Re: [Patch 5/7] synchronous block I/O delays

[Shailabh Nagar <nagar@watson.ibm.com>]

Arjan van de Ven wrote:

>>+static inline void delayacct_blkio(void)
>>+{
>>+	if (unlikely(current->delays && delayacct_on))
>>+		__delayacct_blkio();
>>+}
>>    
>>
>
>why is this unlikely?
>  
>
delayacct_on is expected to be off most of the time, hence the compound is
unlikely too.

>  
>
>>+	u64 blkio_delay;	/* wait for sync block io completion */
>>    
>>
>
>this misses O_SYNC, msync(), and general throttling.
>
Hmm, that it does :-(

>I get the feeling this is being measured at the wrong level
>currently.... since the number of entry points that needs measuring at
>the current level is hardly finite...
>  
>
Will take another look if it can be done elsewhere. Earlier was using 
io_schedule but that isn't
called from everywhere.

--Shailabh