Re: Unneeded Code Found??

[Nick Piggin <piggin@cyberone.com.au>]

Randy Appleton wrote:

> Bill Davidsen wrote:
>
>> Randy Appleton wrote:
>>
>>> I think I have found some useless code in the Linux kernel
>>> in the block request functions.
>>>                                                                                         
>>>
>>> I have modified the __make_request function in ll_rw_blk.c.
>>> Now every request for a block off the hard drive is logged.
>>>                                                                                         
>>>
>>> The function __make_request has code to attempt to merge the current
>>> block request with some contigious existing request for better
>>> performance. This merge function keeps a one-entry cache pointing to 
>>> the
>>> last block request made.  An attempt is made to merge the current
>>> request with the last request, and if that is not possible then
>>> a search of the whole queue is done, looking at merger possibililites.
>>>                                                                                         
>>>
>>> Looking at the data from my logs, I notice that over 50% of all 
>>> requests
>>> can be merged.  However, a merge only ever happens between the
>>> current request and the previous one.  It never happens between the
>>> current request and any other request that might be in the queue (for
>>> more than 50,000 requests examined).
>>>                                                                                         
>>>
>>> This is true for several test runs, including "daily usage" and doing
>>> two kernel compiles at the same time.  I have only tested on a
>>> single-CPU machine.
>>>                                                                                         
>>>
>>> I wonder if the code (and CPU time) used to search the entire request
>>> queue is actually useful.  Would this be a reasonable candidate for 
>>> code
>>> elimination?
>>
>>
>>
>> If you never get a hit, it means either (a) your test load actually 
>> doesn't have one, or (b) the code isn't correctly finding them.
>
>
>
> It might be buggy code on my part, but it looks pretty solid to me.   
> I'd be happy to show anyone interested.
> My load ought to find such a merge, if they happen with any freqency 
> at all.  Compiling two kernels
> at the same time and "general running" are my two current loads.  The 
> disk queue gets to over 70
> entries, which is rather high for a personal workstation, and I'm 
> searching tens of thousands to accesses
> in total.
>
> Does anyone know that this code is actualy useful?  Has anyone ever 
> seen it actually do a merge of consecutive
> data accesses for requests that were not issued themselves consequtively?
>

Yes it gets used.

I think its a lot more common with direct io and when you have lots of
processes.