The last time I got up close to the ATA specs was before SATA was invented
and I don't have any 840 EVOs (yet), so I'm going to use a lot of weasel
words. Sorry about that.

On 18 October 2014 07:31, Ian Collins via smartos-discuss <
[email protected]> wrote:

> Andre Sachs via smartos-discuss wrote:
>
>> We have a bunch of Samsung EVO 840's that we are trying to use as
>> logdevices on some old nodes to give them a bit of life.
>>
>> The nodes are using an LSI 2008 controller and run well.
>>
>
I have to admit, that's a combination that I'm inclined to try myself.


> Even though they performed reasonably well, I wouldn't use them for logs
> because they don't have power loss protection.
>

I would expect that the kernel is either using cache flushing or the Force
Unit Access bit to ensure that it knows when all ZIL writes have actually
made it to stable storage. This in turn means that no upper layer will ever
be told that data has been written when it hasn't, regardless of power loss
protection. On the other hand, my motto is "Expectation is the mother of
disappointment".

What I also expect is that power loss protection will allow the SSD to lie
about when data has made it to stable storage, which should increase your
IOPS when trying to write through the cache.

I thought the 840 EVOs had some firmware issues. There is a firmware update
on the Samsung web site (which isn't very recent) as well as program that
you run under Windows to fix some read performance problem. The are
promising a DOS boot image for the rest of us sometime this month.

Cheers,
Lloyd



-------------------------------------------
smartos-discuss
Archives: https://www.listbox.com/member/archive/184463/=now
RSS Feed: https://www.listbox.com/member/archive/rss/184463/25769125-55cfbc00
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=25769125&id_secret=25769125-7688e9fb
Powered by Listbox: http://www.listbox.com

Reply via email to