UNSOLVED

dave12341

updated

18 years ago

D

dave12341

14 Posts

0

2319

May 13th, 2009 17:00

DMX-4 Large meta-lun performance

Hi all,

We currently have a dmx-4 with 100 disks and 8gb hypers, the problem is some of the sql databases are 450-500gb in size. Therefore we are creating meta luns of 500-600gb in size.

The performance obviously goes to crap because of the contention for spindles, what is the best way to work around this problem? Ideally best performance would be around the 200gb meta-lun size. Has anyone else worked around this?


Thanks
Dave
  • Quincy561

    1281 Posts

    933

    1

    Posted May 13th, 2009 19:00

    Dave,

    Are you running 5773? If not, that should be your first step. 5773 introduced a front-end aware prefetch that knows what a meta volume is. Previous releases of Enginuity did not have meta aware prefetch.

    I would suggest making logical volumes that will satisfy your host volume size with 4 or 8 meta members if possible. Fewer members, and fewer logicals in the box generally gives better overall performance.
  • dave12341

    14 Posts

    936

    0

    Posted May 13th, 2009 20:00

    Quincy,
    when you say logicals I assume you are referring to the hypers?

    So can I use ECC to change some of the 8gb hypers to larger sizes?


    Alok Jain,
    Host based lvm had crossed my mind but i would like to keep it simplier. Which LVM software do you use at the host level?
  • alokjain1

    44 Posts

    936

    0

    Posted May 13th, 2009 20:00

    Looks like you have SQL Server. In which case, just use the Windows Disk Manager to create striped volumes with smaller striped Metas presented to the host. I have seen very good performance with using striped metas and then striping at the host level. It spread the load to many spindles in the back-end. Also make sure you are properly aligning the cylinder boundaries at the host by starting the partition at 64k boundary. I would still like to understand the metric used to determine spindle bottleneck? - Alok
  • alokjain1

    44 Posts

    439

    0

    Posted May 13th, 2009 20:00

    Dave,

    Are these striped meta LUNs? One thing to keep in mind is that more LUNs at the host level (as opposed to 1 large meta LUN) provide higher number of LUN queues that improve the performance. So presenting higher number of LUNs to host and then using a volume manager to stripe at the host level will provide better performance (at least in my experience)

    BTW, what is the measurement (which metric and at host or at the array) that is showing disk contention?
  • dave12341

    14 Posts

    933

    0

    Posted May 13th, 2009 20:00

    Hi Quincy,
    Yes I am running 5773.

    the problem with using less members is the fact that our physical database is a specific size that needs to be minimum
  • Quincy561

    1281 Posts

    933

    1

    Posted May 13th, 2009 20:00

    DMX4 supports logical volumes of up to about a 60GB. With a logical volume that size, you would need about 8 members to get your required 500GB.
  • dave12341

    14 Posts

    936

    0

    Posted May 13th, 2009 21:00

    yeah i am running a sql server.

    What you suggest would work for me, however I am reluctant to leave my data integrity up to windows.

    Yes we are using 64k alignment.

    The best approach for me I think is to change some of the unmapped 8gb hypers into 16 or 24gb hypers
  • alokjain1

    44 Posts

    936

    0

    Posted May 13th, 2009 21:00

    I have run exchange servers with 30K users with SRDF on using windows striping on DMX2/3. No issues observed in last 3-4 years that I know of.
    If single LUN at the host is the bottleneck, then having bigger hypers will not help. Check to make sure you are not hitting any target LUN queue depths because of single LUN. For databases it is advisable to have multiple LUNs to separate out the data/logs/indexs etc. You can try it out.
  • dave12341

    14 Posts

    936

    0

    Posted May 13th, 2009 22:00

    Your design obviously works well for you, however I am just saying even srdf does not protect against windows corrupting the striped luns

    We are using seperate luns, logs,data and backup. The speed problem is because the dba's refuse to archive/split/reduce the size of databases, gradually larger and larger luns are required.

    We have got to the point were the large luns are performing 5 times worse than the smaller luns attached to the same server. We know this from our benchmarking, but you guys have seen the same thing.

    Increasing the hyper size sounds like it might be the workaround we need.
  • RRR

    6 Operator

    •

    5739 Posts

    862

    0

    Posted May 14th, 2009 01:00

    I would suggest making logical volumes that will satisfy your host volume size with 4 or 8 meta members if possible. Fewer members, and fewer logicals in the box generally gives better overall performance.


    Quincy56, I always check (symdev show) to see what the physical underlying spindels are and I make sure I'm not including a single spindel in the same META twice. In the Symm Performance Workshop my instructor Desirée T. agreed with this aproach and so far I haven't seen performance issues. I have RAID5 META's as large as 32 members, where the 32 members each consist of 4 spindels (3RAID5, so 4 spindels per symdev) and 32 x 4 = 128 spindels, which (coincidence ?) is exactly the range of spindels I'm creating symdevs on ;) So each member of this large META is on it's own set of 4 spindels and all 32 members of this META are on individual spindels.

    I'm using my backend as good as possible, I think.