[CentOS] stripe size for SSDs? ( cyrus spool on btrfs?)

Wed Sep 13 17:23:58 UTC 2017
hw <hw at gc-24.de>

Stephen John Smoogen wrote:
> On 13 September 2017 at 12:00, hw <hw at gc-24.de> wrote:
>
>>>
>>> It will depend on the type of SSD. Ones with large cache and various
>>> smarts (SAS Enterprise type) can take many different sizes. For SATA
>>> ones it depends on what the cache and write of the SSD is and very few
>>> of them seem to be the same. The SSD also has all kinds of logic which
>>> moves data around constantly on disk to wipe level so it makes it
>>> opaque. The people who have tested this usually have to burn through
>>> an SSD set to get an idea about a particular 'run' of a model but it
>>> doesn't go over every version of the model of SATA SSD.
>>
>>
>> Hm, so much to SSDs ...  I can only hope they will be replaced with
>> something better.
>>
>>
>> I have decided against putting anything onto these SSDs other than temporary
>> data, but even for that, I would need to make an md-RAID, which I don´t
>> want.
>> It may work or not, and "may work" is not enough.
>>
>
> May work is part of any commodity hardware build. The SATA hard drives
> do not use the same technology as 4 years ago and you may end up with
> them having crap out on shorter lifetimes because they aren't built to
> live longer than 3 years depending on the model. [It doesn't matter
> the brand.. they get built with the same tech and at the same place
> these days.]

Spinning disks don´t have the trouble with writing as SSDs have, and they
are used for hardware RAID in this case.  The SSDs may work with hardware
RAID or may not.  They may work for their purpose or they may not.  The
spinning disks will work, they have done so for the last two years ---
with ZFS rather than hardware RAID, but WD Reds should do fine, and do
so since about a month now.

My experience is that spinning disks fail either within the first three
months or when about three years old --- or virtually never because they
get so old that they are being replaced by disks with greater capacity
before they fail.

Nowadays, what isn´t build to fail as soon as the manufacturer can get
away with? :(  Even cars you pay 70k for are built to fail after only
three years, same as those that cost 256k used.  (The 256k one I saw at a
BWM dealer, and the sales guy told me they are built to fail.  Go figure :) )

>> If the performance on the hardware RAID isn´t as good, it can not get worse
>> than it is now, and it may be even better than with the SSDs.
>>
>>
>> I have two at home with the system installed on btrfs.  I´m going to change
>> that
>> to md-RAID1 and xfs.  Is there anything special involved in copying the
>> system
>> to another disk?  Will 'cp -ax' do, or should I use rsync to copy xattrs
>> etc.?
>> Using the commonly used stripe size of 128kb is something I´d expect the
>> SSDs
>> being able to handle.
>>
>
> Depending on what CentOS you are working, cp -a will preserve xattrs.

Centos 7