[dpdk-dev] [PATCH 0/4] lib/librte_table: Fix bugs occuring in corner cases

I take the opportunity of this patchset to talk about commit formatting. 2014-09-11 19:47, Balazs Nemeth: > This e-mail and any attachments may contain confidential material for the > sole use of the intended recipient(s). Any review or distribution by others > is strictly prohibited. If you

[dpdk-dev] Safe practices for adding to rte_table_hash_lru

Hey guys Is it safe to add an entry to the rte_table_hash while the pipeline is being run - for instance if I were to try and add an entry on a port reader action when the packet enters the pipeline? Thanks Avik

[dpdk-dev] [PATCH] igb_ethdev.c: complete switches for i211 NC

2014-09-10 01:28, Zhang, Helin: > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Sergey Mironov > > Hi! I have got an update for my "i212 problem". First of all, I found that > > I have > > made a mistake. My controller is named i211, not i212 :) Next, i211 > > controller is > >

[dpdk-dev] rte_malloc_socket UNABLE to allocate 8GB.

Dear list, I'm experiencing problems allocating big chunks of memory with rte_malloc_socket. Basically, it successfully allocates 6GB but returns NULL when I try to allocate 8GB. I tried dpdk-1.5.1 and 1.7.1 and got similar behavior. First machine I was trying this on had 29*1GB hugepages on

[dpdk-dev] [PATCH] examples/vmdq: support i40e in vmdq example

This patch supports i40e in vmdq example. 1. queue index is added by vmdq queue base in rte_eth_rx_burst. 2. pool index is added by vmdq pool base when mac address is added to pools. 3. add some error message print Besides, due to some limitation in PMD, 1. mac addresses are needed to be

[dpdk-dev] [PATCH] examples/vmdq: support i40e in vmdq example

With i40e, the queue index of VMDQ pools doesn't always start from zero, and the queues aren't all occupied by VMDQ. These information are retrieved through rte_eth_dev_info_get, and used to initialise VMDQ. Huawei Xie (1): support i40e in vmdq example examples/vmdq/main.c | 162

[dpdk-dev] [PATCH v2 10/10] VM Power Management Unit Tests

Updated the unit tests to cover both librte_power implementations as well as the external API. Signed-off-by: Alan Carew --- app/test/Makefile | 3 +- app/test/autotest_data.py | 26 ++ app/test/test_power.c | 445 +++---

[dpdk-dev] [PATCH v2 09/10] Build system integration for VM Power Management(Guest and Host)

librte_power now contains both rte_power_acpi_cpufreq and rte_power_kvm_vm implementations. Signed-off-by: Alan Carew --- lib/librte_power/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/librte_power/Makefile b/lib/librte_power/Makefile index 6185812..d672a5a

[dpdk-dev] [PATCH v2 08/10] Packet format for VM Power Management(Host and Guest).

Provides a command packet format for host and guest. Signed-off-by: Alan Carew --- lib/librte_power/channel_commands.h | 68 + 1 file changed, 68 insertions(+) create mode 100644 lib/librte_power/channel_commands.h diff --git

[dpdk-dev] [PATCH v2 07/10] librte_power common interface for Guest and Host

Moved the current librte_power implementation to rte_power_acpi_cpufreq, with renaming of functions only. Added rte_power_kvm_vm implmentation to support Power Management from a VM. librte_power now hides the implementation based on the environment used. A new call rte_power_set_env() can

[dpdk-dev] [PATCH v2 06/10] VM communication channels for VM Power Management(Guest).

Allows for the opening of Virtio-Serial devices on a VM, where a DPDK application can send packets to the host based monitor. The packet formatted is specified in channel_commands.h Each device appears as a serial device in path /dev/virtio-ports/virtio.serial.port.. where each lcore in a DPDK

[dpdk-dev] [PATCH v2 05/10] VM Power Management CLI(Guest).

Provides a small sample application(guest_vm_power_mgr) to run on a VM. The application is run by providing a core mask(-c) and number of memory channels(-n). The core mask corresponds to the number of lcore channels to attempt to open. A maximum of 64 channels per VM is allowed. The channels must

[dpdk-dev] [PATCH v2 04/10] VM Power Management application and Makefile.

For launching CLI thread and Monitor thread and initialising resources. Requires a minimum of two lcores to run, additional cores specified by eal core mask are not used. Signed-off-by: Alan Carew --- examples/vm_power_manager/Makefile | 57 +++ examples/vm_power_manager/main.c

[dpdk-dev] [PATCH v2 03/10] CPU Frequency Power Management(Host).

A wrapper around librte_power(using ACPI cpufreq), providing locking around the non-threadsafe library, allowing for frequency changes based on core masks and core numbers from both the CLI thread and epoll monitor thread. Signed-off-by: Alan Carew --- examples/vm_power_manager/power_manager.c

[dpdk-dev] [PATCH v2 02/10] VM Power Management CLI(Host).

The CLI is used for administrating the channel monitor and manager and manually setting the CPU frequency on the host. Supports the following commands: add_vm [Mul-choice STRING]: add_vm|rm_vm , add a VM for subsequent operations with the CLI or remove a previously added VM from the VM Power

[dpdk-dev] [PATCH v2 01/10] Channel Manager and Monitor for VM Power Management(Host).

The manager is responsible for adding communications channels to the Monitor thread, tracking and reporting VM state and employs the libvirt API for synchronization with the KVM Hypervisor. The manager interacts with the Hypervisor to discover the mapping of virtual CPUS(vCPUs) to the host

[dpdk-dev] [PATCH v2 00/10] VM Power Management

Virtual Machine Power Management. The following patches add two DPDK sample applications and an alternate implementation of librte_power for use in virtualized environments. The idea is to provide librte_power functionality from within a VM to address the lack of MSRs to facilitate frequency

[dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost cuse driver library

Hi, 2014-09-24 14:32, Ouyang, Changchun: > This v4 patch remove the jumbo frame related codes > and Huawei will add it back in a separate patch, I'd prefer a v5 which includes these changes. I know this patchset is pending and reworked many times, so I'll try to integrate v5 with top priority.

[dpdk-dev] [memnic PATCH 7/7] pmd: split calling mbuf free

2014-09-11 07:52, Hiroshi Shimamoto: > @@ -408,9 +408,9 @@ retry: > > rte_compiler_barrier(); > p->status = MEMNIC_PKT_ST_FILLED; > - > - rte_pktmbuf_free(tx_pkts[nr]); > } > + for (i = 0; i < nr; i++) > +

[dpdk-dev] [memnic PATCH 4/7] pmd: use compiler barrier

2014-09-11 07:48, Hiroshi Shimamoto: > x86 can keep store ordering with standard operations. Are we sure it's always the case (including old 32-bit CPU)? I would prefer to have a reference here. I know we already discussed this kind of things but having a reference in commit log could help for

[dpdk-dev] [memnic PATCH 3/7] pmd: use helper macros

2014-09-11 07:47, Hiroshi Shimamoto: > Do not touch pktmbuf directly. > > Instead of direct access, use rte_pktmbuf_pkt_len() and rte_pktmbuf_data_len() > to access the property. I guess this change is for compatibility with DPDK 1.8. Does it have an impact on performance? -- Thomas

[dpdk-dev] [memnic PATCH 2/7] pmd: remove needless assignment

2014-09-11 07:47, Hiroshi Shimamoto: > Because these assignment are done in rte_pktmbuf_alloc(), get rid of them. Is it increasing the performances? -- Thomas

[dpdk-dev] [memnic PATCH 1/7] guest: memnic-tester: PMD benchmark in guest

Hi Hiroshi, 2014-09-11 07:46, Hiroshi Shimamoto: > master |<- put packets ->| |<- get packets ->| > slave | |<- rx packets ->|<- tx packets ->| | > |<- set ->| > > Measuring how many sets in the certain period, that represents > the MEMNIC PMD

[dpdk-dev] Safe practices for adding to rte_table_hash_lru

On Wed, Sep 24, 2014 at 07:38:49PM +, Saha, Avik (AWS) wrote: > Hey guys >Is it safe to add an entry to the rte_table_hash while the pipeline is > being run - for instance if I were to try and add an entry on a port reader > action when the packet enters the pipeline? > > Thanks > Avik

[dpdk-dev] [memnic PATCH 7/7] pmd: split calling mbuf free

On Sep 24, 2014, at 10:20 AM, Thomas Monjalon wrote: > 2014-09-11 07:52, Hiroshi Shimamoto: >> @@ -408,9 +408,9 @@ retry: >> >> rte_compiler_barrier(); >> p->status = MEMNIC_PKT_ST_FILLED; >> - >> -rte_pktmbuf_free(tx_pkts[nr]); >> } >> +for (i =

[dpdk-dev] [PATCH v2] distributor_app: new sample app

From: Reshma Pattan A new sample app that shows the usage of the distributor library. This app works as follows: * An RX thread runs which pulls packets from each ethernet port in turn and passes those packets to worker using a distributor component. * The workers

[dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost cuse driver library

Hi, > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Huawei Xie > Sent: Friday, September 12, 2014 6:55 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost cuse > driver library > > This set of patches transforms

[dpdk-dev] [PATCH v3] virtio: Support mergeable buffer in virtio pmd

Hi Thomas, > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon > Sent: Wednesday, September 24, 2014 5:32 PM > To: Fu, JingguoX > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3] virtio: Support mergeable buffer in virtio > pmd > > Hi

[dpdk-dev] [PATCH 0/4] Add DSO symbol versioning to support backwards compatibility

On Thu, Sep 18, 2014 at 03:14:01PM -0400, Neil Horman wrote: > On Thu, Sep 18, 2014 at 08:23:36PM +0200, Thomas Monjalon wrote: > > Hi Neil, > > > > 2014-09-15 15:23, Neil Horman: > > > The DPDK ABI develops and changes quickly, which makes it difficult for > > > applications to keep up with the

[dpdk-dev] LD_PRELOAD libraries for DPDK to run unmodified applications with DPDK?

On Wed, Sep 24, 2014 at 01:10:32PM -0700, Malveeka Tewari wrote: > > There is already a rump-kernel based TCP/IP stack for DPDK > https://github.com/rumpkernel/dpdk-rumptcpip/. ... > But these solutions are again too heavy weight. Try using this along with

[dpdk-dev] [PATCH v3 4/5] bond: lsc polling support

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Declan Doherty > Sent: Tuesday, September 23, 2014 2:18 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v3 4/5] bond: lsc polling support > > Adds link status polling functionality to bonding device as

[dpdk-dev] LD_PRELOAD libraries for DPDK to run unmodified applications with DPDK?

Hi all, I've been trying to run unmodified applications with the DPDK framework. I used the KNI module and while it allowed me to run stock applications with DPDK infrastructure, it was not optimized for performance. There is already a rump-kernel based TCP/IP stack for DPDK

[dpdk-dev] [PATCH] pcap: set in_port value in packet mbuf data when each packet is received

Hi, How about the following patch for the next DPDK release? Thanks, Saori 2014-09-05 19:10 GMT+09:00 Saori USAMI : > The pkt.in_port parameter in mbuf should be set with an input port id > because DPDK apps may use it to know where each packet came from. > > Signed-off-by: Saori USAMI > ---

[dpdk-dev] [PATCH] Change alarm cancel function to thread-safe.

This patch is related to discussion from mode 4 link bonding patch set. Best regards Michal -Original Message- From: Jastrzebski, MichalX K Sent: Tuesday, September 23, 2014 5:02 PM To: dev at dpdk.org Cc: Jastrzebski, MichalX K; Wodkowski, PawelX Subject: [PATCH] Change alarm cancel

[dpdk-dev] [PATCH] examples/vmdq: support i40e in vmdq example

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Xie, Huawei > Sent: Wednesday, September 24, 2014 6:58 PM > To: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH] examples/vmdq: support i40e in vmdq example > > This patch depends on "[dpdk-dev] [PATCH 0/6]

[dpdk-dev] [PATCH] examples/vmdq: support i40e in vmdq example

This patch depends on "[dpdk-dev] [PATCH 0/6] i40e VMDQ support" > -Original Message- > From: Xie, Huawei > Sent: Wednesday, September 24, 2014 6:54 PM > To: dev at dpdk.org > Cc: Xie, Huawei > Subject: [PATCH] examples/vmdq: support i40e in vmdq example > > This patch supports i40e in

[dpdk-dev] DPDK 1.7 crashes on table initialization

I am not getting a useful core - I just get the error message -PIPELINE: rte_pipeline_table_create: Table creation failed on the command line So I played around with the action_data_size and for some reason, the application comes up fine if it I specify it as sizeof(struct

[dpdk-dev] [PATCH] examples/vhost: Support jumbo frame in user space vhost

Tested-by: Jingguo Fu This patch includes 1 file, and has been tested by Intel. Please see information as the following: Host: Fedora 19 x86_64, Linux Kernel 3.9.0, GCC 4.8.2 Intel Xeon CPU E5-2680 v2 @ 2.80GHz NIC: Intel Niantic 82599, Intel i350, Intel 82580 and Intel 82576 Guest: Fedora

[dpdk-dev] [PATCH v3] virtio: Support mergeable buffer in virtio pmd

Tested-by: Jingguo Fu This patch includes 1 files, and has been tested by Intel. Please see information as the following: Host: Fedora 19 x86_64, Linux Kernel 3.9.0, GCC 4.8.2 Intel Xeon CPU E5-2680 v2 @ 2.80GHz NIC: Intel Niantic 82599, Intel i350, Intel 82580 and Intel 82576 Guest: Fedora

[dpdk-dev] [PATCH] examples/vhost: Support jumbo frame in user space vhost

Tested-by: Jingguo Fu This patch includes 1 file, and has been tested by Intel. Please see information as the following: Host: Fedora 19 x86_64, Linux Kernel 3.9.0, GCC 4.8.2 Intel Xeon CPU E5-2680 v2 @ 2.80GHz NIC: Intel Niantic 82599, Intel i350, Intel 82580 and Intel 82576 Guest: Fedora

[dpdk-dev] [PATCH 0/5] Support virtio multicast feature

Tested-by: Xiaonan Zhang This patch includes five files, and has been tested by Intel. Please see information as the following: Host: Fedora 20 x86_64, Linux Kernel 3.11.10-301.fc20.x86_64, GCC 4.8.3 20140624 Intel Xeon CPU E5-2680 v2 @ 2.80GHz NIC: Intel Niantic 82599, Intel i350, Intel

[dpdk-dev] [PATCH v2 3/5] testpmd: Change rxfreet default to 32

> -Original Message- > From: Neil Horman [mailto:nhorman at tuxdriver.com] > Sent: Tuesday, September 23, 2014 6:03 PM > To: Richardson, Bruce > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2 3/5] testpmd: Change rxfreet default to 32 > > On Tue, Sep 23, 2014 at 12:08:15PM +0100,

[dpdk-dev] DPDK 1.7 crashes on table initialization

On Wed, Sep 24, 2014 at 09:37:07AM +, Saha, Avik (AWS) wrote: > I am not getting a useful core - > I just get the error message -PIPELINE: rte_pipeline_table_create: Table > creation failed on the command line > > So I played around with the action_data_size and for some reason, the >

[dpdk-dev] [PATCH v2 3/5] testpmd: Change rxfreet default to 32

On Wed, Sep 24, 2014 at 09:03:20AM +, Richardson, Bruce wrote: > > -Original Message- > > From: Neil Horman [mailto:nhorman at tuxdriver.com] > > Sent: Tuesday, September 23, 2014 6:03 PM > > To: Richardson, Bruce > > Cc: dev at dpdk.org > > Subject: Re: [dpdk-dev] [PATCH v2 3/5]

[dpdk-dev] [PATCH v2 0/7] Support flow director programming on fortville

Tested-by: Min Cao I have tested this patch with Fortville. Flow director is tested with 2*40G, 1*40G and 4*10G NIC. -Original Message- From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Jingjing Wu Sent: Wednesday, August 27, 2014 10:14 AM To: dev at dpdk.org Subject: [dpdk-dev]

[dpdk-dev] Can not init NIC after merge to DPDK 1.7 problem

This does resolve the problem. Thank you so much. From: Sanford, Robert [rsanf...@akamai.com] Sent: Tuesday, September 23, 2014 2:50 PM To: Wang, Shawn; dev at dpdk.org Subject: Re: [dpdk-dev] Can not init NIC after merge to DPDK 1.7 problem We ran into