Re: [lng-odp] Classification Queue Group

On 11/10 15:17:15, Bala Manoharan wrote: > On 10 November 2016 at 13:26, Brian Brooks wrote: > > On 11/07 16:46:12, Bala Manoharan wrote: > >> Hi, > > > > Hiya > > > >> This mail thread discusses the design of classification queue group > >> RFC. The same can be found in

Re: [lng-odp] continuous memory allocation for drivers

I hoped such a kernel module would already exist, but I am surprised that DPDK would not rely on it. Maybe there is a limitation I cannot see. I'll keep searching. Francois, maybe you know the answer? On 10 November 2016 at 19:10, Mike Holmes wrote: > > > On 10 November

[lng-odp] [RFC] example: traffic_mgmt: enhancement with multiple pktios

From: Xuelin Shi This patch made the following changes: - receiving packets from multiple pktios other than generating packets - identifying TM user by ip with individual class of service - print the user service while starting the program

Re: [lng-odp] [API-NEXT PATCH 1/3] drv: shm: function to query for physical addresses

On 10 November 2016 at 20:05, Maxim Uvarov wrote: > On 11/10/16 20:21, Christophe Milard wrote: > >> The capability "can_getphy" is introduced and tells whether physical >> address queries are available. >> The function odpdrv_getphy() is added to query for physical

Re: [lng-odp] [API-NEXT PATCH 1/3] drv: shm: function to query for physical addresses

On 11/10/16 20:21, Christophe Milard wrote: The capability "can_getphy" is introduced and tells whether physical address queries are available. The function odpdrv_getphy() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard

Re: [lng-odp] Classification Queue Group

On 10 November 2016 at 04:14, Bala Manoharan wrote: > Regards, > Bala > > > On 10 November 2016 at 07:34, Bill Fischofer > wrote: > > > > > > On Mon, Nov 7, 2016 at 5:16 AM, Bala Manoharan < > bala.manoha...@linaro.org> > > wrote: > >> > >>

Re: [lng-odp] continuous memory allocation for drivers

On 10 November 2016 at 12:52, Christophe Milard < christophe.mil...@linaro.org> wrote: > Hi, > > My hope was that packet segments would all be smaller than one page > (either normal pages or huge pages) to guarantee physical memory > continuity which is needed by some drivers (read non vfio

[lng-odp] continuous memory allocation for drivers

Hi, My hope was that packet segments would all be smaller than one page (either normal pages or huge pages) to guarantee physical memory continuity which is needed by some drivers (read non vfio drivers for PCI). Francois Ozog's experience (with dpdk)shows that this hope will fail in some case:

[lng-odp] [API-NEXT PATCH 2/3] linux-gen: drv: functions to query for physical addresses

The capability "can_getphy" is introduced and tells whether physical address queries are available. The function odpdrv_getphy() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard --- platform/linux-generic/drv_shm.c

[lng-odp] [API-NEXT PATCH 3/3] test: drv: shm: adding test for physical address queries

Signed-off-by: Christophe Milard --- .../common_plat/validation/drv/drvshmem/drvshmem.c | 37 ++ .../common_plat/validation/drv/drvshmem/drvshmem.h | 1 + 2 files changed, 38 insertions(+) diff --git

[lng-odp] [API-NEXT PATCH 1/3] drv: shm: function to query for physical addresses

The capability "can_getphy" is introduced and tells whether physical address queries are available. The function odpdrv_getphy() is added to query for physical address (from virtual address) Signed-off-by: Christophe Milard --- include/odp/drv/spec/shm.h | 35

[lng-odp] [API-NEXT PATCH 0/3] physical address query on DRV interface

NOTE: Must be applied on top of "getting physical addresses from _ishmphy" Brings the physical address query functions on the driver interface. Christophe Milard (3): drv: shm: function to query for physical addresses linux-gen: drv: functions to query for physical addresses test: drv:

[lng-odp] [Bug 2437] LAVA: FAIL: odp_timer_simple Juno

https://bugs.linaro.org/show_bug.cgi?id=2437 Mike Holmes changed: What|Removed |Added Resolution|--- |NON REPRODUCIBLE

[lng-odp] [Bug 2438] LAVA: FAIL: odp_pktio_perf arndale

https://bugs.linaro.org/show_bug.cgi?id=2438 Mike Holmes changed: What|Removed |Added Resolution|--- |NON REPRODUCIBLE

[lng-odp] [Bug 2558] Upgrade socket mmap to TPACKET_V3

https://bugs.linaro.org/show_bug.cgi?id=2558 Mike Holmes changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED

[lng-odp] [Bug 2512] validation: TCP checksum update

https://bugs.linaro.org/show_bug.cgi?id=2512 --- Comment #5 from Bala Manoharan --- V2 Patch in mailing list. Needs review. -- You are receiving this mail because: You are on the CC list for the bug.

[lng-odp] [Bug 2497] validation: odp_schedule_multi waiting for n number of packets

https://bugs.linaro.org/show_bug.cgi?id=2497 Bala Manoharan changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED

[lng-odp] [PATCHv2 1/1] validation: pktio: fix invalid mac addr

Fixes https://bugs.linaro.org/show_bug.cgi?id=2496 Signed-off-by: Balasubramanian Manoharan --- v2: Incorporate review comments test/common_plat/validation/api/pktio/pktio.c | 24 +--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git

Re: [lng-odp] [API-NEXT PATCH v3 05/19] linux-gen: pool: reimplement pool with ring

This series fails bisectability with this patch: Using patch: 0005-linux-gen-pool-reimplement-pool-with-ring.patch Trying to apply patch Patch applied Building with patch PASS: odp_crypto PASS: odp_pktio_perf SKIP: odp_l2fwd_run.sh PASS: odp_sched_latency_run.sh PASS: odp_scheduling_run.sh

[lng-odp] [Bug 2494] Extend odp_pktio_capability_t to include minimal pool size required by pktio implementation.

https://bugs.linaro.org/show_bug.cgi?id=2494 --- Comment #7 from Bala Manoharan --- Regards, Bala On 3 November 2016 at 19:36, wrote: > https://bugs.linaro.org/show_bug.cgi?id=2494 > > --- Comment #6 from Maciej Czekaj

Re: [lng-odp] [Bug 2494] Extend odp_pktio_capability_t to include minimal pool size required by pktio implementation.

Regards, Bala On 3 November 2016 at 19:36, wrote: > https://bugs.linaro.org/show_bug.cgi?id=2494 > > --- Comment #6 from Maciej Czekaj --- > (In reply to Bala Manoharan from comment #5) >> Application portability across

Re: [lng-odp] [API-NEXT PATCH v3 17/19] api: packet: added limits for packet len on alloc

On 11/10/16 14:07, Petri Savolainen wrote: There's no use case for application to allocate zero length packets. Application should always have some knowledge about the new packet data length before allocation. Also implementations are more efficient when a check for zero length is avoided. Also

[lng-odp] [API-NEXT PATCH v3 05/19] linux-gen: pool: reimplement pool with ring

Used the ring data structure to implement pool. Also buffer structure was simplified to enable future driver interface. Every buffer includes a packet header, so each buffer can be used as a packet head or segment. Segmentation was disabled and segment size was fixed to a large number (64kB) to

[lng-odp] [API-NEXT PATCH v3 15/19] linux-gen: packet: added support for segmented packets

Added support for multi-segmented packets. The first segments is the packet descriptor, which contains all metadata and pointers to other segments. Signed-off-by: Petri Savolainen --- .../include/odp/api/plat/packet_types.h| 6 +-

[lng-odp] [API-NEXT PATCH v3 09/19] linux-gen: pool: clean up pool inlines functions

Removed odp_pool_to_entry(), which was a duplicate of pool_entry_from_hdl(). Renamed odp_buf_to_hdr() to buf_hdl_to_hdr(), which describes more accurately the internal function. Inlined pool_entry(), pool_entry_from_hdl() and buf_hdl_to_hdr(), which are used often and also outside of pool.c.

[lng-odp] [API-NEXT PATCH v3 03/19] linux-gen: ring: created common ring implementation

Moved scheduler ring code into a new header file, so that it can be used also in other parts of the implementation. Signed-off-by: Petri Savolainen --- platform/linux-generic/Makefile.am | 1 + platform/linux-generic/include/odp_ring_internal.h |

[lng-odp] [API-NEXT PATCH v3 08/19] linux-gen: pool: optimize buffer alloc

Round up global pool allocations to a burst size. Cache any extra buffers for future use. Prefetch buffers header which very newly allocated from global pool and will be returned to the caller. Signed-off-by: Petri Savolainen ---

[lng-odp] [API-NEXT PATCH v3 11/19] test: validation: buf: test alignment

Added checks for correct alignment. Also updated tests to call odp_pool_param_init() for parameter initialization. Signed-off-by: Petri Savolainen --- test/common_plat/validation/api/buffer/buffer.c | 113 +--- 1 file changed, 63 insertions(+), 50

[lng-odp] [API-NEXT PATCH v3 10/19] linux-gen: pool: ptr instead of hdl in buffer_alloc_multi

Improve performance by changing the first parameter of buffer_alloc_multi() to pool pointer (from handle), to avoid double lookup of the pool pointer. Pointer is available for packet alloc calls already. Signed-off-by: Petri Savolainen ---

[lng-odp] [API-NEXT PATCH v3 07/19] linux-gen: pool: use ring multi enq and deq operations

Use multi enq and deq operations to optimize global pool access performance. Temporary uint32_t arrays are needed since handles are pointer size variables. Signed-off-by: Petri Savolainen --- platform/linux-generic/odp_pool.c | 32 1

[lng-odp] [API-NEXT PATCH v3 00/19] pool optimization

Pool performance is optimized by using a ring as the global buffer storage. IPC build is disabled, since it needs large modifications due to dependency to pool internals. Old pool implementation was based on locks and linked list of buffer headers. New implementation maintain a ring of buffer

[lng-odp] [API-NEXT PATCH v3 13/19] test: correctly initialize pool parameters

Use odp_pool_param_init() to initialize pool parameters. Also pktio test must use capability to determine maximum packet segment length. Signed-off-by: Petri Savolainen --- example/generator/odp_generator.c | 2 +-

[lng-odp] [API-NEXT PATCH v3 12/19] test: performance: crypto: use capability to select max packet

Applications must use pool capabilibty to check maximum values for parameters. Used maximum segment length since application seems to support only single segment packets. Signed-off-by: Petri Savolainen --- test/common_plat/performance/odp_crypto.c | 47

[lng-odp] [API-NEXT PATCH v3 18/19] linux-gen: packet: remove zero len support from alloc

Remove support for zero length allocations which were never required by the API specification or tested by the validation suite. Signed-off-by: Petri Savolainen --- platform/linux-generic/odp_packet.c | 28 1 file changed, 28 deletions(-)

[lng-odp] [API-NEXT PATCH v3 17/19] api: packet: added limits for packet len on alloc

There's no use case for application to allocate zero length packets. Application should always have some knowledge about the new packet data length before allocation. Also implementations are more efficient when a check for zero length is avoided. Also added a pool parameter to specify the

[lng-odp] [API-NEXT PATCH v3 16/19] test: validation: packet: improved multi-segment alloc test

Added test cases to allocate and free multiple multi-segment packets. Signed-off-by: Petri Savolainen --- test/common_plat/validation/api/packet/packet.c | 73 +++-- 1 file changed, 68 insertions(+), 5 deletions(-) diff --git

[lng-odp] [API-NEXT PATCH v3 14/19] test: validation: packet: fix bugs in tailroom and concat tests

Tailroom test did not call odp_packet_extend_tail() since it pushed tail too few bytes. Corrected the test to extend the tail by 100 bytes. Concat test did pass the same packet as src and dst packets. There's no valid use case to concatenate a packet into itself (forms a loop). Corrected the test

[lng-odp] [API-NEXT PATCH v3 06/19] linux-gen: ring: added multi enq and deq

Added multi-data versions of ring enqueue and dequeue operations. Signed-off-by: Petri Savolainen --- platform/linux-generic/include/odp_ring_internal.h | 65 ++ 1 file changed, 65 insertions(+) diff --git

[lng-odp] [API-NEXT PATCH v3 04/19] linux-gen: align: added round up power of two

Added a macro to round up a value to the next power of two, if it's not already a power of two. Also removed duplicated code from the same file. Signed-off-by: Petri Savolainen --- .../linux-generic/include/odp_align_internal.h | 34 +- 1 file

[lng-odp] [API-NEXT PATCH v3 02/19] linux-gen: pktio: do not free zero packets

In some error cases, netmap and dpdk pktios were calling odp_packet_free_multi with zero packets. Moved existing error check to avoid a free call with zero packets. Signed-off-by: Petri Savolainen --- platform/linux-generic/pktio/dpdk.c | 10 ++

[lng-odp] [API-NEXT PATCH v3 19/19] linux-gen: packet: enable multi-segment packets

Enable segmentation support with CONFIG_PACKET_MAX_SEGS configuration option. Signed-off-by: Petri Savolainen --- platform/linux-generic/include/odp_config_internal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git

[lng-odp] [API-NEXT PATCH v3 01/19] linux-gen: ipc: disable build of ipc pktio

IPC pktio implementation depends heavily on pool internals. It's build is disabled due to pool re-implementation. IPC should be re-implemented with a cleaner internal interface towards pool and shm. Signed-off-by: Petri Savolainen ---

Re: [lng-odp] Classification Queue Group

On 10 November 2016 at 13:26, Brian Brooks wrote: > On 11/07 16:46:12, Bala Manoharan wrote: >> Hi, > > Hiya > >> This mail thread discusses the design of classification queue group >> RFC. The same can be found in the google doc whose link is given >> below. >> Users can

Re: [lng-odp] driver interface thinkings....

On 11/09 09:42:49, Francois Ozog wrote: > To deal with drivers we need to have additional "standard" (helper or API?) > objects to deal with MAC addresses. > > ODP could be made to handle SDH, SDLC, FrameRelay or ATM packets. A > packet_io is pretty generic... > > But as soon as we talk with

Re: [lng-odp] Classification Queue Group

Regards, Bala On 10 November 2016 at 07:34, Bill Fischofer wrote: > > > On Mon, Nov 7, 2016 at 5:16 AM, Bala Manoharan > wrote: >> >> Hi, >> >> This mail thread discusses the design of classification queue group >> RFC. The same can be

Re: [lng-odp] Classification Queue Group

Good points Brian. I can add some data point with real life observations of a DPI box analyzing two 10Gbps links (four 10 Gbps ports): there are approximately 50M known flows (TCP, UDP...), may be not active (TCP Close_wait). FF On 10 November 2016 at 08:56, Brian Brooks