Re: [PATCH v5 0/6] Stage-Ordered API and other extensions for ring library

[Stephen Hemminger <stephen@networkplumber.org>]

On Tue, 15 Oct 2024 14:01:05 +0100
Konstantin Ananyev <konstantin.v.ananyev@yandex.ru> wrote:

> From: Konstantin Ananyev <konstantin.ananyev@huawei.com>
> 
> NOTE UPFRONT: this version is still not ready for merging.
> Missing items:
> - ARM/PPC tests passing
> - PG update
> 
> v4 -> v5
> - fix public API/doc comments from Jerin
> - update devtools/build-dict.sh (Stephen)
> - fix MSVC warnings
> - introduce new test-suite for meson (stress) with
>   ring_stress_autotest and soring_stress_autotest in it
> - enhance error report in tests
> - reorder some sync code in soring and add extra checks
>   (for better debuggability)
> 
> v3 -> v4:
> - fix compilation/doxygen complains (attempt #2)
> - updated release notes
> 
> v2 -> v3:
> - fix compilation/doxygen complains
> - dropped patch:
>   "examples/l3fwd: make ACL work in pipeline and eventdev modes": [2]
>   As was mentioned in the patch desctiption it was way too big,
>   controversial and incomplete. If the community is ok to introduce
>   pipeline model into the l3fwd, then it is propbably worth to be
>   a separate patch series.
> 
> v1 -> v2:
> - rename 'elmst/objst' to 'meta' (Morten)
> - introduce new data-path APIs set: one with both meta{} and objs[],
>   second with just objs[] (Morten)
> - split data-path APIs into burst/bulk flavours (same as rte_ring)
> - added dump function for te_soring and improved dump() for rte_ring.
> - dropped patch:
>   " ring: minimize reads of the counterpart cache-line"
>   - no performance gain observed
>   - actually it does change behavior of conventional rte_ring
>     enqueue/dequeue APIs -
>     it could return available/free less then actually exist in the ring.
>     As in some other libs we reliy on that information - it will
>     introduce problems.
> 
> The main aim of these series is to extend ring library with
> new API that allows user to create/use Staged-Ordered-Ring (SORING)
> abstraction. In addition to that there are few other patches that serve
> different purposes:
> - first two patches are just code reordering to de-duplicate
>   and generalize existing rte_ring code.
> - patch #3 extends rte_ring_dump() to correctly print head/tail metadata
>   for different sync modes.
> - next two patches introduce SORING API into the ring library and
>   provide UT for it.
> 
> SORING overview
> ===============
> Staged-Ordered-Ring (SORING) provides a SW abstraction for 'ordered' queues
> with multiple processing 'stages'. It is based on conventional DPDK
> rte_ring, re-uses many of its concepts, and even substantial part of
> its code.
> It can be viewed as an 'extension' of rte_ring functionality.
> In particular, main SORING properties:
> - circular ring buffer with fixed size objects
> - producer, consumer plus multiple processing stages in between.
> - allows to split objects processing into multiple stages.
> - objects remain in the same ring while moving from one stage to the other,
>   initial order is preserved, no extra copying needed.
> - preserves the ingress order of objects within the queue across multiple
>   stages
> - each stage (and producer/consumer) can be served by single and/or
>   multiple threads.
> 
> - number of stages, size and number of objects in the ring are
>  configurable at ring initialization time.
> 
> Data-path API provides four main operations:
> - enqueue/dequeue works in the same manner as for conventional rte_ring,
>   all rte_ring synchronization types are supported.
> - acquire/release - for each stage there is an acquire (start) and
>   release (finish) operation. After some objects are 'acquired' -
>   given thread can safely assume that it has exclusive ownership of
>   these objects till it will invoke 'release' for them.
>   After 'release', objects can be 'acquired' by next stage and/or dequeued
>   by the consumer (in case of last stage).
> 
> Expected use-case: applications that uses pipeline model
> (probably with multiple stages) for packet processing, when preserving
> incoming packet order is important.
> 
> The concept of ‘ring with stages’ is similar to DPDK OPDL eventdev PMD [1],
> but the internals are different.
> In particular, SORING maintains internal array of 'states' for each element
> in the ring that is  shared by all threads/processes that access the ring.
> That allows 'release' to avoid excessive waits on the tail value and helps
> to improve performancei and scalability.
> In terms of performance, with our measurements rte_soring and
> conventional rte_ring provide nearly identical numbers.
> As an example, on our SUT: Intel ICX CPU @ 2.00GHz,
> l3fwd (--lookup=acl) in pipeline mode [2] both
> rte_ring and rte_soring reach ~20Mpps for single I/O lcore and same
> number of worker lcores.
> 
> [1] https://www.dpdk.org/wp-content/uploads/sites/35/2018/06/DPDK-China2017-Ma-OPDL.pdf
> [2] https://patchwork.dpdk.org/project/dpdk/patch/20240906131348.804-7-konstantin.v.ananyev@yandex.ru/
> 
> Eimear Morrissey (1):
>   ring: make dump function more verbose
> 
> Konstantin Ananyev (5):
>   ring: common functions for 'move head' ops
>   ring: make copying functions generic
>   ring/soring: introduce Staged Ordered Ring
>   app/test: add unit tests for soring API
>   test: add stress test suite
> 
>  .mailmap                               |   1 +
>  app/test/meson.build                   |   3 +
>  app/test/suites/meson.build            |  10 +
>  app/test/test.h                        |   1 +
>  app/test/test_ring_stress.c            |   2 +-
>  app/test/test_ring_stress_impl.h       |   1 +
>  app/test/test_soring.c                 | 442 +++++++++++++
>  app/test/test_soring_mt_stress.c       |  40 ++
>  app/test/test_soring_stress.c          |  48 ++
>  app/test/test_soring_stress.h          |  35 ++
>  app/test/test_soring_stress_impl.h     | 834 +++++++++++++++++++++++++
>  devtools/build-dict.sh                 |   1 +
>  doc/api/doxy-api-index.md              |   1 +
>  doc/guides/rel_notes/release_24_11.rst |   8 +
>  lib/ring/meson.build                   |   4 +-
>  lib/ring/rte_ring.c                    |  87 ++-
>  lib/ring/rte_ring.h                    |  15 +
>  lib/ring/rte_ring_c11_pvt.h            | 134 +---
>  lib/ring/rte_ring_elem_pvt.h           | 181 ++++--
>  lib/ring/rte_ring_generic_pvt.h        | 121 +---
>  lib/ring/rte_ring_hts_elem_pvt.h       |  85 +--
>  lib/ring/rte_ring_rts_elem_pvt.h       |  85 +--
>  lib/ring/rte_soring.c                  | 182 ++++++
>  lib/ring/rte_soring.h                  | 555 ++++++++++++++++
>  lib/ring/soring.c                      | 561 +++++++++++++++++
>  lib/ring/soring.h                      | 124 ++++
>  lib/ring/version.map                   |  26 +
>  27 files changed, 3190 insertions(+), 397 deletions(-)
>  create mode 100644 app/test/test_soring.c
>  create mode 100644 app/test/test_soring_mt_stress.c
>  create mode 100644 app/test/test_soring_stress.c
>  create mode 100644 app/test/test_soring_stress.h
>  create mode 100644 app/test/test_soring_stress_impl.h
>  create mode 100644 lib/ring/rte_soring.c
>  create mode 100644 lib/ring/rte_soring.h
>  create mode 100644 lib/ring/soring.c
>  create mode 100644 lib/ring/soring.h
> 

And some build failures
####################################################################################
#### [Begin job log] "ubuntu-22.04-gcc-mini" at step Build and test
####################################################################################
../lib/eal/include/rte_bitops.h:1481:9: note: in expansion of macro ‘__RTE_BIT_OVERLOAD_SZ_4R’
 1481 |         __RTE_BIT_OVERLOAD_SZ_4R(family, fun, qualifier, 64, ret_type, arg1_type, arg1_name, \
      |         ^~~~~~~~~~~~~~~~~~~~~~~~
../lib/eal/include/rte_bitops.h:1497:1: note: in expansion of macro ‘__RTE_BIT_OVERLOAD_4R’
 1497 | __RTE_BIT_OVERLOAD_4R(atomic_, test_and_assign,, bool, unsigned int, nr, bool, value,
      | ^~~~~~~~~~~~~~~~~~~~~
../lib/eal/include/rte_bitops.h:1463:1: note: previous declaration ‘bool rte_bit_atomic_test_and_assign(uint32_t*, unsigned int, bool, int)’
 1463 | rte_bit_ ## family ## fun(qualifier uint ## size ## _t *addr, arg1_type arg1_name, \
      | ^~~~~~~~
../lib/eal/include/rte_bitops.h:1472:9: note: in expansion of macro ‘__RTE_BIT_OVERLOAD_V_4R’
 1472 |         __RTE_BIT_OVERLOAD_V_4R(family,, fun, qualifier, size, ret_type, arg1_type, arg1_name, \
      |         ^~~~~~~~~~~~~~~~~~~~~~~
../lib/eal/include/rte_bitops.h:1479:9: note: in expansion of macro ‘__RTE_BIT_OVERLOAD_SZ_4R’
 1479 |         __RTE_BIT_OVERLOAD_SZ_4R(family, fun, qualifier, 32, ret_type, arg1_type, arg1_name, \
      |         ^~~~~~~~~~~~~~~~~~~~~~~~
../lib/eal/include/rte_bitops.h:1497:1: note: in expansion of macro ‘__RTE_BIT_OVERLOAD_4R’
 1497 | __RTE_BIT_OVERLOAD_4R(atomic_, test_and_assign,, bool, unsigned int, nr, bool, value,
      | ^~~~~~~~~~~~~~~~~~~~~
[847/912] Compiling C++ object 'buildtools/chkincs/fe389a9@@chkincs-cpp at exe/meson-generated_rte_mbuf_dyn.cpp.o'.
[848/912] Compiling C++ object 'buildtools/chkincs/fe389a9@@chkincs-cpp at exe/meson-generated_rte_mempool.cpp.o'.
[849/912] Compiling C++ object 'buildtools/chkincs/fe389a9@@chkincs-cpp at exe/meson-generated_rte_mempool_trace_fp.cpp.o'.
[850/912] Compiling C++ object 'buildtools/chkincs/fe389a9@@chkincs-cpp at exe/meson-generated_rte_mbuf.cpp.o'.
[851/912] Compiling C object 'app/a172ced@@dpdk-test at exe/test_test_memcpy_perf.c.o'.
ninja: build stopped: subcommand failed.
##[error]Process completed with exit code 1.
####################################################################################
#### [End job log] "ubuntu-22.04-gcc-mini" at step Build and test
####################################################################################