<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="pt-BR">
	<id>https://wiki.slacam.com.br/index.php?action=history&amp;feed=atom&amp;title=DiskTestDD</id>
	<title>DiskTestDD - Histórico de revisão</title>
	<link rel="self" type="application/atom+xml" href="https://wiki.slacam.com.br/index.php?action=history&amp;feed=atom&amp;title=DiskTestDD"/>
	<link rel="alternate" type="text/html" href="https://wiki.slacam.com.br/index.php?title=DiskTestDD&amp;action=history"/>
	<updated>2026-11-17T00:37:06Z</updated>
	<subtitle>Histórico de revisões para esta página neste wiki</subtitle>
	<generator>MediaWiki 1.35.14</generator>
	<entry>
		<id>https://wiki.slacam.com.br/index.php?title=DiskTestDD&amp;diff=877&amp;oldid=prev</id>
		<title>Machado em 20h39min de 20 de outubro de 2016</title>
		<link rel="alternate" type="text/html" href="https://wiki.slacam.com.br/index.php?title=DiskTestDD&amp;diff=877&amp;oldid=prev"/>
		<updated>2016-10-20T20:39:57Z</updated>

		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left diff-editfont-monospace&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;pt-BR&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Edição anterior&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Edição das 20h39min de 20 de outubro de 2016&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l86&quot; &gt;Linha 86:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Linha 86:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;==References==&lt;/div&gt;&lt;/td&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;==References==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;references/&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;references/&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class=&#039;diff-marker&#039;&gt;+&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class=&#039;diff-marker&#039;&gt;+&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;https://www.thomas-krenn.com/en/wiki/Linux_I/O_Performance_Tests_using_dd&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{Wfischer}}&lt;/div&gt;&lt;/td&gt;&lt;td class=&#039;diff-marker&#039;&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{Wfischer}}&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Machado</name></author>
	</entry>
	<entry>
		<id>https://wiki.slacam.com.br/index.php?title=DiskTestDD&amp;diff=876&amp;oldid=prev</id>
		<title>Machado: Criou página com &#039;Under Linux, the &lt;code&gt;dd&lt;/code&gt; command can be used for &#039;&#039;&#039;simple sequential I/O performance measurements&#039;&#039;&#039;. This article will provide valuable information about which param...&#039;</title>
		<link rel="alternate" type="text/html" href="https://wiki.slacam.com.br/index.php?title=DiskTestDD&amp;diff=876&amp;oldid=prev"/>
		<updated>2016-10-20T20:39:02Z</updated>

		<summary type="html">&lt;p&gt;Criou página com &amp;#039;Under Linux, the &amp;lt;code&amp;gt;dd&amp;lt;/code&amp;gt; command can be used for &amp;#039;&amp;#039;&amp;#039;simple sequential I/O performance measurements&amp;#039;&amp;#039;&amp;#039;. This article will provide valuable information about which param...&amp;#039;&lt;/p&gt;
&lt;p&gt;&lt;b&gt;Página nova&lt;/b&gt;&lt;/p&gt;&lt;div&gt;Under Linux, the &amp;lt;code&amp;gt;dd&amp;lt;/code&amp;gt; command can be used for &amp;#039;&amp;#039;&amp;#039;simple sequential I/O performance measurements&amp;#039;&amp;#039;&amp;#039;. This article will provide valuable information about which parameters should be used. For more detailed I/O performance benchmarking, the Flexible I/O Tester ([[Fio]]) can be used.&lt;br /&gt;
&lt;br /&gt;
==Basics==&lt;br /&gt;
&amp;lt;code&amp;gt;dd&amp;lt;/code&amp;gt; can be used for simplified copying of data at the low level.&amp;lt;ref&amp;gt;[http://en.wikipedia.org/wiki/Dd_(Unix) Dd (Unix)] (en.wikipedia.org)&amp;lt;/ref&amp;gt; In doing this, device files are often access directly. Beware that erroneous usage of &amp;lt;code&amp;gt;dd&amp;lt;/code&amp;gt; can quickly lead to data loss. &amp;lt;b&amp;gt;We absolutely recommend performing the steps described below on test systems. If &amp;lt;code&amp;gt;dd&amp;lt;/code&amp;gt; is used incorrectly, data loss will be the result.&amp;lt;/b&amp;gt;&lt;br /&gt;
&lt;br /&gt;
==Measuring Write Performance==&lt;br /&gt;
Modern operating systems do not normally write files immediately to RAID systems or hard disks. Temporary memory that is not currently in use will be used to cache writes and reads (regarding this, see also [[RAID Controller and Hard Disk Cache Settings#Operating System Cache|Operating System Caches]]).&lt;br /&gt;
&lt;br /&gt;
So that I/O performance measurements will not be affected by these caches (temporary memory), the &amp;lt;code&amp;gt;oflag&amp;lt;/code&amp;gt; parameter can be used. Thereby, the following two flags are interesting (for details, see &amp;lt;code&amp;gt;dd --help&amp;lt;/code&amp;gt; and [[Dd using direct or synchronized I/O]]):&lt;br /&gt;
* direct (use direct I/O for data)&lt;br /&gt;
* dsync (use synchronized I/O for data)&lt;br /&gt;
* sync (likewise, but also for metadata)&lt;br /&gt;
&lt;br /&gt;
For measuring write performance, the data to be written should be read from /dev/zero&amp;lt;ref&amp;gt;[http://en.wikipedia.org/wiki//dev/zero /dev/zero] (en.wikipedia.org)&amp;lt;/ref&amp;gt; and ideally written it to an &amp;#039;&amp;#039;&amp;#039;empty RAID array, hard disk or partition&amp;#039;&amp;#039;&amp;#039; (such as using of=/dev/sda for the first hard disk or of=/dev/sda2 for the second partition on the first hard disk). If this is not possible, a &amp;#039;&amp;#039;&amp;#039;normal file in the file system&amp;#039;&amp;#039;&amp;#039; (such as using of=/root/testfile) can be written. For safety reasons we are using test files in the following examples. The write performance achieved thereby will be a little slower (because metadata will also be written to the file system).&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039;Important:&amp;#039;&amp;#039;&amp;#039; When writing to a device (such as /dev/sda), the data stored there will be lost. For that reason, you should only use &amp;#039;&amp;#039;&amp;#039;empty&amp;#039;&amp;#039;&amp;#039; RAID arrays, hard disks or partitions.&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039;Note:&amp;#039;&amp;#039;&amp;#039;&lt;br /&gt;
* When using if=/dev/zero and bs=1G, Linux will need 1GB of free space in RAM. If your test system does not have sufficient RAM available, use a smaller parameter for bs (such as 512MB).&lt;br /&gt;
* In order to get results closer to real-life, we recommend performing the tests described several times (three to ten times, for example). By doing so, you can quickly detect [http://en.wikipedia.org/wiki/Outlier outliers]. Such outliers can include cron jobs, interrupts or general conditions due to parallel processing, which can all briefly affect performance. An extreme example, which clarifies this issue, would be the parallel [[Linux Analyses of Execution Time using time|execution of updatedb]] by a cron job.&lt;br /&gt;
&lt;br /&gt;
===Laptop Example===&lt;br /&gt;
In this example, the test data will be written to /root/testfile. The test system (a Thinkpad T43 Type 2668-4GG) had 1.5 GByte of RAM and a Fujitsu MHT2060AH hard disk rotating at 5,400 rpm.&lt;br /&gt;
&lt;br /&gt;
====Laptop Throughput (Streaming I/O)====&lt;br /&gt;
One gigabyte was written for the test, first with the cache activated (hdparm -W1 /dev/sda):&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
root@grml ~ # dd if=/dev/zero of=/root/testfile bs=1G count=1 oflag=direct&lt;br /&gt;
1+0 records in&lt;br /&gt;
1+0 records out&lt;br /&gt;
1073741824 bytes (1.1 GB) copied, 32.474 s, 33.1 MB/s&lt;br /&gt;
root@grml ~ # &lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Then, with the cache deactivated (hdparm -W0 /dev/sda):&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
root@grml ~ # dd if=/dev/zero of=/root/testfile bs=1G count=1 oflag=direct    &lt;br /&gt;
1+0 records in&lt;br /&gt;
1+0 records out&lt;br /&gt;
1073741824 bytes (1.1 GB) copied, 123.37 s, 8.7 MB/s&lt;br /&gt;
root@grml ~ # &lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
====Laptop Latency====&lt;br /&gt;
In this test, 512 bytes were written one thousand times, first with the cache activated (hdparm -W1 /dev/sda):&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
root@grml ~ # dd if=/dev/zero of=/root/testfile bs=512 count=1000 oflag=direct&lt;br /&gt;
1000+0 records in&lt;br /&gt;
1000+0 records out&lt;br /&gt;
512000 bytes (512 kB) copied, 0.36084 s, 1.4 MB/s&lt;br /&gt;
root@grml ~ #&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Then, with the cache deactivated (hdparm -W0 /dev/sda): One thousand accesses required 11.18 seconds, meaning one access took 11.18 ms.&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
root@grml ~ # dd if=/dev/zero of=/root/testfile bs=512 count=1000 oflag=direct&lt;br /&gt;
1000+0 records in&lt;br /&gt;
1000+0 records out&lt;br /&gt;
512000 bytes (512 kB) copied, 11.1865 s, 45.8 kB/s&lt;br /&gt;
root@grml ~ # &lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
===Server with RAID10 Example===&lt;br /&gt;
In this example, the test data was written to an empty partition. The test system was an 2HE Intel Dual-CPU SC823 Server with six 147 GB SAS Fujitsu MBA3147RC (15,000 rpm) hard disks and an Adaptec 5805 RAID controller with the cache activated and a BBU.&lt;br /&gt;
&lt;br /&gt;
====Server Throughput (Streaming I/O)====&lt;br /&gt;
One gigabyte was written for the test:&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
test-sles10sp2:~ # dd if=/dev/zero of=/root/testfile bs=1G count=1 oflag=dsync&lt;br /&gt;
1+0 records in&lt;br /&gt;
1+0 records out&lt;br /&gt;
1073741824 bytes (1.1 GB) copied, 5.11273 seconds, 210 MB/s&lt;br /&gt;
test-sles10sp2:~ &lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
====Server Latency====&lt;br /&gt;
In this test, 512 bytes were written one thousand times. Thereby, the 0.084 seconds that were measured for one thousand accesses corresponded to precisely 0.084 ms for each access. This value is so low because of the RAID controller’s cache:&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
test-sles10sp2:~ # dd if=/dev/zero of=/root/testfile bs=512 count=1000 oflag=dsync&lt;br /&gt;
1000+0 records in&lt;br /&gt;
1000+0 records out&lt;br /&gt;
512000 bytes (512 kB) copied, 0.083902 seconds, 6.1 MB/s&lt;br /&gt;
test-sles10sp2:~ #&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
==References==&lt;br /&gt;
&amp;lt;references/&amp;gt;&lt;br /&gt;
&lt;br /&gt;
{{Wfischer}}&lt;br /&gt;
&lt;br /&gt;
[[Category:Linux]]&lt;br /&gt;
[[Category:Linux Performance]]&lt;br /&gt;
[[de:Linux I/O Performance Tests mit dd]]&lt;br /&gt;
[[pl:Test wydajności I/O programem dd w Linuksie]]&lt;/div&gt;</summary>
		<author><name>Machado</name></author>
	</entry>
</feed>