mirror of https://github.com/tLDP/LDP
2001-04-24 Gregory Leblanc <gleblanc@grego1.cu-portland.edu>
* added a section and question about benchmarking
This commit is contained in:
parent
99ffc8815c
commit
4fc3b450cf
|
@ -17,6 +17,14 @@
|
|||
|
||||
<revhistory>
|
||||
|
||||
<revision>
|
||||
<revnumber>v0.0.10</revnumber>
|
||||
<date>24 April 2001</date>
|
||||
<authorinitials>gml</authorinitials>
|
||||
<revremark>
|
||||
Added a new section and question about benchmarking.</revremark>
|
||||
</revision>
|
||||
|
||||
<revision>
|
||||
<revnumber>v0.0.9</revnumber>
|
||||
<date>9 October 2000</date>
|
||||
|
@ -26,16 +34,6 @@
|
|||
things which I can't remember.</revremark>
|
||||
</revision>
|
||||
|
||||
<revision>
|
||||
<revnumber>v0.0.8</revnumber>
|
||||
<date>6 September 2000</date>
|
||||
<authorinitials>gml</authorinitials>
|
||||
<revremark>
|
||||
The info/welcome message on vger.kernel.org has a pointer to this
|
||||
FAQ. New section on recovery, and fixed a few markup things.
|
||||
</revremark>
|
||||
</revision>
|
||||
|
||||
</revhistory>
|
||||
|
||||
|
||||
|
@ -414,6 +412,48 @@ unused devices: <none>
|
|||
|
||||
</qandadiv>
|
||||
|
||||
<qandadiv>
|
||||
<title>Benchmarking</title>
|
||||
|
||||
<qandaentry>
|
||||
|
||||
<question>
|
||||
<para>How should I benchmark my RAID devices? Are there any
|
||||
tools that work particularly well?</para>
|
||||
</question>
|
||||
|
||||
<answer>
|
||||
<para>There are really a few options for benchmarking your RAID
|
||||
array, depending on what you're looking to test. RAID offers the
|
||||
greatest speed increases when there are multiple threads reading
|
||||
from the same RAID volume.</para>
|
||||
|
||||
<para>One tool specificly designed to test and show off these
|
||||
performance gains is <ulink
|
||||
url="http://tiobench.sourceforge.net/"
|
||||
type="http"><application>tiobench</application></ulink>. It uses
|
||||
multiple read and write threads on the disk, and has some pretty
|
||||
good reporting.</para>
|
||||
|
||||
<para>Another good tool to use is <ulink
|
||||
url="http://www.coker.com.au/bonnie++/"
|
||||
type="http"><application>bonnie++</application></ulink>. It
|
||||
seems to be more targeted at benchmarking single drives that at
|
||||
RAID, but still provides useful information.</para>
|
||||
|
||||
<para>One tool <emphasis>NOT</emphasis> to use is
|
||||
<application>hdparm</application>. It does not give useful
|
||||
performance numbers for any drives that I've heard about, and has
|
||||
been known to give some incredibly off-the-wall numbers as well.
|
||||
If you want to do <emphasis>real</emphasis> benchmarking, use
|
||||
one of the tools listed above.</para>
|
||||
|
||||
</answer>
|
||||
|
||||
</qandaentry>
|
||||
|
||||
</qandadiv>
|
||||
|
||||
</qandaset>
|
||||
|
||||
</article>
|
||||
|
|
|
@ -17,6 +17,14 @@
|
|||
|
||||
<revhistory>
|
||||
|
||||
<revision>
|
||||
<revnumber>v0.0.10</revnumber>
|
||||
<date>24 April 2001</date>
|
||||
<authorinitials>gml</authorinitials>
|
||||
<revremark>
|
||||
Added a new section and question about benchmarking.</revremark>
|
||||
</revision>
|
||||
|
||||
<revision>
|
||||
<revnumber>v0.0.9</revnumber>
|
||||
<date>9 October 2000</date>
|
||||
|
@ -26,16 +34,6 @@
|
|||
things which I can't remember.</revremark>
|
||||
</revision>
|
||||
|
||||
<revision>
|
||||
<revnumber>v0.0.8</revnumber>
|
||||
<date>6 September 2000</date>
|
||||
<authorinitials>gml</authorinitials>
|
||||
<revremark>
|
||||
The info/welcome message on vger.kernel.org has a pointer to this
|
||||
FAQ. New section on recovery, and fixed a few markup things.
|
||||
</revremark>
|
||||
</revision>
|
||||
|
||||
</revhistory>
|
||||
|
||||
|
||||
|
@ -414,6 +412,48 @@ unused devices: <none>
|
|||
|
||||
</qandadiv>
|
||||
|
||||
<qandadiv>
|
||||
<title>Benchmarking</title>
|
||||
|
||||
<qandaentry>
|
||||
|
||||
<question>
|
||||
<para>How should I benchmark my RAID devices? Are there any
|
||||
tools that work particularly well?</para>
|
||||
</question>
|
||||
|
||||
<answer>
|
||||
<para>There are really a few options for benchmarking your RAID
|
||||
array, depending on what you're looking to test. RAID offers the
|
||||
greatest speed increases when there are multiple threads reading
|
||||
from the same RAID volume.</para>
|
||||
|
||||
<para>One tool specificly designed to test and show off these
|
||||
performance gains is <ulink
|
||||
url="http://tiobench.sourceforge.net/"
|
||||
type="http"><application>tiobench</application></ulink>. It uses
|
||||
multiple read and write threads on the disk, and has some pretty
|
||||
good reporting.</para>
|
||||
|
||||
<para>Another good tool to use is <ulink
|
||||
url="http://www.coker.com.au/bonnie++/"
|
||||
type="http"><application>bonnie++</application></ulink>. It
|
||||
seems to be more targeted at benchmarking single drives that at
|
||||
RAID, but still provides useful information.</para>
|
||||
|
||||
<para>One tool <emphasis>NOT</emphasis> to use is
|
||||
<application>hdparm</application>. It does not give useful
|
||||
performance numbers for any drives that I've heard about, and has
|
||||
been known to give some incredibly off-the-wall numbers as well.
|
||||
If you want to do <emphasis>real</emphasis> benchmarking, use
|
||||
one of the tools listed above.</para>
|
||||
|
||||
</answer>
|
||||
|
||||
</qandaentry>
|
||||
|
||||
</qandadiv>
|
||||
|
||||
</qandaset>
|
||||
|
||||
</article>
|
||||
|
|
Loading…
Reference in New Issue