On Thu, 10 Dec 2015 14:05:26 -0800, Barton Robinson wrote:
> If anybody in endicott is listening, ONE REQUEST. The current diagnose
> used by the CMM function to release a page actually causes z/VM to read
> the page in from the paging subsystem before releasing it. So release
> 100,000 pages
Has something changed in last 5 years? This has been in my standard
SHARE presentations for the last 5 years, with CMM drop 20,000 pages,
and there are 20,000 page reads. Drop another 20,000 pages, and there
are 40,000 page reads (and 20,000 page writes becuase it was a
constrained storage
One possibility that occurred to me that would cause this "page in only to
release" behavior is if Linux has the pages to be released on a linked
list, and the linked list is maintained with pointers in the pages
themselves, rather than an outside structure. If that's the case, then
Linux has to
It couldn't be pgmbk, this was a result of a LINUX CMM command, and it
was the Linux storage assigned to the virtual machine that was targeted.
On 12/11/2015 11:01 AM, Bill Holder wrote:
Barton Robinson wrote:
Drop another 20,000 pages, and there
are 40,000 page reads (and 20,000 page writes
Barton Robinson wrote:
> Drop another 20,000 pages, and there
> are 40,000 page reads (and 20,000 page writes becuase it was a
> constrained storage experiment).
Now that is rather interesting - that instance where the number
of reads is exactly twice the number of pages being released
maps
On 12/10/2015 05:58 AM, Alan Altmark wrote:
> On Wednesday, 12/09/2015 at 08:15 GMT, Barton Robinson
> wrote:
>> My request to get this fixed was rejected by ibm several years ago. The
>> problem is that even though linux doesn't have anything on the vdisk,
>> z/vm
VERY COOL. So Linux has the technology, z/VM has the technology, now it
just takes someone to use them.
If anybody in endicott is listening, ONE REQUEST. The current diagnose
used by the CMM function to release a page actually causes z/VM to read
the page in from the paging subsystem
Alan Altmark wrote:
> E.g. possibly just re-formatting it could cause a formatted page to be
released. We'd need some input from Bill Holder on that.
Thanks, Alan. Yes, CP will recognize format write CCWs and release the
corresponding vdisk backing storage. So I think that would mean SWAPOFF,
On Behalf Of Mrohs,
Ray (JMD)
Sent: Thursday, December 10, 2015 6:18 AM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: [LINUX-390] Status of VDISK after swap space usage
It's a bit of a balancing act. Running zLinux lean and mean also opens up the
possibility of extensive swapping under unusual
>>> On 12/10/2015 at 07:07 AM, Bill Holder wrote:
> Alan Altmark wrote:
>> E.g. possibly just re-formatting it could cause a formatted page to be
> released. We'd need some input from Bill Holder on that.
>
> Thanks, Alan. Yes, CP will recognize format write CCWs and
: Wednesday, December 09, 2015 6:06 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: Status of VDISK after swap space usage
This is interesting.
Having 2TB of page space in test/dev I'm sure we have some potential space
savings if this could be done across all dev/test servers...
However, you'd really
to define its own
VDISK.
Aria
-Original Message-
From: Linux on 390 Port [mailto:LINUX-390@VM.MARIST.EDU] On Behalf Of Mrohs,
Ray (JMD)
Sent: Wednesday, December 09, 2015 3:05 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Status of VDISK after swap space usage
Hi,
Our environment consists of SLES
Hi,
Our environment consists of SLES 11.4 servers under VM 6.2.
Sometimes we have misbehaving Linux applications that dip heavily into the
SWAPGEN configured swap space. After things settle down, Linux never lets go of
the space until we issue a swapoff -a, and swapon -a. Of course I do this
My request to get this fixed was rejected by ibm several years ago. The
problem is that even though linux doesn't have anything on the vdisk,
z/vm still has to back it. I asked for a diagnose as we do with real
storage - a way for Linux to tell z/vm the page no longer needs
backing. So after
@VM.MARIST.EDU] On Behalf Of Barton
Robinson
Sent: Wednesday, December 09, 2015 12:13 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: [LINUX-390] Status of VDISK after swap space usage
My request to get this fixed was rejected by ibm several years ago. The problem
is that even though linux doesn't have
On Wednesday, 12/09/2015 at 08:15 GMT, Barton Robinson
wrote:
> My request to get this fixed was rejected by ibm several years ago. The
> problem is that even though linux doesn't have anything on the vdisk,
> z/vm still has to back it. I asked for a diagnose as we
16 matches
Mail list logo