Forget using drives all together for heavy hit applications. Build data that can fit on a ram Drive (8GB) then your able to do 20K qps.
For instance, have a main master that holds a majority of tables call it MASTER. Then a sub master that holds the tables which you desire to run out of memory, call it SUBMASTER. Each slave connected to SUBMASTER then does a LOAD DATA FROM MASTER on startup based on init_file=<path to the SQL file> Defined in the my.cnf file Loading 2GB of data across the network on a GigE is very fast. So now you have the ability to handle 20K qps on a single box (assuming the box is a 4GB X86 Opteron with 2 processors and the main lookup is on a primary key) and also have redundancy with real time replication. For instance I have 5 servers with 4 GB of ram - the table that displays user names which is seen on friendster only takes 1.6 G of memory. All DB access is real time producing 3000 qps during peak per server where one server can handle the site, since that query type benchmarks for 20000 qps. More then enough head room to scale since I can LB the reads across the 5 boxes. The front end will fall over before the backend - Easy cheap solution that can handle a crap load of load. DVP ---- Dathan Vance Pattishall http://www.friendster.com > -----Original Message----- > From: Kevin Burton [mailto:[EMAIL PROTECTED] > Sent: Wednesday, May 11, 2005 12:30 PM > To: mysql@lists.mysql.com > Subject: SATA vs SCSI > > Were kicking around using SATA drives in software RAID0 config. > > The price diff is significant. You can also get SATA drives > in 10k RPM form now., > > Kevin > > -- > > > Use Rojo (RSS/Atom aggregator)! - visit http://rojo.com. > See irc.freenode.net #rojo if you want to chat. > > Rojo is Hiring! - http://www.rojonetworks.com/JobsAtRojo.html > > Kevin A. Burton, Location - San Francisco, CA > AIM/YIM - sfburtonator, Web - http://peerfear.org/ GPG > fingerprint: 5FB2 F3E2 760E 70A8 6174 D393 E84D 8D04 99F1 4412 > > > -- > MySQL General Mailing List > For list archives: http://lists.mysql.com/mysql > To unsubscribe: > http://lists.mysql.com/[EMAIL PROTECTED] > > -- MySQL General Mailing List For list archives: http://lists.mysql.com/mysql To unsubscribe: http://lists.mysql.com/[EMAIL PROTECTED]
