Re: Mini-survey: Linux usability
When I first got my mitts on this stuff I had awful trouble getting anything working until Rob walked down the corridor and helped me out. We then had a series of discussions concerning a bog-standard DDR image that would get people up and running. That was nearly 10 years ago. Given the recent discussion about having to send notes to Novell to generate sufficient interest to get something similar, it depresses me to see just how far things have come in 10 years. -- Rod (Moan over - back to fixing Access dBs (sigh)...) -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
DASD IO Performance problems
Looking into performance problems, in search of some ideas of what to look for. I believe the issue may be related to the type of DASD being used. Scenario, dd command to generate a 1G file if=/dev/zero takes 15s on x86_64 platform. The same command takes 15m on the s390x platform. In my environment the command takes 16s. My environment leverages MOD-3 DASD while the environment in question has MOD-9 and MOD-27 devices. I know historically the MOD-9 is typically a slower device but I don't know much about the MOD-27. Is it truly possible that the performance of these devices is bad enough to see such a difference between MOD-3 and x86_64 v. MOD-9 and MOD-27? What else should / can I look at to determine the root cause of the performance issues? Thanks! Eric -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: IBM typo or pre-announce ???
Spann, Elizebeth (Betsie) wrote: Agreed. How I wish people here would put their comments in context!! To what have you agreed, Bettie? Betsie -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Dave Jones Sent: Tuesday, June 12, 2007 12:27 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: IBM typo or pre-announce ??? No, it's the usual suspects at Tivoli being their usual idiotic selves... If you said Agreed, here then it would be clear. Lionel B. Dyck wrote: Take a look at this and tell me - is it a typo or is IBM pre-announcing something: http://tinyurl.com/33m27d smile Lionel B. Dyck, Consultant/Specialist Enterprise Platform Services, Mainframe Engineering KP-IT Enterprise Engineering, Client and Platform Engineering Services (CAPES) 925-926-5332 (8-473-5332) | E-Mail: [EMAIL PROTECTED] AIM: lbdyck | Yahoo IM: lbdyck Kaiser Service Credo: Our cause is health. Our passion is service. We?re here to make lives better.? ?Never attribute to malice what can be caused by miscommunication.? NOTICE TO RECIPIENT: If you are not the intended recipient of this e-mail, you are prohibited from sharing, copying, or otherwise using or disclosing its contents. If you have received this e-mail in error, please notify the sender immediately by reply e-mail and permanently delete this e-mail and any attachments without reading, forwarding or saving them. Thank you. And trimming the junk is generally welcomed too! snip By going through a letter and making comments in context, it's easier for one to be sure of not missing some point, and easier for one's reader to see the context in which comments are made so undwrstand them more clearly. Email is not paper mail, and we should adopt forms that benefit from the differences. There's even, so I understand, an RFC* dealing with all this:-) * Internet rule or standard. -- Cheers John -- spambait [EMAIL PROTECTED] [EMAIL PROTECTED] Would you believe people actually try to send email to these spambait addresses? Please do not reply off-list -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. K -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of David Kreuter Sent: Tuesday, June 12, 2007 8:30 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info What would the goal of your POC be? z/VM does many things well - but running one thing only like one Oracle machine is not advisable. Run multiple Oracle machines in your POC. Be careful when comparing performance; show many virtual machines running Oracle, not one. Think business case. Show license savings and the excellent vertical and horizontal growth potential with z/VM in IFLs. Rapid deployment. I have no idea what SOA is other than vaporware and white papers, but, hey, if it's good for z/VM, I like it! David -Original Message- From: Linux on 390 Port on behalf of Yukus, Mary J CIV USMEPCOM Sent: Tue 6/12/2007 3:37 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Thanks for your input everyone. Here are some answers to your questions. The driving forces here are pushing SOA. (I'm still trying to define what this means vs. our current processing architecture) I have seen some articles recently that point to Oracle on LINUX as being a good option for SOA. I am trying to find out what determines this. We currently run on a 2 CPU z-800 2066-0a2 (somewhere around 243 mips). We have a 2 LPAR multi-system sysplex for production running zos on one and zos.e on the other. Originally we had 1 Oracle data base on the zos.e side. And this worked well...for quite a while. We are now doing a lot more (9 data bases) and we are really juggling WLM to try to improve performance. We have divided the data bases over the 2 LPARS now. We have a lot of feeds coming in from other servers and users, replication, etc to keep the data base as current as possible for all the queries that come in. We also have 1 IFL (I believe 192 mips) running z/VM with a handful of LINUX (SLES 8) instances which are used mainly for file servers. One user successfully attempted to put Oracle on a LINUX instance a few years ago but their management chose another path before it was implemented. We are in the same branch with the DBAs so we have the possibility of laying out an Oracle instance in LINUX. We would like to do some type of proof of concept, but I've never done this before. Any and all suggestions/directions/comments are greatly appreciated. Thanks everyone, Mary -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Richards.Bob Sent: Tuesday, June 12, 2007 8:08 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Mary, It has been done quite successfully by numerous people on this list, but I am sure they want more specific information about your configuration in order to advise you further. Information like the number of databases, the number of servers, etc. License costs should be a definite pro. Also contact a local IBMer and see if you can subscribe to one of the z/Linux councils. Lots of good presentations available there, including one on Oracle just put out there recently by David Kreuter of VM-Resources Ltd. [EMAIL PROTECTED] We are in the process of evaluating distributed database consolidations ourselves. Bob Richards -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Yukus, Mary J CIV USMEPCOM Sent: Tuesday, June 12, 2007 7:30 AM To: LINUX-390@VM.MARIST.EDU Subject: Need z/VM-LINUX info Hi Everyone, We are doing research to see if moving some/all of our Oracle data bases from z/OS (1.4 or 1.7) to LINUX on a z/VM IFL would be a good move. We will be moving toward SOA and I need some strong support to recommend this verses going to another platform such as UNIX or Windows. I have read some articles that sound good, but I'm hoping to get some comments, ideas, pro's or con's from anyone out there that can help me either justify the move or reject the idea. Thanks for your help! Mary Yukus :-) LEGAL DISCLAIMER The information transmitted is intended solely for the individual or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of or taking action in reliance upon this information by persons or entities other than the intended recipient is prohibited. If you have received this email in error please contact the sender and delete the material from any computer. SunTrust and Seeing beyond money are federally registered service marks of SunTrust Banks, Inc. [ST:XCL] -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: IBM typo or pre-announce ???
I disagree with you John. It was quite clear that Betsie was replying to Dave Jones' statement that No, it's the usual suspects at Tivoli being their usual idiotic selves... I hope we're not going to get into the whole top-posting vs bottom-posting vs inter-posting debate on here as well. Fuzzy On 6/13/07, John Summerfield [EMAIL PROTECTED] wrote: Spann, Elizebeth (Betsie) wrote: Agreed. How I wish people here would put their comments in context!! To what have you agreed, Bettie? Betsie -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Dave Jones Sent: Tuesday, June 12, 2007 12:27 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: IBM typo or pre-announce ??? No, it's the usual suspects at Tivoli being their usual idiotic selves... If you said Agreed, here then it would be clear. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
An ispf like editor on linux would be great. :) MA On 6/12/07, Spann, Elizebeth (Betsie) [EMAIL PROTECTED] wrote: The kicker for me in my first install was formatting the Linux disk w/out having a Linux system. Having to drop out of the text based menus and figure out how to format and then return to the install. B -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Tom Duerbusch Sent: Tuesday, June 12, 2007 3:01 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Mini-survey: Linux usability Background... I started with SLES7 on z/VM 4.2 on a MP3000 H30. Now up to SLES9 on z/VM 5.2 on a z/890 plus an IFL. The initial, first, worst fight I had, had to do with installing from some media, on some other foreign (foreign to me, being a VM and VSE type for 30+ years). I first used Win/98 and mounted CDs there. I think I was using Samba. Eventually, I got the networking issues straight and I could install SLES7, which I did over an over (practice makes perfect and I was trying out different machine configurations). This was on a 10 mb LAN. 3-4 hours and it was done (I would be doing other work during this time.) A year passed. Time for some more images. SLES8 was now available. However, I was now on Win/2000. Samba didn't work so well. Many days of fighting this. Finally went to the FTP route. Got a freebie FTP server, and had many trials and tribulations in using it. Networking isn't my knowledge base. And SLES8 had different install options and features. Some nice, some good, but it all looked different. It took a lot of time to realize that I did know what I was doing. However, it still took me a long time to give up on the Samba option and go to a FTP server. Another couple years passed. SLES9 was now available. FTP didn't seem to work anymore. I never figured out what the problem was. But I could still install SLES8. So I created a FTP server from SLES8 to store the SLES9 images on. SLES9 didn't seem to install much differently then SLES8, and it was much faster (no vswitch at that time, just routed thru VM's TCPIP stack). We need something, that can take a dummy like myself and drop down a Linux image, preconfigured and preloaded with the Linux images so a person can do the install from a fast, reliable place. And then documentation on how to install a Linux image, based on this preconfigured/preloaded server. Plus, documentation on how to upload new Service Packs and new releases to this server. About as close to free beer as you can get, without actually having a beer G. Some of the many problems I hit, besides changing PC platforms: Some PC based software didn't understand the long file format of Linux. I think that was mostly on Win/98. I don't know if there is any PCs now that have that type of problem. The default FTP server in SLES8 is configured not to allow you to use that FTP server as a source for a SLES install. You have to know you need to change the FTP config file to allow this. My notes are: Joe /etc/vsftpd.conf Uncomment: Local_enable = yes Write_enable = yes Save Chroot_local_user=yes Required for ftp server for zLinux install During installation, when entered *s390x/sles9root*, it gets translated to */s390x/sles9root*. For install to work, it must remain in the suse9 subdirectory and not changed to be off of root. All the Redbooks on installing zLinux, assume that the servers you are using to install from, are properly setup. Well, this dummy, in which my FTP server experience was limited to the VM FTP server and the default configuration for the CSI FTP server on VSE, there was a lot of knowledge that had to be gained for a Linux FTP server, in order to make it useful. So I was in a Catch-22. My knowledge wasn't sufficient on FTP servers to configure one properly. However, to have a FTP server running to test with, I needed a FTP server to be running. Many times, I put it down and went to other projects for a few months. Then, comes firewalls. From my PC, I can basically do anything I need to. But not from the mainframe. YOU (Yast Online Update), just isn't going to work. The network guys are Windows oriented. They also have very major concerns about viruses. Rightly so, as when a virus hits our PC network (4,000 PCs in a City Wide WAN), it takes months to fix the problems. For access outside of the firewall, they want antivirus software installed. Which we don't have. What I keep thinking of, is some Windows based software, that can pull all the new fixes from Novell, and send them up to a mirror residing on zLinux for distirbution via YOU to my zLinux images. Doable...yes. Do I have time? No. It would be nice to have a drop in solution. And yes, we do have a Novell maintenance contract (and we had a SUSE one prior to that). Next topic: TAPE DRIVES Damn it. We are mainframe. We have Ficon and Escon attached tape drives. They may be behind a VTS. They may be managed by a robotic unit.
Re: Mini-survey: Linux usability
Mary Anne Matyaz [EMAIL PROTECTED] wrote: An ispf like editor on linux would be great. :) MA SlickEdit has an ISPF-like mode. And - the IBM LPEX editor is ISPF-like. It's provided as part of Wdz... Unless, you meant, a free one... - Dave Rivers - -- [EMAIL PROTECTED]Work: (919) 676-0847 Get your mainframe programming tools at http://www.dignus.com -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
-Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Wednesday, June 13, 2007 6:27 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Mini-survey: Linux usability An ispf like editor on linux would be great. :) MA You don't like THE? Granted, more like Xedit than PDF EDIT. But, what do I know? I actually like vim! -- John McKown Senior Systems Programmer HealthMarkets Keeping the Promise of Affordable Coverage Administrative Services Group Information Technology The information contained in this e-mail message may be privileged and/or confidential. It is for intended addressee(s) only. If you are not the intended recipient, you are hereby notified that any disclosure, reproduction, distribution or other use of this communication is strictly prohibited and could, in certain circumstances, be a criminal offense. If you have received this e-mail in error, please notify the sender by reply and delete this message without copying or disclosing it. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: IBM typo or pre-announce ???
Fuzzy Logic wrote: I disagree with you John. It was quite clear that Betsie was replying to Dave Jones' statement that No, it's the usual suspects at Tivoli being their usual idiotic selves... You're quite entitled you your opinion, but the fact remains that it did take me a while to work out what Betsie was talking about. I hope we're not going to get into the whole top-posting vs bottom-posting vs inter-posting debate on here as well. _Those_ terms speak of a religious debate, and for that reason I try to avoid them. Besides, bottom posting as it's usually defined is not really the opposite of top posting. It's more between two extremes, the middle course. I didn't have a clear position on the matter until I sought information and a quote for a computer system. Had the salesperson followed my suggestion and followed _this_ procedure, he'd have addressed all my points and probably got the sale. He didn't, he missed some important points and I bought elsewhere. And at that time I understood the reason for interleaving one's reply and took my side. Previously, I'd been doing it anyway, but only because it suited me to do that. Fuzzy -- Cheers John -- spambait [EMAIL PROTECTED] [EMAIL PROTECTED] Please do not reply off-list -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
The what? MA On 6/13/07, McKown, John [EMAIL PROTECTED] wrote: -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Wednesday, June 13, 2007 6:27 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Mini-survey: Linux usability An ispf like editor on linux would be great. :) MA You don't like THE? Granted, more like Xedit than PDF EDIT. But, what do I know? I actually like vim! -- John McKown Senior Systems Programmer HealthMarkets Keeping the Promise of Affordable Coverage Administrative Services Group Information Technology The information contained in this e-mail message may be privileged and/or confidential. It is for intended addressee(s) only. If you are not the intended recipient, you are hereby notified that any disclosure, reproduction, distribution or other use of this communication is strictly prohibited and could, in certain circumstances, be a criminal offense. If you have received this e-mail in error, please notify the sender by reply and delete this message without copying or disclosing it. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
FW: [IP] Mr. Wizard -- Don Herbert, dies at 89
Subject: Mr. Wizard -- Don Herbert, dies at 89 For many of my generation, Mr. Wizard was a key inspiration for becoming involved with science and technology, not to mention performing any number of extremely messy tabletop and kitchen sink experiments. I still have some of his books in my collection. He'd been living just a few miles up the road from where I'm sitting typing this right now. The theme music from his Watch Mr. Wizard show is now running through my head in an endless loop. Goodbye, Mr. Wizard. Obit: http://tinyurl.com/2lrqjj -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
If you know anybody talking Dutch, ask him/her what it means in Dutch, you will be surprised and never forget to smile when you hear SOA :) Marian --- Evans, Kevin R [EMAIL PROTECTED] wrote: I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. Be a better Globetrotter. Get better travel answers from someone who knows. Yahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=listsid=396545469 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
-Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Wednesday, June 13, 2007 7:55 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Mini-survey: Linux usability The what? MA THE == The Hessling Editor http://hessling-editor.sourceforge.net/ -- John McKown Senior Systems Programmer HealthMarkets Keeping the Promise of Affordable Coverage Administrative Services Group Information Technology The information contained in this e-mail message may be privileged and/or confidential. It is for intended addressee(s) only. If you are not the intended recipient, you are hereby notified that any disclosure, reproduction, distribution or other use of this communication is strictly prohibited and could, in certain circumstances, be a criminal offense. If you have received this e-mail in error, please notify the sender by reply and delete this message without copying or disclosing it. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
On 6/13/07, Marian Gasparovic [EMAIL PROTECTED] wrote: If you know anybody talking Dutch, ask him/her what it means in Dutch, you will be surprised and never forget to smile when you hear SOA :) Yep. That's probably why we hear a lot about it at conferences. The leaflets in the hospital waiting room state that when you have a SOA you should inform anyone you've been in contact with ;-) Rob ;-) -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
For those of us who don't know anyone who speaks Dutch, would you mind terribly providing some insight? Steve Mitchell Sr Systems Software Specialist Blue Cross Blue Shield of Kansas (785) 291-8885 'There are no degrees of Honesty-you're either Honest or you're not! Marian Gasparovic [EMAIL PROTECTED] To Sent by: Linux on LINUX-390@VM.MARIST.EDU 390 Port cc [EMAIL PROTECTED] IST.EDUTopic Subject 06/13/2007 07:55 Re: Need z/VM-LINUX info AM Please respond to Linux on 390 Port [EMAIL PROTECTED] IST.EDU If you know anybody talking Dutch, ask him/her what it means in Dutch, you will be surprised and never forget to smile when you hear SOA :) Marian --- Evans, Kevin R [EMAIL PROTECTED] wrote: I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. Be a better Globetrotter. Get better travel answers from someone who knows. Yahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=listsid=396545469 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Well if you couldn't derive it based on Rob's comment, it is: Seksueel Overdraagbare Aandoening (Sexually Transmitted Disease) -Sam -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Steve Mitchell Sent: Wednesday, June 13, 2007 9:00 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info For those of us who don't know anyone who speaks Dutch, would you mind terribly providing some insight? Steve Mitchell Sr Systems Software Specialist Blue Cross Blue Shield of Kansas (785) 291-8885 'There are no degrees of Honesty-you're either Honest or you're not! Marian Gasparovic [EMAIL PROTECTED] To Sent by: Linux on LINUX-390@VM.MARIST.EDU 390 Port cc [EMAIL PROTECTED] IST.EDU Topic Subject 06/13/2007 07:55 Re: Need z/VM-LINUX info AM Please respond to Linux on 390 Port [EMAIL PROTECTED] IST.EDU If you know anybody talking Dutch, ask him/her what it means in Dutch, you will be surprised and never forget to smile when you hear SOA :) Marian --- Evans, Kevin R [EMAIL PROTECTED] wrote: I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. Be a better Globetrotter. Get better travel answers from someone who knows. Yahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=listsid=396545469 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
SOA (was RE: Need z/VM-LINUX info
-Original Message- From: Linux on 390 Port On Behalf Of Steve Mitchell For those of us who don't know anyone who speaks Dutch, would you mind terribly providing some insight? http://www.acronymfinder.com Second page of results for SOA.. -jc- -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: DASD IO Performance problems
On 6/13/07, Eric and Barbara Sammons [EMAIL PROTECTED] wrote: Looking into performance problems, in search of some ideas of what to look for. I believe the issue may be related to the type of DASD being used. Fortunately there's instrumentation on the platform, and you need a performance monitor to analyze your configuration and workload to understand what is holding you back. Scenario, dd command to generate a 1G file if=/dev/zero takes 15s on x86_64 platform. The same command takes 15m on the s390x platform. In my environment the command takes 16s. My environment leverages MOD-3 DASD while the environment in question has MOD-9 and MOD-27 devices. I know historically the MOD-9 is typically a slower device but I don't know much about the MOD-27. The slow was for real 3390's. Modern DASD only emulates the number of cylinders on the logical volumes, so a 3390-27 is not necessarily slower than a 3390-3. However, since there is only one I/O active at the same time to the logical volume, the subchannel might become a bottleneck. Or phrased differently, when your workload is such that it could run multiple I/O's in parallel, you might be able to take advantage of providing the disk space in multiple logical volumes (and thus multiple subchannels). Second best could be PAV in some situations. Your test is in general not enough to understand the capabilities. After all, the mainframe was meant to run a lot in parallel and it would be better to measure how many servers could be doing this test at the same time without impacting each other heavily. Is it truly possible that the performance of these devices is bad enough to see such a difference between MOD-3 and x86_64 v. MOD-9 and MOD-27? What else should / can I look at to determine the root cause of the performance issues? Your numbers look weird enough to be suspicious. Most likely your x86 platform has a huge amount of memory so it never even did a single I/O to disk for your benchmark. If you were given a fairly small Linux server on the mainframe, it suddenly had to do I/O and wait for that to complete. Very different cases. If you do 1 GB in 15 min, that's 1 MB/s. Still rather slow. First you'd need to see whether this is ESCON or FICON. There may also be other things holding back the virtual machine (like paging, CPU contention, failure to drop from queue, etc). Collect performance data and see what's going on. Rob -- Rob van der Heij Velocity Software, Inc http://velocitysoftware.com/ -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
-Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Kielek, Samuel Sent: Wednesday, June 13, 2007 8:04 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Well if you couldn't derive it based on Rob's comment, it is: Seksueel Overdraagbare Aandoening (Sexually Transmitted Disease) -Sam Oh, gee, like THANKS A LOT. Now I won't be able to sit in any meeting where SOA is mentioned without suppressing laughter or at least have a weird smile flit across my face. GRIN -- John McKown Senior Systems Programmer HealthMarkets Keeping the Promise of Affordable Coverage Administrative Services Group Information Technology The information contained in this e-mail message may be privileged and/or confidential. It is for intended addressee(s) only. If you are not the intended recipient, you are hereby notified that any disclosure, reproduction, distribution or other use of this communication is strictly prohibited and could, in certain circumstances, be a criminal offense. If you have received this e-mail in error, please notify the sender by reply and delete this message without copying or disclosing it. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: DASD IO Performance problems
Rob, I have performance data from ESAMON; however, the format that it was given to me I am unable to read (binary). Is there a way to read the ESAMON data, collected on VM, on Linux x86? The only other data I have is iostat -dkx which shows that there are some greater than expected wait and service times for the DASD in question, by greater I mean 100s and 1000s+. Thanks! Eric Rob van der Heij wrote: On 6/13/07, Eric and Barbara Sammons [EMAIL PROTECTED] wrote: Looking into performance problems, in search of some ideas of what to look for. I believe the issue may be related to the type of DASD being used. Fortunately there's instrumentation on the platform, and you need a performance monitor to analyze your configuration and workload to understand what is holding you back. Scenario, dd command to generate a 1G file if=/dev/zero takes 15s on x86_64 platform. The same command takes 15m on the s390x platform. In my environment the command takes 16s. My environment leverages MOD-3 DASD while the environment in question has MOD-9 and MOD-27 devices. I know historically the MOD-9 is typically a slower device but I don't know much about the MOD-27. The slow was for real 3390's. Modern DASD only emulates the number of cylinders on the logical volumes, so a 3390-27 is not necessarily slower than a 3390-3. However, since there is only one I/O active at the same time to the logical volume, the subchannel might become a bottleneck. Or phrased differently, when your workload is such that it could run multiple I/O's in parallel, you might be able to take advantage of providing the disk space in multiple logical volumes (and thus multiple subchannels). Second best could be PAV in some situations. Your test is in general not enough to understand the capabilities. After all, the mainframe was meant to run a lot in parallel and it would be better to measure how many servers could be doing this test at the same time without impacting each other heavily. Is it truly possible that the performance of these devices is bad enough to see such a difference between MOD-3 and x86_64 v. MOD-9 and MOD-27? What else should / can I look at to determine the root cause of the performance issues? Your numbers look weird enough to be suspicious. Most likely your x86 platform has a huge amount of memory so it never even did a single I/O to disk for your benchmark. If you were given a fairly small Linux server on the mainframe, it suddenly had to do I/O and wait for that to complete. Very different cases. If you do 1 GB in 15 min, that's 1 MB/s. Still rather slow. First you'd need to see whether this is ESCON or FICON. There may also be other things holding back the virtual machine (like paging, CPU contention, failure to drop from queue, etc). Collect performance data and see what's going on. Rob -- Rob van der Heij Velocity Software, Inc http://velocitysoftware.com/ -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
Yeah, was kidding John. :) Should've smiled. MA On 6/13/07, McKown, John [EMAIL PROTECTED] wrote: -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mary Anne Matyaz Sent: Wednesday, June 13, 2007 7:55 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Mini-survey: Linux usability The what? MA THE == The Hessling Editor http://hessling-editor.sourceforge.net/ -- John McKown Senior Systems Programmer HealthMarkets Keeping the Promise of Affordable Coverage Administrative Services Group Information Technology The information contained in this e-mail message may be privileged and/or confidential. It is for intended addressee(s) only. If you are not the intended recipient, you are hereby notified that any disclosure, reproduction, distribution or other use of this communication is strictly prohibited and could, in certain circumstances, be a criminal offense. If you have received this e-mail in error, please notify the sender by reply and delete this message without copying or disclosing it. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
FTP server doing compression
I like to know what are the disadvantages/advantages of having ftp server doing the compress during the download and uncompress from the upload. Currently the tar command issue the fork() to gzip. Visit our website at http://www.nyse.com Note: The information contained in this message and any attachment to it is privileged, confidential and protected from disclosure. If the reader of this message is not the intended recipient, or an employee or agent responsible for delivering this message to the intended recipient, you are hereby notified that any dissemination, distribution or copying of this communication is strictly prohibited. If you have received this communication in error, please notify the sender immediately by replying to the message, and please delete it from your system. Thank you. NYSE Group, Inc. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Enter SOA Dutch into your favorite Google, don't even click on the first link, just read it. Marian --- Steve Mitchell [EMAIL PROTECTED] wrote: For those of us who don't know anyone who speaks Dutch, would you mind terribly providing some insight? Steve Mitchell Sr Systems Software Specialist Blue Cross Blue Shield of Kansas (785) 291-8885 'There are no degrees of Honesty-you're either Honest or you're not! Marian Gasparovic [EMAIL PROTECTED] To Sent by: Linux on LINUX-390@VM.MARIST.EDU 390 Port cc [EMAIL PROTECTED] IST.EDU Topic Subject 06/13/2007 07:55 Re: Need z/VM-LINUX info AM Please respond to Linux on 390 Port [EMAIL PROTECTED] IST.EDU If you know anybody talking Dutch, ask him/her what it means in Dutch, you will be surprised and never forget to smile when you hear SOA :) Marian --- Evans, Kevin R [EMAIL PROTECTED] wrote: I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. Be a better Globetrotter. Get better travel answers from someone who knows. Yahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=listsid=396545469 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 No need to miss a message. Get email on-the-go with Yahoo! Mail for Mobile. Get started. http://mobile.yahoo.com/mail -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: IBM typo or pre-announce ???
If you do a search on ibm.com for 'Linux for z/OS' you will see the term has been in use for a while. Probably just an earlier term for 'Linux on zSeries' I also saw Linux/390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
SOA (was: Need z/VM-LINUX info)
On Wednesday 13 June 2007 07:16, Evans, Kevin R wrote: I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. I've always thought it meant Service Occasionally Available. :-) - MacK. - Edmund R. MacKenty Software Architect Rocket Software, Inc. Newton, MA USA -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: IBM typo or pre-announce ???
And used incorrectly by the people that think that mainframe==z/OS. Ken Porowski wrote: If you do a search on ibm.com for 'Linux for z/OS' you will see the term has been in use for a while. -- Rich Smrcina VM Assist, Inc. Phone: 414-491-6001 Ans Service: 360-715-2467 rich.smrcina at vmassist.com Catch the WAVV! http://www.wavv.org WAVV 2008 - Chattanooga - April 18-22, 2008 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: IBM typo or pre-announce ???
On 6/13/07, Ken Porowski [EMAIL PROTECTED] wrote: Probably just an earlier term for 'Linux on zSeries' I recently explained to a non-mainframe audience that z/OS was on the mainframe like Windows on the PC. Those who use it often believe it's the only operating system in the world, and abuse the name to identify the hardware or even hardware plus OS plus applications. Back then I threatened to trademark Linux on OS/390 and then have IBM pay for each time they abuse my trademark ;-) My business case was based on search of the IBM web site. In those days Jim Elliott owned the corporate gun to address those things and I showed him the list. When I tried to demonstrate it to someone else, the reference was still in the search engine but almost all were corrected (except one who changed to Linux on z/OS). But Jim may have run out of ammunition... Rob -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Nope, I still get the same message. Mary -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mark Post Sent: Tuesday, June 12, 2007 6:34 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info On Tue, Jun 12, 2007 at 4:09 PM, in message [EMAIL PROTECTED], Yukus, Mary J CIV USMEPCOM [EMAIL PROTECTED] wrote: Neale, Do you happen to have a copy of the Nationwide document? I get a message that the file is damaged and could not be repaired when I click on the link. Try it again. I re-uploaded it, and it seems to check out now. Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: DASD IO Performance problems
Hi, Eric and Barbara Sammons [EMAIL PROTECTED] wrote: Looking into performance problems, in search of some ideas of what to look for. I believe the issue may be related to the type of DASD being used. Scenario, dd command to generate a 1G file if=/dev/zero takes 15s on x86_64 platform. The same command takes 15m on the s390x platform. In my environment the command takes 16s. My environment leverages MOD-3 DASD while the environment in question has MOD-9 and MOD-27 devices. I know historically the MOD-9 is typically a slower device but I don't know much about the MOD-27. Is it truly possible that the performance of these devices is bad enough to see such a difference between MOD-3 and x86_64 v. MOD-9 and MOD-27? I think the use of different models should not result in such a big performance difference. Today these different models just indicate the different sizes of the DASD volumes as they are defined on a storage server. I would rather look for the difference in the storage servers that these DASDs are defined on. What else should / can I look at to determine the root cause of the performance issues? You can get an indication of what is going on in the DASD device driver by looking at the /proc/dasd/statistics interface. A documentation on how to use that interface and how to interpret the data can be found on developer works: http://www.ibm.com/developerworks/linux/linux390/perf/tuning_how_tools_dasd.html You may also want to check /var/log/messages or dmesg for messages that indicate errors or recovery actions. Best Regards / Mit freundlichen Grüßen Stefan Weinhuber -- Linux for zSeries Development Services, Dept. 3303 IBM Deutschland Entwicklung GmbH Vorsitzender des Aufsichtsrats: Martin Jetter Geschäftsführung: Herbert Kircher Sitz der Gesellschaft: Böblingen Registergericht: Amtsgericht Stuttgart, HRB 243294 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Link worked OK for me K -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Yukus, Mary J CIV USMEPCOM Sent: Wednesday, June 13, 2007 9:58 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Nope, I still get the same message. Mary -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mark Post Sent: Tuesday, June 12, 2007 6:34 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info On Tue, Jun 12, 2007 at 4:09 PM, in message [EMAIL PROTECTED], Yukus, Mary J CIV USMEPCOM [EMAIL PROTECTED] wrote: Neale, Do you happen to have a copy of the Nationwide document? I get a message that the file is damaged and could not be repaired when I click on the link. Try it again. I re-uploaded it, and it seems to check out now. Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
The 'trade press' doesn't help, either. Every article has a different definition. Every 'consultant/analyst' report/insert your favorite color here -paper says everyone should be doing 'it', and if you're not, you're not 'agile', or competitive, or ... Major FUD factor here. And then the next article discusses how expensive it is, but that you should not look at/for ROI on all that investment in money, time, etc, but instead look at businesss flexibility and agility. 'They' talk about 'it' here, too, a lot, and the SOA term is thrown around very liberally, but more because it's the 'in' thing, and because 'Gartner says... ', than anything else. Cynically, Dave Dave Stuart Prin. Info. Systems Support Analyst County of Ventura, CA 805-662-6731 [EMAIL PROTECTED] Evans, Kevin R [EMAIL PROTECTED] 6/13/2007 4:16 AM I love the SOA comment...it's a big buzzword around here right now. I am sure that SOA means different things to different people. K -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
WebSphere, SLES 9 64 bit and Above/below the bar strangeness
Greetings. This may be 'working as designed' but I'm not sure If anyone has seen this please feel free to enlighten. We have a WebSphere cluster, with WebSphere in Network Deployment configuration. This means that the primary node has a configuration slightly different than the secondary node in that the primary has a deployment manager task. That in and of itself causes a nearly 600 meg difference in memory footprint. WebSphere on Linux for z/Series is a 31 bit task, running in a 64 bit operating system. I've verified that both machines are at the same maintenance level, and both are indeed 64 bit SLES. So the conundrum here is why would the node with the deployment manager consistently have almost twice as many resident pages above the bar as the node without the Deployment manager? Is there some function of the Deployment manager that would request memory above the bar to a much greater extent than the node agent or the app server tasks? Just curious as we'd like to explain the behavior difference. -J -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: WebSphere, SLES 9 64 bit and Above/below the bar strangeness
When we ran through the design review with IBM of our big WAS cluster, the recommendation was to run dmgr on a server by itself. So we do that. It doesn't even have to be up unless you are deploying something or updating configurations. Marcy Cortes This message may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose, or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of James Melin Sent: Wednesday, June 13, 2007 9:15 AM To: LINUX-390@VM.MARIST.EDU Subject: [LINUX-390] WebSphere, SLES 9 64 bit and Above/below the bar strangeness Greetings. This may be 'working as designed' but I'm not sure If anyone has seen this please feel free to enlighten. We have a WebSphere cluster, with WebSphere in Network Deployment configuration. This means that the primary node has a configuration slightly different than the secondary node in that the primary has a deployment manager task. That in and of itself causes a nearly 600 meg difference in memory footprint. WebSphere on Linux for z/Series is a 31 bit task, running in a 64 bit operating system. I've verified that both machines are at the same maintenance level, and both are indeed 64 bit SLES. So the conundrum here is why would the node with the deployment manager consistently have almost twice as many resident pages above the bar as the node without the Deployment manager? Is there some function of the Deployment manager that would request memory above the bar to a much greater extent than the node agent or the app server tasks? Just curious as we'd like to explain the behavior difference. -J -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 smime.p7s Description: S/MIME cryptographic signature
Re: Need z/VM-LINUX info
Every article has a different definition. Every 'consultant/analyst' report/insert your favorite color here -paper says everyone should be doing 'it', and if you're not, you're not 'agile', or competitive, or ... Major FUD factor here. Is it just me, or does no one in the computer science field get taught how to do basic literature searches for past inventions? *Major* ancient history. All SOA is is a way to wrap existing apps in a framework, find the apps in a directory, and communicate input and results in a standardized way. Doesn't solve the problem of who can use the app, how it should be used, or whether the app is even useful in that form. It's just a rehash of object wrapper/broker capability published in the XNS Reference Architecture circa 1972 or so. Or NCS. Or Corba. Or DOM. Or any of dozens of other distributed object reference technologies over the past 3-4 decades. I annoy numerous people every time I point out that there is absolutely nothing new about this concept, and have them actually do the homework on how their SOA commentary or strategy is different that the dozen or so times this has been tried before. I ask them to focus on why the previous efforts failed, both technically and organizationally. Usually, they don't come back. -- db -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: WebSphere, SLES 9 64 bit and Above/below the bar strangeness
Sorry about the digital sig on the previous one. That's the default here. -- When we ran through the design review with IBM of our big WAS cluster, the recommendation was to run dmgr on a server by itself. So we do that. It doesn't even have to be up unless you are deploying something or updating configurations. Marcy Cortes This message may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose, or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of James Melin Sent: Wednesday, June 13, 2007 9:15 AM To: LINUX-390@VM.MARIST.EDU Subject: [LINUX-390] WebSphere, SLES 9 64 bit and Above/below the bar strangeness Greetings. This may be 'working as designed' but I'm not sure If anyone has seen this please feel free to enlighten. We have a WebSphere cluster, with WebSphere in Network Deployment configuration. This means that the primary node has a configuration slightly different than the secondary node in that the primary has a deployment manager task. That in and of itself causes a nearly 600 meg difference in memory footprint. WebSphere on Linux for z/Series is a 31 bit task, running in a 64 bit operating system. I've verified that both machines are at the same maintenance level, and both are indeed 64 bit SLES. So the conundrum here is why would the node with the deployment manager consistently have almost twice as many resident pages above the bar as the node without the Deployment manager? Is there some function of the Deployment manager that would request memory above the bar to a much greater extent than the node agent or the app server tasks? Just curious as we'd like to explain the behavior difference. -J -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Cics Transaction Gateway
Hi anyone running CTG under Linux, with or without z/VM. I have been tasked to look at the option, actually I talked my way into looking at the option, I would like to ensure I have all the bases covered, currently we run CTG under z/OS and need to upgrade to V7. Regards Gerard Ceruti __ Standard Bank Disclaimer and Confidentiality Note This e-mail, its attachments and any rights attaching hereto are, unless the context clearly indicates otherwise, the property of Standard Bank Group Limited and/or its subsidiaries (the Group). It is confidential, private and intended for the addressee only. Should you not be the addressee and receive this e-mail by mistake, kindly notify the sender, and delete this e-mail, immediately and do not disclose or use same in any manner whatsoever. Views and opinions expressed in this e-mail are those of the sender unless clearly stated as those of the Group. The Group accepts no liability whatsoever for any loss or damages whatsoever and howsoever incurred, or suffered, resulting, or arising, from the use of this email or its attachments. The Group does not warrant the integrity of this e-mail nor that it is free of errors, viruses, interception or interference. Licensed divisions of the Standard Bank Group are authorised financial services providers in terms of the Financial Advisory and Intermediary Services Act, No 37 of 2002 (FAIS). For information about the Standard Bank Group Limited visit our website http://www.standardbank.co.za ___ -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Mary, Try right-clicking on the link, downloading it to your local machine, and opening it locally. You might have the bug in some of the Windows browsers that caused bad parms to be passed to plugins. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Cics Transaction Gateway
Was there a question? Check the zJournal archive, I wrote an article about CTG on Linux for zSeries some time ago. Ceruti, Gerard G wrote: Hi anyone running CTG under Linux, with or without z/VM. I have been tasked to look at the option, actually I talked my way into looking at the option, I would like to ensure I have all the bases covered, currently we run CTG under z/OS and need to upgrade to V7. Regards Gerard Ceruti -- Rich Smrcina VM Assist, Inc. Phone: 414-491-6001 Ans Service: 360-715-2467 rich.smrcina at vmassist.com Catch the WAVV! http://www.wavv.org WAVV 2008 - Chattanooga - April 18-22, 2008 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Sorry Dave, But this is one of my pet peeves, here. I probably should have pulled out my Soapbox On. Is it just me, or does no one in the computer science field get taught how to do basic literature searches for past inventions? Doesn't really matter what is being taught. The problem, here, at least, and probably other places, is that management isn't doing basic literature searches, whether or not they know/were taught how. Here, we seem to be suffering from Drive-by Management (from Scott Adams' Dilbert), or Management by Airline Magazine/Consultant Report/... As the articles and reports change, so does the 'strategic direction'. Dave Dave Stuart Prin. Info. Systems Support Analyst County of Ventura, CA 805-662-6731 [EMAIL PROTECTED] David Boyes [EMAIL PROTECTED] 6/13/2007 9:24 AM snip. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
On Wed, 13 Jun 2007 09:13:38 -0700 David Stuart [EMAIL PROTECTED] wrote: The 'trade press' doesn't help, either. Every article has a different definition. Every 'consultant/analyst' report/insert your favorite color here -paper says everyone should be doing 'it', and if you're not, you're not 'agile', or competitive, or ... Major FUD factor here. The consultant and analyst exist to sell their own services, which require that they are therefore the only one doing the right version of something you need to be. Even more impressive is the business model used by some market analysts and trend analysts who ask everyone what they are doing, summarize the answer and sell it back to the people the asked. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
But this is one of my pet peeves, here. Doesn't really matter what is being taught. The problem, here, at least, and probably other places, is that management isn't doing basic literature searches, whether or not they know/were taught how. Mine too. I suppose it's not limited to CS -- I used to get the same problem when I taught business students as well. Annoying as all get out. A few students got a real surprise when they asked me why I failed their design essays as plagiarism. Here, we seem to be suffering from Drive-by Management (from Scott Adams' Dilbert), or Management by Airline Magazine/Consultant Report/... As the articles and reports change, so does the 'strategic direction'. One leads to the other, I'm afraid. They don't know what's been done before, and thus have no effective BS detector. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
I find some of the reasoning in this thread very interesting. We are in the middle of moving a lot of our Oracle out of AIX and SUN to zVM/Linux. This was done to improve RAS and to reduce Oracle-batch turn-around time. We use RAC not only to improve availability but also to separate batch from on-line processing. We are now contemplating Oracle under zOS (we have DB2) for those applications that require even better availability. When you think about it, zOS is rock solid compared to Linux. SOA, which is being pursued by our developers, has not come up as a reason not to move to zOS. I am going to ask the question. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
actually I find linux rock solid. 200 servers; production 1+ year; no linux software outages. Nuthin' wrong with that! David -Original Message- From: Linux on 390 Port on behalf of Yu Safin Sent: Wed 6/13/2007 1:19 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info I find some of the reasoning in this thread very interesting. We are in the middle of moving a lot of our Oracle out of AIX and SUN to zVM/Linux. This was done to improve RAS and to reduce Oracle-batch turn-around time. We use RAC not only to improve availability but also to separate batch from on-line processing. We are now contemplating Oracle under zOS (we have DB2) for those applications that require even better availability. When you think about it, zOS is rock solid compared to Linux. SOA, which is being pursued by our developers, has not come up as a reason not to move to zOS. I am going to ask the question. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: DASD IO Performance problems
We ran a very extensive set of Oracle-Java benchmarks that compared I/O's on an EMC Symm under AIX/P-570 versus the same EMC Symm but with 3390-m3 under zVM/SLES 9.3. We were running a very I/O intensive application that was hitting close to 5000 I/O's per second for hours at a time. This is the way it behaves in production so it was a real-life workload. We found that the I/O response was very similar between both environments once we tuned and spread the I/O's across as many devices as possible so a single device would never go over 30% busy when doing lots of I/O's. We were able to achieve an overall response of 5 msec under both platforms. This was done because we needed to test the CPU's and not the I/O subsystem as part of our decision. Yes, it does take longer to setup and configure disk under zVM/Linux than it did under the P-570/AIX platform. However, we only care about response time for our applications so we can put up with the slow formatting of disk space. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
We are now contemplating Oracle under zOS (we have DB2) for those applications that require even better availability. When you think about it, zOS is rock solid compared to Linux. It better be. There's certainly been a bunch of code written to make sure that it is. SOA, which is being pursued by our developers, has not come up as a reason not to move to zOS. I am going to ask the question. It won't come up. IBM and others have spent a fair amount of money making sure that Linux and z/OS can participate (mostly to save older apps from moving off the platform). It's not cheap to do, though -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
We are now at 6 IFL's and are in the process of adding 6 more under our z9. We moved our workload from AIX to zVM/Linux SLES. Next is the SUN workloads and that will require more IFL's. We had a zOS systems programmer and no experience with zVM. My background is also zOS and I had used VM back in the early 80's before PR/SM came along. Challenges: 1) getting our AIX and SUN compadres to give up on the idea that they own the hardware. They found it hard to accept that the zVM was kind of a big brother. 2) changing the paradigm on how I/O's are handle in the zVM / z9 world compared to the distributed system environment. 3) changing the way we do fail-over and how we mitigate risk in this new z-Series brave world. 4) convincing software vendors that licensing had to change to deal with virtualization. Some never accepted it so we are paying more than we need to. 5) some software vendors (SAS for example) just refused to support their product under Linux when running under z-Series. 6) the hardware is expensive. Our distributed system fellows go crazy when we say $80k for 8 GB of memory. They go nuts when we say we have to reduce memory to the point of paging to the SWAP allocated under zVM virtual disks (going most likely to expanded memory). Good news: 1) big improvements in batch processing turn-around time. 2) less number of CPU's to do the same work with the consequences in CPU-based licensing. 3) floor space and power usage (our diesel requirements dropped). 4) RAS. 5) We can now provision servers on minutes instead of months. 6) Our peaks have more head room now under the z9 than before because all of the CPU's can be made available to a single guest. Hope this helps. -- Yours truly, Yu -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
On 6/13/07, David Kreuter [EMAIL PROTECTED] wrote: actually I find linux rock solid. 200 servers; production 1+ year; no linux software outages. Nuthin' wrong with that! David David, No disagreement here. We have been running Linux for z-Series for over two years without a single incident. Compared to AIX and SUN I would say hardly any difference even when Linux is the new kid in the block. I was the one who championed Linux.around here but I have also been very clear that it is a newer OS compared to the other OS so it may show up when you least expect it. I guess I have beent trying to set up an expectation. I have also being with zOS/MVS since 1982. The difference is that zOS can handle more hic ups than Linux without an impact. I saw that over and over again early on in my career when we spent a lot of money in fault-tolerant systems just to see MVS be more reliable with higher availability. You alwys pay more when you go from 99.99% availability to 99.%. That is the level I am talking about. It is not always the best use of money unless your business demand it (think NASA). -- Yours truly, Yu -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Shouldn't you have had a Soapbox On/ there ? K -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of David Stuart Sent: Wednesday, June 13, 2007 12:45 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Sorry Dave, But this is one of my pet peeves, here. I probably should have pulled out my Soapbox On. Is it just me, or does no one in the computer science field get taught how to do basic literature searches for past inventions? Doesn't really matter what is being taught. The problem, here, at least, and probably other places, is that management isn't doing basic literature searches, whether or not they know/were taught how. Here, we seem to be suffering from Drive-by Management (from Scott Adams' Dilbert), or Management by Airline Magazine/Consultant Report/... As the articles and reports change, so does the 'strategic direction'. Dave Dave Stuart Prin. Info. Systems Support Analyst County of Ventura, CA 805-662-6731 [EMAIL PROTECTED] David Boyes [EMAIL PROTECTED] 6/13/2007 9:24 AM snip. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Mini-survey: Linux usability
On Tue, Jun 12, 2007 at 11:06 PM, in message [EMAIL PROTECTED], Spann, Elizebeth (Betsie) [EMAIL PROTECTED] wrote: Let me add the difficulty of learning to google for problem identification and solution, rather than using IBM manuals (item one) Personally, I see this as a plus. As fast as Linux matures, can you imagine how soon a manual would be out of date after it got published? (See the Redbooks for a real example.) Conversely, can you imagine how long it would take to get new functionality if we had to wait for the manuals to be updated before the software was released? No thanks. Plus, given that about 90% of the problems anyone ever runs into are not mainframe-specific, having an absolutely enormous testing community out there finding problems/solutions out there before you do is really great. and (item two) figuring out how to set up a gui interface. Most Linux classes teach gui sysadmin interfaces. The teacher looks at you funny when you continue to ask about command line alternatives. :-) You need to hang out with more Slackers, then. We give odd looks to people that want to use GUIs. Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Hmm, that's strange. I still can't get to it. I can get to the DGTIC - one, but not the Nationwide - one. Anyone have any suggestions? -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Evans, Kevin R Sent: Wednesday, June 13, 2007 11:11 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Link worked OK for me K -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Yukus, Mary J CIV USMEPCOM Sent: Wednesday, June 13, 2007 9:58 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Nope, I still get the same message. Mary -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mark Post Sent: Tuesday, June 12, 2007 6:34 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info On Tue, Jun 12, 2007 at 4:09 PM, in message [EMAIL PROTECTED], Yukus, Mary J CIV USMEPCOM [EMAIL PROTECTED] wrote: Neale, Do you happen to have a copy of the Nationwide document? I get a message that the file is damaged and could not be repaired when I click on the link. Try it again. I re-uploaded it, and it seems to check out now. Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Never mind, I went to the web site and was able to find it without the link. I was then able to open it. Thanks! Mary :-) -Original Message- From: Yukus, Mary J CIV USMEPCOM Sent: Wednesday, June 13, 2007 12:22 PM To: 'Linux on 390 Port' Subject: RE: Need z/VM-LINUX info Hmm, that's strange. I still can't get to it. I can get to the DGTIC - one, but not the Nationwide - one. Anyone have any suggestions? -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Evans, Kevin R Sent: Wednesday, June 13, 2007 11:11 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Link worked OK for me K -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Yukus, Mary J CIV USMEPCOM Sent: Wednesday, June 13, 2007 9:58 AM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info Nope, I still get the same message. Mary -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Mark Post Sent: Tuesday, June 12, 2007 6:34 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Need z/VM-LINUX info On Tue, Jun 12, 2007 at 4:09 PM, in message [EMAIL PROTECTED], Yukus, Mary J CIV USMEPCOM [EMAIL PROTECTED] wrote: Neale, Do you happen to have a copy of the Nationwide document? I get a message that the file is damaged and could not be repaired when I click on the link. Try it again. I re-uploaded it, and it seems to check out now. Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: WebSphere, SLES 9 64 bit and Above/below the bar strangeness
That makes a lot of sense. OUr Dmgr didn't used to be porcine in nature, but as our applications have grown, the deployment manager JVM has grown. Hence the disparity. Still doesn't explain the above the bar/below the bar issue, but we might be able to see if we can move it. Marcy Cortes [EMAIL PROTECTED] Sent by: Linux on 390 Port LINUX-390@VM.MARIST.EDU To LINUX-390@VM.MARIST.EDU cc 06/13/2007 11:29 AM Subject Re: WebSphere, SLES 9 64 bit and Above/below the bar strangeness Please respond to Linux on 390 Port LINUX-390@VM.MARIST.EDU Sorry about the digital sig on the previous one. That's the default here. -- When we ran through the design review with IBM of our big WAS cluster, the recommendation was to run dmgr on a server by itself. So we do that. It doesn't even have to be up unless you are deploying something or updating configurations. Marcy Cortes This message may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose, or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of James Melin Sent: Wednesday, June 13, 2007 9:15 AM To: LINUX-390@VM.MARIST.EDU Subject: [LINUX-390] WebSphere, SLES 9 64 bit and Above/below the bar strangeness Greetings. This may be 'working as designed' but I'm not sure If anyone has seen this please feel free to enlighten. We have a WebSphere cluster, with WebSphere in Network Deployment configuration. This means that the primary node has a configuration slightly different than the secondary node in that the primary has a deployment manager task. That in and of itself causes a nearly 600 meg difference in memory footprint. WebSphere on Linux for z/Series is a 31 bit task, running in a 64 bit operating system. I've verified that both machines are at the same maintenance level, and both are indeed 64 bit SLES. So the conundrum here is why would the node with the deployment manager consistently have almost twice as many resident pages above the bar as the node without the Deployment manager? Is there some function of the Deployment manager that would request memory above the bar to a much greater extent than the node agent or the app server tasks? Just curious as we'd like to explain the behavior difference. -J -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Oracle workload profile differences
I got an internal query about one of our customers who is currently running Oracle on Linux on Intel/AMD. They're looking at moving that to Linux on the mainframe, and they've seen some good things during their testing. For example, one long-running query went from 14+ minutes to about 2.5 minutes. Something that caught their attention though was that the number of I/Os on the mainframe were about 30 times (not percent) higher than on Intel. They said they'd used an Oracle tool to determine this. Not knowing anything about Oracle's tools in this arena, I have no idea if they're any good or not. I told them they needed to get a real performance monitor to verify that, but with a 5.6-to-1 performance _improvement_, it's not yet critical. My question is, does anyone know if Oracle uses different internal algorithms on the various architectures to maximize performance? That is, since I/O is a strength of the mainframe, they might do more I/Os versus something else on Intel Linux. Anyone have any insight on this? Thanks, Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Oracle workload profile differences
What filesystems are they using on both platforms? David -Original Message- From: Linux on 390 Port on behalf of Mark Post Sent: Wed 6/13/2007 4:26 PM To: LINUX-390@VM.MARIST.EDU Subject: Oracle workload profile differences I got an internal query about one of our customers who is currently running Oracle on Linux on Intel/AMD. They're looking at moving that to Linux on the mainframe, and they've seen some good things during their testing. For example, one long-running query went from 14+ minutes to about 2.5 minutes. Something that caught their attention though was that the number of I/Os on the mainframe were about 30 times (not percent) higher than on Intel. They said they'd used an Oracle tool to determine this. Not knowing anything about Oracle's tools in this arena, I have no idea if they're any good or not. I told them they needed to get a real performance monitor to verify that, but with a 5.6-to-1 performance _improvement_, it's not yet critical. My question is, does anyone know if Oracle uses different internal algorithms on the various architectures to maximize performance? That is, since I/O is a strength of the mainframe, they might do more I/Os versus something else on Intel Linux. Anyone have any insight on this? Thanks, Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Oracle workload profile differences
On Wed, Jun 13, 2007 at 4:30 PM, in message [EMAIL PROTECTED], David Kreuter [EMAIL PROTECTED] wrote: What filesystems are they using on both platforms? Supposedly raw disks with ASM on a 3390-3, with Oracle FRA (objects) on LVM using 3390-27. Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Oracle workload profile differences
Something that caught their attention though was that the number of I/Os on the mainframe were about 30 times (not percent) higher than on Intel. They said they'd used an Oracle tool to determine this. Not knowing anything about Oracle's tools in this arena, I have no idea if they're any good or not. I told them they needed to get a real performance monitor to verify that, but with a 5.6-to-1 performance _improvement_, it's not yet critical. Oracle tends to aggressively cache data in RAM when it can, doing I/O only when it can't avoid it -- which is why most distributed Oracle servers tend to have truly obscene quantities of RAM. If someone did the virtual machine sizing to minimize the size of the virtual machine (as any good virtual machine should do), then it's logical to expect the virtual machine to do more I/O to reflect that it isn't caching as much, and the System z I/O subsystem is just absorbing the difference, as designed. My question is, does anyone know if Oracle uses different internal algorithms on the various architectures to maximize performance? That is, since I/O is a strength of the mainframe, they might do more I/Os versus something else on Intel Linux. Anyone have any insight on this? Don't know for certain here, but several Oracle people have said in other forums that they try to keep the code as similar as possible for multiple platforms. The only platform that's radically different is z/OS; the rest are mostly the same. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Oracle workload profile differences
My initial assumption about this is: On Intel/AMD, they are using 512 byte blocks. Standard PC file system...right? And even though we are using the same 512 byte blocks under the RAID covers, we are using, at least 4K blocks if not tracks. So, on each of the Linux images, you need to look at: /proc/dasd/statistics To see what you are dealing with. See http://www.ibm.com/developerworks/linux/linux390/perf/tuning_how_tools_dasd.html to help understand /proc/dasd/statistics. Tom Duerbusch THD Consulting Mark Post [EMAIL PROTECTED] 6/13/2007 3:26 PM I got an internal query about one of our customers who is currently running Oracle on Linux on Intel/AMD. They're looking at moving that to Linux on the mainframe, and they've seen some good things during their testing. For example, one long-running query went from 14+ minutes to about 2.5 minutes. Something that caught their attention though was that the number of I/Os on the mainframe were about 30 times (not percent) higher than on Intel. They said they'd used an Oracle tool to determine this. Not knowing anything about Oracle's tools in this arena, I have no idea if they're any good or not. I told them they needed to get a real performance monitor to verify that, but with a 5.6-to-1 performance _improvement_, it's not yet critical. My question is, does anyone know if Oracle uses different internal algorithms on the various architectures to maximize performance? That is, since I/O is a strength of the mainframe, they might do more I/Os versus something else on Intel Linux. Anyone have any insight on this? Thanks, Mark Post -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
“Those who do not learn from history are doomed to repeat it” George Santayana Evans, Kevin R wrote: Is it just me, or does no one in the computer science field get taught how to do basic literature searches for past inventions? Doesn't really matter what is being taught. The problem, here, at least, and probably other places, is that management isn't doing basic literature searches, whether or not they know/were taught how. Here, we seem to be suffering from Drive-by Management (from Scott Adams' Dilbert), or Management by Airline Magazine/Consultant Report/... As the articles and reports change, so does the 'strategic direction'. -- DJ V/Soft -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
On Wed, 13 Jun 2007 16:47:53 -0500 Dave Jones [EMAIL PROTECTED] wrote: “Those who do not learn from history are doomed to repeat it” George Santayana History repeats itself, it has to as nobody is listening -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: FTP server doing compression
Eddie Chen wrote: I like to know what are the disadvantages/advantages of having ftp server doing the compress during the download and uncompress from the upload. You know the answer to this is, as always, it depends. With FTP or any other transmission - you can even extend it to include tape -, it depends on the speeds of the wire and of the CPUs. Assuming a file will compress decently - jpeg, rpms an debs don't - then you will find it quicker to compresss, transfer then decompress, if the link is slow. An extreme example, but one I have to live with, is transferring files through my modem. It doesn't matter how slow the CPU is, compression is worth-while. OTOH when transferring across the LAN, compression's never worth-while, I can transfer faster than I can compress. It might depend on cost too; I can imagine the proud owner of a Zed deciding there are better uses for the CPU than compressing files and instead preferring to plan around the transfer (or deciding to delegate the task to a desktop peecee). -- Cheers John -- spambait [EMAIL PROTECTED] [EMAIL PROTECTED] Please do not reply off-list -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Cics Transaction Gateway
Thanks Rich Got that one already, nice reference doc. I was looking for folks who have it up and running production, Do they have multiple CTG's on the same Linux image, or one CTG task per image , how much memory allocated ( with z/VM or if in LPAR mode) Did they migrate from z/OS if so why and easy or some gotcha's. Was the migration the first application on zSeries Linux or an extension of a current setup. Regards Gerard Ceruti -Original Message- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Rich Smrcina Sent: 13 June 2007 06:40 PM To: LINUX-390@VM.MARIST.EDU Subject: Re: Cics Transaction Gateway Was there a question? Check the zJournal archive, I wrote an article about CTG on Linux for zSeries some time ago. Ceruti, Gerard G wrote: Hi anyone running CTG under Linux, with or without z/VM. I have been tasked to look at the option, actually I talked my way into looking at the option, I would like to ensure I have all the bases covered, currently we run CTG under z/OS and need to upgrade to V7. Regards Gerard Ceruti -- Rich Smrcina VM Assist, Inc. Phone: 414-491-6001 Ans Service: 360-715-2467 rich.smrcina at vmassist.com Catch the WAVV! http://www.wavv.org WAVV 2008 - Chattanooga - April 18-22, 2008 -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 __ Standard Bank Disclaimer and Confidentiality Note This e-mail, its attachments and any rights attaching hereto are, unless the context clearly indicates otherwise, the property of Standard Bank Group Limited and/or its subsidiaries (the Group). It is confidential, private and intended for the addressee only. Should you not be the addressee and receive this e-mail by mistake, kindly notify the sender, and delete this e-mail, immediately and do not disclose or use same in any manner whatsoever. Views and opinions expressed in this e-mail are those of the sender unless clearly stated as those of the Group. The Group accepts no liability whatsoever for any loss or damages whatsoever and howsoever incurred, or suffered, resulting, or arising, from the use of this email or its attachments. The Group does not warrant the integrity of this e-mail nor that it is free of errors, viruses, interception or interference. Licensed divisions of the Standard Bank Group are authorised financial services providers in terms of the Financial Advisory and Intermediary Services Act, No 37 of 2002 (FAIS). For information about the Standard Bank Group Limited visit our website http://www.standardbank.co.za ___ -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Oracle workload profile differences
Tom Duerbusch wrote: My initial assumption about this is: On Intel/AMD, they are using 512 byte blocks. Standard PC file system...right? The _disk_ might use 512 byte sectors, but the filesystem does not. Odds are good your very expensive DASD also uses 512 byte sectors. How the data gets from user-space to disk (and even whether it does) is up to the kernel. I'd not expect the application tools to be able to measure the real disk I/O as it applies to a particular application. And even though we are using the same 512 byte blocks under the RAID covers, we are using, at least 4K blocks if not tracks. Mark didn't say how Oracle's managing storage on the toy. I'd want to know it's using properly-equivalent specifications: if it's using files on one and raw disk on the other, all bets are off. I'd not consider reiserfs on one, ext3 on the other to be equivalent either. So, on each of the Linux images, you need to look at: /proc/dasd/statistics To see what you are dealing with. See http://www.ibm.com/developerworks/linux/linux390/perf/tuning_how_tools_dasd.html to help understand /proc/dasd/statistics. Tom Duerbusch THD Consulting Mark Post [EMAIL PROTECTED] 6/13/2007 3:26 PM I got an internal query about one of our customers who is currently running Oracle on Linux on Intel/AMD. They're looking at moving that to Linux on the mainframe, and they've seen some good things during their testing. For example, one long-running query went from 14+ minutes to about 2.5 minutes. Something that caught their attention though was that the number of I/Os on the mainframe were about 30 times (not percent) higher than on Intel. They said they'd used an Oracle tool to determine this. Not knowing anything about Oracle's tools in this arena, I have no idea if they're any good or not. I told them they needed to get a real performance monitor to verify that, but with a 5.6-to-1 performance _improvement_, it's not yet critical. My question is, does anyone know if Oracle uses different internal algorithms on the various architectures to maximize performance? That is, since I/O is a strength of the mainframe, they might do more I/Os versus something else on Intel Linux. Anyone have any insight on this? -- Cheers John -- spambait [EMAIL PROTECTED] [EMAIL PROTECTED] Please do not reply off-list -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: Need z/VM-LINUX info
Those who do not learn from history are doomed to repeat it George Santayana And do an even worse job at making the same mistakes. *grump* -- db -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
Re: DASD IO Performance problems
I'd like to know what you used for that workload if it's publicly available. It sounds like it might be a nice thrasher to use for testing system recoverability and what not. On 6/13/07, Yu Safin [EMAIL PROTECTED] wrote: We ran a very extensive set of Oracle-Java benchmarks that compared I/O's on an EMC Symm under AIX/P-570 versus the same EMC Symm but with 3390-m3 under zVM/SLES 9.3. We were running a very I/O intensive application that was hitting close to 5000 I/O's per second for hours at a time. This is the way it behaves in production so it was a real-life workload. We found that the I/O response was very similar between both environments once we tuned and spread the I/O's across as many devices as possible so a single device would never go over 30% busy when doing lots of I/O's. We were able to achieve an overall response of 5 msec under both platforms. This was done because we needed to test the CPU's and not the I/O subsystem as part of our decision. Yes, it does take longer to setup and configure disk under zVM/Linux than it did under the P-570/AIX platform. However, we only care about response time for our applications so we can put up with the slow formatting of disk space. -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 -- Jay Brenneman -- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390