Veritas-bu

[Veritas-bu] iostat during duplication - strange

2002-04-03 15:04:36
Subject: [Veritas-bu] iostat during duplication - strange
From: Mark.Donaldson AT experianems DOT com (Donaldson, Mark)
Date: Wed, 3 Apr 2002 13:04:36 -0700
This message is in MIME format. Since your mail reader does not understand
this format, some or all of this message may not be legible.

------_=_NextPart_001_01C1DB4A.C749F420
Content-Type: text/plain;
        charset="iso-8859-1"

I am demultiplexing during duplication - but I thought that multiplexed
backups were interwoven fragments.  Shouldn't I be reading one image's
fragment, skipping over another, then reading another appropriate fragment?
(you know: "mt fsf #")

Your comments suggest that data within fragments is from multiple clients?

If this is the case, I may have the answer to my slow duplications - I have
to read through piles of junk to cull out what I want to duplicate.



-----Original Message-----
From: Ballowe, Charles [mailto:CBallowe AT usg DOT com]
Sent: Wednesday, April 03, 2002 12:41 PM
To: 'Donaldson, Mark'
Subject: RE: [Veritas-bu] iostat during duplication - strange


are you maybe de-multiplexing durring duplication?

-----Original Message-----
From: Donaldson, Mark [mailto:Mark.Donaldson AT experianems DOT com]
Sent: Wednesday, April 03, 2002 12:42 PM
To: Veritasbu (E-mail)
Subject: [Veritas-bu] iostat during duplication - strange


So here I am, testing the I/O characteristics of my new buffer settings for
duplications.  I'm doing an "iostat" and I see the following for the two
tape drives that are source and destination for this dup.
$ sudo iostat -xtnc 5 | egrep "rmt.[01]|wsvc" 
  r/s  w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b device 
 32.0  0.0 8192.1    0.0  0.0  1.0    0.0   31.1   0 100 rmt/0 
  0.0 14.0    0.0 3584.0  0.0  0.6    0.0   45.4   0  63 rmt/1 
  r/s  w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b device 
 31.2  0.0 7986.9    0.0  0.0  1.0    0.0   31.9   0  99 rmt/0 
  0.0 16.8    0.0 4300.6  0.0  0.7    0.0   38.7   0  65 rmt/1 
  r/s  w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b device 
 31.0  0.0 7935.8    0.0  0.0  1.0    0.0   32.1   0 100 rmt/0 
  0.0 16.4    0.0 4198.3  0.0  0.5    0.0   32.8   0  54 rmt/1 
It's easy to see which is source and which is destination.  The strange
thing, consistent over about 10 minutes of this, is the nearly 2-to-1
difference between read volume (kr/s) & write volume (kw/s).  
My first thought was blocking factors for read and write were different but
the iostat man page says these columes are KBytes/sec not blocks/sec.  
Next I speculated that it was read-ahead buffering but eventually the
buffers would be full and I'd see the volume turn around - which I haven't.

I've verified that this is the only source and destination tapes in use -
the other tapes in other drives are doing other work.
tpconfig has each of these devices with the same settings, /dev/rmt/[01]cbn.
I would expect input volumes to match output volumes since the compression
is taking on the device.
So the new quandry - why doesn't the read volume match the write volume? 
BTW: Sol 2.6 master/media, VxNB 3.4.1. 
----------------------------------------------------------------------- 
   Mark Donaldson - Sr. Systems Engineer 
   Experian EMS - Denver Colorado 
----------------------------------------------------------------------- 

------_=_NextPart_001_01C1DB4A.C749F420
Content-Type: text/html;
        charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; =
charset=3Diso-8859-1">
<META NAME=3D"Generator" CONTENT=3D"MS Exchange Server version =
5.5.2653.12">
<TITLE>RE: [Veritas-bu] iostat during duplication - strange</TITLE>
</HEAD>
<BODY>

<P><FONT SIZE=3D2>I am demultiplexing during duplication - but I =
thought that multiplexed backups were interwoven fragments.&nbsp; =
Shouldn't I be reading one image's fragment, skipping over another, =
then reading another appropriate fragment?&nbsp; (you know: &quot;mt =
fsf #&quot;)</FONT></P>

<P><FONT SIZE=3D2>Your comments suggest that data within fragments is =
from multiple clients?</FONT>
</P>

<P><FONT SIZE=3D2>If this is the case, I may have the answer to my slow =
duplications - I have to read through piles of junk to cull out what I =
want to duplicate.</FONT></P>
<BR>
<BR>

<P><FONT SIZE=3D2>-----Original Message-----</FONT>
<BR><FONT SIZE=3D2>From: Ballowe, Charles [<A =
HREF=3D"mailto:CBallowe AT usg DOT com">mailto:CBallowe AT usg DOT 
com</A>]</FONT>
<BR><FONT SIZE=3D2>Sent: Wednesday, April 03, 2002 12:41 PM</FONT>
<BR><FONT SIZE=3D2>To: 'Donaldson, Mark'</FONT>
<BR><FONT SIZE=3D2>Subject: RE: [Veritas-bu] iostat during duplication =
- strange</FONT>
</P>
<BR>

<P><FONT SIZE=3D2>are you maybe de-multiplexing durring =
duplication?</FONT>
</P>

<P><FONT SIZE=3D2>-----Original Message-----</FONT>
<BR><FONT SIZE=3D2>From: Donaldson, Mark [<A =
HREF=3D"mailto:Mark.Donaldson AT experianems DOT com">mailto:Mark.Donaldson@exp=
erianems.com</A>]</FONT>
<BR><FONT SIZE=3D2>Sent: Wednesday, April 03, 2002 12:42 PM</FONT>
<BR><FONT SIZE=3D2>To: Veritasbu (E-mail)</FONT>
<BR><FONT SIZE=3D2>Subject: [Veritas-bu] iostat during duplication - =
strange</FONT>
</P>
<BR>

<P><FONT SIZE=3D2>So here I am, testing the I/O characteristics of my =
new buffer settings for</FONT>
<BR><FONT SIZE=3D2>duplications.&nbsp; I'm doing an &quot;iostat&quot; =
and I see the following for the two</FONT>
<BR><FONT SIZE=3D2>tape drives that are source and destination for this =
dup.</FONT>
<BR><FONT SIZE=3D2>$ sudo iostat -xtnc 5 | egrep =
&quot;rmt.[01]|wsvc&quot; </FONT>
<BR><FONT SIZE=3D2>&nbsp; r/s&nbsp; w/s&nbsp;&nbsp; kr/s&nbsp;&nbsp; =
kw/s wait actv wsvc_t asvc_t&nbsp; %w&nbsp; %b device </FONT>
<BR><FONT SIZE=3D2>&nbsp;32.0&nbsp; 0.0 8192.1&nbsp;&nbsp;&nbsp; =
0.0&nbsp; 0.0&nbsp; 1.0&nbsp;&nbsp;&nbsp; 0.0&nbsp;&nbsp; =
31.1&nbsp;&nbsp; 0 100 rmt/0 </FONT>
<BR><FONT SIZE=3D2>&nbsp; 0.0 14.0&nbsp;&nbsp;&nbsp; 0.0 3584.0&nbsp; =
0.0&nbsp; 0.6&nbsp;&nbsp;&nbsp; 0.0&nbsp;&nbsp; 45.4&nbsp;&nbsp; =
0&nbsp; 63 rmt/1 </FONT>
<BR><FONT SIZE=3D2>&nbsp; r/s&nbsp; w/s&nbsp;&nbsp; kr/s&nbsp;&nbsp; =
kw/s wait actv wsvc_t asvc_t&nbsp; %w&nbsp; %b device </FONT>
<BR><FONT SIZE=3D2>&nbsp;31.2&nbsp; 0.0 7986.9&nbsp;&nbsp;&nbsp; =
0.0&nbsp; 0.0&nbsp; 1.0&nbsp;&nbsp;&nbsp; 0.0&nbsp;&nbsp; =
31.9&nbsp;&nbsp; 0&nbsp; 99 rmt/0 </FONT>
<BR><FONT SIZE=3D2>&nbsp; 0.0 16.8&nbsp;&nbsp;&nbsp; 0.0 4300.6&nbsp; =
0.0&nbsp; 0.7&nbsp;&nbsp;&nbsp; 0.0&nbsp;&nbsp; 38.7&nbsp;&nbsp; =
0&nbsp; 65 rmt/1 </FONT>
<BR><FONT SIZE=3D2>&nbsp; r/s&nbsp; w/s&nbsp;&nbsp; kr/s&nbsp;&nbsp; =
kw/s wait actv wsvc_t asvc_t&nbsp; %w&nbsp; %b device </FONT>
<BR><FONT SIZE=3D2>&nbsp;31.0&nbsp; 0.0 7935.8&nbsp;&nbsp;&nbsp; =
0.0&nbsp; 0.0&nbsp; 1.0&nbsp;&nbsp;&nbsp; 0.0&nbsp;&nbsp; =
32.1&nbsp;&nbsp; 0 100 rmt/0 </FONT>
<BR><FONT SIZE=3D2>&nbsp; 0.0 16.4&nbsp;&nbsp;&nbsp; 0.0 4198.3&nbsp; =
0.0&nbsp; 0.5&nbsp;&nbsp;&nbsp; 0.0&nbsp;&nbsp; 32.8&nbsp;&nbsp; =
0&nbsp; 54 rmt/1 </FONT>
<BR><FONT SIZE=3D2>It's easy to see which is source and which is =
destination.&nbsp; The strange</FONT>
<BR><FONT SIZE=3D2>thing, consistent over about 10 minutes of this, is =
the nearly 2-to-1</FONT>
<BR><FONT SIZE=3D2>difference between read volume (kr/s) &amp; write =
volume (kw/s).&nbsp; </FONT>
<BR><FONT SIZE=3D2>My first thought was blocking factors for read and =
write were different but</FONT>
<BR><FONT SIZE=3D2>the iostat man page says these columes are =
KBytes/sec not blocks/sec.&nbsp; </FONT>
<BR><FONT SIZE=3D2>Next I speculated that it was read-ahead buffering =
but eventually the</FONT>
<BR><FONT SIZE=3D2>buffers would be full and I'd see the volume turn =
around - which I haven't.</FONT>
</P>

<P><FONT SIZE=3D2>I've verified that this is the only source and =
destination tapes in use -</FONT>
<BR><FONT SIZE=3D2>the other tapes in other drives are doing other =
work.</FONT>
<BR><FONT SIZE=3D2>tpconfig has each of these devices with the same =
settings, /dev/rmt/[01]cbn.</FONT>
<BR><FONT SIZE=3D2>I would expect input volumes to match output volumes =
since the compression</FONT>
<BR><FONT SIZE=3D2>is taking on the device.</FONT>
<BR><FONT SIZE=3D2>So the new quandry - why doesn't the read volume =
match the write volume? </FONT>
<BR><FONT SIZE=3D2>BTW: Sol 2.6 master/media, VxNB 3.4.1. </FONT>
<BR><FONT =
SIZE=3D2>---------------------------------------------------------------=
-------- </FONT>
<BR><FONT SIZE=3D2>&nbsp;&nbsp; Mark Donaldson - Sr. Systems Engineer =
</FONT>
<BR><FONT SIZE=3D2>&nbsp;&nbsp; Experian EMS - Denver Colorado </FONT>
<BR><FONT =
SIZE=3D2>---------------------------------------------------------------=
-------- </FONT>
</P>

</BODY>
</HTML>
------_=_NextPart_001_01C1DB4A.C749F420--