mbox series

[for-next,00/11] RDMA/rxe: Various fixes and cleanups

Message ID 20240326174325.300849-2-rpearsonhpe@gmail.com (mailing list archive)
Headers show
Series RDMA/rxe: Various fixes and cleanups | expand

Message

Bob Pearson March 26, 2024, 5:43 p.m. UTC
This series of patches is the result of high scale testing on a large
HPC system with a large attached Lustre file system. Several errors
were found which had not been previously seen at smaller scales. In
this case up to 1600 QPs on 1024 compute nodes attached to about 100
flash storage nodes. Each patch has it's own description.

Bob Pearson (11):
  RDMA/rxe: Fix seg fault in rxe_comp_queue_pkt
  RDMA/rxe: Allow good work requests to be executed
  RDMA/rxe: Remove redundant scheduling of rxe_completer
  RDMA/rxe: Merge request and complete tasks
  RDMA/rxe: Remove save/rollback_state in rxe_requester
  RDMA/rxe: Don't schedule rxe_completer() in rxe_requester()
  RDMA/rxe: Don't call rxe_requester from rxe_completer
  RDMA/rxe: Don't call direct between tasks
  RDMA/rxe: Fix incorrect rxe_put in error path
  RDMA/rxe: Make rxe_loopback match rxe_send behavior
  RDMA/rxe: Get rid of pkt resend on err

 drivers/infiniband/sw/rxe/rxe_comp.c        | 34 ++++-----
 drivers/infiniband/sw/rxe/rxe_hw_counters.c |  2 +-
 drivers/infiniband/sw/rxe/rxe_hw_counters.h |  2 +-
 drivers/infiniband/sw/rxe/rxe_loc.h         |  3 +-
 drivers/infiniband/sw/rxe/rxe_net.c         | 22 +++---
 drivers/infiniband/sw/rxe/rxe_qp.c          | 44 +++++-------
 drivers/infiniband/sw/rxe/rxe_req.c         | 80 ++++++---------------
 drivers/infiniband/sw/rxe/rxe_resp.c        | 14 +---
 drivers/infiniband/sw/rxe/rxe_verbs.c       | 17 +++--
 drivers/infiniband/sw/rxe/rxe_verbs.h       |  6 +-
 10 files changed, 81 insertions(+), 143 deletions(-)

Comments

Zhu Yanjun March 26, 2024, 7:01 p.m. UTC | #1
在 2024/3/26 18:43, Bob Pearson 写道:
> This series of patches is the result of high scale testing on a large
> HPC system with a large attached Lustre file system. Several errors
> were found which had not been previously seen at smaller scales. In
> this case up to 1600 QPs on 1024 compute nodes attached to about 100
> flash storage nodes. Each patch has it's own description.

Thanks a lot. I never thought that RXE can act as an important role in a 
system up to 1600 QPs on 1024 compute nodes attached to about 100
flash storage nodes.

It is my honor to review these patches.

Thanks Bob for sharing these patches.

Zhu Yanjun

> 
> Bob Pearson (11):
>    RDMA/rxe: Fix seg fault in rxe_comp_queue_pkt
>    RDMA/rxe: Allow good work requests to be executed
>    RDMA/rxe: Remove redundant scheduling of rxe_completer
>    RDMA/rxe: Merge request and complete tasks
>    RDMA/rxe: Remove save/rollback_state in rxe_requester
>    RDMA/rxe: Don't schedule rxe_completer() in rxe_requester()
>    RDMA/rxe: Don't call rxe_requester from rxe_completer
>    RDMA/rxe: Don't call direct between tasks
>    RDMA/rxe: Fix incorrect rxe_put in error path
>    RDMA/rxe: Make rxe_loopback match rxe_send behavior
>    RDMA/rxe: Get rid of pkt resend on err
> 
>   drivers/infiniband/sw/rxe/rxe_comp.c        | 34 ++++-----
>   drivers/infiniband/sw/rxe/rxe_hw_counters.c |  2 +-
>   drivers/infiniband/sw/rxe/rxe_hw_counters.h |  2 +-
>   drivers/infiniband/sw/rxe/rxe_loc.h         |  3 +-
>   drivers/infiniband/sw/rxe/rxe_net.c         | 22 +++---
>   drivers/infiniband/sw/rxe/rxe_qp.c          | 44 +++++-------
>   drivers/infiniband/sw/rxe/rxe_req.c         | 80 ++++++---------------
>   drivers/infiniband/sw/rxe/rxe_resp.c        | 14 +---
>   drivers/infiniband/sw/rxe/rxe_verbs.c       | 17 +++--
>   drivers/infiniband/sw/rxe/rxe_verbs.h       |  6 +-
>   10 files changed, 81 insertions(+), 143 deletions(-)
>