Veritas-bu

[Veritas-bu] drive metrics

2002-12-20 13:47:05
Subject: [Veritas-bu] drive metrics
From: scott.kendall AT abbott DOT com (scott.kendall AT abbott DOT com)
Date: Fri, 20 Dec 2002 12:47:05 -0600
This is a multipart message in MIME format.
--=_alternative 0067277386256C95_=
Content-Type: text/plain; charset="us-ascii"

Don't forget to look at network buffers (NET_BUFFER_SZ) and number and 
size of data buffers (waited for empty and waited for full in bptm logs). 
this is all in perf tuning guides from veritas or there is plenty on the 
list about it.

Also, pay attention to number jobs/client, and mpx on drives and schedules 
and make sure your Storage Units are set up to balance the load nicely 
across your media servers.


- Scott





"Shuster, James" <jshuster AT etrade DOT com>
Sent by: veritas-bu-admin AT mailman.eng.auburn DOT edu
12/16/2002 04:38 PM

 
        To:     veritas-bu AT mailman.eng.auburn DOT edu
        cc: 
        Subject:        [Veritas-bu] drive metrics


I am trying to get performance metrics. I have 10 dlt7000 drives in an 
L700
on 3 Crossroads bridges connected to 
an E4500 with 3 JNI 1 Gb HBAs.

I am graphing the drives in Cricket calling a script with iostat -Mcxnt.
My performance seems to avarage around 3 M/per second.

Does anyone have any suggestions for performance improvement and or tools 
to
drill down further to find the bottleneck?
_______________________________________________
Veritas-bu maillist  -  Veritas-bu AT mailman.eng.auburn DOT edu
http://mailman.eng.auburn.edu/mailman/listinfo/veritas-bu



--=_alternative 0067277386256C95_=
Content-Type: text/html; charset="us-ascii"


<br><font size=2 face="Arial">Don't forget to look at network buffers 
(NET_BUFFER_SZ) and number and size of data buffers (waited for empty and 
waited for full in bptm logs). &nbsp;this is all in perf tuning guides from 
veritas or there is plenty on the list about it.</font>
<br>
<br><font size=2 face="Arial">Also, pay attention to number jobs/client, and 
mpx on drives and schedules and make sure your Storage Units are set up to 
balance the load nicely across your media servers.</font>
<br>
<br>
<br><font size=2 face="Arial">- Scott</font>
<br>
<br>
<br>
<br>
<table width=100%>
<tr valign=top>
<td>
<td><font size=1 face="sans-serif"><b>&quot;Shuster, James&quot; &lt;jshuster 
AT etrade DOT com&gt;</b></font>
<br><font size=1 face="sans-serif">Sent by: veritas-bu-admin AT 
mailman.eng.auburn DOT edu</font>
<p><font size=1 face="sans-serif">12/16/2002 04:38 PM</font>
<br>
<td><font size=1 face="Arial">&nbsp; &nbsp; &nbsp; &nbsp; </font>
<br><font size=1 face="sans-serif">&nbsp; &nbsp; &nbsp; &nbsp; To: &nbsp; 
&nbsp; &nbsp; &nbsp;veritas-bu AT mailman.eng.auburn DOT edu</font>
<br><font size=1 face="sans-serif">&nbsp; &nbsp; &nbsp; &nbsp; cc: &nbsp; 
&nbsp; &nbsp; &nbsp;</font>
<br><font size=1 face="sans-serif">&nbsp; &nbsp; &nbsp; &nbsp; Subject: &nbsp; 
&nbsp; &nbsp; &nbsp;[Veritas-bu] drive metrics</font></table>
<br>
<br>
<br><font size=2 face="Courier New">I am trying to get performance metrics. I 
have 10 dlt7000 drives in an L700<br>
on 3 Crossroads bridges connected to <br>
an E4500 with 3 JNI 1 Gb HBAs.<br>
<br>
I am graphing the drives in Cricket calling a script with iostat -Mcxnt.<br>
My performance seems to avarage around 3 M/per second.<br>
<br>
Does anyone have any suggestions for performance improvement and or tools to<br>
drill down further to find the bottleneck?<br>
_______________________________________________<br>
Veritas-bu maillist &nbsp;- &nbsp;Veritas-bu AT mailman.eng.auburn DOT edu<br>
http://mailman.eng.auburn.edu/mailman/listinfo/veritas-bu<br>
</font>
<br>
<br>
--=_alternative 0067277386256C95_=--

<Prev in Thread] Current Thread [Next in Thread>