Re: calculating optimal chunk size for Linux software-RAID

[Stan Hoeppner <stan@hardwarefreak.com>]

On 3/7/2014 9:15 PM, Martin T wrote:
> Stan,
> 
> ok, I see. However, are there utilities out there which help one to
> analyze how applications on a server use the file-system over the time
> and help to make an educated decision regarding the chunk size?

My apologies.  You're a complete novice and I'm leading you down the
textbook storage architectural design path.  Let's short circuit that as
I don't have the time.

As you're starting from zero, let me give you what works best with 99%
of workloads.  Use a chunk size of 32KB or 64KB.  Such a chunk will work
extremely well with any singular or mixed workloads, on parity and
non-parity RAID.  The only workload that should have a significantly
larger chunk than this is a purely streaming allocation workload of
large files.

If you want a more technical explanation, you can read all of my
relevant posts in the linux-raid or XFS archives, as I've explained this
hundreds of times in great detail.  Or you can wait a few months to read
the kernel documentation I'm working on, which will teach the reader the
formal storage stack design process, soup to nuts.  I wish it was
already finished, as I could simply paste the link for you, which,
coincidentally, is the exact reason I'm writing it. :)



> regards,
> Martin
> 
> On Fri, Mar 7, 2014 at 11:58 PM, Stan Hoeppner <stan@hardwarefreak.com> wrote:
>> On 3/6/2014 8:06 PM, Martin T wrote:
>>> Am I correct that optimal chunk size is usually the size of the
>>> average file read/written to disk divided by number of block devices
>>> in RAID array storing the data? For example if the average file size
>>> is 1024KiB and I have four disks in RAID1, then I should choose the
>>> chunk size around 256KiB to get the optimal read performance? Or if I
>>> have two drives in RAID0, then I should choose the chunk size 512KiB
>>> instead? Or are there better methods/benchmarks to determine the
>>> optimal chunk size for software-RAID?
>>
>> You're asking the wrong question.  Storage architecture design always
>> begins with the workload.  The correct question is:
>>
>> My workload (application mix) performs *most* IO in manner X, where X is
>>
>> 1.  large streaming write/read
>> 2.  small file write/read
>> 3.  metadata heavy
>>
>> I have Y number of disk drives.  I plan to use XFS/EXT4/etc filesystem.
>>  What RAID level and chunk size are optimal for my workload, and how do
>> I properly tune my filesystem to my workload and storage stack?
>>
>>> Last but not least, is there a
>>> good utility which could help one to measure the average I/O
>>> read/write size?
>>
>> In flight IO size has no correlation to stripe and chunk size.  What you
>> need to know is how your application(s) write to the filesystem and how
>> your filesystem issues write IOs.  You should already know that the
>> former, and it's easy to determine the latter.

-- 
Stan