Re: [rfc][patch] remove racy sync_page?

[Nick Piggin <nickpiggin@yahoo.com.au>]

Nick Piggin wrote:
> Linus Torvalds wrote:
> 
>> Tell me WHERE you can unplug in that sequence. I will tell you where 
>> you can NOT unplug:
> 
> 
> ...
> 
>>  - you can NOT just unplug in the path _after_ "readpage()", because 
>> the    IO may have been started by SOMEBODY ELSE that just did 
>> read-ahead, and    didn't unplug (on _purpose_ - the whole point of 
>> doing read-ahead is to    allow concurrent IO execution, so a 
>> read-aheader that unplugs is broken    by definition)
> 
> 
> Umm, this happens with the current lock_page() after readpage. And
> with per-task plugs, you do not unplug anybody else.

If this wasn't clear: I don't mean per-task plugs as in "the task
explicitly plugs and unplugs the block device"[*]; I mean really
per-task plugs.

[*] That would be crazy anyway because that would imply some random
     task can plug an filled request queue that is going full tilt.

-- 
SUSE Labs, Novell Inc.
Send instant messages to your online friends http://au.messenger.yahoo.com