Re: RAID performance - new kernel results - 5x SSD RAID5

[Phil Turmel <philip@turmel.org>]

On 03/03/2013 10:19 AM, Adam Goryachev wrote:
> Phil Turmel <philip@turmel.org> wrote:
> 
>> On 03/02/2013 04:15 AM, Stan Hoeppner wrote:
>>> On 3/1/2013 10:06 AM, Adam Goryachev wrote:
>>
>>>> 15) "Make sure all LVs are aligned to the underlying md device
>>>> geometry. This will eliminate any possible alignment issues."
>>>> What does this mean? The drive partitions are now aligned properly,
>>>> but how does LVM allocate the blocks for each LV, and how do I
>>>> ensure it does so optimally? How do I even check this?
>>>
>>> I'm not an LVM user so I can't give you command lines.  But what I
>>> can tell you follows, and it is somewhat critical to RMW performance,
>>> more for rust but also for SSD to a lesser degree.
>> Run "dmsetup table" and look at the start sectors for your volumes:
>> Fast-Root: 0 314572800 linear 9:3 3072
>> This volume starts at sector 3072 (1.5MB) on /dev/sda3.  So the volume
>> alignment within LVM is 512K.
> 
> I see this (for the first LV)
> vg0-hostname: 0 204808192 linear 147:2 512
> So, I'm guessing mine is starting at 512, and is also aligned at 512k ?

Not quite.  Those size and offset numbers are shown in *sectors*, so you
have 256k alignment.  But that's exactly the minimum you need to match
your raid5 chunk size, so you are good for the moment.

> Also, pvdisplay tells me the PE Size is 4M, so I'm assuming that regardless of how the LV's are arranged, they will always be 512k aligned?

256k, but yeah.

> So, is that enough to be sure that this is not an issue?

It looks to me like you are good on alignment.

Phil