In a message dated 10/17/2005 11:26:21 A.M. Central Daylight Time,
[EMAIL PROTECTED] writes:
>Disabling caching doesn't work on most recent control units. There are
>flags in the Define Extent CCW but in the IBM 2105 (Shark) manual they say:
>001 - bypass cache - tracks accessed by this
But not all I/Os use caching. Some access methods disable caching for
certain I/Os which could account for a high percentage of cache misses.
Disabling caching doesn't work on most recent control units. There are
flags in the Define Extent CCW but in the IBM 2105 (Shark) manual they say:
In a message dated 10/6/2005 11:39:54 A.M. Central Daylight Time,
[EMAIL PROTECTED] writes:
>Unless I have my head on backwards today (it happens), search with key or
similar >operations which cannot be converted to ECKD, cause large CONNECT
time, not >disconnect, since they are essentiall
There are several reasons for disconnect time
- read cache miss
- reconnect misses
- PPRC (I don't know how they call it on HDS)
- CU busy
Are you on ESCON or FICON ?
On 10/6/05, Bruce Black <[EMAIL PROTECTED]> wrote:
>
> >
> >
> >We have a high disconnect time on a IMS vsam database. device is H
We have a high disconnect time on a IMS vsam database. device is HDS
9980V. I guess this is because the channel program is performing SEEK
for a specific block, or Search with Key. Can't see any other reason why
this happens.
Unless I have my head on backwards today (it happens), search with k
disconnect time on IMS vsam db
We do. But this database is almost read only (98.8% of the total IO for
the disk drive the DB resides on). There is no RPM miss on that kind of
device, so I guess it is a search with key or Seek. I looked at the SSAs
but couldn't see any special argument that
ack and get the info from there.
Ron
> -Original Message-
> From: IBM Mainframe Discussion List [mailto:[EMAIL PROTECTED] On
> Behalf Of Itschak Mugzach
> Sent: Thursday, 6 October 2005 11:01 PM
> To: IBM-MAIN@BAMA.UA.EDU
> Subject: Re: High disconnect time on IMS vsam db
; From: IBM Mainframe Discussion List [mailto:[EMAIL PROTECTED] On
> Behalf Of Itschak Mugzach
> Sent: Thursday, 6 October 2005 4:30 PM
> To: IBM-MAIN@BAMA.UA.EDU
> Subject: High disconnect time on IMS vsam db
>
> We have a high disconnect time on a IMS vsam database. device is H
We do. But this database is almost read only (98.8% of the total IO for
the disk drive the DB resides on). There is no RPM miss on that kind of
device, so I guess it is a search with key or Seek. I looked at the SSAs
but couldn't see any special argument that might cause that.
Itschak
-
Mainframe Discussion List [EMAIL PROTECTED]
Sent: 10/06/2005 04:51 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: High disconnect time on IMS vsam db
Ron, wherefore art thou Ron
Might even make a bit of sense with a bit of luck
Shane ...
From: "Itschak Mugzach"
> W
Ron, wherefore art thou Ron
Might even make a bit of sense with a bit of luck
Shane ...
From: "Itschak Mugzach"
> We have a high disconnect time on a IMS vsam database. device is HDS
> 9980V. I guess this is because the channel program is performing SEEK
> for a specific block,
We have a high disconnect time on a IMS vsam database. device is HDS
9980V. I guess this is because the channel program is performing SEEK
for a specific block, or Search with Key. Can't see any other reason why
this happens.
Thanks for your advise.
Itschak
---
12 matches
Mail list logo
