[Search for users] [Overall Top Noters] [List of all Conferences] [Download this site]

Conference vaxaxp::vmsnotes

Title:	VAX and Alpha VMS
Notice:	This is a new VMSnotes, please read note 2.1
Moderator:	VAXAXP::BERNARDO

Created:	Wed Jan 22 1997
Last Modified:	Fri Jun 06 1997
Last Successful Update:	Fri Jun 06 1997
Number of topics:	703
Total number of notes:	3722

346.0. "Shadowing on FDDI cluster..." by MSAM00::ONGKIENHIN () Tue Mar 18 1997 19:36

    Hi,
    
    My customer is running OpenVMS AXP 6.2-1h3 FDDI cluster and shadowing with 
    the following configuration:
    
    	------------             ------------------             ----------
        |           |DEFEA-AA ---|FDDI Concentrator| ---DEFAA-DA|        |
        | AS2000    |		 ------------------             |DEC4710 |
        |           |		------	FDDI  ------		|	 |
    	| 256MB	    |DE422-SA --|900EF|-------|900EF|---Ethernet|256MB	 |
        |	    |	      -	------	      ------		|	 |
	|___________	     |					_________
                             |
        ------------         |
    	| Dec2000  |----------
    	-----------
        Quorum node
    
    Previously, they were having DEC4710 instead of Alphaserver2000 which
    is using the DEFEA-AA(EISA FDDI). They experience slower shadow copying
    between the two system. Is there any system parameter that can speed up
    the shadow copying? How can I determine that the shadow copying and
    cluster communication run over FDDI instead of ethernet?
    
    Thks.
    
    Ong

T.R	Title	User	Personal Name	Date	Lines
346.1	NISCS_MAX_PKTSZ = 4468 ?	OSLAGE::AGE_P	Aage Ronning, Oslo, Norway, (DTN 872-8464)	`Wed Mar 19 1997 02:10`	19
	>>Is there any system parameter that can speed up the shadow copying? Set NISCS_MAX_PKTSZ to 4468 to take advantage of the FDDI. >>How can I determine that the shadow copying and cluster communication >>run over FDDI instead of ethernet? You can only look at the counters for the different virtual circuits in SDA: SDA> show port SDA> show port/vc/ch/addr-=pe_pdt Look at the counters for Ethernet and FDDI to the specific node. FDDI should be the preferred path when NISCS_MAX_PKTSZ is set to 4468 on both FDDI systems. And you can stop one of the busses with the LAVC$STOP_BUS program in sys$examples to see the difference between running on only FDDI or Ethernet. \�ge
346.2		AMCFAC::RABAHY	dtn 471-5160, outside 1-810-347-5160	`Wed Mar 19 1997 09:35`	24
	Hmm, do any of numbers below look funny? VMScluster data structures -------------------------- --- Port Block 81CCB200 --- Status: 0001 authorize VC Count: 6 Secs Since Last Zeroed: 3354473 SBUF Size 484 LBUF Size 4786 Fork Count 1575931337 SBUF Count 14 LBUF Count 1 Refork Count 0 SBUF Max 768 LBUF Max 384 Last Refork 00000000 SBUF Quo 14 LBUF Quo 1 SCS Messages1282086734 SBUF Miss 53567 LBUF Miss 45708 VC Queue Cnt1202131752 SBUF Allocs 2126600208 LBUF Allocs 972707301 TQE Received 33544733 SBUFs In Use 2 LBUFs In Use 0 Timer Done 33544733 Peak SBUF In Use 99 Peak LBUF In Use 90 RWAITQ Count 560898077 SBUF Queue Empty 0 LBUF Queue Empty 0 LDL Buf/Msg 1431248 TR SBUF Queue Empty 0 Ticks/Second 10 ACK Delay 1000000 No SBUF for ACK 0 Listen Timeout 8 Hello Interval 30 I suspect RWAITQ Count is high?