Re: Syslets, Threadlets, generic AIO support, v6

From: Ingo Molnar <mingo@xxxxxxx>
Date: Wed, 30 May 2007 09:20:55 +0200

* Jeff Garzik <jeff@xxxxxxxxxx> wrote:

You should pick up the kevent work :)

3 months ago i verified the published kevent vs. epoll benchmark and
found that benchmark to be fatally flawed. When i redid it properly
kevent showed no significant advantage over epoll. Note that i did those
measurements _before_ the recent round of epoll speedups. So unless
someone does believable benchmarks i consider kevent an over-hyped,
mis-benchmarked complication to do something that epoll is perfectly
capable of doing.

Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Follow-Ups:
- Re: Syslets, Threadlets, generic AIO support, v6
  - From: Jeff Garzik
- Re: Syslets, Threadlets, generic AIO support, v6
  - From: Evgeniy Polyakov
- Re: Syslets, Threadlets, generic AIO support, v6
  - From: Ulrich Drepper

References:
- Syslets, Threadlets, generic AIO support, v6
  - From: Zach Brown
- Re: Syslets, Threadlets, generic AIO support, v6
  - From: Jeff Garzik

Prev by Date: Re: [PATCH 05/10] Containers(V10): Add container_clone() interface
Next by Date: Re: [PATCH 01/10] Containers(V10): Basic container framework
Previous by thread: Re: Syslets, Threadlets, generic AIO support, v6
Next by thread: Re: Syslets, Threadlets, generic AIO support, v6
Index(es):
- Date
- Thread

Relevant Pages

Re: Syslets, Threadlets, generic AIO support, v6
... found that benchmark to be fatally flawed. ... kevent showed no significant advantage over epoll. ... Event rings most closely match what is going on in the hardware ...
(Linux-Kernel)
Re: Syslets, Threadlets, generic AIO support, v6
... found that benchmark to be fatally flawed. ... kevent showed no significant advantage over epoll. ...
(Linux-Kernel)
Re: Syslets, Threadlets, generic AIO support, v6
... months ago i verified the published kevent vs. epoll benchmark and found that benchmark to be fatally flawed. ... When i redid it properly kevent showed no significant advantage over epoll. ... Event rings most closely match what is going on in the hardware and often closely match what is going on in multi-socket, ...
(Linux-Kernel)
Re: [patch 00/13] Syslets, "Threadlets", generic AIO support, v3
... "Threadlets are bad for IO because kevent is 2 times faster than epoll?" ... mlocked userspace buffer, or some kernel pages mapped to userspace. ... you don't need to change the API by ...
(Linux-Kernel)
Re: [patch 00/13] Syslets, "Threadlets", generic AIO support, v3
... Kevent does not need that - if event is ... calls ->poll for each event and transfer it to userspace if it is ready. ... while in epoll() there are two queues. ... Using or not epoll has nearly zero cost over standard kernel (only struct file ...
(Linux-Kernel)