RFC fast poll multishot mode
Get series with b4
b4 am [email protected]Versions newest first
- v1 RFC Latest6 patches 39 repliesIn review
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/6 | io_uring: enhance flush completion logicfs/ | +4 | 5 replies | |
| 2/6 | io_uring: add IORING_ACCEPT_MULTISHOT for acceptinclude/ | +4 | 0 replies | |
| 3/6 | io_uring: add REQ_F_APOLL_MULTISHOT for requestsfs/ | +3 | 0 replies | |
| 4/6 | io_uring: let fast poll support multishotfs/ | +12 | 13 replies | |
| 5/6 | io_uring: implement multishot mode for acceptfs/ | +29 | 3 replies | |
| 6/6 | io_uring: enable multishot mode for acceptfs/ | +12 | 17 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.
Cover letter [RFC 0/6] fast poll multishot mode
Let multishot support multishot mode, currently only add accept as its first comsumer.
theoretical analysis:
1) when connections come in fast
- singleshot:
add accept sqe(userpsace) --> accept inline
^ |
|-----------------|
- multishot:
add accept sqe(userspace) --> accept inline
^ |
|--*--|
we do accept repeatedly in * place until get EAGAIN 2) when connections come in at a low pressure
similar thing like 1), we reduce a lot of userspace-kernel context switch and useless vfs_poll()
tests:
Did some tests, which goes in this way:
server client(multiple) accept connect read write write read close close
Basically, raise up a number of clients(on same machine with server) to connect to the server, and then write some data to it, the server will write those data back to the client after it receives them, and then close the connection after write return. Then the client will read the data and then close the connection. Here I test 10000 clients connect one server, data size 128 bytes. And each client has a go routine for it, so they come to the server in short time.
test 20 times before/after this patchset, time spent:(unit cycle, which is the return value of clock())
before:
1930136+1940725+1907981+1947601+1923812+1928226+1911087+1905897+1941075 +1934374+1906614+1912504+1949110+1908790+1909951+1941672+1969525+1934984 +1934226+1914385)/20.0 = 1927633.75
after:
1858905+1917104+1895455+1963963+1892706+1889208+1874175+1904753+1874112 +1874985+1882706+1884642+1864694+1906508+1916150+1924250+1869060+1889506 +1871324+1940803)/20.0 = 1894750.45
(1927633.75 - 1894750.45) / 1927633.75 = 1.65%
Higher pressure like 10^5 connections causes problems since ports are in use.
I'll test the cancellation path and try to lift pressure to much high level to see if numbers get better. Sent this early for comments and suggestions.
Hao Xu (6):
io_uring: enhance flush completion logic
io_uring: add IORING_ACCEPT_MULTISHOT for accept
io_uring: add REQ_F_APOLL_MULTISHOT for requests
io_uring: let fast poll support multishot
io_uring: implement multishot mode for accept
io_uring: enable multishot mode for accept
fs/io_uring.c | 72 +++++++++++++++++++++++++++++------ include/uapi/linux/io_uring.h | 4 ++ 2 files changed, 64 insertions(+), 12 deletions(-)
Signature · 1 line
2.24.4