[dpdk-dev] [PATCH] igb_uio: fix missing include of slab.h

The missing header prevents to build with linux v3.18. Signed-off-by: Jan Viktorin --- lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c index ba1364b..865a276

[dpdk-dev] [PATCH] rte_ethdev.h: fix make sure that all functions has C linkage type.

> Move #ifdef __cplusplus to the end of the file. > > Signed-off-by: Konstantin Ananyev Fixes: 64b7acd861b1 ("ethdev: add multicast address filtering") Applied, thanks

[dpdk-dev] Register for Userspace 2015

Hi all Just a gentle reminder to register your attendance for DPDK Userspace 2015 at https://dpdksummit.com/us/en/userspace2015 as places are filling up and are strictly limited :) Thanks Siobhan

[dpdk-dev] ixgbe vPMD RX functions and buffer number minimum requirement

Hi Zoltan, > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zoltan Kiss > Sent: Friday, July 24, 2015 4:00 PM > To: Richardson, Bruce; dev at dpdk.org > Subject: [dpdk-dev] ixgbe vPMD RX functions and buffer number minimum > requirement > > Hi, > > I was

[dpdk-dev] [PATCH] rte_ethdev.h: fix make sure that all functions has C linkage type.

Move #ifdef __cplusplus to the end of the file. Signed-off-by: Konstantin Ananyev --- lib/librte_ether/rte_ethdev.h | 9 + 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h index c901a2c..9b50858 100644 ---

[dpdk-dev] ixgbe vPMD RX functions and buffer number minimum requirement

Hi, I was thinking how to handle the situation when you call rte_eth_rx_burst with less than RTE_IXGBE_VPMD_RX_BURST buffers. In ODP-DPDK unfortunately we can't force this requirement onto the calling application. One idea I had to check in ixgbe_recv_pkts_vec() if nb_pkts <

[dpdk-dev] [PATCHv2 4/5] ixgbe: rename tx queue release function for consistency

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Konstantin Ananyev > Sent: Friday, July 24, 2015 6:58 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCHv2 4/5] ixgbe: rename tx queue release function for > consistency > > The function inside the

[dpdk-dev] [PATCHv2 1/5] Revert "ixgbe: check mbuf refcnt when clearing a ring"

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Konstantin Ananyev > Sent: Friday, July 24, 2015 6:58 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCHv2 1/5] Revert "ixgbe: check mbuf refcnt when > clearing a ring" > > This reverts commit

[dpdk-dev] [PATCH] mbuf: fix tunnel flags check

I just noticed a few minor typos in comments: diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 917dd59..6352c32 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -680,14 +680,14 @@ extern "C" { /** * Check if the (outer) L3 header is IPv4. To

[dpdk-dev] Packets reorder in the second pass on mempool

Hi I'm new to dpdk and I hope you can solve my weird problem. I see packet reordering correlated with the batchsize and mempool size. I have a very simple setting of a sender and a receiver connected with a simple 10G switch. The sender sends udp packets at 14.88MPPS and just puts a 32bit

[dpdk-dev] [PATCHv2 5/5] ixgbe: remove awkward typecasts from ixgbe SSE PMD

The vector/SSE pmd used a different element type for the tx queue sw_ring entries. This led to lots of typecasts in the code which required specific use of bracketing, leading to subtle errors. For example, in the original code: txe = (struct ixgbe_tx_entry_v *)>sw_ring[i]; instead needs

[dpdk-dev] [PATCHv2 4/5] ixgbe: rename tx queue release function for consistency

The function inside the vector/SSE poll-mode driver for releasing the mbufs on the TX queues had the same name as another function inside the regular PMD. To keep consistency and avoid confusion, rename the vector PMD version to have a "_vec" suffix. Signed-off-by: Bruce Richardson

[dpdk-dev] [PATCHv2 3/5] ixgbe: fix bug on release of mbufs from queue

The calculations of what mbufs were valid in the RX and TX queues were incorrect when freeing the mbufs for the vector PMD. This led to crashes due to invalid reference counts when mbuf debugging was turned on, and possibly other more subtle problems (such as mbufs being freed when in use) in

[dpdk-dev] [PATCHv2 2/5] ixgbe: fix comments on rx_queue fields

The two fields for vector RX rearming in the rx queue structure were incorrectly labelled. Switching the comments on each around makes things clearer. Signed-off-by: Bruce Richardson Signed-off-by: Konstantin Ananyev --- drivers/net/ixgbe/ixgbe_rxtx.h | 4 ++-- 1 file changed, 2 insertions(+),

[dpdk-dev] [PATCHv2 1/5] Revert "ixgbe: check mbuf refcnt when clearing a ring"

This reverts commit b35d0d80f0a809939549ddde99c1a76b7e38bff3. The bug fix was incorrect as it did not take account of the fact that the mbufs that were previously freed may have since be re-allocated. Signed-off-by: Bruce Richardson Signed-off-by: Konstantin Ananyev ---

[dpdk-dev] [PATCHv2 0/5] ixgbe: fix mbuf release on RX and TX

Konstantin has correctly pointed out that the previously applied fix: b35d0d80f0a8 ("ixgbe: check mbuf refcnt when clearing a ring") is not a proper fix for the reported issue at all. Ref: http://permalink.gmane.org/gmane.comp.networking.dpdk.devel/21932 This patch set reverts the original fix,

[dpdk-dev] [RFC] l2fwd: trying to expose eth_igb_xmit_pkts unusual behavior

Hi, On 24/07/15 11:13, Ciprian Barbu wrote: > From: Ciprian Barbu > > This tries to show an approximate behavior described in an earlier discussion > called "can eth_igb_xmit_pkts called with len 0 affect transmission?" > > I'm using Intel i350 dual port 1Gb card and I've tweaked the pool size

[dpdk-dev] can eth_igb_xmit_pkts called with len 0 affect transmission?

Hi Lu, Thank you for getting back to me. On 24.07.2015 05:49, Lu, Wenzhuo wrote: > Hi Ciprian, > >> -Original Message- >> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of ciprian.barbu >> Sent: Thursday, July 23, 2015 11:20 PM >> To: dev at dpdk.org >> Subject: Re: [dpdk-dev] can

[dpdk-dev] [RFC] l2fwd: trying to expose eth_igb_xmit_pkts unusual behavior

From: Ciprian Barbu This tries to show an approximate behavior described in an earlier discussion called "can eth_igb_xmit_pkts called with len 0 affect transmission?" I'm using Intel i350 dual port 1Gb card and I've tweaked the pool size to the minimum possible. But

[dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX queue information

2015-07-24 09:15, Ananyev, Konstantin: > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > 2015-07-22 19:28, Konstantin Ananyev: > > > +struct rte_eth_rxq_info { > > > + struct rte_mempool *mp; /**< mempool used by that queue. */ > > > + struct rte_eth_rxconf conf; /**< queue

[dpdk-dev] [PATCH] ixgbe: remove RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC option

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Pablo de Lara > Sent: Thursday, July 23, 2015 3:30 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH] ixgbe: remove > RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC option > > RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC

[dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX queue information

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Friday, July 24, 2015 10:24 AM > To: Ananyev, Konstantin > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX > queue information > > 2015-07-24

[dpdk-dev] Fwd: distributed tests of a patch

Hi, With the help of Thomas Herbert and Stephen Finucane, we started a discussion to have a distributed continuous integration system in patchwork: http://thread.gmane.org/gmane.comp.version-control.patchwork/1242 The goal is to allow many contributors to run their own tests when a patch is

[dpdk-dev] [PATCH 11/11] bond: remove useless cast

Found by coccinelle script. drivers/net/bonding/rte_eth_bond_pmd.c:1587:34-54: WARNING: casting value returned by memory allocation function to (struct bond_rx_queue *) is useless. drivers/net/bonding/rte_eth_bond_pmd.c:1611:35-55: WARNING: casting value returned by memory allocation function to

[dpdk-dev] [PATCH 10/11] i40e: remove useless cast

drivers/net/i40e/i40e_ethdev.c:2360:18-56: WARNING: casting value returned by memory allocation function to (struct i40e_aqc_get_switch_config_resp *) is useless. Signed-off-by: Stephen Hemminger --- drivers/net/i40e/i40e_ethdev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff

[dpdk-dev] [PATCH 09/11] kni: remove useless cast

lib/librte_kni/rte_kni.c:224:27-54: WARNING: casting value returned by memory allocation function to (struct rte_kni_memzone_slot *) is useless. Signed-off-by: Stephen Hemminger --- lib/librte_kni/rte_kni.c | 7 ++- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git

[dpdk-dev] [PATCH 08/11] hash: remove useless casts

Found by coccinelle. lib/librte_hash/rte_fbk_hash.c:153:7-32: WARNING: casting value returned by memory allocation function to (struct rte_fbk_hash_table *) is useless. lib/librte_hash/rte_cuckoo_hash.c:218:6-21: WARNING: casting value returned by memory allocation function to (struct rte_hash

[dpdk-dev] [PATCH 07/11] lpm: remove useless casts

Found by modified coccinelle script. lib/librte_lpm/rte_lpm6.c:196:8-23: WARNING: casting value returned by memory allocation function to (struct rte_lpm6 *) is useless. lib/librte_lpm/rte_lpm6.c:205:19-39: WARNING: casting value returned by memory allocation function to (struct rte_lpm6_rule *)

[dpdk-dev] [PATCH 06/11] pipeline: remove useless cast

Found by modified version of acll_cast.cocci lib/librte_pipeline/rte_pipeline.c:358:18-49: WARNING: casting value returned by memory allocation function to (struct rte_pipeline_table_entry *) is useless. Signed-off-by: Stephen Hemminger --- lib/librte_pipeline/rte_pipeline.c | 4 ++-- 1 file

[dpdk-dev] [PATCH 05/11] kni: eliminate unnecessary return variables

If function just sets a variable (and never changes it) and then returns that value, just move the constant to return. Found with returnvar.cocci Signed-off-by: Stephen Hemminger --- lib/librte_eal/linuxapp/kni/ethtool/igb/e1000_82575.c | 16 +---

[dpdk-dev] [PATCH 04/11] eth: remove unnecessary return value

Eliminate unnecessary variable for return value Found with returnvar.cocci Signed-off-by: Stephen Hemminger --- lib/librte_ether/rte_ethdev.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c index

[dpdk-dev] [PATCH 03/11] kni: remove useless semicolon

Found by coccinelle semicolon.cocci script Signed-off-by: Stephen Hemminger --- lib/librte_eal/linuxapp/kni/ethtool/ixgbe/ixgbe_common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/librte_eal/linuxapp/kni/ethtool/ixgbe/ixgbe_common.c

[dpdk-dev] [PATCH 02/11] eth: do simple return

Found by coccinelle simple_return.cocci This function can just use direct return. Signed-off-by: Stephen Hemminger --- lib/librte_ether/rte_ethdev.c | 7 +-- 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c index

[dpdk-dev] [PATCH 01/11] eth: move queue check for rx_queue_count

All implemenations of rx_queue_count need to check for queue_id being valid, therefore move the test to common code. Also, add missing queue validation for rx_descriptor_done Signed-off-by: Stephen Hemminger --- drivers/net/e1000/em_rxtx.c| 5 - drivers/net/e1000/igb_rxtx.c | 5

[dpdk-dev] [PATCH 00/11] misc cleanup patches

These are all low risk, low reward changes found by reviewing while doing other work. Ok to defer them to 2.2 if necessary. Stephen Hemminger (11): eth: move queue check for rx_queue_count eth: do simple return kni: remove useless semicolon eth: remove unnecessary return value kni:

[dpdk-dev] [PATCH] The VMXNET3 PMD can't receive packet suddenly after a lot of traffic coming in

Hi Marco, It seems it is a new version of the patch. Please, in order to ease patch management and review, could you add: - a version number - a changelog - threading with previous patches It can be done with: - subject-prefix option - annotate option

[dpdk-dev] iommu Error on DL380 G8 with RHEL 7.1

Hi Monroy, Thanks for the reply :) Ok Will check with Lee. -Original Message- From: Gonzalez Monroy, Sergio [mailto:sergio.gonzalez.mon...@intel.com] Sent: Friday, July 24, 2015 2:47 PM To: Rapelly, Varun Cc: dev at dpdk.org Subject: Re: [dpdk-dev] iommu Error on DL380 G8 with RHEL 7.1

[dpdk-dev] iommu Error on DL380 G8 with RHEL 7.1

attachment was scrubbed... Name: iommu_Gen8_version.png Type: image/png Size: 114600 bytes Desc: iommu_Gen8_version.png URL: <http://dpdk.org/ml/archives/dev/attachments/20150724/62a027af/attachment-0001.png>

[dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX queue information

> -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Thursday, July 23, 2015 5:26 PM > To: Ananyev, Konstantin > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX > queue information > > 2015-07-22

[dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX queue information

Hi Thomas, > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Thursday, July 23, 2015 5:17 PM > To: Ananyev, Konstantin > Cc: dev at dpdk.org; Stephen Hemminger > Subject: Re: [dpdk-dev] [PATCHv4 1/5] ethdev: add new API to retrieve RX/TX > queue

[dpdk-dev] iommu Error on DL380 G8 with RHEL 7.1

Hi All, I'm not able to send packets through OVS bridge [with dpdk] when iommu is enabled on HP DL380 G8 [RHEL 7.1]. Getting following errors in dmesg. [0.657681] IOMMU: Setting identity map for device :01:00.2 [0xbdff6000 - 0xbdffcfff] [0.657686] IOMMU: Prepare 0-16MiB unity

[dpdk-dev] [PATCH] The VMXNET3 PMD can't receive packet suddenly after a lot of traffic coming in

The RX of VMXNET3 PMD will have deadlock when a lot of traffic coming in. The root cause is due to mbuf allocation fail in vmxnet3_post_rx_bufs() and there is no error handling when it is called from vmxnet3_recv_pkts(). The RXD will not have "free" mbuf for it but the counter still increment.

[dpdk-dev] can eth_igb_xmit_pkts called with len 0 affect transmission?

Hi Ciprian, > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of ciprian.barbu > Sent: Thursday, July 23, 2015 11:20 PM > To: dev at dpdk.org > Subject: Re: [dpdk-dev] can eth_igb_xmit_pkts called with len 0 affect > transmission? > > Anyone? > > On 17.07.2015

[dpdk-dev] [PATCH] examples/l3fwd: increase lookup burst size to 8

> -Original Message- > From: Xu, Qian Q > Sent: Friday, July 24, 2015 2:09 AM > To: De Lara Guarch, Pablo; Qiu, Michael; dev at dpdk.org > Subject: RE: [dpdk-dev] [PATCH] examples/l3fwd: increase lookup burst size > to 8 > > And this patch will be only related to exact match, the common

[dpdk-dev] [PATCH] examples/l3fwd: increase lookup burst size to 8

And this patch will be only related to exact match, the common usage of lpm is not impacted. Thanks Qian -Original Message- From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch, Pablo Sent: Friday, July 24, 2015 8:29 AM To: Qiu, Michael; dev at dpdk.org Subject: Re:

[dpdk-dev] [PATCH] examples/l3fwd: increase lookup burst size to 8

Hi Michael, > -Original Message- > From: Qiu, Michael > Sent: Thursday, July 23, 2015 6:26 PM > To: De Lara Guarch, Pablo; dev at dpdk.org > Subject: RE: [dpdk-dev] [PATCH] examples/l3fwd: increase lookup burst size > to 8 > > Hi, Pablo > > Is there any performance data for this change?