Jump to content

Io uring: Difference between revisions

Edit links
From Wikipedia, the free encyclopedia
Browse history interactively
← Previous editNext edit →
Content deleted Content added
VisualWikitext
No edit summary
No edit summary
Line 3: Line 3:
'''io_uring''' (previously known as '''aioring''') is a [[Linux kernel]] [[system call]] interface for storage device [[asynchronous I/O]] operations supposed to address performance issues with similar interfaces provided by functions like {{Code|read()}}/{{Code|write()}} or {{Code|aio_read()}}/{{Code|aio_write()}} etc. for [[File operation|operation]]<nowiki/>s on data accessed by [[file descriptor]]<nowiki/>s.<ref name="Axboe2019" /><ref>{{Cite web|last=Axboe|first=Jens|date=October 15, 2019|title=Efficient IO with io_uring|url=https://kernel.dk/io_uring.pdf|url-status=live}}</ref>{{Rp|page=2}} It has been primarily developed by [[Jens Axboe]] at Facebook.<ref name="Axboe2019" />
'''io_uring''' (previously known as '''aioring''') is a [[Linux kernel]] [[system call]] interface for storage device [[asynchronous I/O]] operations supposed to address performance issues with similar interfaces provided by functions like {{Code|read()}}/{{Code|write()}} or {{Code|aio_read()}}/{{Code|aio_write()}} etc. for [[File operation|operation]]<nowiki/>s on data accessed by [[file descriptor]]<nowiki/>s.<ref name="Axboe2019" /><ref>{{Cite web|last=Axboe|first=Jens|date=October 15, 2019|title=Efficient IO with io_uring|url=https://kernel.dk/io_uring.pdf|url-status=live}}</ref>{{Rp|page=2}} It has been primarily developed by [[Jens Axboe]] at Facebook.<ref name="Axboe2019" />


Internally it works by creating two buffers dubbed as "queue rings" ([[circular buffer]]<nowiki/>s) for storage of submission and completion of I/O requests (for storage devices, submission queue (SQ) and completion queue (CQ) respectively).<ref name=":1">{{Cite web|title=Getting Hands-on with io_uring using Go|url=https://developers.mattermost.com/blog/hands-on-iouring-go/|access-date=2021-11-20|website=developers.mattermost.com|language=en-us}}</ref> Most importantly, keeping these buffers shared between the kernel and application helps to boost the [[IOPS|I/O performance]] by eliminating the need to issue extra and expensive system calls to copy these buffers between the two.<ref name="Axboe2019">{{Cite web|title=Linux Kernel Getting io_uring To Deliver Fast & Efficient I/O - Phoronix|url=https://www.phoronix.com/scan.php?page=news_item&px=Linux-io_uring-Fast-Efficient|url-status=live|access-date=2021-03-14|website=[[Phoronix]]}}</ref><ref name=":0">{{Cite web|title=The rapid growth of io_uring [LWN.net]|url=https://lwn.net/Articles/810414/|access-date=2021-11-20|website=lwn.net}}</ref><ref name=":1" /> According to the io_ring design paper, the SQ buffer is writable only by consumer application, and CQ - by kernel.{{R|name=Axboe2019|page=3}}
Internally it works by creating two buffers dubbed as "queue rings" ([[circular buffer]]<nowiki/>s) for storage of submission and completion of I/O requests (for storage devices, submission queue (SQ) and completion queue (CQ) respectively).<ref name=":1">{{Cite web|title=Getting Hands-on with io_uring using Go|url=https://developers.mattermost.com/blog/hands-on-iouring-go/|access-date=2021-11-20|website=developers.mattermost.com|language=en-us}}</ref> Most importantly, keeping these buffers shared between the kernel and application helps to boost the [[IOPS|I/O performance]] by eliminating the need to issue extra and expensive system calls to copy these buffers between the two.<ref name="Axboe2019">{{Cite web|title=Linux Kernel Getting io_uring To Deliver Fast & Efficient I/O - Phoronix|url=https://www.phoronix.com/scan.php?page=news_item&px=Linux-io_uring-Fast-Efficient|url-status=live|access-date=2021-03-14|website=[[Phoronix]]}}</ref><ref name=":0">{{Cite web|title=The rapid growth of io_uring [LWN.net]|url=https://lwn.net/Articles/810414/|access-date=2021-11-20|website=lwn.net}}</ref><ref name=":1" /> According to the io_uring design paper, the SQ buffer is writable only by consumer application, and CQ - by kernel.{{R|name=Axboe2019|page=3}}


The API provided by {{Code|liburing}} library for userspace (applications) can be used to interact with the kernel interface more easily.<ref name="Axboe2019" />{{R|name=Axboe2019|page=12}}
The API provided by {{Code|liburing}} library for userspace (applications) can be used to interact with the kernel interface more easily.<ref name="Axboe2019" />{{R|name=Axboe2019|page=12}}

Revision as of 10:21, 23 November 2021

io_uring (previously known as aioring) is a Linux kernel system call interface for storage device asynchronous I/O operations supposed to address performance issues with similar interfaces provided by functions like read()/write() or aio_read()/aio_write() etc. for operations on data accessed by file descriptors.[1][2]: 2  It has been primarily developed by Jens Axboe at Facebook.[1]

Internally it works by creating two buffers dubbed as "queue rings" (circular buffers) for storage of submission and completion of I/O requests (for storage devices, submission queue (SQ) and completion queue (CQ) respectively).[3] Most importantly, keeping these buffers shared between the kernel and application helps to boost the I/O performance by eliminating the need to issue extra and expensive system calls to copy these buffers between the two.[1][4][3] According to the io_uring design paper, the SQ buffer is writable only by consumer application, and CQ - by kernel.[1]: 3 

The API provided by liburing library for userspace (applications) can be used to interact with the kernel interface more easily.[1][1]: 12 

Both kernel interface and library were adapted in Linux 5.1 kernel version.[1][4][5]

History

The Linux kernel had asynchronous I/O since version 2.5, but it was seen as difficult to use and inefficient.[6]

References

  1. ^ a b c d e f g "Linux Kernel Getting io_uring To Deliver Fast & Efficient I/O - Phoronix". Phoronix. Retrieved 2021-03-14.{{cite web}}: CS1 maint: url-status (link)
  2. ^ Axboe, Jens (October 15, 2019). "Efficient IO with io_uring" (PDF).{{cite web}}: CS1 maint: url-status (link)
  3. ^ a b "Getting Hands-on with io_uring using Go". developers.mattermost.com. Retrieved 2021-11-20.
  4. ^ a b "The rapid growth of io_uring [LWN.net]". lwn.net. Retrieved 2021-11-20.
  5. ^ "Faster IO through io_uring | Kernel Recipes 2019". Retrieved 2021-03-14.
  6. ^ Corbet, Jonathan. "Ringing in a new asynchronous I/O API". LWN.net. Retrieved 2021-03-14.{{cite web}}: CS1 maint: url-status (link)
  • Efficient I/O with io_uring, in-depth description of motivation behind io_uring, interface (data structures etc.), and performance assessment


Retrieved from "https://en.wikipedia.org/enwiki/w/index.php?title=Io_uring&oldid=1056755082"