diff options
| author |   Jens Axboe <axboe@kernel.dk> | 2022-03-10 12:59:35 -0700 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2022-03-10 13:05:25 -0700 |
| commit | bcbb7bf6ccde7cb969a5642879832bc84ebf06a3 (patch) | |
| tree | 18a39891555fe3acd6b4197fd097f10745777b4b /tools/perf/scripts/python/export-to-postgresql.py | |
| parent | io_uring: recycle provided buffers if request goes async (diff) | |
| download | wireguard-linux-bcbb7bf6ccde7cb969a5642879832bc84ebf06a3.tar.xz wireguard-linux-bcbb7bf6ccde7cb969a5642879832bc84ebf06a3.zip | |
io_uring: allow submissions to continue on error
By default, io_uring will stop submitting a batch of requests if we run
into an error submitting a request. This isn't strictly necessary, as
the error result is passed out-of-band via a CQE anyway. And it can be
a bit confusing for some applications.
Provide a way to setup a ring that will continue submitting on error,
when the error CQE has been posted.
There's still one case that will break out of submission. If we fail
allocating a request, then we'll still return -ENOMEM. We could in theory
post a CQE for that condition too even if we never got a request. Leave
that for a potential followup.
Reported-by: Dylan Yudaken <dylany@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'tools/perf/scripts/python/export-to-postgresql.py')
0 files changed, 0 insertions, 0 deletions