Veritas-bu

Re: [Veritas-bu] MPX Explanation

2007-09-06 08:24:35
Subject: Re: [Veritas-bu] MPX Explanation
From: "Kevin Whittaker" <Kevin.Whittaker AT syniverse DOT com>
To: "Justin Piszcz" <jpiszcz AT lucidpixels DOT com>, "Clooney, David" <david.clooney AT bankofamerica DOT com>
Date: Thu, 6 Sep 2007 07:56:55 -0400
I would agree, that is what I have seen happen.  If one stream lags
behind it just skips putting it on the drive until it is ready. 

-----Original Message-----
From: veritas-bu-bounces AT mailman.eng.auburn DOT edu
[mailto:veritas-bu-bounces AT mailman.eng.auburn DOT edu] On Behalf Of Justin
Piszcz
Sent: Thursday, September 06, 2007 7:19 AM
To: Clooney, David
Cc: veritas-bu AT mailman.eng.auburn DOT edu
Subject: Re: [Veritas-bu] MPX Explanation



On Thu, 6 Sep 2007, Clooney, David wrote:

> Hi All
>
>
>
> Is there any chance someone could clarify MPX for me.
>
>
>
> If you have MPX set to 4 for example and there are 4 streams hitting 
> the drive. All 4 streams are writing in parallel as the tape spins. 
> And if 3 streams are writing at 15mb/sec and 1 stream is writing at 
> 10mb/sec, would the slower of the streams be a bottle neck for the 
> other 3. My lack of the tape technology is most probably to blame, I 
> am thinking of each stream the way fragments work on a tape , finish 1

> start the next , please tell me this is not the same on each stream.
>

That is a good question, but I don't think so(?) I think the 3 streams a
15MB/s continue to truck along and the 10MB/s stream writes at 10MB/s
but its more stretched out, example:

15MB/s stream:
# # # # # # # # # # # # # # # #

10MB/s stream:
#   #   #   #   #   #   #   #   #

Justin.

_______________________________________________
Veritas-bu maillist  -  Veritas-bu AT mailman.eng.auburn DOT edu
http://mailman.eng.auburn.edu/mailman/listinfo/veritas-bu


_______________________________________________
Veritas-bu maillist  -  Veritas-bu AT mailman.eng.auburn DOT edu
http://mailman.eng.auburn.edu/mailman/listinfo/veritas-bu

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