io_uring/zcrx: scale refilling with large pages

Browse source

io_zcrx_ring_refill() caps the loop by mixing the max number of
allocated netmems and the number of available RQEs together, which
caps the number of entries to process the pp cache size. As a result,
when niovs are heavily fragmented, the refilling logic allocates only a
small number of niovs per call on average and sometimes even none.

Keep a separate counter for the number of processed RQ entries, which is
capped by a roughly calculated from the page size value to keep the
cache full. And separately break if it allocates enough niovs.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://patch.msgid.link/143cf439299728759eb0a840c866363fe99293f0.1786108672.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

...

This commit is contained in:

Pavel Begunkov 2026-08-07 14:19:19 +01:00 • committed by Jens Axboe

parent 297b5ccea4

commit 1afcef59fe

1 changed files with 14 additions and 7 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

21

io_uring/zcrx.c

View file