[OpenIndiana-discuss] Good SLOG devices?

wessels wessels147 at gmail.com
Wed Mar 2 01:54:43 UTC 2011

forget the acard for the x4150

there aren't many datapoints (experiences, tests) about the OCZ Vertex
2 series, not like the intel SSD's or the DDRdrive and I've no
experience with them or any SSD as SLOG for that matter.
Yes the zil is checksummoned. But you need another copy of the data.
Otherwise when the zil is read, and errors are detected, from the slog
device you're still in trouble. Remember the zil is rarely read, it's
mainly write-only. But when the slog devices fails during normal
operation it's offlined and the zil is written on the pool like
without the slog.
The mtbf isn't correlated with the wear of the device. Every time you
(implicit) erase a page the cells in the page wear a bit. As rule of
thumb SLC cells can be programmed 100000x and MLC cells 10000x. So
after these erases the cell's can't be used anymore. 10000 writes is a
bit short but the SSD employ wear-leveling techniques to ensure that
all cells gets evenly erased. How long your SSD last is a function of
how much data you write to it. A smaller SSD will wear out earlier
than a larger SSD of the same product line because of wear leveling.
Google the calculations. And newer is not always better. The new 25nm
generation of flash memory wears out much faster than previous 34nm
To determine how much the zil is used you can use the excellent tool
from Richard Elling at
http://www.richardelling.com/Home/scripts-and-programs-1/zilstat By
monitoring how much your zil is used you can determine how much is
written to it in say a day. With that number you can calculate when
your ssd wears out.
TRIM is not needed on good SSD. Look at early intel SSD's they didn't
have TRIM and still performed excellent. Remember the zil is very
small a couple of gigabytes at the most. So the rest of the drive can
be used for wear-leveling. Maybe the drive can be helped be limiting
it's capacity via e.g. DCO you only need 4 or 6GB for the zil. But you
need to test this.
All of the above is explained in much more depth in the ddrdrive paper
I mentioned earlier.

The DDRdrive and the Intel X25E are validated solutions all other
drives are a gamble...
Labeling a product "enterprise" doesn't necessary mean it's a
validated enterprise product...

Good luck

On Wed, Mar 2, 2011 at 1:31 AM, Ivar Janmaat <ijanmaat at xs4all.nl> wrote:
> Yes, would be interested in an acard.
> But my primairy project is boosting performance on a x4150 system which is
> used for storing iscsi targets.
> Oracle VDI Windows images to be exact.
> I don't see the acard and the ddrdrive work in a X4150.
> I was thinking of inserting a OCZ Vertex 2 Pro Series SAS 6.0 2.5" 50 GB SSD
> or the regular Oracle 32 GB SSD and use it as a ZIL.
> Then install Nexentastor and see what will happen.
> I was under the impression that  ZIL data is checksummed and the ZIL device
> is offlined if it contains to many errors.
> That means that if the SSD is worn out it needs to be replaced but no real
> harm is done.
> Am I correct?
> With a mtbf of 10 milj. hours (1141 years) for the OCZ ssd I thought I give
> it a try.
> I see from the graphs in your links that I don't need to expect the 50.000
> write iops.
> The avarage is more around the 4 - 5 K iops. (inline with the enterprise
> statistics)
> But that will be sufficient for what I need.
> The fact that zfs does not use the TRIM function bothers me a bit.
> Can you tell me a bit more about the real life effects of this?
> Kind regard,
> Ivar
> wessels schreef:
>> the difference can be largely explained by the type of memory used: MLC
>> and SLC
>> please google this and read the links I posted earlier, it'll make
>> your choice easier.
>> @Ivar. If you're interesested in the potential hard to find acard
>> drives I can help you with a supplier.
> _______________________________________________
> OpenIndiana-discuss mailing list
> OpenIndiana-discuss at openindiana.org
> http://openindiana.org/mailman/listinfo/openindiana-discuss

More information about the OpenIndiana-discuss mailing list