SUMMARY: a1000 vs d1000

From: Matthew Hannigan (mlh@zip.com.au)
Date: Wed Sep 11 2002 - 01:13:26 EDT


Thanks to
        Graham Wood
        Bill McCaffrey
        Darren Dunham
        Jay Lessert
        Jason Watson

Short Summary:
> 1. Will the memory cache make the performance
> much better? Considering that there is a maximum
> of 40Mb to cache 430+ GB!

A: It depends :-) See the comments below.

> 2. Can you even use the memory cache on the a1000
> if you're not using the RAID features?

A: Yes (literally no, but really yes). Since you
cannot use the A1000 without using the raid features,
you always get the benefit of the cache. "Not using" the
raid features in this case would mean making each drive
a single concat. Or I could make one or two giant raid0's.

Longer Summary:

Two responses leaned towards the D1000, one neutral
and two leaned towards the A1000.

The D1000 has two external scsi connections which
could make it more flexible and perhaps make it
perform better.

But as things turn out, we have the extra money for
the a1000 -- it was just within our budget, so it
looks like we'll be going with that.

I have further commments below amongst the replies below.

Graham Wood

        [ re performance ]
        This all depends on how evenly spread over the 430GB the queries are. If
        you're looking at a database, then it is possible that the indexes will be
        less than this size, and therefore be cached quite effectively. The biggest
        problem with any form of caching is that you are unable to accurately predict
        anything.

        [ re memory cache ]
        No. But since you can't use an A1000 without using the raid side of things,
        its a totally irrelevant question. The A1000 has a SCSI external connection,
        but the disks are internally on 2 different SCSI busses, the same as the
        D1000.

        For performance reasons, I'd recommend the D1000. Instead of a single SCSI
        connection to the 12 disks, you can have 2. Also the A1000 would add an extra
        layer of logic on top that you are not after. The main advantage of the A1000
        is that since the raid controller is hardware, you get very little performance
        hit compared to software. In your case you are not looking at raid, therefore
        this is not relevant. The sustainable transfer rate through a HDD these days
        is a large fraction of the 40MB/s that is transferable through the SCSI
        interface on the back of an A/D1000. This means that from a purely data
        throughput point of view (quite likely to be the bottleneck with a good server
        and a datawarehousing system) you are best maximising your connectivity to the
        disks.

        Also you have to remember that your RDBM will be doing caching with all the
        available system ram that it can too. You are probably best going for the
        D1000 and putting any money saved into extra money for the server.

        Final thought - if you really need top performance from the system, I would
        consider going for a T3 instead of the A/D1000. The fibre connection is more
        than double the speed, and there is an easy upgrade path to mirroring/etc if
        you want to do that later.

me: T3 is way out of our budget for this project.

Bill McCaffrey

        We have found that the D1000 out-performs the A1000 with an oracle database.
        We have not used then without mirroring, but the D1000 with software raid
        had better throughput than the A1000 with hardware raid.

Darren Dunham

        You can't even afford to dedicate 1 of the 12 drives to parity? That
        gives you ~396GB of redundant data on the A1000.

me: that may be possible but I would think that the one parity drive
would be a performance bottleneck. Performance is more important
than uptime for this project. The data can be just reimported from
our production system in case of disaster.

        [ re cache and performance ]

        It should make writes perform better, but probably not reads to any
        significant amount. The more RAM you have in the host, the more that is
        true.

Jay Lessert

        I've used an A1000 in "one-big-RAID5" mode. If you're doing 5-10%
        writes, the NV cache makes a huge difference, and the A1000 really
        rocks.

        10% writes is a pretty big percentage, by the way.

Jason Watson

        [ re performance ]

        Unless you are doing heavy data throughput (such as video editing or
        completely random) reads and
        writes the cache will help. The cache needs only to buffer the activity
        to and from the disk; it doesn't have to be huge to accomodate the
        size of the array. For
        your purposes I think 40 MB would do well.

        [ re use of cache ]

        I don't see any reason why not. You would be putting the array into
        spanning or RAID-0. If the RAID controller is worth its salt it will
        cache RAID-0 just as well as any of the other RAID levels.

        The other advantage the A1000 will have is that it off-loads the RAID-0
        work from the host CPU to the RAID controller. That can make a noticable
        difference between the two. Especially if the attached box is really
        hitting its processor for the data mining.

--
_______________________________________________
sunmanagers mailing list
sunmanagers@sunmanagers.org
http://www.sunmanagers.org/mailman/listinfo/sunmanagers


This archive was generated by hypermail 2.1.7 : Wed Apr 09 2008 - 23:24:55 EDT