re: Storage Performance for SQL Server
Thanks for nice info. It’s useful for me. Can you give me some more information with details? I will wait for your next post.
View ArticleA year in review, The 31 best blog posts on SQLBlog for 2008
Wow, it has been already a year since I wrote A year in review, The 21 + 1 best blog posts on SQLBlog
View Articlere: Storage Performance for SQL Server
russel, not sure, send me a email, I do not like the idea of constantly reading the ldf, I do recall an EMC fellow telling me of firmware problems of this sort. try making a log of what you are...
View Articlere: Storage Performance for SQL Server
Hi Joe! How have you been! I miss working with you at Quest, but anyhow I am at GoldenGate now, replicating SQL Server databases. Quite fun!Anyhow, to get right to the point, if you can shed light on...
View Articlere: Storage Performance for SQL Server
Questions 1-4:1. If the execution plan shows key lookups, or loop joins, which require disk IO, more than likely it will be 8K read IO, except when the cache is cold, in which case it will be 64K....
View Articlere: Storage Performance for SQL Server
Ok, I have a question. I see Joe and Linchi going back and forth abotu disk alignment and RAID. Yes they are two different things, and something about not needing to align the disks on RAID 1? Or if...
View Articlere: Storage Performance for SQL Server
Just wanted to say that this is the best post on the subject that I've read in a long while.
View Articlere: Storage Performance for SQL Server
The TPC-C IO load was seriously getting out of hand to the point of distorting the server system architecture required to run the benchmark. Do you remember the original Intel Merced platform that did...
View Articlere: Storage Performance for SQL Server
Nice post Joe. Don't you think the new TPC-E benchmark is a little more realistic than TPC-C in terms of disk I/O requirements?
View ArticlePerformance impact of controller read cache: large sequential I/Os
In the next several blog posts, I’ll share with you some empirical results concerning the performance
View Articlere: Storage Performance for SQL Server
then about 40GB+ of the SAN cache is wasted, they should have gone to a server that supports 128 or even 256GB memory. It also depends how disks there are, at this level, if they have less than 200-400...
View Articlere: Storage Performance for SQL Server
> A separate disk cache for a database engine is fundamentally a silly idea.I think it depends on the transaction rate and database size. One client of mine just increased their performance by...
View Articlere: Storage Performance for SQL Server
my fault, I thought you were saying the opposite, I have not tested the tiny 2M read cache myself, but it is very apparent that a cache does add overhead, hence read cache should be kept small or...
View Articlere: Storage Performance for SQL Server
Regardless of what the Oracle said, I have reproducible data to show that read cache is not good for sequential reads. I'm not claiming this is univerally true, but I have observed it in my own tests.
View Articlere: Storage Performance for SQL Server
the Oracle guy actually said read cache does benefit read ahead, just that you only need 2MB per LUN, not 4GB.I am saying read cache in the storage controller is not effective in reducing disk load, as...
View Articlere: Storage Performance for SQL Server
I agree that in the simplest case (i.e. with a single disk), read cache doesn't benefit read-ahead. This basically says that read cache doesn't benefit sequential reads. I'll have to respond in more...
View Articlere: Storage Performance for SQL Server
yes, partition alignment and RAID are separate topics, but this is one issue,partitions not aligned to 32K or 64K boundaries on single disks, or in theory, RAID 1, is not an issue, because an IO...
View Articlere: Storage Performance for SQL Server
> Disk partition alignment is a problem caused by the Windows operating system in RAID stripes.Although RAID stripes can add complication to the disk partition misalignment issue, the two are not...
View Articlere: Storage Performance for SQL Server
Joe, thank you so much for taking the time to write this post!
View Articlere: Storage Performance for SQL Server
I should have included a pointer to Andys blog, which lists key sources from MS, Jimmy's handle is...
View ArticleStorage Performance
Storage has changed dramatically over the last three years driven by SSD developments. Most of the key
View Articlere: Storage Performance for SQL Server
But the same still applies for alignment for those not using all SSD.
View Article
