io_uring: add napi busy polling support
Subsystems (3)
v6 cover io_uring: add napi busy polling support
From: Stefan Roesch <[email protected]>
This adds the napi busy polling support in io_uring.c. It adds a new napi_list to the io_ring_ctx structure. This list contains the list of napi_id's that are currently enabled for busy polling. This list is used to determine which napi id's enabled busy polling. For faster access it also adds a hash table.
When a new napi id is added, the hash table is used to locate if the napi id has already been added. When processing the busy poll loop the list is used to process the individual elements.
io-uring allows specifying two parameters:
- busy poll timeout and
- prefer busy poll to call of io_napi_busy_loop()
This sets the above parameters for the ring. The settings are passed with a new structure io_uring_napi.
There is also a corresponding liburing patch series, which enables this feature. The name of the series is "liburing: add add api for napi busy poll timeout". It also contains two programs to test the this.
Testing has shown that the round-trip times are reduced to 38us from 55us by enabling napi busy polling with a busy poll timeout of 100us. More detailled results are part of the commit message of the first patch.
Changes:
- V6:
- Add a hash table on top of the list for faster access during the add operation. The linked list and the hash table use the same data structure
- V5:
- Refreshed to 6.1-rc6
- Use copy_from_user instead of memdup/kfree
- Removed the moving of napi_busy_poll_to
- Return -EINVAL if any of the reserved or padded fields are not 0.
- V4:
- Pass structure for napi config, instead of individual parameters
- V3:
- Refreshed to 6.1-rc5
- Added a new io-uring api for the prefer napi busy poll api and wire it to io_napi_busy_loop().
- Removed the unregister (implemented as register)
- Added more performance results to the first commit message.
- V2:
- Add missing defines if CONFIG_NET_RX_BUSY_POLL is not defined
- Changes signature of function io_napi_add_list to static inline if CONFIG_NET_RX_BUSY_POLL is not defined
- define some functions as static
Stefan Roesch (3):
io_uring: add napi busy polling support
io_uring: add api to set / get napi configuration.
io_uring: add api to set napi prefer busy poll
include/linux/io_uring_types.h | 10 ++ include/uapi/linux/io_uring.h | 12 ++ io_uring/io_uring.c | 300 +++++++++++++++++++++++++++++++++ io_uring/napi.h | 23 +++ io_uring/poll.c | 2 + io_uring/sqpoll.c | 17 ++ 6 files changed, 364 insertions(+) create mode 100644 io_uring/napi.h
base-commit: c0b67534c95c537f7a506a06b98e5e85d72e2b7d
Signature · 1 line
2.30.2
PATCH v6 1/3 io_uring: add napi busy polling support
This adds the napi busy polling support in io_uring.c. It adds a new napi_list to the io_ring_ctx structure. This list contains the list of napi_id's that are currently enabled for busy polling. The list is synchronized by the new napi_lock spin lock. The current default napi busy polling time is stored in napi_busy_poll_to. If napi busy polling is not enabled, the value is 0.
In addition there is also a hash table. The hash table store the napi id ond the pointer to the above list nodes. The hash table is used to speed up the lookup to the list elements.
The NAPI_TIMEOUT is stored as a timeout to make sure that the time a napi entry is stored in the napi list is limited.
The busy poll timeout is also stored as part of the io_wait_queue. This is necessary as for sq polling the poll interval needs to be adjusted and the napi callback allows only to pass in one value.
This has been tested with two simple programs from the liburing library
repository: the napi client and the napi server program. The client sends a request, which has a timestamp in its payload and the server replies with the same payload. The client calculates the roundtrip time and stores it to calcualte the results.
The client is running on host1 and the server is running on host 2 (in the same rack). The measured times below are roundtrip times. They are average times over 5 runs each. Each run measures 1 million roundtrips.
no rx coal rx coal: frames=88,usecs=33
Default 57us 56us
client_poll=100us 47us 46us
server_poll=100us 51us 46us
client_poll=100us+ 40us 40us
server_poll=100us
client_poll=100us+ 41us 39us
server_poll=100us+
prefer napi busy poll on client
client_poll=100us+ 41us 39us
server_poll=100us+
prefer napi busy poll on server
client_poll=100us+ 41us 39us
server_poll=100us+
prefer napi busy poll on client + server
--- include/linux/io_uring_types.h | 10 ++ io_uring/io_uring.c | 241 +++++++++++++++++++++++++++++++++ io_uring/napi.h | 23 ++++ io_uring/poll.c | 2 + io_uring/sqpoll.c | 17 +++ 5 files changed, 293 insertions(+) create mode 100644 io_uring/napi.h
include/linux/io_uring_types.h +10 -0
@@ -2,6 +2,7 @@#define IO_URING_TYPES_H #include <linux/blkdev.h> +#include <linux/hashtable.h> #include <linux/task_work.h> #include <linux/bitmap.h> #include <linux/llist.h>
@@ -274,6 +275,15 @@ struct io_ring_ctx {struct xarray personalities;u32 pers_next; +#ifdef CONFIG_NET_RX_BUSY_POLL +struct list_head napi_list;/* track busy poll napi_id */ +DECLARE_HASHTABLE (napi_ht,8 ); +spinlock_t napi_lock;/* napi_list lock */ + +unsigned int napi_busy_poll_to;/* napi busy poll default timeout */ +bool napi_prefer_busy_poll; +#endif +struct {/* * We cache a range of free CQEs we can use, once exhausted it
io_uring/io_uring.c +241 -0
295 lines not on this page · raw message
io_uring/napi.h new file +23 -0
@@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef IOU_NAPI_H +#define IOU_NAPI_H + +#include <linux/kernel.h> +#include <linux/io_uring.h> +#include <net/busy_poll.h> + +#ifdef CONFIG_NET_RX_BUSY_POLL + +void io_napi_add (struct file *file,struct io_ring_ctx *ctx); +bool io_napi_busy_loop (struct list_head *napi_list,bool prefer_busy_poll); +void io_napi_merge_lists (struct io_ring_ctx *ctx,struct list_head *napi_list); + +#else + +static inline void io_napi_add (struct file *file,struct io_ring_ctx *ctx) +{ +} + +#endif +#endif
io_uring/poll.c +2 -0
@@ -15,6 +15,7 @@#include "io_uring.h" #include "refs.h" +#include "napi.h" #include "opdef.h" #include "kbuf.h" #include "poll.h"
@@ -629,6 +630,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,__io_poll_execute (req, mask);return 0 ; } +io_napi_add (req->file, req->ctx);if (ipt->owning) {/*
io_uring/sqpoll.c +17 -0
@@ -15,6 +15,7 @@#include <uapi/linux/io_uring.h> #include "io_uring.h" +#include "napi.h" #include "sqpoll.h" #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
@@ -168,6 +169,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) {unsigned int to_submit;int ret =0 ; +#ifdef CONFIG_NET_RX_BUSY_POLL +LIST_HEAD (local_napi_list); +#endif to_submit =io_sqring_entries (ctx);/* if we're handling multiple rings, cap submit size for fairness */
@@ -193,6 +197,19 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) ret =io_submit_sqes (ctx, to_submit);mutex_unlock (&ctx->uring_lock); +#ifdef CONFIG_NET_RX_BUSY_POLL +spin_lock (&ctx->napi_lock); +list_splice_init (&ctx->napi_list, &local_napi_list); +spin_unlock (&ctx->napi_lock); + +if (!list_empty (&local_napi_list) && +READ_ONCE (ctx->napi_busy_poll_to) >0 && +io_napi_busy_loop (&local_napi_list, ctx->napi_prefer_busy_poll)) { +io_napi_merge_lists (ctx, &local_napi_list); + ++ret; + } +#endif +if (to_submit &&wq_has_sleeper (&ctx->sqo_sq_wait))wake_up (&ctx->sqo_sq_wait);if (creds)
Signature · 1 line
2.30.2
PATCH v6 2/3 io_uring: add api to set / get napi configuration.
In reply to Stefan RoeschThis adds an api to register the busy poll timeout from liburing. To be able to use this functionality, the corresponding liburing patch is needed.
--- include/uapi/linux/io_uring.h | 11 +++++++ io_uring/io_uring.c | 55 +++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+)
include/uapi/linux/io_uring.h +11 -0
@@ -516,6 +516,10 @@ enum {/* register a range of fixed file slots for automatic slot allocation */ IORING_REGISTER_FILE_ALLOC_RANGE =25 , +/* set/clear busy poll settings */ +IORING_REGISTER_NAPI =26 , +IORING_UNREGISTER_NAPI =27 , +/* this goes last */ IORING_REGISTER_LAST };
@@ -638,6 +642,13 @@ struct io_uring_buf_reg {__u64 resv[3 ]; }; +/* argument for IORING_(UN)REGISTER_NAPI */ +struct io_uring_napi { +__u32 busy_poll_to; +__u32 pad; +__u64 resv; +}; +/* * io_uring_restriction->opcode values */
io_uring/io_uring.c +55 -0
67 lines not on this page · raw message
Signature · 1 line
2.30.2
Re: [PATCH v6 2/3] io_uring: add api to set / get napi configuration.
Quoted 8 lines · Stefan Roesch
io_uring/io_uring.c +8
-0+static int io_unregister_napi (struct io_ring_ctx *ctx,void __user *arg) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL +const struct io_uring_napi curr = { + .busy_poll_to = ctx->napi_busy_poll_to, + }; + +if (arg) {
io_uring/io_uring.c static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, · line 4290
Quoted 10 lines
io_uring/io_uring.c +10
-0+if (copy_to_user (arg, &curr,sizeof (curr))) + return -EFAULT; + } + +WRITE_ONCE (ctx->napi_busy_poll_to,0 ); +return 0 ; +#else +return -EINVAL ; +#endif +}
Just to follow the common pattern when a feature is not enabled the return value is -EOPNOTSUPP instead of -EINVAL. What do you think?
io_uring/io_uring.c static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, · line 4461
Quoted 6 lines
io_uring/io_uring.c +6
-0+case IORING_UNREGISTER_NAPI : + ret = -EINVAL ; +if (!arg) +break ; + ret =io_unregister_napi (ctx, arg); +break ;
This needs to be corrected. If the @arg var is NULL, you return -EINVAL. So io_unregister_napi() will always have @arg != NULL. This @arg check should go, allow the user to pass a NULL pointer to it.
Our previous agreement on this API is to allow the user to pass a NULL pointer in case the user doesn't care about the old value.
Also, having a liburing test case that verifies this behavior would be excellent.
Signature · 1 line
Ammar Faizi
Re: [PATCH v6 2/3] io_uring: add api to set / get napi configuration.
Quoted 14 lines · Ammar Faizi
Quoted 13 lines · Stefan Roesch
io_uring/io_uring.c +13
-0+static int io_unregister_napi (struct io_ring_ctx *ctx,void __user *arg) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL +const struct io_uring_napi curr = { + .busy_poll_to = ctx->napi_busy_poll_to, + }; + +if (arg) { +if (copy_to_user (arg, &curr,sizeof (curr))) +return -EFAULT ; + } + +WRITE_ONCE (ctx->napi_busy_poll_to,0 );
Quoted 9 lines
io_uring/io_uring.c static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, · line 4271
Quoted 5 lines
io_uring/io_uring.c +5
-0+return 0 ; +#else +return -EINVAL ; +#endif +}Just to follow the common pattern when a feature is not enabled the return value is
-EOPNOTSUPPinstead of-EINVAL. What do you think?
Sounds good, I'll return -EOPNOTSUPP when CONFIG_NET_RX_BUSY_POLL is not enabled. I'll make the change for the register and the unregister function.
Quoted 11 lines
io_uring/io_uring.c static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, · line 4461
Quoted 6 lines
io_uring/io_uring.c +6
-0+case IORING_UNREGISTER_NAPI : + ret = -EINVAL ; +if (!arg) +break ; + ret =io_unregister_napi (ctx, arg); +break ;This needs to be corrected. If the @arg var is NULL, you return
-EINVAL. Soio_unregister_napi()will always have @arg != NULL. This @arg check should go, allow the user to pass a NULL pointer to it.
Quoted 6 lines
Our previous agreement on this API is to allow the user to pass a NULL pointer in case the user doesn't care about the old value.
Also, having a liburing test case that verifies this behavior would be excellent.
I'll remove the check for the arg parameter. In addition I will output the busy poll timeout and the prefer busy poll setting in the client example program if one of the settings has been enabled.
PATCH v6 3/3 io_uring: add api to set napi prefer busy poll
In reply to Stefan RoeschThis adds an api to register and unregister the napi prefer busy poll setting from liburing. To be able to use this functionality, the corresponding liburing patch is needed.
--- include/uapi/linux/io_uring.h | 3 ++- io_uring/io_uring.c | 6 +++++- 2 files changed, 7 insertions(+), 2 deletions(-)
include/uapi/linux/io_uring.h +2 -1
@@ -645,7 +645,8 @@ struct io_uring_buf_reg {/* argument for IORING_(UN)REGISTER_NAPI */ struct io_uring_napi {__u32 busy_poll_to; -__u32 pad; +__u8 prefer_busy_poll; +__u8 pad[3 ];__u64 resv; };
io_uring/io_uring.c +5 -1
@@ -4251,15 +4251,17 @@ static int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)#ifdef CONFIG_NET_RX_BUSY_POLL const struct io_uring_napi curr = { .busy_poll_to = ctx->napi_busy_poll_to, + .prefer_busy_poll = ctx->napi_prefer_busy_poll };struct io_uring_napi napi;if (copy_from_user (&napi, arg,sizeof (napi)))return -EFAULT ; -if (napi.pad || napi.resv) +if (napi.pad[0 ] || napi.pad[1 ] || napi.pad[2 ] || napi.resv)return -EINVAL ;WRITE_ONCE (ctx->napi_busy_poll_to, napi.busy_poll_to); +WRITE_ONCE (ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);if (copy_to_user (arg, &curr,sizeof (curr)))return -EFAULT ;
@@ -4275,6 +4277,7 @@ static int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)#ifdef CONFIG_NET_RX_BUSY_POLL const struct io_uring_napi curr = { .busy_poll_to = ctx->napi_busy_poll_to, + .prefer_busy_poll = ctx->napi_prefer_busy_poll };if (arg) {
@@ -4283,6 +4286,7 @@ static int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) }WRITE_ONCE (ctx->napi_busy_poll_to,0 ); +WRITE_ONCE (ctx->napi_prefer_busy_poll, false);return 0 ;#else return -EINVAL ;
Signature · 1 line
2.30.2