Académique Documents
Professionnel Documents
Culture Documents
(http://blog.open-e.com)
(http://www.facebook.com/sharer/sharer.php?
(https://twitter.com/intent/tweet?
(https://plus.google.com/share?
(http://www.linkedin.com/shareArticle?
u=http%3A%2F%2Fblog.opentext=Random+vs.+Sequential+explained.&url=http%3A%2F%2Fblog.openurl=http%3A%2F%2Fblog.openmini=true&url=http%3A%2F%2Fblog.opene.com%2Frandome.com%2Frandome.com%2Frandome.com%2Frandomvs-
vs-
vs-
vs-
sequentialsequentialsequentialsequential-
explained%2F&display=popup)
explained%2F)
explained%2F&t=Random+vs.+Sequential+explained.)
explained%2F&title=Random+vs.+Sequential+explained.&ro=false&summary=Very+often
Test
Transfer
Percent
Percent
Percent
Percent
MB /
IO /
Pattern
Request Size
Sequential
Random
Write
Read
second
second
2KB
100
100
24,75
12674
2KB
100
100
52,17
26708
2KB
100
33
67
0,75
383
64KB
100
100
103,82
1661
64KB
100
100
94,06
1504
256KB
100
100
141,68
566
256KB
100
100
100,65
402
When you the read the marketing material about this particular server hardware you will find the
claim that it provides over 25,000 I/O per second and over 140MB/second. These are very nice figures.
http://blog.open-e.com/random-vs-sequential-explained/
1/6
9/22/2015
claim that it provides over 25,000 I/O per second and over 140MB/second. These are very nice figures.
But imagine you are going to index a database (similar to test case #3). Your server will actually
perform at about 400 I/O per second and below 1 MB/second. Test case #3 uses the default IOmeter
test pattern: 100% Random, 2kB Block Size, 33% writes and 67% reads. This test pattern shows very
poor results.
Believe me, I have seen plenty of very disappointed users running the default test pattern on IOmeter.
I recall an incident at the CEBIT show few years ago when a RAID controller vendor engineer was
preparing their demo and noticed that one IOmeter worker was running the default pattern; instead
of the desired 400MB/sec., it was showing only about 4MB/sec. This is 100 times slower!
Lets check the ratios between the best and worst results in our test case above.
IO / sec
MB / sec
10392
20.30
Local RAID5
383
0.75
So it looks like the single SSD powered iSCSI target was 27 times faster than the local Windows 2008
RAID5 while running the IOmeter default test pattern. The IOmeter default pattern is a good test if we
are running an application such as database indexing. The SSD powered iSCSI target was 27 times
better because the SSD drive has extremely good IOPS compared to SATA hard disks. But if you run
any sequential pattern the results are comparable. Here are IOmeter screenshots from the default
test pattern on SSD powered iSCSI Target vs. local hard disks powered with RAID5.
(http://blog.open-e.com/wpcontent/uploads/2011/04/IOmeter-default_test_pattern_local_RAID.png?871a4d)
(http://blog.open-e.com/wpcontent/uploads/2011/04/IOmeter-default_test_pattern_iSCSI_SSD.png?871a4d)
http://blog.open-e.com/random-vs-sequential-explained/
2/6
9/22/2015
content/uploads/2011/04/IOmeter-default_test_pattern_iSCSI_SSD.png?871a4d)
These are some very interesting results. Not what you would necessarily expect.
So as you can see many factors influence overall storage performance. And understanding how
performance numbers are produced can give big insight into their validity. Careful use of
performance measurement tools can give you useful results. It is always a good idea to understand
how your storage clients will access their data on your servers.
DSS V6 (http://blog.open-e.com/tag/dss-v6/)
IOmeter (http://blog.open-e.com/tag/iometer/)
random (http://blog.open-e.com/tag/random/)
sequential (http://blog.open-e.com/tag/sequential/)
SSD (http://blog.open-e.com/tag/ssd/)
Related Project
Leave a Reply
NAME
EMAIL
URL
MESSAGE
http://blog.open-e.com/random-vs-sequential-explained/
3/6
9/22/2015
Post Comment
Search
Software-defined
storage: reliability,
performance and
scalability.
Check it out!
(http://www.opene.com/products/joviandata-storagesoftware/)
Popular
Comments
FROM BLOG
POST CATEGORIES
Events (http://blog.open-e.com/category/events/)
(14)
(59)
(77)
Virtualization (http://blog.open-e.com/category/virtualization/)
(18)
Webinars (http://blog.open-e.com/category/webinars/)
(12)
http://blog.open-e.com/random-vs-sequential-explained/
4/6
9/22/2015
TAGS
ACTIVE-ACTIVE FAILOVER FOR ISCSI (HTTP://BLOG.OPENE.COM/TAG/ACTIVE-ACTIVE-FAILOVER-FOR-ISCSI/) BACKUP
(HTTP://BLOG.OPEN-E.COM/TAG/BACKUP/) BONDING (HTTP://BLOG.OPENE.COM/TAG/BONDING/)
E.COM/TAG/DATA-REPLICATION/)
DSS V6 (HTTP://BLOG.OPEN-E.COM/TAG/DSS-V6/)
SSD (HTTP://BLOG.OPEN-
About Open-E
Open-E is a pioneering leader and developer of IP-based data storage software. Our software turns
any server into a SAN or NAS appliance. The products have the ability to support a variety of
technologies - like cloud storage - and protocols, such as iSCSI, Fibre Channel or Infiniband and offers
automatic failover for high availability and business continuity. With over 24,000 installations, in over
100 countries, Open-E Data Storage solutions are used by Fortune 500 customers world-wide.
http://blog.open-e.com/random-vs-sequential-explained/
5/6
9/22/2015
Recent Articles
Case Study: POLY-TOOLS implements iSCSI cluster with Open-E DSS V7 (http://blog.o
September 17, 2015
New update: Open-E JovianDSS High Availability cluster for NFS and iSCSI (http://blo
September 10, 2015
Author Profiles
Janusz Bk
Chief Technical Officer
Kasia Koodziej
Technical Content Specialist
Vera Neumeyer
PR & Marketing Manager
http://blog.open-e.com/random-vs-sequential-explained/
6/6