:
> The option CONFIG_RTE_LIBRTE_VHOST_NUMA depends on availability of
> libnuma in the system.
> The configuration option DPDK_DEP_NUMA can be set if available for
> the DPDK_TARGET being built.
>
> Fixes: cd31ca579c0d ("scripts: add build tests")
>
> Signed-off-
2016-07-12 17:56, Thomas Monjalon:
> The config option CONFIG_RTE_PCI_CONFIG does not exist anymore.
>
> Fixes: 7d619406f31d ("pci: remove deprecated specific config")
>
> Signed-off-by: Thomas Monjalon
Applied
2016-07-15 15:55, Thomas Monjalon:
> The script test-build.sh can be used to test building several
> targets with different configurations. The directory name reflects
> the target and the customized configuration.
> When there is a failure, it is convenient to print this build
> directory to quick
> > This commit addresses the following warning reported by clang, which
> > happens by default, as long as CONFIG_RTE_LIBRTE_MEMPOOL_DEBUG is disabled:
> >
> > warning: empty struct has size 0 in C, size 1 in C++
> >
> > C and C++ must use the same size for objects to avoid corruption during run
2016-07-15 16:37, Thomas Monjalon:
> I will apply it with trivial changes suggested by Jan and
> the small needed changes that I describe below:
>
> 2016-07-14 20:03, Jan Viktorin:
> > On Thu, 14 Jul 2016 15:27:29 +0200
> > damarion at cisco.com wrote:
> > > --- /dev/null
> > > +++ b/lib/librte_ea
On Fri, Jul 15, 2016 at 09:23:26AM +, Chandran, Sugesh wrote:
> Thank you Adrien,
> Please find below for some more comments/inputs
>
> Let me know your thoughts on this.
Thanks, stripping again non relevant parts.
[...]
> > > > > [Sugesh] Is it a limitation to use only 32 bit ID? Is it poss
On Tue, Jul 12, 2016 at 09:38:06AM -0400, Chas Williams wrote:
> ELINK_INCLUDE_EMUL and ELINK_INCLUDE_FPGA are never defined. Remove them
> along with enumeration constants dependent on their inclusion.
>
> Fixes: 540a211084a7 ("bnx2x: driver core")
>
> Signed-off-by: Chas Williams <3chas3 at gm
You see that no body cares it :)
So I will make a patch to mark vhost-cuse as deprecated shortly.
Thomas, works to you?
--yliu
On Mon, Jul 11, 2016 at 11:59:55AM +0800, Yuanhan Liu wrote:
> It's something echoed around in my mind for a long while, and here I'm
> gonna make it public: a p
Since we are now heading to RC3 for 16.07 and there are quite a number of
open comments on this patch unresolved, it's going to be deferred till
16.11, when it can have more review and discussion.
/Bruce
On Thu, Jul 07, 2016 at 12:24:43PM +, Ananyev, Konstantin wrote:
>
>
> > -Original
On Fri, Jul 15, 2016 at 10:23:12AM +0300, Ilya Maximets wrote:
> On 15.07.2016 09:17, Yuanhan Liu wrote:
> > On Thu, Jul 14, 2016 at 11:18:39AM +0300, Ilya Maximets wrote:
> >> In current implementation vhost will crash with segmentation fault
> >> if malicious or buggy virtio application breaks ad
> From: Chas Williams [mailto:3chas3 at gmail.com]
> Sent: Friday, July 15, 2016 3:35 AM
>
> On Thu, 2016-07-14 at 10:03 -0700, Rasesh Mody wrote:
> > Disable fastpath interrupts and remove unneeded delay in
> > bnx2x_interrupt_action(). This patch fixes and prevents performance
> > degradation fo
I will apply it with trivial changes suggested by Jan and
the small needed changes that I describe below:
2016-07-14 20:03, Jan Viktorin:
> On Thu, 14 Jul 2016 15:27:29 +0200
> damarion at cisco.com wrote:
> > --- /dev/null
> > +++ b/lib/librte_eal/common/arch/x86/rte_spinlock.c
[...]
> > +uint8_t
2016-07-15 16:23, David Marchand:
> On Wed, Jul 13, 2016 at 11:24 PM, Thomas Monjalon
> wrote:
> > Some tests can fail to run because they are not compiled.
> > It has been more visible recently when the PCI test became disabled
> > in the default configuration because of dependency on libarchive:
On Wed, Jul 13, 2016 at 11:24 PM, Thomas Monjalon
wrote:
> Some tests can fail to run because they are not compiled.
> It has been more visible recently when the PCI test became disabled
> in the default configuration because of dependency on libarchive:
> PCI autotest:Fail [Not found]
>
>
On Thursday 14 July 2016 09:27 PM, Jan Viktorin wrote:
> On Thu, 14 Jul 2016 10:57:55 +0530
> Shreyansh jain wrote:
>
>> Hi Jan,
>>
>> On Wednesday 13 July 2016 11:04 PM, Jan Viktorin wrote:
>>> On Wed, 13 Jul 2016 11:20:43 +0200
>>> Jan Viktorin wrote:
>>>
Hello Shreyansh,
On
On Thursday 14 July 2016 10:21 PM, Jan Viktorin wrote:
> On Tue, 12 Jul 2016 11:31:21 +0530
> Shreyansh Jain wrote:
>
>> Remove bus logic from ethdev hotplug by using eal for this.
>>
>> Current api is preserved:
>> - the last port that has been created is tracked to return it to the
>> applica
The script test-build.sh can be used to test building several
targets with different configurations. The directory name reflects
the target and the customized configuration.
When there is a failure, it is convenient to print this build
directory to quickly know which case is failing without scrolli
On Thursday 14 July 2016 10:20 PM, Jan Viktorin wrote:
> On Tue, 12 Jul 2016 11:31:20 +0530
> Shreyansh Jain wrote:
>
>> Hotplug which deals with resources should come from the layer that already
>> handles them, i.e. EAL.
>>
>> For both attach and detach operations, 'name' is used to select the
2016-07-08 21:09, Jan Viktorin:
> Hello,
>
> based on the discussions with Shreyansh, I propose a patchset with
> the important EAL changes. It is incomplete and I suppose to extend
> and change certain things in the foreseeable future.
>
> Important notes:
>
> * pmd_type is removed
> * introduc
On Thursday 14 July 2016 10:31 PM, Jan Viktorin wrote:
> On Tue, 12 Jul 2016 11:31:18 +0530
> Shreyansh Jain wrote:
>
>> This helper updates a pci device object with latest information it can
>> find.
>> It will be used mainly for hotplug code.
>>
>> Signed-off-by: David Marchand
>> Signed-off-b
On Thursday 14 July 2016 10:25 PM, Jan Viktorin wrote:
> On Tue, 12 Jul 2016 11:31:17 +0530
> Shreyansh Jain wrote:
>
>> eal is a better place than crypto / ethdev for naming resources.
>
> s/for naming/to name/
OK.
>
> What is meant by "resources" here?
This has historic context (from earli
Hi guys,
2016-07-15 16:18, Shreyansh jain:
> On Thursday 14 July 2016 09:27 PM, Jan Viktorin wrote:
> > Please. The time is almost gone. 18/7/2016 is the release (according
> > to the roadmap)... I have to fix it in my patchset, otherwise it
> > does not build (after moving the .name from rte_pci_
On Fri, 2016-07-15 at 16:56 +0100, Bruce Richardson wrote:
> On Tue, Jul 12, 2016 at 09:38:06AM -0400, Chas Williams wrote:
> > ELINK_INCLUDE_EMUL and ELINK_INCLUDE_FPGA are never defined.??Remove them
> > along with enumeration constants dependent on their inclusion.
> >?
> > Fixes: 540a211084a7 (
On Thu, Jul 14, 2016 at 11:18:39AM +0300, Ilya Maximets wrote:
> In current implementation vhost will crash with segmentation fault
> if malicious or buggy virtio application breaks addresses of descriptors.
>
> Before commit 0823c1cb0a73 this crash was reproducible even with
> normal DPDK applica
In current implementation vhost will crash with segmentation fault
if malicious or buggy virtio application breaks addresses of descriptors.
Before commit 0823c1cb0a73 ("vhost: workaround stale vring base")
this crash was reproducible even with normal DPDK application that tries
to change number o
Return value on error changed from '-1' to '0' because it returns
unsigned value and it means number of used descriptors.
Also fixed updating of 'last_used_idx' by using actual number of
used descriptors.
Fixes: 623bc47054d0 ("vhost: do sanity check for ring descriptor length")
Signed-off-by: Il
Version 3:
* Patch splitted in two.
* Applied workaround from Rich Lane and added comment about
performance issue with some compilers and 'unlikely' macro.
Version 2:
* Rebased on top of current master.
* host's address now checked in meargeable case,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Raja Jayapal
> Sent: Friday, July 15, 2016 6:55 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] capture packets on VM
>
> Hi All,
>
> I have installed dpdk on VM and would like to know how to capture the packe
On Fri, 15 Jul 2016 11:56:38 +0200
Thomas Monjalon wrote:
> 2016-07-15 15:09, Shreyansh jain:
> > On Thursday 14 July 2016 10:25 PM, Jan Viktorin wrote:
> > > What is meant by "resources" here?
> >
> > This has historic context (from earlier version of this patch).
> > But I could relate th
On Fri, 15 Jul 2016 16:06:25 +0530
Shreyansh jain wrote:
> On Thursday 14 July 2016 10:21 PM, Jan Viktorin wrote:
> > On Tue, 12 Jul 2016 11:31:21 +0530
> > Shreyansh Jain wrote:
> >
> >> Remove bus logic from ethdev hotplug by using eal for this.
> >>
> >> Current api is preserved:
> >> - th
Hello Yu Liu,
I've sent second version of patch to test on icc16 compiler, Yongjie is
helping me to test issues on icc.
Jan
> The offset of the 2nd mmap() when mapping the region after msix_bar
> needs to take region address into consideration as mmap() takes address
> that is resource-relative instead of bar-relative. This is exposed when
> binding vmxnet3 to vfio-pci.
>
> Fixes: 90a1633b2347 ("eal/linux: allow to ma
it is fixed in 16.07-rc2 that I checked
Vincent
On Fri, Jul 15, 2016 at 11:48 AM, Harish Patil
wrote:
> Hi Huawie/Yuanhan,
> I encounter segfault issue in virtio PMD driver when I run any DPDK
> application in the VM. The virtio devices should not have been probed in
> the first place since the
The enic PMD code has diverged from code that was once
shared with the enic kernel mode driver for performance
reasons. It is confusing and misleading to print the
internal version number. Remove it.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: John Daley
---
drivers/net/enic/enic.h
>
> Consumer queue dequeuing must be guaranteed to be done fully before the tail
> is updated. This is not guaranteed with a read barrier,
> changed to a write barrier just before tail update which in practice
> guarantees correct order of reads and writes.
>
> Signed-off-by: Juhamatti Kuusisaa
2016-07-15 09:54, Damjan Marion:
> So we don?t have much pending beside 2 patches for i40e which
> Jeff submitted yesterday and they will i guess need to wait for 16.11.
Yes these i40e patches will probably have to wait 16.11.
> Only one which I have on my mind is:
>
> https://git.fd.io/cgit/vp
On Thu, Jul 14, 2016 at 12:56:11PM +, Ananyev, Konstantin wrote:
>
>
> > The CPU also
> > knows already the value that will be written to cons.tail and that value
> > does not depend on the previous read either. The CPU does not
> > know we are planning to do a spinlock there, so it might do
On Fri, 15 Jul 2016 15:09:58 +0530
Shreyansh jain wrote:
> On Thursday 14 July 2016 10:25 PM, Jan Viktorin wrote:
> > On Tue, 12 Jul 2016 11:31:17 +0530
> > Shreyansh Jain wrote:
> >
> >> eal is a better place than crypto / ethdev for naming resources.
> >
> > s/for naming/to name/
>
>
2016-07-15 15:09, Shreyansh jain:
> On Thursday 14 July 2016 10:25 PM, Jan Viktorin wrote:
> > What is meant by "resources" here?
>
> This has historic context (from earlier version of this patch).
> But I could relate the word 'resources' to EAL representation of devices -
> whether PCI or Cryp
Hi John,
> > Subject: [PATCH v3 1/2] doc: live migration of VM with Virtio and VF
> >
> > This patch describes the procedure to be be followed to perform Live
> > Migration of a VM with Virtio and VF PMD's using the bonding PMD.
> >
> > It includes sample host and VM scripts used in the procedur
Hi All,
I have installed dpdk on VM and would like to know how to capture the packets
on dpdk ports.
I am sending traffic from host? and want to know how to confirm whether the
packets are flowing via dpdk ports.
I tried with tcpdump and wireshark but could not capture the packets inside VM.
set
Gowrishankar,
When I tried the patches, I got some compilation error:
In file included from
/root/test/sub/dpdk/lib/librte_acl/acl_run_altivec.c:34:0:
/root/test/sub/dpdk/lib/librte_acl/acl_run_altivec.h: In function
'transition4':
/root/test/sub/dpdk/lib/librte_acl/acl_run_altivec.h:198:2: error
2016-07-15 16:42, Yuanhan Liu:
> You see that no body cares it :)
>
> So I will make a patch to mark vhost-cuse as deprecated shortly.
> Thomas, works to you?
Perfect. Thanks Yuanhan
> On Mon, Jul 11, 2016 at 11:59:55AM +0800, Yuanhan Liu wrote:
> > It's something echoed around in my mind for a
Hi Jan,
Any update on ena related error?
Thanks,
Yu Liu
From: Gu, YongjieX
Sent: Thursday, July 14, 2016 5:23 PM
To: thomas.monjalon at 6wind.com; Richardson, Bruce ; Yigit, Ferruh ; Gonzalez Monroy, Sergio
; Jan Medala ; dev at
dpdk.org
Cc: Cao, Waterman ; Liu, Yu Y ; Chen, WeichunX ; Xu, Hui
> -Original Message-
> From: Iremonger, Bernard
> Sent: Monday, July 11, 2016 4:05 PM
> To: Mcnamara, John ; dev at dpdk.org
> Cc: Liu, Yong ; Xu, Qian Q ;
> yuanhan.liu at linux.intel.com; Iremonger, Bernard
>
> Subject: [PATCH 2/2] doc: add vhost_user live migration image
>
> This patch
> -Original Message-
> From: Iremonger, Bernard
> Sent: Thursday, July 7, 2016 11:43 AM
> To: Mcnamara, John ; dev at dpdk.org
> Cc: Liu, Yong ; Xu, Qian Q ;
> Iremonger, Bernard
> Subject: [PATCH v3 1/2] doc: live migration of VM with Virtio and VF
>
> This patch describes the procedure
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Tuesday, July 12, 2016 11:22 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] mk: fix default rule of test subdirectory
>
> When using "make -C app/test" (with RTE_SDK/RTE_TARGET
Hi Jerin,
> >
> >
> > > The CPU also
> > > knows already the value that will be written to cons.tail and that
> > > value does not depend on the previous read either. The CPU does not know
> > > we are planning to do a spinlock there, so it might do things
> out-of-order without proper dependenci
2016-07-14 22:20, Damjan Marion:
>
> > On 15 Jul 2016, at 00:06, Thomas Monjalon
> > wrote:
> >
> > 2016-07-14 18:10, Damjan Marion:
> >> Dear Jan,
> >>
> >> Thank you for your comments. A bit too much overhead to submit simple patch
> >> so let?s forget about it. I will just add it as it is t
On weak memory order architecture like POWER, rte_smp_wmb/rte_smp_rmb
need to use CPU instructions, not compiler barrier. This patch fixes
this. Also, to improve performance on PPC64, use light weight sync
instruction instead of sync instruction.
Signed-off-by: Chao Zhu
---
.../common/include/ar
On 15.07.2016 09:17, Yuanhan Liu wrote:
> On Thu, Jul 14, 2016 at 11:18:39AM +0300, Ilya Maximets wrote:
>> In current implementation vhost will crash with segmentation fault
>> if malicious or buggy virtio application breaks addresses of descriptors.
>>
>> Before commit 0823c1cb0a73 this crash was
Inside flush_fwd_rx_queues removed redundant prev_tsc update with cur_tsc,
as prev_tsc value is always updated with rte_rdtsc() in for loop.
Coverity issue: 127797
Fixes: f487715f36f5 ("app/testpmd: add timeout in Rx queue flushing")
Signed-off-by: Reshma Pattan
---
app/test-pmd/testpmd.c | 1
2016-07-14 22:45, Wiles, Keith:
> > On Jul 14, 2016, at 2:59 PM, Thomas Monjalon
> > wrote:
> >
> > Thanks Keith for continuing work.
> >
> > 2016-07-14 14:31, Keith Wiles:
> >> lib/librte_eal/bsdapp/eal/Makefile | 1 +
> >> lib/librte_eal/common/arch/arm/rte_spinlock.c | 4
Hi Sugesh,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Chandran, Sugesh
> Sent: Friday, July 15, 2016 10:23 AM
> To: 'Adrien Mazarguil'
> > > > To PMD maintainers: please comment if you know devices that
> > > > support tagging matching packets with m
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Reshma Pattan
> Sent: Thursday, July 14, 2016 4:49 PM
> To: dev at dpdk.org
> Cc: Pattan, Reshma
> Subject: [dpdk-dev] [PATCH] examples/distributor: fix Rx thread logic for zero
> packets
>
> From: Reshma Patt
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Reshma Pattan
> Sent: Friday, July 15, 2016 10:19 AM
> To: dev at dpdk.org
> Cc: Pattan, Reshma
> Subject: [dpdk-dev] [PATCH] app/testpmd: fix redundant time update
>
> Inside flush_fwd_rx_queues removed redun
> On 15 Jul 2016, at 10:31, Thomas Monjalon
> wrote:
>
> 2016-07-14 22:20, Damjan Marion:
>>
>>> On 15 Jul 2016, at 00:06, Thomas Monjalon
>>> wrote:
>>>
>>> 2016-07-14 18:10, Damjan Marion:
Dear Jan,
Thank you for your comments. A bit too much overhead to submit simple patc
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Shreyansh Jain
> Sent: Tuesday, July 12, 2016 10:45 AM
> To: olivier.matz at 6wind.com
> Cc: dev at dpdk.org; thomas.monjalon at 6wind.com
> Subject: [dpdk-dev] [PATCH] doc: fix consumer/producer mixup in Ring li
On Thu, Jul 14, 2016 at 06:31:11PM +0200, viktorin at rehivetech.com wrote:
> On Tue, 12 Jul 2016 11:30:25 +0200
> Maxime Coquelin wrote:
>
> > The error is reported using test build script:
>
> I recommend to note that the error is reported only by GCC 6+.
Agreed!
--yliu
>
> >
> > $
Thank you Adrien,
Please find below for some more comments/inputs
Let me know your thoughts on this.
Regards
_Sugesh
> -Original Message-
> From: Adrien Mazarguil [mailto:adrien.mazarguil at 6wind.com]
> Sent: Wednesday, July 13, 2016 9:03 PM
> To: Chandran, Sugesh
> Cc: dev at dpdk.o
Hey Raja,
When you bind the ports to the DPDK poll mode drivers, the kernel no longer
has visibility into them. This makes some sense intuitively - it would be
very bad for both the kernel and a user mode application to both attempt to
control the ports. This is why tools like tcpdump and wiresh
Consumer queue dequeuing must be guaranteed to be done fully before
the tail is updated. This is not guaranteed with a read barrier,
changed to a write barrier just before tail update which in practice
guarantees correct order of reads and writes.
Signed-off-by: Juhamatti Kuusisaari
---
lib/libr
On Thu, 2016-07-14 at 10:03 -0700, Rasesh Mody wrote:
> Disable fastpath interrupts and remove unneeded delay in
> bnx2x_interrupt_action(). This patch fixes and prevents performance
> degradation for BNX2X PMD.
>
> Fixes: 540a2110 ("bnx2x: driver core")
>
> Signed-off-by: Rasesh Mody
>?
> diff
Hi Konstantin,
> Hi Juhamatti,
>
> >
> > Hi Konstantin,
> >
> > > > > > > It is quite safe to move the barrier before DEQUEUE because
> > > > > > > after the DEQUEUE there is nothing really that we would want
> > > > > > > to protect
> > > with a
> > > > > read barrier.
> > > > > >
> > > > > > I
2016-07-14 18:10, Damjan Marion:
> Dear Jan,
>
> Thank you for your comments. A bit too much overhead to submit simple patch
> so let?s forget about it. I will just add it as it is to our private
> collection of patches.
These are changes trivial to fix when applying.
I strongly prefer that you u
96 matches
Mail list logo
