- Community Home
- >
- Storage
- >
- HPE Nimble Storage
- >
- Array Performance and Data Protection
- >
- Re: IO operation size vs. read/write size
Categories
Company
Local Language
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Discussions
Discussions
Forums
Forums
Discussions
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Community
Resources
Forums
Blogs
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО05-29-2017 11:39 PM
тАО05-29-2017 11:39 PM
Looking at Infosight volume performance on a sql volume running under Hyper-V 2012r2 as VM guest, i don┬┤understand the difference between IO operation size vs. read/write size numbers.
The volume is a VM guest formattet with NTFS 64KB blocks and Nimble performance policy is Hyper-V 2012.
What would be the best block size for the NTFS volume?
Solved! Go to Solution.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО05-30-2017 08:34 AM
тАО05-30-2017 08:34 AM
SolutionHello Robert,
The difference in the graphs is that the first two show I/O operations specific to type (read or write), while the last graph shows the I/O operations for that timeframe in entirety (read+write). There is an excellent video that we have published on YouTube that covers the I/O metrics gathered and how they are interpreted (note that the link takes you to the approximate time that covers your question): https://youtu.be/2a1btnZp218?t=7m29s.
With regards to your second question, the NTFS allocation size (also referenced as cluster size) should be 64K for SQL Server volumes that contain user database, transaction log, or tempdb files. For binaries and OS files, the default allocation should be 4K. NTFS allocation size is not the same as I/O size as set by performance policies. For Hyper-V deployments, Microsoft recommends deploying SQL server with in guest iSCSI, vFC, or SQL over SMB. In deployments where the guest is using vFC or in guest iSCSI, use SQL Server performance policies. For SQL over SMB, Microsoft recommends leveraging SOFS.
Please refer to the following deployment considerations guides for more information:
Hope this helps.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО05-30-2017 10:06 AM
тАО05-30-2017 10:06 AM
Re: IO operation size vs. read/write size
Thanks - I┬┤ll read the provided links.
I┬┤m already using 64K cluster size for my DB volume, but i┬┤m unable to use in-guest iscsi initator as Veeam does not support this, and i only have 1 nimble box, therefore san replication is not a option for DR.