| Author |
 Topic  |
|
|
bissa
Starting Member
27 Posts |
 Posted - 08/19/2012 : 02:21:02
|
Hello,
I'm currently hosting a game server with the current specification
E1230
32GB Ram
4x 500Gb SATA
Windows 2008 server
SQL Server 2012
Databse size is 10Gb
Number of players 1k
- The problem at first I had I/O bottleneck with 2x1Tb as I was using the default SQL configuration and all the files .mdf and .ldf were stored in default C:/SQLSERVER
- Then I added 2 more 1 Tb disks and I isolated .mdf and .ldf and TempDB locations. Problem has been fixed and I/O is performing well.
- Now I have the opportunity to change the disks system to 4x 300GB SAS in HW RAID 10, the problem I'm limited to 4 Disks 1 Array only, so I will have to store mdf, ldf and tempdb files in the same array and not isolated.
- Will I have I/O issue with this configuration? it will be better than 4x single HDD's which every physical HDD contains mdf, ldf, and tempdb files which I already use at the moment without issue or performance could be worse with shared 4x SAS 300GB RAID 10?
Thank you |
Edited by - bissa on 08/20/2012 03:07:28
|
|
|
jackv
Flowing Fount of Yak Knowledge
United Kingdom
1770 Posts |
Posted - 08/19/2012 : 06:58:05
|
1) Are there other applications?
2) What is the main type of IO activity? random ,sequential etc.
3) Do you have a current IO profile , such as read ops and write iops
Jack Vamvas
--------------------
http://www.sqlserver-dba.com |
 |
|
|
bissa
Starting Member
27 Posts |
Posted - 08/19/2012 : 10:48:17
|
1- No other application
2- Not sure but the HDD activity is always in use so it is not random, as it is a game server, the activity of the HDD is always in the range 50% ~ 80%, sometimes it will bounce to 100% during peak load.
3- No
Is there a query I can use to check this things?
Thanks |
Edited by - bissa on 08/19/2012 10:52:32 |
|
|
|
chadmat
The Chadinator
USA
1958 Posts |
Posted - 08/19/2012 : 15:37:21
|
Run SQLIO against the new setup if you can, see what throughput you get vs the current setup.
-Chad |
|
|
|
jackv
Flowing Fount of Yak Knowledge
United Kingdom
1770 Posts |
Posted - 08/20/2012 : 01:42:28
|
Tools such as SQLIO are good. Interpreting results from SQLIO can be tricky: focus on IOs\sec , MBs\sec, histogram.
A simple method is to use Perfmon:
Collect Logical Disk:Disk Writes/Sec and Logical Disk: Disk Reads/Sec per database server
Logical Disk: Disk Reads/Sec The rate of read operations from disk
Logical Disk:Disk Writes/Sec The rate of write operations to disk
Ask yourself questions such as :
Is disk drive peformance being achieved , such as < 5ms
Is throughput at the limit?
Jack Vamvas
--------------------
http://www.sqlserver-dba.com |
|
|
|
bissa
Starting Member
27 Posts |
Posted - 08/20/2012 : 03:08:48
|
Hi jackv and chadmat, appreciate your replies and help,
with the current setup which is single 4x 500Gb disks, a physical drive for .mdf files, a physical drive for .ldf files and a physical drive for tempdb files.
I took a live screenshot with the current setup in action. The new setup with Raid 10 4x disks 300Gb SAS is not ready yet for testing.
What do you think?
|
Edited by - bissa on 08/20/2012 03:23:11 |
|
|
|
jackv
Flowing Fount of Yak Knowledge
United Kingdom
1770 Posts |
Posted - 08/20/2012 : 09:00:26
|
was your post supposed to include an image?
With the new set up - if you have an opportunity - do some acceptance testing. That should give you the confidence to make a decision
Jack Vamvas
--------------------
http://www.sqlserver-dba.com |
|
|
| |
Topic |
|
Database I/O shared RAID 10 vs single disks
