[dpdk-dev] Packet drops during non-exhaustive flood with OVS and 1.8.0

On Fri, Feb 13, 2015 at 1:58 PM, Traynor, Kevin wrote: >> -Original Message- >> From: Andrey Korolyov [mailto:andrey at xdel.ru] >> Sent: Thursday, February 12, 2015 3:16 PM >> To: Traynor, Kevin >> Cc: dev at dpdk.org; discuss at openvswitch.org >> Subject: Re: Packet drops during

[dpdk-dev] [PATCH v8 01/14] eal_pci: Add flag to hold kernel driver type

2015-02-16 13:14, Tetsuya Mukawa: > From: Michael Qiu > > Currently, dpdk has no ability to know which type of driver( > vfio-pci/igb_uio/uio_pci_generic) the device used. It only can > check whether vfio is enabled or not staticly. > > It really useful to have the flag, becasue different type

[dpdk-dev] [PATCH v8 03/14] eal/pci, ethdev: Remove assumption that port will not be detached

2015-02-16 13:14, Tetsuya Mukawa: > To remove assumption, do like followings. > > This patch adds "RTE_PCI_DRV_DETACHABLE" to drv_flags of rte_pci_driver > structure. The flags indicate the driver can detach devices at runtime. > Also, remove assumption that port will not be detached. > > To

[dpdk-dev] [PATCH v8 04/14] eal/pci: Consolidate pci address comparison APIs

2015-02-16 13:14, Tetsuya Mukawa: > This patch replaces pci_addr_comparison() and memcmp() of pci addresses by > eal_compare_pci_addr(). > > v8: > - Fix pci_scan_one() to update sysfs values. > (Thanks to Qiu, Michael and Iremonger, Bernard) > v5: > - Fix pci_scan_one to handle pt_driver

[dpdk-dev] [PATCH v8 05/14] ethdev: Add rte_eth_dev_free to free specified device

2015-02-16 13:14, Tetsuya Mukawa: > This patch adds rte_eth_dev_free(). The function is used for changing an > attached status of the device that has specified name. > > v6: > - Use rte_eth_dev structure as the paramter of rte_eth_dev_free(). > v4: > - Add parameter checking. > > Signed-off-by:

[dpdk-dev] [PATCH v8 06/14] eal, ethdev: Add a function and function pointers to close ether device

2015-02-16 13:14, Tetsuya Mukawa: > The patch adds function pointer to rte_pci_driver and eth_driver > structure. These function pointers are used when ports are detached. > Also, the patch adds rte_eth_dev_uninit(). So far, it's not called > by anywhere, but it will be called when port hotplug

[dpdk-dev] [PATCH v8 07/14] ethdev: Add functions that will be used by port hotplug functions

2015-02-16 13:14, Tetsuya Mukawa: > The patch adds following functions. > > - rte_eth_dev_save() > The function is used for saving current rte_eth_dev structures. > - rte_eth_dev_get_changed_port() > The function receives the rte_eth_dev structures, then compare > these with current values

[dpdk-dev] [PATCH v8 08/14] eal/linux/pci: Add functions for unmapping igb_uio resources

2015-02-16 13:14, Tetsuya Mukawa: > The patch adds functions for unmapping igb_uio resources. The patch is only > for Linux and igb_uio environment. VFIO and BSD are not supported. > > v8: > - Fix typo. > (Thanks to Iremonger, Bernard) > v5: > - Fix pci_unmap_device() to check pt_driver. > v4:

[dpdk-dev] [PATCH v8 11/14] ethdev: Add one dev_type parameter to rte_eth_dev_allocate

2015-02-16 13:14, Tetsuya Mukawa: > This new parameter is needed to keep device type like physical or virtual. Actually types are "PCI" and "virtual". > Port detaching processes are different between physical and virtual. > This parameter lets detaching function know a device type of the port.

[dpdk-dev] [PATCH v8 13/14] eal: Enable port hotplug framework in Linux

2015-02-16 13:14, Tetsuya Mukawa: > The patch enables CONFIG_RTE_LIBRTE_EAL_HOTPLUG in Linux configuration. This patch should be introduced earlier in the patchset.

[dpdk-dev] [PATCH v7 04/19] eal: fix wrong strnlen() return value in 32bit icc

> -Original Message- > From: Olivier MATZ [mailto:olivier.matz at 6wind.com] > Sent: Monday, February 16, 2015 10:52 PM > To: Liang, Cunming; dev at dpdk.org > Cc: Ananyev, Konstantin; nhorman at tuxdriver.com > Subject: Re: [PATCH v7 04/19] eal: fix wrong strnlen() return value in 32bit

[dpdk-dev] [PATCH v8 12/14] eal/pci: Add rte_eal_dev_attach/detach() functions

2015-02-16 13:14, Tetsuya Mukawa: > These functions are used for attaching or detaching a port. > When rte_eal_dev_attach() is called, the function tries to realize the > device name as pci address. If this is done successfully, > rte_eal_dev_attach() will attach physical device port. If not,

[dpdk-dev] [PATCH v8 00/19] support multi-pthread per core

v8 changes: keep using strlen for trusted input string v7 changes: update EAL version map for new public EAL API rollback to use strnlen() passing EAL core option v6 changes: rename RTE_RING_PAUSE_REP(_COUNT) and set default to 0 rollback to use RTE_MAX_LCORE when checking valid

[dpdk-dev] [PATCH v8 03/19] eal: new eal option '--lcores' for cpu assignment

It supports one new eal long option '--lcores' for EAL thread cpuset assignment. The format pattern: --lcores='[<,lcores[@cpus]>...]' lcores, cpus could be a single digit/range or a group. '(' and ')' are necessary if it's a group. If not supply '@cpus', the value of cpus

[dpdk-dev] [PATCH v8 02/19] eal: fix PAGE_SIZE redefine complaint on freebsd

Signed-off-by: Cunming Liang --- lib/librte_eal/bsdapp/eal/eal_memory.c | 8 +--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/lib/librte_eal/bsdapp/eal/eal_memory.c b/lib/librte_eal/bsdapp/eal/eal_memory.c index 65ee87d..33ebd0f 100644 ---

[dpdk-dev] [PATCH v8 05/19] eal: add public function parsing socket_id from cpu_id

It defines eal_cpu_socket_id() which exposing the origin private cpu_socket_id(). The function is only used inside EAL. It returns socket_id of the specified cpu_id. Signed-off-by: Cunming Liang --- v7 changes: reword comments v5 changes: expose cpu_socket_id as eal_cpu_socket_id for

[dpdk-dev] [PATCH v8 01/19] eal: add cpuset into per EAL thread lcore_config

The patch adds 'cpuset' into per-lcore configure 'lcore_config[]', as the lcore no longer always 1:1 pinning with physical cpu. The lcore now stands for a EAL thread rather than a logical cpu. It doesn't change the default behavior of 1:1 mapping, but allows to affinity the EAL thread to multiple

[dpdk-dev] [PATCH v8 04/19] eal: fix wrong strnlen() return value in 32bit icc

The problem is that strnlen() here may return invalid value with 32bit icc. (actually it returns it?s second parameter,e.g: sysconf(_SC_ARG_MAX)). It starts to manifest hwen max_len parameter is > 2M and using icc ?m32 ?O2 (or above). Suggested-by: Konstantin Ananyev Signed-off-by: Cunming

[dpdk-dev] [PATCH v8 06/19] eal: new TLS definition and API declaration

1. add two TLS *_socket_id* and *_cpuset* 2. add one internal API, eal_cpu_socket_id/eal_thread_dump_affinity 3. add two public API, rte_thread_set/get_affinity 4. update EAL version map for EAL public API Signed-off-by: Cunming Liang --- v7 changes: update version map for EAL public API and

[dpdk-dev] [PATCH v8 07/19] eal: add eal_common_thread.c for common thread API

The API works for both EAL thread and none EAL thread. When calling rte_thread_set_affinity, the *_socket_id* and *_cpuset* of calling thread will be updated if the thread successful set the cpu affinity. Signed-off-by: Cunming Liang --- v5 changes: refine code of rte_thread_set_affinity()

[dpdk-dev] [PATCH v8 08/19] eal: standardize init sequence between linux and bsd

Signed-off-by: Cunming Liang --- lib/librte_eal/bsdapp/eal/eal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/librte_eal/bsdapp/eal/eal.c b/lib/librte_eal/bsdapp/eal/eal.c index 69f3c03..cb11b5c 100644 --- a/lib/librte_eal/bsdapp/eal/eal.c +++

[dpdk-dev] [PATCH v8 09/19] eal: add rte_gettid() to acquire unique system tid

The rte_gettid() wraps the linux and freebsd syscall gettid(). It provides a persistent unique thread id for the calling thread. It will save the unique id in TLS on the first time. Signed-off-by: Cunming Liang --- lib/librte_eal/bsdapp/eal/eal_thread.c | 9 +

[dpdk-dev] [PATCH v8 10/19] eal: apply affinity of EAL thread by assigned cpuset

EAL threads use assigned cpuset to set core affinity during startup. It keeps 1:1 mapping, if no '--lcores' option is used. Signed-off-by: Cunming Liang --- v5 changes: add return check for dump_affinity call rte_thread_set_affinity() directly during EAL thread set

[dpdk-dev] [PATCH v8 11/19] enic: fix re-define freebsd compile complain

Some macro already been defined by freebsd 'sys/param.h'. Signed-off-by: Cunming Liang --- v5 changes: rename the redefined MACRO instead of undefine them lib/librte_pmd_enic/enic.h | 4 ++-- lib/librte_pmd_enic/enic_compat.h | 2 +- lib/librte_pmd_enic/vnic/vnic_dev.c | 6

[dpdk-dev] [PATCH v8 12/19] malloc: fix the issue of SOCKET_ID_ANY

Add check for rte_socket_id(), avoid get unexpected return like (-1). By using rte_malloc_socket(), socket id is assigned by socket_arg. If socket_arg set to SOCKET_ID_ANY, it expects to use the socket id to which the current cores belongs. As the thread may affinity on a cpuset, the cores in the

[dpdk-dev] [PATCH v8 13/19] log: fix the gap to support non-EAL thread

For those non-EAL thread, *_lcore_id* is invalid and probably larger than RTE_MAX_LCORE. The patch adds the check and allows only EAL thread using EAL per thread log level and log type. Others shares the global log level. Signed-off-by: Cunming Liang --- lib/librte_eal/common/eal_common_log.c

[dpdk-dev] [PATCH v8 14/19] eal: set _lcore_id and _socket_id to (-1) by default

For those none EAL thread, *_lcore_id* shall always be LCORE_ID_ANY. The libraries using *_lcore_id* as index need to take care. *_socket_id* always be SOCKET_ID_ANY unitl the thread changes the affinity by rte_thread_set_affinity() Signed-off-by: Cunming Liang --- v5 changes: define

[dpdk-dev] [PATCH v8 16/19] mempool: add support to non-EAL thread

For non-EAL thread, bypass per lcore cache, directly use ring pool. It allows using rte_mempool in either EAL thread or any user pthread. As in non-EAL thread, it directly rely on rte_ring and it's none preemptive. It doesn't suggest to run multi-pthread/cpu which compete the rte_mempool. It will

[dpdk-dev] [PATCH v8 17/19] ring: add support to non-EAL thread

ring debug stat won't take care non-EAL thread. Signed-off-by: Cunming Liang --- v6 changes: rollback v5 changes v5 changes: check __lcore_id with LCORE_ID_ANY instead of RTE_MAX_LCORE lib/librte_ring/rte_ring.h | 10 ++ 1 file changed, 6 insertions(+), 4 deletions(-) diff

[dpdk-dev] [PATCH v8 15/19] eal: fix recursive spinlock in non-EAL thraed

In non-EAL thread, lcore_id alrways be LCORE_ID_ANY. It cann't be used as unique id for recursive spinlock. Then use rte_gettid() to replace it. Signed-off-by: Cunming Liang --- lib/librte_eal/common/include/generic/rte_spinlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff

[dpdk-dev] [PATCH v8 18/19] ring: add sched_yield to avoid spin forever

Add a sched_yield() syscall if the thread spins for too long, waiting other thread to finish its operations on the ring. That gives pre-empted thread a chance to proceed and finish with ring enqnue/dequeue operation. The purpose is to reduce contention on the ring. By ring_perf_test, it doesn't

[dpdk-dev] [PATCH v8 19/19] timer: add support to non-EAL thread

Allow to setup timers only for EAL (lcore) threads (__lcore_id < MAX_LCORE_ID). E.g. ? dynamically created thread will be able to reset/stop timer for lcore thread, but it will be not allowed to setup timer for itself or another non-lcore thread. rte_timer_manage() for non-lcore thread would

[dpdk-dev] [PATCH v7 00/19] support multi-pthread per core

Tested-by: qun.wan Patch name:[PATCH v7 00/19] support multi-pthread per core Test Flag: Tested-by Tester name: qun.wan at intel.com Result summary: total 46 cases, 46 passed, 0 failed OS Environment: Linux Fedora 20

[dpdk-dev] [PATCH v2 14/15] examples/l3fwd: support of unified packet type

> -Original Message- > From: Ananyev, Konstantin > Sent: Tuesday, February 17, 2015 1:05 AM > To: Zhang, Helin; dev at dpdk.org > Cc: Cao, Waterman; Liang, Cunming; Liu, Jijiang; Richardson, Bruce > Subject: RE: [PATCH v2 14/15] examples/l3fwd: support of unified packet type > > Hi

[dpdk-dev] [PATCH v8 01/14] eal_pci: Add flag to hold kernel driver type

On 2/17/2015 8:13 AM, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> From: Michael Qiu >> >> Currently, dpdk has no ability to know which type of driver( >> vfio-pci/igb_uio/uio_pci_generic) the device used. It only can >> check whether vfio is enabled or not staticly. >> >> It

[dpdk-dev] [PATCH v8 08/14] eal/linux/pci: Add functions for unmapping igb_uio resources

On 2015/02/16 21:45, Neil Horman wrote: > On Mon, Feb 16, 2015 at 01:14:27PM +0900, Tetsuya Mukawa wrote: >> The patch adds functions for unmapping igb_uio resources. The patch is only >> for Linux and igb_uio environment. VFIO and BSD are not supported. >> >> v8: >> - Fix typo. >> (Thanks to

[dpdk-dev] [PATCH v8 07/14] ethdev: Add functions that will be used by port hotplug functions

On 2015/02/16 21:41, Neil Horman wrote: > On Mon, Feb 16, 2015 at 01:14:26PM +0900, Tetsuya Mukawa wrote: >> The patch adds following functions. >> >> - rte_eth_dev_save() >> The function is used for saving current rte_eth_dev structures. >> - rte_eth_dev_get_changed_port() >> The function

[dpdk-dev] [PATCH v4 00/26] Single virtio implementation

Acked-by Huawei Xie On 2/9/2015 9:14 AM, Ouyang, Changchun wrote: > This is the patch set for single virtio implementation. > > Why we need single virtio? > > As we know currently there are at least 3 virtio PMD driver implementations: > A)

[dpdk-dev] [PATCH v8 03/14] eal/pci, ethdev: Remove assumption that port will not be detached

Hi Thomas, I appreciate for your all comments. On 2015/02/17 9:36, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> To remove assumption, do like followings. >> >> This patch adds "RTE_PCI_DRV_DETACHABLE" to drv_flags of rte_pci_driver >> structure. The flags indicate the driver can

[dpdk-dev] How to get register dumps of 82599 NICs with a dpdk application

Hi, We are trying to experiment with DPDK?s l2fwd application with two 82599 Intel 10G adapters. Am able to run the l2fwd application and traffic is successfully forwarded. We want to verify the NIC registers and ring descriptors when the ports are bound to DPDK. Is there a way like

[dpdk-dev] [PATCH v8 04/14] eal/pci: Consolidate pci address comparison APIs

On 2015/02/17 9:44, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> This patch replaces pci_addr_comparison() and memcmp() of pci addresses by >> eal_compare_pci_addr(). >> >> v8: >> - Fix pci_scan_one() to update sysfs values. >> (Thanks to Qiu, Michael and Iremonger, Bernard) >>

[dpdk-dev] [PATCH v8 05/14] ethdev: Add rte_eth_dev_free to free specified device

On 2015/02/17 9:46, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> This patch adds rte_eth_dev_free(). The function is used for changing an >> attached status of the device that has specified name. >> >> v6: >> - Use rte_eth_dev structure as the paramter of rte_eth_dev_free(). >>

[dpdk-dev] [PATCH v8 06/14] eal, ethdev: Add a function and function pointers to close ether device

On 2015/02/17 9:56, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> The patch adds function pointer to rte_pci_driver and eth_driver >> structure. These function pointers are used when ports are detached. >> Also, the patch adds rte_eth_dev_uninit(). So far, it's not called >> by

[dpdk-dev] [PATCH v8 08/14] eal/linux/pci: Add functions for unmapping igb_uio resources

On 2015/02/17 10:11, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> The patch adds functions for unmapping igb_uio resources. The patch is only >> for Linux and igb_uio environment. VFIO and BSD are not supported. >> >> v8: >> - Fix typo. >> (Thanks to Iremonger, Bernard) >> v5:

[dpdk-dev] [PATCH v8 10/14] eal/pci: Cleanup pci driver initialization code

On 2015/02/17 10:18, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> - Add rte_eal_pci_close_one_dirver() >> The function is used for closing the specified driver and device. >> - Add pci_invoke_all_drivers() >> The function is based on pci_probe_all_drivers. But it can not only

[dpdk-dev] [PATCH v8 11/14] ethdev: Add one dev_type parameter to rte_eth_dev_allocate

On 2015/02/17 10:24, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> This new parameter is needed to keep device type like physical or virtual. > Actually types are "PCI" and "virtual". OK, I will change above sentence to explain it more clearly. >> Port detaching processes are

[dpdk-dev] [PATCH v8 13/14] eal: Enable port hotplug framework in Linux

On 2015/02/17 10:25, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> The patch enables CONFIG_RTE_LIBRTE_EAL_HOTPLUG in Linux configuration. > This patch should be introduced earlier in the patchset. Sure, I will.

[dpdk-dev] [PATCH v3 00/16] unified packet type

Currently only 6 bits which are stored in ol_flags are used to indicate the packet types. This is not enough, as some NIC hardware can recognize quite a lot of packet types, e.g i40e hardware can recognize more than 150 packet types. Hiding those packet types hides hardware offload capabilities

[dpdk-dev] [PATCH v3 02/16] ixgbe: support of unified packet type for vector

To unify the packet type, bit masks of packet type for ol_flags are replaced. In addition, more packet types (UDP, TCP and SCTP) are supported in vectorized ixgbe PMD. Note that around 2% performance drop (64B) was observed of doing 4 ports (1 port per 82599 card) IO forwarding on the same SNB

[dpdk-dev] [PATCH v3 04/16] e1000: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_e1000/igb_rxtx.c | 98 ++--- 1 file changed, 83 insertions(+), 15 deletions(-) v2 changes: * Used

[dpdk-dev] [PATCH v3 03/16] mbuf: add definitions of unified packet types

As there are only 6 bit flags in ol_flags for indicating packet types, which is not enough to describe all the possible packet types hardware can recognize. For example, i40e hardware can recognize more than 150 packet types. Unified packet type is composed of L2 type, L3 type, L4 type, tunnel

[dpdk-dev] [PATCH v3 06/16] i40e: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_i40e/i40e_rxtx.c | 786 ++-- 1 file changed, 512 insertions(+), 274 deletions(-) v2 changes: *

[dpdk-dev] [PATCH v3 07/16] enic: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_enic/enic_main.c | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) v2 changes: * Used redefined packet types and

[dpdk-dev] [PATCH v3 09/16] app/test-pipeline: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- app/test-pipeline/pipeline_hash.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) v2 changes: * Used redefined packet types and

[dpdk-dev] [PATCH v3 10/16] app/testpmd: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang Signed-off-by: Jijiang Liu --- app/test-pmd/csumonly.c | 10 +- app/test-pmd/rxonly.c | 9 +++-- 2 files changed, 8 insertions(+), 11

[dpdk-dev] [PATCH v3 11/16] examples/ip_fragmentation: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- examples/ip_fragmentation/main.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) v2 changes: * Used redefined packet types and enlarged

[dpdk-dev] [PATCH v3 14/16] examples/l3fwd-power: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- examples/l3fwd-power/main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) v2 changes: * Used redefined packet types and enlarged

[dpdk-dev] [PATCH v3 16/16] mbuf: remove old packet type bit masks

As unified packet types are used instead, those old bit masks and the relevant macros for packet type indication need to be removed. Signed-off-by: Helin Zhang --- lib/librte_mbuf/rte_mbuf.c | 6 -- lib/librte_mbuf/rte_mbuf.h | 14 -- 2 files changed, 4 insertions(+), 16

[dpdk-dev] [PATCH v3 08/16] vmxnet3: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) v2 changes: * Used redefined packet types and

[dpdk-dev] [PATCH v3 05/16] ixgbe: support of unified packet type

To unify packet type among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Note that around 2.5% performance drop (64B) was observed of doing 4 ports (1 port per 82599 card) IO forwarding on the same SNB core. Signed-off-by: Helin Zhang ---

[dpdk-dev] [PATCH v3 15/16] examples/l3fwd: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- examples/l3fwd/main.c | 71 +-- 1 file changed, 40 insertions(+), 31 deletions(-) v2 changes: * Used

[dpdk-dev] [PATCH v3 00/16] unified packet type

> -Original Message- > From: Zhang, Helin > Sent: Tuesday, February 17, 2015 2:59 PM > To: dev at dpdk.org > Cc: Cao, Waterman; Liang, Cunming; Liu, Jijiang; Ananyev, Konstantin; > Richardson, > Bruce; Zhang, Helin > Subject: [PATCH v3 00/16] unified packet type > > Currently only 6

[dpdk-dev] [PATCH v3 12/16] examples/ip_reassembly: support of unified packet type

To unify packet types among all PMDs, bit masks of packet type for 'ol_flags' are replaced by unified packet type. Signed-off-by: Helin Zhang --- examples/ip_reassembly/main.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) v2 changes: * Used redefined packet types and enlarged

[dpdk-dev] [PATCH v2 4/5] eal: add per rx queue interrupt handling based on VFIO

> -Original Message- > From: Liang, Cunming > Sent: Friday, February 13, 2015 11:48 AM > To: Zhou, Danny; dev at dpdk.org > Subject: RE: [dpdk-dev] [PATCH v2 4/5] eal: add per rx queue interrupt > handling based on VFIO > > Hi, > > > -Original Message- > > From: dev

[dpdk-dev] rte_memcpy optimization patch to dpdk ver 1.7

Hi, I am trying to use rte_memcpy optimization patch along with dpdk version 1.7. With the patch, while dpdk itself is compiled, applications failed with below error: --- include/rte_memcpy.h:629:2: error: implicit declaration of function '_mm_alignr_epi8'

[dpdk-dev] [PATCH 0/2] Removal of RTE_MBUF_REFCNT

On 16/02/2015 20:47, Stephen Hemminger wrote: > On Mon, 16 Feb 2015 16:08:31 + > Sergio Gonzalez Monroy wrote: > >> This patch tries to remove the RTE_MBUF_REFCNT config options and >> dependencies >> by introducing a new mbuf flag IND_ATTACHED_MBUF that would indicate when >> the mbuf >>

[dpdk-dev] Previous DPDK version API documentation for app developers

On Feb 12, 2015, at 1:29 AM, Thomas Monjalon wrote: > Yes you can: make doc > For doxygen API only: make doc-api-html > For sphinx only: doc-guides-html. Hi Thomas, In 1.7 for me at least I found the target was called: doc-htmlapi . Did the way this stuff works get changed at some point?

[dpdk-dev] Memory Initialization for RTE_EAL

Hi Team , I am using DPDK-1.7.1 , but couldn't get how memory Initialization happening for RTE_EAL . I followed dpd_porg_guide.pdf but couldn't get the proper flow . If possible any one please tell me the flow of memory Initialization . Regards Kuldeep

[dpdk-dev] [PATCH v8 07/14] ethdev: Add functions that will be used by port hotplug functions

On 2015/02/17 10:04, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> The patch adds following functions. >> >> - rte_eth_dev_save() >> The function is used for saving current rte_eth_dev structures. >> - rte_eth_dev_get_changed_port() >> The function receives the rte_eth_dev

[dpdk-dev] [PATCH v8 12/14] eal/pci: Add rte_eal_dev_attach/detach() functions

On 2015/02/17 10:48, Thomas Monjalon wrote: > 2015-02-16 13:14, Tetsuya Mukawa: >> These functions are used for attaching or detaching a port. >> When rte_eal_dev_attach() is called, the function tries to realize the >> device name as pci address. If this is done successfully, >>

[dpdk-dev] [PATCH v3 03/16] mbuf: add definitions of unified packet types

Hi Helin, On 02/17/2015 07:59 AM, Helin Zhang wrote: > As there are only 6 bit flags in ol_flags for indicating packet > types, which is not enough to describe all the possible packet > types hardware can recognize. For example, i40e hardware can > recognize more than 150 packet types. Unified

[dpdk-dev] Lcore-vports-queues mapping

Hi Team , I am using DPDK-1.7.1 , I am trying find out how to map lcore -- >vports -- > queuesin code level as well as user command prompt level . Suggestions are welcome on this . Regards, Kuldeep

[dpdk-dev] [PATCH v8 12/14] eal/pci: Add rte_eal_dev_attach/detach() functions

2015-02-17 17:51, Tetsuya Mukawa: > On 2015/02/17 10:48, Thomas Monjalon wrote: > > 2015-02-16 13:14, Tetsuya Mukawa: > >> +/* attach the new physical device, then store port_id of the device */ > >> +static int > >> +rte_eal_dev_attach_pdev(struct rte_pci_addr *addr, uint8_t *port_id) > >> +{ >

[dpdk-dev] Previous DPDK version API documentation for app developers

2015-02-17 00:48, Matthew Hall: > On Feb 12, 2015, at 1:29 AM, Thomas Monjalon > wrote: > > Yes you can: make doc > > For doxygen API only: make doc-api-html > > For sphinx only: doc-guides-html. > > Hi Thomas, > > In 1.7 for me at least I found the target was called: doc-htmlapi . > > Did

[dpdk-dev] Previous DPDK version API documentation for app developers

On Feb 17, 2015, at 1:30 AM, Thomas Monjalon wrote: > Yes, you're right. It has been renamed. > But I think you should better work on improving the HEAD ;) Yes, I agree. But to get to this point I have to get the core application features to even work in 1.7, before I can switch the app to

[dpdk-dev] [PATCH v3 00/16] unified packet type

> -Original Message- > From: Zhang, Helin > Sent: Tuesday, February 17, 2015 6:59 AM > To: dev at dpdk.org > Cc: Cao, Waterman; Liang, Cunming; Liu, Jijiang; Ananyev, Konstantin; > Richardson, Bruce; Zhang, Helin > Subject: [PATCH v3 00/16] unified packet type > > Currently only 6 bits

[dpdk-dev] Lcore-vports-queues mapping

On Tue, Feb 17, 2015 at 09:08:07AM +, kuldeep.samasi at wipro.com wrote: > Hi Team , > > I am using DPDK-1.7.1 , I am trying find out how to map lcore -- >vports -- > > queuesin code level as well as user command prompt level . > Suggestions are welcome on this . > > Hi, cores and ports

[dpdk-dev] [PATCH v8 00/19] support multi-pthread per core

> -Original Message- > From: Liang, Cunming > Sent: Tuesday, February 17, 2015 2:08 AM > To: dev at dpdk.org > Cc: Ananyev, Konstantin; olivier.matz at 6wind.com; nhorman at tuxdriver.com; > thomas.monjalon at 6wind.com; Liang, Cunming > Subject: [PATCH v8 00/19] support multi-pthread

[dpdk-dev] Lcore-vports-queues mapping

Hi Bruce , Thanks for suggestion , I want to map the lcore -- vport -- queue manually by command prompt , which program file I needs to enhance . Regards Kuldeep -Original Message- From: Bruce Richardson [mailto:bruce.richard...@intel.com] Sent: Tuesday, February 17, 2015 3:44 PM

[dpdk-dev] [PATCH v8 12/14] eal/pci: Add rte_eal_dev_attach/detach() functions

On 2015/02/17 18:23, Thomas Monjalon wrote: > 2015-02-17 17:51, Tetsuya Mukawa: >> On 2015/02/17 10:48, Thomas Monjalon wrote: >>> 2015-02-16 13:14, Tetsuya Mukawa: +/* attach the new physical device, then store port_id of the device */ +static int +rte_eal_dev_attach_pdev(struct

[dpdk-dev] Lcore-vports-queues mapping

On Tue, Feb 17, 2015 at 10:20:14AM +, kuldeep.samasi at wipro.com wrote: > Hi Bruce , > > Thanks for suggestion , I want to map the lcore -- vport -- queue manually by > command prompt , which program file I needs to enhance . > What application are you using? DPDK is primarily a set of

[dpdk-dev] Lcore-vports-queues mapping

I am using OVDK (dpdk openvswitch ), where I need to enhance the packet processing speed on DPDK data path by modifying lcore-- port-- queue mapping . -Original Message- From: Bruce Richardson [mailto:bruce.richard...@intel.com] Sent: Tuesday, February 17, 2015 3:59 PM To: Kuldeep

[dpdk-dev] [PATCH v2 3/4] examples: example showing use of callbacks.

On 16/02/15 17:34, Thomas Monjalon wrote: > 2015-02-16 15:16, Bruce Richardson: >> On Mon, Feb 16, 2015 at 03:33:40PM +0100, Olivier MATZ wrote: >>> Hi John, >>> >>> On 02/13/2015 04:39 PM, John McNamara wrote: From: Richardson, Bruce Example showing how callbacks can be used to

[dpdk-dev] [PATCH v2 3/4] examples: example showing use of callbacks.

On Mon, Feb 16, 2015 at 06:34:37PM +0100, Thomas Monjalon wrote: > 2015-02-16 15:16, Bruce Richardson: > > On Mon, Feb 16, 2015 at 03:33:40PM +0100, Olivier MATZ wrote: > > > Hi John, > > > > > > On 02/13/2015 04:39 PM, John McNamara wrote: > > > > From: Richardson, Bruce > > > > > > > >

[dpdk-dev] rte_memcpy optimization patch to dpdk ver 1.7

On Tue, Feb 17, 2015 at 08:39:22AM +, Vithal S Mohare wrote: > Hi, > > I am trying to use rte_memcpy optimization patch along with dpdk version 1.7. > With the patch, while dpdk itself is compiled, applications failed with > below error: > --- >

[dpdk-dev] [PATCH v5 06/17] fm10k: add rx_queue_setup/release function

Hi, From: David Marchand [mailto:david.march...@6wind.com] Sent: Friday, February 13, 2015 7:08 PM To: Chen, Jing D Cc: dev at dpdk.org; Zhang, Helin; Qiu, Michael; Neil Horman; Thomas Monjalon; Shaw, Jeffrey B Subject: Re: [PATCH v5 06/17] fm10k: add rx_queue_setup/release function Hello,?

[dpdk-dev] [PATCH v5 10/17] fm10k: add receive and tranmit function

Hi, From: David Marchand [mailto:david.march...@6wind.com] Sent: Friday, February 13, 2015 7:43 PM To: Chen, Jing D Cc: dev at dpdk.org; Zhang, Helin; Qiu, Michael; Neil Horman; Thomas Monjalon; Shaw, Jeffrey B Subject: Re: [PATCH v5 10/17] fm10k: add receive and tranmit function Hello,? On

[dpdk-dev] [PATCH v5 10/17] fm10k: add receive and tranmit function

Hi, From: David Marchand [mailto:david.march...@6wind.com] Sent: Friday, February 13, 2015 7:54 PM To: Chen, Jing D Cc: dev at dpdk.org; Zhang, Helin; Qiu, Michael; Neil Horman; Thomas Monjalon; Shaw, Jeffrey B Subject: Re: [PATCH v5 10/17] fm10k: add receive and tranmit function On Fri, Feb

[dpdk-dev] [PATCH v5 12/17] fm10k: Add scatter receive function

Hi, From: David Marchand [mailto:david.march...@6wind.com] Sent: Friday, February 13, 2015 7:55 PM To: Chen, Jing D Cc: dev at dpdk.org; Zhang, Helin; Qiu, Michael; Neil Horman; Thomas Monjalon; Shaw, Jeffrey B Subject: Re: [PATCH v5 12/17] fm10k: Add scatter receive function Hello, On Fri,

[dpdk-dev] [PATCH v5 15/17] fm10k: add PF and VF interrupt handling function

Hi, From: David Marchand [mailto:david.march...@6wind.com] Sent: Friday, February 13, 2015 7:42 PM To: Chen, Jing D Cc: dev at dpdk.org; Zhang, Helin; Qiu, Michael; Neil Horman; Thomas Monjalon; Shaw, Jeffrey B Subject: Re: [PATCH v5 15/17] fm10k: add PF and VF interrupt handling function

[dpdk-dev] [PATCH v2 3/4] examples: example showing use of callbacks.

Hi Bruce, On 02/17/2015 01:25 PM, Bruce Richardson wrote: > On Mon, Feb 16, 2015 at 06:34:37PM +0100, Thomas Monjalon wrote: >> 2015-02-16 15:16, Bruce Richardson: >>> In this specific instance, given that the application does little else, >>> there >>> is no real advantage to using the

[dpdk-dev] [PATCH v3 0/5] Interrupt mode PMD

v3 changes - Add return value for interrupt enable/disable functions - Move spinlok from PMD to L3fwd-power - Remove unnecessary variables in e1000_mac_info - Fix miscelleous review comments v2 changes - Fix compilation issue in Makefile for missed header file. - Consolidate internal and

[dpdk-dev] [PATCH v3 2/5] ixgbe: enable rx queue interrupts for both PF and VF

v3 changes - Remove spinlok from PMD v2 changes - Consolidate review comments related to coding style The patch does below things for ixgbe PF and VF: - Setup NIC to generate MSI-X interrupts - Set the IVAR register to map interrupt causes to vectors - Implement interrupt enable/disable

[dpdk-dev] [PATCH v3 1/5] ethdev: add rx interrupt enable/disable functions

v3 changes - Add return value for interrupt enable/disable functions Add two dev_ops functions to enable and disable rx queue interrupts Signed-off-by: Danny Zhou Tested-by: Yong Liu --- lib/librte_ether/rte_ethdev.c | 43 lib/librte_ether/rte_ethdev.h | 57

[dpdk-dev] [PATCH v3 3/5] igb: enable rx queue interrupts for PF

v3 changes - Remove unnecessary variables in e1000_mac_info - Remove spinlok from PMD v2 changes - Consolidate review comments related to coding style The patch does below for igb PF: - Setup NIC to generate MSI-X interrupts - Set the IVAR register to map interrupt causes to vectors - Implement

[dpdk-dev] [PATCH v3 4/5] eal: add per rx queue interrupt handling based on VFIO

v3 changes: - Fix review comments v2 changes: - Fix compilation issue for a missed header file - Bug fix: free unreleased resources on the exception path before return - Consolidate coding style related review comments This patch does below: - Create multiple VFIO eventfd for rx queues. - Handle

[dpdk-dev] [PATCH v3 5/5] l3fwd-power: enable one-shot rx interrupt and polling/interrupt mode switch

v3 changes - Add spinlock to ensure thread safe when accessing interrupt mask register v2 changes - Remove unused function which is for debug purpose Demonstrate how to handle per rx queue interrupt in a NAPI-like implementation in usersapce. PDK polling thread mainly works in polling mode and

[dpdk-dev] [PATCH v2 3/4] examples: example showing use of callbacks.

On Tue, Feb 17, 2015 at 02:28:02PM +0100, Olivier MATZ wrote: > Hi Bruce, > > On 02/17/2015 01:25 PM, Bruce Richardson wrote: > >On Mon, Feb 16, 2015 at 06:34:37PM +0100, Thomas Monjalon wrote: > >>2015-02-16 15:16, Bruce Richardson: > >>>In this specific instance, given that the application does

[dpdk-dev] [PATCH v6 00/16] lib/librte_pmd_fm10k : fm10k pmd driver

From: "Chen Jing D(Mark)" The patch set add poll mode driver for the host interface of Intel Ethernet Switch FM1 Series of silicons, which integrate NIC and switch functionalities. The patch set include below features: 1. Basic RX/TX functions for PF/VF. 2. Interrupt

[dpdk-dev] [PATCH v6 01/16] fm10k: add base driver

From: Jeff Shaw Base driver is developed and maintained by Intel ND team, includes basic functional service to Intel Ethernet Switch FM1 Series of silicons. Any suggestion on bug fix and improvement within this directory is welcome, but need this team to change and

  1   2   >