Unsolved
This post is more than 5 years old
58 Posts
0
855
VPLEX Geo Information
I'm looking for information on how VPLEX Geo functions and seem to be coming up with slim pickings. I understand metro and synchronous replication, but am very unclear on the async replication functions and how they work. Also very unclear on how the data access works in the async world...as in what happens if a host at SiteA writes a data block and half a second later a host at SiteB tries to read that block.
Can someone point me at some whitepapers or guides on VPLEX Geo and how it functions?
garyo
89 Posts
0
November 4th, 2014 13:00
Hi raid-zero,
This might be too high level, but I'd start with these:
EMC VPLEX 5.0 Architecture Guide
http://www.emc.com/collateral/hardware/white-papers/h8232-vplex-architecture-wp.pdf
Long-distance Application Mobility Enabled by EMC VPLEX Geo - An Architectural Overview
http://www.emc.com/collateral/hardware/white-papers/h8214-application-mobility-vplex-geo-wp.pdf
From the Arch Guide:
VPLEX Geo uses write-back caching to achieve data durability without requiring synchronous operation. In this cache mode VPLEX accepts host writes into cache and places a protection copy in the memory of another local director before acknowledging the data to the host. The data is then destaged asynchronously to the back-end storage arrays. Cache vaulting logic within VPLEX stores any unwritten cache data onto local SSD storage in the event of a power failure.
VPLEX's cache coherency protocol keeps the directors knowledgeable about which director holds the most recent copy of a block. So in your example, SiteB will always know that SiteA has the most up to date version of the page. There are also optimizations in place so that not every single read request required inter-cluster communication to determine cache state.
If you want more details than that, I encourage you reach out to your account rep or SE.
Gary