Re: Tape drive disconnect time issue



Check the CHPid percent utilization on the HMC SAD display.



-----Original Message-----
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@xxxxxxxxxxx] On Behalf Of John Kelly
Sent: Wednesday, February 03, 2010 3:10 PM
To: IBM-MAIN@xxxxxxxxxxx
Subject: Re: Tape drive disconnect time issue

<snip>
some of those STK drives were faster than ESCON could go. Have you looked
at the path?
</snip>

the LCU display doesn't show any contention and each drive has its own
ESCON so I would image that the throttle would be the CHP and/or I/O
processor in the z9. The total number of I/O vary by about 9% but they
stay in the range of 600k in a 15 minute RMF interval. The higher
disconnect time occur with the same I/O load but at different times, ie
the 0130 hrs interval would have high disconnect and the 0145 interval
would not and both intervals are within 2k SIOs for the intervals.

Jack Kelly
202-502-2390 (Office)



From:
Hal Merritt <HMerritt@xxxxxxxxxxxxx>
To:
IBM-MAIN@xxxxxxxxxxx
Date:
02/03/2010 03:32 PM
Subject:
Re: Tape drive disconnect time issue
Sent by:
IBM Mainframe Discussion List <IBM-MAIN@xxxxxxxxxxx>



IIRC, some of those STK drives were faster than ESCON could go. Have you
looked at the path?



-----Original Message-----
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@xxxxxxxxxxx] On
Behalf Of John Kelly
Sent: Wednesday, February 03, 2010 12:51 PM
To: IBM-MAIN@xxxxxxxxxxx
Subject: Tape drive disconnect time issue

I have an old STK tape system ( ten 9840's in 3490 emulation mode inside a

9740. Each drive ESCON point to point) , that will hopefully go away but
.....

I have an issue with HSM dump running longer than expected. The problem
appears disconnect time. During the HSM dumps, we're using four drives for

two DumpClasses and most other stuff is stopped (some FTPs will come in).
No other tasks or LPAR is using any tape drive. Cpu is in the low 20%
range, DASD service time is around 4 ms and DASD rate is around 50 and
tape rate is around 600.

One set of tape drives (1 tape for each of the two DumpClasses) has an RMF

average disconnect time of .84 and the other set of drives has an average
disconnect time of .06. This translates into a difference of 40k SIO in a
15 minute interval. This disparity will last for almost an hour, then the
high disconnect time goes away (still using the same four tapes and
drives). SMF21 doesn't indicate any Erase Gaps or temporary errors which

I know causes high disconnect times.

Jack Kelly
202-502-2390 (Office)


NOTICE: This electronic mail message and any files transmitted with it are
intended
exclusively for the individual or entity to which it is addressed. The
message,
together with any attachment, may contain confidential and/or privileged
information.
Any unauthorized review, use, printing, saving, copying, disclosure or
distribution
is strictly prohibited. If you have received this message in error, please

immediately advise the sender by reply email and delete all copies.

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to listserv@xxxxxxxxxxx with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to listserv@xxxxxxxxxxx with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
NOTICE: This electronic mail message and any files transmitted with it are intended
exclusively for the individual or entity to which it is addressed. The message,
together with any attachment, may contain confidential and/or privileged information.
Any unauthorized review, use, printing, saving, copying, disclosure or distribution
is strictly prohibited. If you have received this message in error, please
immediately advise the sender by reply email and delete all copies.

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to listserv@xxxxxxxxxxx with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
.



Relevant Pages

  • Re: Tape drive disconnect time issue
    ... some of those STK drives were faster than ESCON could go. ... Tape drive disconnect time issue ... One set of tape drives has an RMF ...
    (bit.listserv.ibm-main)
  • Re: Tape drive disconnect time issue
    ... I don't have a SAD going but I have RMF's channel report and again these ... Tape drive disconnect time issue ... some of those STK drives were faster than ESCON could go. ... One set of tape drives has an RMF ...
    (bit.listserv.ibm-main)
  • Re: Tape drive disconnect time issue
    ... ESCON so I would image that the throttle would be the CHP and/or I/O ... disconnect time occur with the same I/O load but at different times, ... some of those STK drives were faster than ESCON could go. ... One set of tape drives has an RMF ...
    (bit.listserv.ibm-main)
  • Tape drive disconnect time issue
    ... I have an issue with HSM dump running longer than expected. ... No other tasks or LPAR is using any tape drive. ... One set of tape drives has an RMF ... average disconnect time of .84 and the other set of drives has an average ...
    (bit.listserv.ibm-main)
  • Re: IBM announces Encrypting tape drives
    ... Too bad that wasn't offloaded to zIIPs/zAAPs/zEEPs ("Enhanced Encryption Processor" - I just made that up) to generalize the support somehow. ... I'm not sure what the delays might be for opening a large number of small encrypted files once you get past the first one because I've completely lost track of how the drives to buffering and tape positioning these days. ... Offloading the CPU busy to a zAAP or zIIP would solve the CP busy problem but introduce another--you'd have to buy at least one zAAP/zIIP/zEEP/whatever to benefit from the offload, and you'd have to buy enough of them to sustain the maximum aggregate data rate you needed to meet your requirements without using up any CP cycles to maximize that benefit. ... while I don't have the numbers handy, my understanding is that a bunch of tape drives can simply sustain a significantly higher data rate with compression and encryption. ...
    (bit.listserv.ibm-main)