[dpdk-dev] [PATCH v3 0/9] New sync modes for ring

[Konstantin Ananyev <konstantin.ananyev@intel.com>]

V2 - V3
1. Few more compilation fixes (for gcc 4.8.X)
2. Extra update devtools/libabigail.abignore (workaround) 

V1 - v2 changes:
1. Fix compilation issues
2. Add C11 atomics support
3. Updates devtools/libabigail.abignore (workaround)

RFC - V1 changes:
1. remove ABI brekage (at least I hope I did)
2. Add support for ring_elem
3. Rework peek related API a bit
4. Rework test to make it less verbose and unite all test-cases
   in one command
5. Add new test-case for MT peek API

TODO list:
1. Update docs

These days more and more customers use(/try to use) DPDK based apps within
overcommitted systems (multiple acttive threads over same pysical cores):
VM, container deployments, etc.
One quite common problem they hit:
Lock-Holder-Preemption/Lock-Waiter-Preemption with rte_ring.
LHP is quite a common problem for spin-based sync primitives
(spin-locks, etc.) on overcommitted systems.
The situation gets much worse when some sort of
fair-locking technique is used (ticket-lock, etc.).
As now not only lock-owner but also lock-waiters scheduling
order matters a lot (LWP).
These two problems are well-known for kernel within VMs:
http://www-archive.xenproject.org/files/xensummitboston08/LHP.pdf
https://www.cs.hs-rm.de/~kaiser/events/wamos2017/Slides/selcuk.pdf
The problem with rte_ring is that while head accusion is sort of
un-fair locking, waiting on tail is very similar to ticket lock schema -
tail has to be updated in particular order.
That makes current rte_ring implementation to perform
really pure on some overcommited scenarios.
It is probably not possible to completely resolve LHP problem in
userspace only (without some kernel communication/intervention).
But removing fairness at tail update helps to avoid LWP and
can mitigate the situation significantly.
This patch proposes two new optional ring synchronization modes:
1) Head/Tail Sync (HTS) mode
In that mode enqueue/dequeue operation is fully serialized:
    only one thread at a time is allowed to perform given op.
    As another enhancement provide ability to split enqueue/dequeue
    operation into two phases:
      - enqueue/dequeue start
      - enqueue/dequeue finish
    That allows user to inspect objects in the ring without removing
    them from it (aka MT safe peek).
2) Relaxed Tail Sync (RTS)
The main difference from original MP/MC algorithm is that
tail value is increased not by every thread that finished enqueue/dequeue,
but only by the last one.
That allows threads to avoid spinning on ring tail value,
leaving actual tail value change to the last thread in the update queue.

Note that these new sync modes are optional.
For current rte_ring users nothing should change
(both in terms of API/ABI and performance).
Existing sync modes MP/MC,SP/SC kept untouched, set up in the same
way (via flags and _init_), and MP/MC remains as default one.
The only thing that changed:
Format of prod/cons now could differ depending on mode selected at _init_.
So user has to stick with one sync model through whole ring lifetime.
In other words, user can't create a ring for let say SP mode and then
in the middle of data-path change his mind and start using MP_RTS mode.
For existing modes (SP/MP, SC/MC) format remains the same and
user can still use them interchangeably, though of course it is an
error prone practice.

Test results on IA (see below) show significant improvements
for average enqueue/dequeue op times on overcommitted systems.
For 'classic' DPDK deployments (one thread per core) original MP/MC
algorithm still shows best numbers, though for 64-bit target
RTS numbers are not that far away.
Numbers were produced by new UT test-case: ring_stress_autotest, i.e.:
echo ring_stress_autotest | ./dpdk-test -n 4 --lcores='...'

X86_64 @ Intel(R) Xeon(R) Platinum 8160 CPU @ 2.10GHz
DEQ+ENQ average cycles/obj

                                                MP/MC      HTS     RTS
1thread@1core(--lcores=6-7)                     8.00       8.15    8.99
2thread@2core(--lcores=6-8)                     19.14      19.61   20.35
4thread@4core(--lcores=6-10)                    29.43      29.79   31.82
8thread@8core(--lcores=6-14)                    110.59     192.81  119.50
16thread@16core(--lcores=6-22)                  461.03     813.12  495.59
32thread/@32core(--lcores='6-22,55-70')         982.90     1972.38 1160.51

2thread@1core(--lcores='6,(10-11)@7'            20140.50   23.58   25.14
4thread@2core(--lcores='6,(10-11)@7,(20-21)@8'  153680.60  76.88   80.05
8thread@2core(--lcores='6,(10-13)@7,(20-23)@8'  280314.32  294.72  318.79
16thread@2core(--lcores='6,(10-17)@7,(20-27)@8' 643176.59  1144.02 1175.14
32thread@2core(--lcores='6,(10-25)@7,(30-45)@8' 4264238.80 4627.48 4892.68

8thread@2core(--lcores='6,(10-17)@(7,8))'       321085.98  298.59  307.47
16thread@4core(--lcores='6,(20-35)@(7-10))'     1900705.61 575.35  678.29
32thread@4core(--lcores='6,(20-51)@(7-10))'     5510445.85 2164.36 2714.12

i686 @ Intel(R) Xeon(R) Platinum 8160 CPU @ 2.10GHz
DEQ+ENQ average cycles/obj

                                                MP/MC      HTS     RTS
1thread@1core(--lcores=6-7)                     7.85       12.13   11.31
2thread@2core(--lcores=6-8)                     17.89      24.52   21.86
8thread@8core(--lcores=6-14)                    32.58      354.20  54.58
32thread/@32core(--lcores='6-22,55-70')         813.77     6072.41 2169.91

2thread@1core(--lcores='6,(10-11)@7'            16095.00   36.06   34.74
8thread@2core(--lcores='6,(10-13)@7,(20-23)@8'  1140354.54 346.61  361.57
16thread@2core(--lcores='6,(10-17)@7,(20-27)@8' 1920417.86 1314.90 1416.65

8thread@2core(--lcores='6,(10-17)@(7,8))'       594358.61  332.70  357.74
32thread@4core(--lcores='6,(20-51)@(7-10))'     5319896.86 2836.44 3028.87

Konstantin Ananyev (9):
  test/ring: add contention stress test
  ring: prepare ring to allow new sync schemes
  ring: introduce RTS ring mode
  test/ring: add contention stress test for RTS ring
  ring: introduce HTS ring mode
  test/ring: add contention stress test for HTS ring
  ring: introduce peek style API
  test/ring: add stress test for MT peek API
  ring: add C11 memory model for new sync modes

 app/test/Makefile                      |   5 +
 app/test/meson.build                   |   5 +
 app/test/test_pdump.c                  |   6 +-
 app/test/test_ring_hts_stress.c        |  32 ++
 app/test/test_ring_mpmc_stress.c       |  31 ++
 app/test/test_ring_peek_stress.c       |  43 +++
 app/test/test_ring_rts_stress.c        |  32 ++
 app/test/test_ring_stress.c            |  57 ++++
 app/test/test_ring_stress.h            |  38 +++
 app/test/test_ring_stress_impl.h       | 444 +++++++++++++++++++++++++
 devtools/libabigail.abignore           |   7 +
 lib/librte_pdump/rte_pdump.c           |   2 +-
 lib/librte_port/rte_port_ring.c        |  12 +-
 lib/librte_ring/Makefile               |  11 +-
 lib/librte_ring/meson.build            |  11 +-
 lib/librte_ring/rte_ring.c             | 114 ++++++-
 lib/librte_ring/rte_ring.h             | 244 ++++++++++++--
 lib/librte_ring/rte_ring_c11_mem.h     |  44 +++
 lib/librte_ring/rte_ring_elem.h        | 105 +++++-
 lib/librte_ring/rte_ring_generic.h     |  48 +++
 lib/librte_ring/rte_ring_hts.h         | 214 ++++++++++++
 lib/librte_ring/rte_ring_hts_c11_mem.h | 222 +++++++++++++
 lib/librte_ring/rte_ring_hts_elem.h    | 209 ++++++++++++
 lib/librte_ring/rte_ring_hts_generic.h | 235 +++++++++++++
 lib/librte_ring/rte_ring_peek.h        | 379 +++++++++++++++++++++
 lib/librte_ring/rte_ring_rts.h         | 320 ++++++++++++++++++
 lib/librte_ring/rte_ring_rts_c11_mem.h | 198 +++++++++++
 lib/librte_ring/rte_ring_rts_elem.h    | 209 ++++++++++++
 lib/librte_ring/rte_ring_rts_generic.h | 210 ++++++++++++
 29 files changed, 3431 insertions(+), 56 deletions(-)
 create mode 100644 app/test/test_ring_hts_stress.c
 create mode 100644 app/test/test_ring_mpmc_stress.c
 create mode 100644 app/test/test_ring_peek_stress.c
 create mode 100644 app/test/test_ring_rts_stress.c
 create mode 100644 app/test/test_ring_stress.c
 create mode 100644 app/test/test_ring_stress.h
 create mode 100644 app/test/test_ring_stress_impl.h
 create mode 100644 lib/librte_ring/rte_ring_hts.h
 create mode 100644 lib/librte_ring/rte_ring_hts_c11_mem.h
 create mode 100644 lib/librte_ring/rte_ring_hts_elem.h
 create mode 100644 lib/librte_ring/rte_ring_hts_generic.h
 create mode 100644 lib/librte_ring/rte_ring_peek.h
 create mode 100644 lib/librte_ring/rte_ring_rts.h
 create mode 100644 lib/librte_ring/rte_ring_rts_c11_mem.h
 create mode 100644 lib/librte_ring/rte_ring_rts_elem.h
 create mode 100644 lib/librte_ring/rte_ring_rts_generic.h

-- 
2.17.1