On 19/02/2006 10:57 p.m., Kevin Burton wrote:
I was talking to a friend tonight about how they use NBD to run a single
system image in memory.
NBD (Network Block Device) allows one Linux box to export a block device
and for you to mount it on another filesystem. For the memory
component they just use a ram disk.
What if you booted a MySQL install and told it to use NBD mounted
memory? Theoretically you could build MUCH cheaper and MUCH faster
clusters. Your DB writes would still back to the local (RAID)
filesystem but your innodb buffer pool and other buffers would be
running out of swap and into your network memory subsystem.
This would allow you to have a HUGE buffer for MySQL. Buffer your whole
damn database in MEMORY.
The main downside I can see is fault tolerance if the ethernet port was
pulled. The box would fail. Of course at this point its a bit like
pulling a SCSI cable out.
If this turns out to be a good way to scale MySQL someone could just pay
to have NBD enhanced to support fault tolerance with mirror nodes.
Thoughts?
Why would this be better than just using MySQL Cluster (NDB)?
With this method you're reliant on one single server, all you get is a
large space for buffering. Which could be good if your database is
mostly static and you can take advantage of query caching and key
buffers, and your operating system may be able to buffer the entire
database into memory. But would be less advantageous if you have many
updates.
But it doesn't really give you any scalability, since everything has to
go through the one MySQL server still. It's just a MySQL server with
lots and lots of high-speed swap space.
And I'd imagine it would be very fault-prone. If any of the "buffer"
servers was to die, it would most likely take the entire database with
it (operating systems can't handle losing swap). And even if you solved
that, the single MySQL server would still be a single point of failure.
If you have many servers with lots of RAM, MySQL Cluster by contrast
enables you to run your database in RAM and make real gains in
scalability and fault tolerance (although it is a little rough round the
edges still).
-Simon
--
MySQL General Mailing List
For list archives: http://lists.mysql.com/mysql
To unsubscribe: http://lists.mysql.com/[EMAIL PROTECTED]
