For hard disk drives, the random IOPS numbers are primarily dependent on the
storage device's random seek time.
7200RPM SATA drives - ~90 IOPS[citation needed]
10kRPM Serial Attached SCSI drives - ~ 140 IOPS[citation needed]
15kRPM Serial Attached SCSI drives - ~180 IOPS[citation needed]
Intel X25-M (MLC; As of March 2010[update]) - ~8,600 IOPS (Intel's data
sheet says 8,600 write, 35,000 read IOPS)
Random read throughput mainly depends on IOPS number per hard disk.
That's to say, if your cassandra node have only one hard disk with 200 IOPS
per second and total rows of this node is far more than 1000,000,000, you
can not read more than 200 different "random" rows per second in one disk
cassadra node when no row-cache.
SSD has high IOPS, So it can highly improve the random read performance.
--------------------------------------------------
From: "Jonathan Ellis" <[email protected]>
Sent: Tuesday, June 08, 2010 10:16 PM
To: <[email protected]>
Subject: Re: Cassandra on flash storage
cassandra is designed to do less random i/o than b-tree based systems
like tokyo cabinet. ssds are not as useful for most workloads.
On Mon, Jun 7, 2010 at 8:37 AM, Héctor Izquierdo <[email protected]>
wrote:
Hi everyone.
I wanted to know if anybody has had any experience with cassandra on
flash
storage. At work we have a cluster of 6 machines running Tokyotyrant on
flash-io drives (320GB) each, but performance is not what we expected,
and
we'are having some issues with replication and availability. It's also
hard
to manage, and adding/removing nodes is pure hell.
We can't afford test hardware with flash storage right now, so could
somebody share his experience?
Thank you very much
Héctor Izquierdo
--
Jonathan Ellis
Project Chair, Apache Cassandra
co-founder of Riptano, the source for professional Cassandra support
http://riptano.com
