Disk write speed

From: L, Raghunath (Raghunath) (lraghunath_at_lucent.com)
Date: 11/28/05

  • Next message: sumeet.chandwani_at_tcs.com: "Bypassing SCCS id keyword" 
    To: "'sunmanagers@sunmanagers.org'" <sunmanagers@sunmanagers.org>
Date: Mon, 28 Nov 2005 15:32:37 +0530

     Hi Managers,
     
     I forgot to put the file argument
     
     Please try /bin/date;/usr/sbin/mkfie 1024m file1 ;/bin/date or
             time /usr/sbin/mkfie 1024m file1

     Thanks to Simon Burr for pointing the mistake.
     --
     Sincerely,
     Raghu
     SDE Team
     <>Fix the problem, not the blame. <>
     
              -----Original Message-----
             From: L, Raghunath (Raghunath)
             Sent: Monday, November 28, 2005 1:08 PM
             To: 'sunmanagers@sunmanagers.org'
             Subject: Disk write time.
     
             Hi Managers,
     
             I have done a small expariment with storage to check the time taken
    for creating 1Gb file in
     
             Location Time taken
     
             1) /tmp (Memory is the fastest) - 3 seconds
             2) T3+ ( Veiritas managed Vol)- 40 seconds
             3) T3+ ( Not Veritas Vol )-20 seconds
             4) 3510 ( Veritas managed)-40 seconds
             5) Cheethah 10RPM internal disk of V20Z-20 seconds
             6) Internal disk of 4 year old E420 R- 30 seconds
     
             T3+ and 3510 have raid five+ volumeslicing enabled.
             T3+ has 1GB Cache and 3510 has 2GB cache
             T3+ FC is at 1GBPS and 2GBPS for 3510
             qlogic swithes used here are in serial loop
     
             If you have SAN or direct attached storage with you can you please
    try this
     
             /bin/date;/usr/sbin/mkfie 1024m;/bin/date # this will create a 1Gb
    file sp please make sure you have enough space before trying this.
     
             I am bit surprised by the time taken by T3+ and 3510 as it looks
    like it's on the slower side compaed to even internal drive of the old
    server.
             --
             Sincerely,
             Raghu
             SDE Team
             <>Fix the problem, not the blame. <>
    _______________________________________________
    sunmanagers mailing list
    sunmanagers@sunmanagers.org
    http://www.sunmanagers.org/mailman/listinfo/sunmanagers

  • Next message: sumeet.chandwani_at_tcs.com: "Bypassing SCCS id keyword"

    Relevant Pages

    • QCD example 9.1 from Elementary Particles by Griffiths
      ... I think there's a mistake in the setup but I'm totally ... exchange for quark-antiquark interaction. ... incoming quark is red, and the incoming antiquark is antiblue. ... The problem is when I fix ...
      (sci.physics)
    • Re: What happened on this ILS approach?
      ... > I recall my instructor preaching against diving for the glideslope, ... this to fix a bad vector - but not your own mistake. ... student to fly, and teach him how to deal with them. ...
      (rec.aviation.ifr)
    • Re: CBS: The Republican War on Science
      ... Then blame GHWBush who betrayed those who tried to overthrow Saddam ... Kuwait safe for democracy-hating sheiks.- Hide quoted text - ... When you decide to fix a mistake, you need to know how to fix it. ...
      (talk.origins)
    • Re: sprintf()/printf() behaves in different way on 64-bit UNIX, for +ve and -ve integer valu
      ... He made a mistake in his code, but got the same result he would have had ... equivalent but correct code would be. ... needs to fix the operator or cast the argument. ... But the reason why it fails obviously with negative numbers, ...
      (comp.unix.programmer)
    • Re: BUSH WINS!
      ... >>does Bush read? ... >>Tell me, dear John, tell me. ... > fix the mistakes. ... Indeed, fix the mistake. ...
      (sci.electronics.design)