Re: CeBIT and mainframes
On 22/03/2016 4:02 PM, David Crayford wrote: On 22/03/2016 1:17 AM, Tom Marchant wrote: On Tue, 22 Mar 2016 00:16:52 +0800, David Crayford wrote: z/OS: DOC:/u/doc/src: >time iospeed real0m 1.15s user0m 0.62s sys 0m 0.20s Dell: davcra01@cervidae:~$ time ./iospeed real0m0.254s user0m0.048s sys 0m0.199s I have two questions. 1. What do the above figures mean? real = elapsed (wall) time user = userspace (application) time sys = system (kernel) time Interestingly the numbers are even worse if I use QSAM instead of zFS. I'm slightly surprised that zFS out-performs QSAM by such a large margin but not shocked. Program Name IOSPEEDQ hh:mm:ss.th Step Name IOSPEED Elapsed Time 11.05 Procedure Step TCB CPU Time 00.41 Return Code 00 SRB CPU Time 00.17 Total I/O 33377 Total CPU Time00.58 Service Units 9175 The blade server is a Dell PowerEdge E5-2640 SandyBridge-EP connected to a direct access disk array using 12Gbit/s SAS. We got 3 blades, the rack and 100TB of disk for $30,000!! Each blade also has 10TB of internal disk, 256GB RAM. Now that's a steal! And the core Hyper-V virtualization software is free! We consolidated all of our existing Windows servers onto one blade and still have 80% capacity free. There is obviously quite a lot of suspend time when running the test on our z/OS system. Otherwise the times are comparable. 2. What happens on z/OS when you put a heavy load on 320 channels all at once? I don't know we've only got 14 channels on the z114 at the lab :^) The Linux server is a VM running under HyperV, which I must say is very impressive tech. I've never been much of a fan of Microsoft but the fail over and live migration capabilities are excellent. Those x86 blades absolutely thrash our zIIP for running Java workloads. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 22/03/2016 1:17 AM, Tom Marchant wrote: On Tue, 22 Mar 2016 00:16:52 +0800, David Crayford wrote: z/OS: DOC:/u/doc/src: >time iospeed real0m 1.15s user0m 0.62s sys 0m 0.20s Dell: davcra01@cervidae:~$ time ./iospeed real0m0.254s user0m0.048s sys 0m0.199s I have two questions. 1. What do the above figures mean? real = elapsed (wall) time user = userspace (application) time sys = system (kernel) time There is obviously quite a lot of suspend time when running the test on our z/OS system. Otherwise the times are comparable. 2. What happens on z/OS when you put a heavy load on 320 channels all at once? I don't know we've only got 14 channels on the z114 at the lab :^) The Linux server is a VM running under HyperV, which I must say is very impressive tech. I've never been much of a fan of Microsoft but the fail over and live migration capabilities are excellent. Those x86 blades absolutely thrash our zIIP for running Java workloads. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Another news article on this subject http://www.datacenterdynamics.com/servers-storage/cebit-lzlabs-enables-mainframe-code-on-commodity-hardware/95850.fullarticle -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Tue, 22 Mar 2016 00:16:52 +0800, David Crayford wrote: >z/OS: > >DOC:/u/doc/src: >time iospeed > >real0m 1.15s >user0m 0.62s >sys 0m 0.20s > >Dell: > >davcra01@cervidae:~$ time ./iospeed > >real0m0.254s >user0m0.048s >sys 0m0.199s I have two questions. 1. What do the above figures mean? 2. What happens on z/OS when you put a heavy load on 320 channels all at once? -- Tom Marchant -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 19 March 2016 at 10:29, Mick Graleywrote: > Nah, not letting him off that easily! > The word "coded" is the same in both languages, and BCD ¬= BSD. > Like us Brits tend to say "kicks" and the Americans tend to say "see, > eye, see, ess" but it's still actually CICS :-) > Often enough in the US "kicks" is "see, ah, see, ess"... What the linguists might call "monophthongal I". Tony H. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Just for fun, because I know this is a very contrived test! I wrote a C program to read/writes block to an zFS file on a z114 z/OS system connected via FICON to an HDS SAN and Ubuntu server on a Dell PowerEdge blade server writing to SAS disks on the rack. Of course, there are latency differences and my program is probably quite lame. The z/OS was idle at the time as was the Linux system. I would imagine if they were both running at full capacity with high throughput sustained I/O the results would be very different. #include #include int main() { size_t numBlocks = 10; char * filename = "./io.temp"; #define BLOCK_SIZE 1024 FILE * fp = fopen( filename, "w+" ); if ( fp == NULL ) { perror( "fopen" ); exit( 8 ); } char buffer[BLOCK_SIZE] = {0}; for ( int j = 0; j < numBlocks; j++ ) { if ( fwrite( buffer, sizeof buffer, 1, fp ) == 0 ) { perror( "fwrite" ); exit( 8 ); } } rewind( fp ); while ( fread( buffer, 1, sizeof buffer, fp ) ) { continue; } remove( filename ); return 0; } z/OS: DOC:/u/doc/src: >time iospeed real0m 1.15s user0m 0.62s sys 0m 0.20s Dell: davcra01@cervidae:~$ time ./iospeed real0m0.254s user0m0.048s sys 0m0.199s On 21/03/2016 10:43 PM, Steve Thompson wrote: A few years ago, IBM took a Power system and a z/Architecture system and configured them as closely as they could. As I recall, they both had the same amount of C-Store available to the operating system, and they both had the same number of channels (8 if I remember correctly), and they ran to equivalently sized RAID boxes. And, if I remember correctly, they were using programs written in C, that were ported from the one to the other. The object was to check out how efficiently I/O was prosecuted (done). The z/Architecture machine finished long before the power system. I thought I had a copy of that comparison, but I just can't find it so I can give a link to it. Regards, Steve Thompson On 03/21/2016 09:40 AM, David Crayford wrote: On 21/03/2016 9:14 PM, R.S. wrote: Well, I observed 1,3M IOPS on EC12 or z196 machine during WAS installation. With minimal CPU utilisation (I mean regular CPU, I haven't checked SAP). IMNSHO a PC server with collection of new shining Emulex cards has wy worse I/O capabilities. We did some tests of database operations on PC. Effects are unequivocal. I admire you honesty :) What class of PC server? Was it connected to a SAN and did it offload I/O to a peripheral device? BTW: Typical z/OS I/O workload is very different from PC workload. Much less IOPS, much more data, much less CPU%. My wife used to work for HDS and I had some interesting conversations with some of the engineers she used to work with. That was a few years ago but in their opinion the high end *nix servers could match a mainframe for I/O throughput. PC commodity hardware is different but racked up with enterprise kit I would be interested to know how they would shape in a drag race. How would a Dell blade with Infiniband, SAN and enterprise class HBAs compare? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 21/03/2016 11:42 PM, Ed Jaffe wrote: On 3/21/2016 7:14 AM, David Crayford wrote: My wife worked on a couple of mainframe to SAP migration projects and I can't recall any performance war stories but they were not big shops. I do recall that the customers had to change their work processes to fit around SAP and not the other way round, which is bad! Some of our largest customers run SAP on the mainframe. I know of some very big mainframe SAP customers in the UK like Royal Mail Parcels who have huge mainframe footprints configured to run SAP with CPs to run DB2. I used to work with the ex-CIO back in the day and she speaks very highly of it. I'm not knocking SAP, my wife has made a good living out of it -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 3/21/2016 7:14 AM, David Crayford wrote: My wife worked on a couple of mainframe to SAP migration projects and I can't recall any performance war stories but they were not big shops. I do recall that the customers had to change their work processes to fit around SAP and not the other way round, which is bad! Some of our largest customers run SAP on the mainframe. -- Edward E Jaffe Phoenix Software International, Inc 831 Parkview Drive North El Segundo, CA 90245 http://www.phoenixsoftware.com/ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
A few years ago, IBM took a Power system and a z/Architecture system and configured them as closely as they could. As I recall, they both had the same amount of C-Store available to the operating system, and they both had the same number of channels (8 if I remember correctly), and they ran to equivalently sized RAID boxes. And, if I remember correctly, they were using programs written in C, that were ported from the one to the other. The object was to check out how efficiently I/O was prosecuted (done). The z/Architecture machine finished long before the power system. I thought I had a copy of that comparison, but I just can't find it so I can give a link to it. Regards, Steve Thompson On 03/21/2016 09:40 AM, David Crayford wrote: On 21/03/2016 9:14 PM, R.S. wrote: Well, I observed 1,3M IOPS on EC12 or z196 machine during WAS installation. With minimal CPU utilisation (I mean regular CPU, I haven't checked SAP). IMNSHO a PC server with collection of new shining Emulex cards has wy worse I/O capabilities. We did some tests of database operations on PC. Effects are unequivocal. I admire you honesty :) What class of PC server? Was it connected to a SAN and did it offload I/O to a peripheral device? BTW: Typical z/OS I/O workload is very different from PC workload. Much less IOPS, much more data, much less CPU%. My wife used to work for HDS and I had some interesting conversations with some of the engineers she used to work with. That was a few years ago but in their opinion the high end *nix servers could match a mainframe for I/O throughput. PC commodity hardware is different but racked up with enterprise kit I would be interested to know how they would shape in a drag race. How would a Dell blade with Infiniband, SAN and enterprise class HBAs compare? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 21/03/2016 9:54 PM, John McKown wrote: On Mon, Mar 21, 2016 at 8:14 AM, R.S.wrote: Well, I observed 1,3M IOPS on EC12 or z196 machine during WAS installation. With minimal CPU utilisation (I mean regular CPU, I haven't checked SAP). IMNSHO a PC server with collection of new shining Emulex cards has wy worse I/O capabilities. We did some tests of database operations on PC. Effects are unequivocal. BTW: Typical z/OS I/O workload is very different from PC workload. Much less IOPS, much more data, much less CPU%. Just relating a story my boss tells. A major U.S. manufacturer decide to move all their z/OS work to a SAP distributed platform. A daily job, which was basically did all the shipping work, ran over a day on the SAP platform (remember, daily job). On the z/OS system, it runs 45 minutes. So they have one, very old, IBM mainframe (don't remember what) which they IPL daily to run this one job, then shut back down until the next day. This is, indeed, "hearsay". But I trust my boss when he says that it is so. My wife worked on a couple of mainframe to SAP migration projects and I can't recall any performance war stories but they were not big shops. I do recall that the customers had to change their work processes to fit around SAP and not the other way round, which is bad! -- Radoslaw Skorupka Lodz, Poland -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Mon, Mar 21, 2016 at 8:14 AM, R.S.wrote: > Well, > I observed 1,3M IOPS on EC12 or z196 machine during WAS installation. With > minimal CPU utilisation (I mean regular CPU, I haven't checked SAP). > IMNSHO a PC server with collection of new shining Emulex cards has wy > worse I/O capabilities. > We did some tests of database operations on PC. Effects are unequivocal. > > BTW: Typical z/OS I/O workload is very different from PC workload. Much > less IOPS, much more data, much less CPU%. > Just relating a story my boss tells. A major U.S. manufacturer decide to move all their z/OS work to a SAP distributed platform. A daily job, which was basically did all the shipping work, ran over a day on the SAP platform (remember, daily job). On the z/OS system, it runs 45 minutes. So they have one, very old, IBM mainframe (don't remember what) which they IPL daily to run this one job, then shut back down until the next day. This is, indeed, "hearsay". But I trust my boss when he says that it is so. > > -- > Radoslaw Skorupka > Lodz, Poland > > > -- A fail-safe circuit will destroy others. -- Klipstein Maranatha! <>< John McKown -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 21/03/2016 9:14 PM, R.S. wrote: Well, I observed 1,3M IOPS on EC12 or z196 machine during WAS installation. With minimal CPU utilisation (I mean regular CPU, I haven't checked SAP). IMNSHO a PC server with collection of new shining Emulex cards has wy worse I/O capabilities. We did some tests of database operations on PC. Effects are unequivocal. I admire you honesty :) What class of PC server? Was it connected to a SAN and did it offload I/O to a peripheral device? BTW: Typical z/OS I/O workload is very different from PC workload. Much less IOPS, much more data, much less CPU%. My wife used to work for HDS and I had some interesting conversations with some of the engineers she used to work with. That was a few years ago but in their opinion the high end *nix servers could match a mainframe for I/O throughput. PC commodity hardware is different but racked up with enterprise kit I would be interested to know how they would shape in a drag race. How would a Dell blade with Infiniband, SAN and enterprise class HBAs compare? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Well, I observed 1,3M IOPS on EC12 or z196 machine during WAS installation. With minimal CPU utilisation (I mean regular CPU, I haven't checked SAP). IMNSHO a PC server with collection of new shining Emulex cards has wy worse I/O capabilities. We did some tests of database operations on PC. Effects are unequivocal. BTW: Typical z/OS I/O workload is very different from PC workload. Much less IOPS, much more data, much less CPU%. -- Radoslaw Skorupka Lodz, Poland W dniu 2016-03-20 o 18:32, Anne & Lynn Wheeler pisze: dcrayf...@gmail.com (David Crayford) writes: Emulex sells an HBA that handles over 1M IOPS on a single port. IIRC, x86 Xeon class servers have something called DDIO which facilitates writes directly to processor cache. It's not too dissimilar to offloading I/O to SAPs. I've got old colleagues that work on distributed now and they are of the opinion that I/O bandwidth is not an issue on x86 systems, but it's not exactly commodity hardware. They're all hooked up using 16Gbs fiber connected to a SAN using PCIe, the same as z Systems. I would question the RAS capabilities rather than I/O. Last published mainframe I/O I've seen was peak I/O benchmark for z196 which got 2M IOPS using 104 FICON (running over 104 fibre-channel). Also that all 14 SAPs would run 100% busy getting 2.2M SSCHs/sec but recommendation was keeping SAPs to 75% or 1.5M SSCHs/sec. About the same time of the z196 peak I/O benchmark there was fibre-channel announced for e5-2600 blade claiming over million IOPS, two such fibre-channel getting more throughput than 104 FICON (running over 104 fibre-channel) ... aka FICON is enormously heavy-weight protocol that drastically cuts the native throughput of fibre-channel. disclaimer: 1980 I was asked to do the support for channel extender for STL (now IBM Silicon Valley Lab), they were moving 300 people from the IMS group to offsite bldg. with access back to the STL datacenter; they had tried remote 3270 but found the human factors intolerable. The channel extender support put channel attached 3270 controllers out at the offsite bldg ... and resulted in response indistinguishable from channel attach 3270 controllers within the STL bldg. The vendor they tried to get approval from IBM to release the support, but there was a group in POK that was playing with some serial stuff and they got it blocked because they were afraid it might interfer with getting their stuff released. In 1988, I'm asked to help standardize some serial stuff that LLNL was playing with which quickly becomes fibre channel standard ... one of the issues is that protocol latency effects increases with increase in bandwidth ... so that it becomes apparent at relatively short distances. One of the features with the 1980 work is that it localized the enormous IBM channel protocol latency at the offsite bldg and then used much more efficient protocol the longer distance. For fibre-channel used the much more efficient protocol for everything. In 1990, the POK group finally get their stuff release as ESCON when it is already obsolete. Then some POK engineers become involved with fibre channel standard and define a protocol that enormously cuts the native throughput ... that is eventually released as FICON. Note that the more recent zHPF/TCW work for FICON looks a little more like the work that I had done back in 1980. Besides the peak I/O benchmark FICON throughput issue (compared to native fibre channel issue) there is also the overhead of CKD simulation. There hasn't been any real CKD disks built for decades, current CKD disks are all simulation on industry standard commodity disks. Other tivia, when I moved to San Jose Research in the 70s, they let me wander around. At the time the disk engineering lab (bldg 14) and disk product test lab (bldg 15) they were running pre-scheduled standalone mainframe around the clock, 7x24. At one point they had tried to us MVS for concurrent testing, but found that MVS had 15mins MTBF in that environment. I offerred to rewrite I/O supervisor that made it bullet proof and never fail ... being able to do ondemand, anytime concurrent testing, greatly improving productivity. I happened to mention that MVS 15min MTBF in an internal-only report on the work ... which brings down the wrath of the MVS group on my head (not that it was untrue, but that it exposed the information to the rest of the company). When they found that they couldn't get me fired, they then were to make sure they made my career as unpleasant as possible (blocking promotions and awards whenever they could). z900, 16 processors, 2.5BIPS (156MIPS/proc), Dec2000 z990, 32 processors, 9BIPS, (281MIPS/proc), 2003 z9, 54 processors, 18BIPS (333MIPS/proc), July2005 z10, 64 processors, 30BIPS (469MIPS/proc), Feb2008 z196, 80 processors, 50BIPS (625MIPS/proc), Jul2010 EC12, 101 processors, 75BIPS (743MIPS/proc), Aug2012 z13 published refs is 30% move throughput than EC12 (or about 100BIPS) with 40% more
Re: LzLabs (Was: CeBIT and mainframes)
On 3/19/2016 6:35 PM, Clark Morris wrote: On 19 Mar 2016 14:53:09 -0700, in bit.listserv.ibm-main you wrote: This is what happens when a billionaire loses a court battle with IBM. Can we expect this product to be the subject of a court battle if it is successful in doing what it claims? What are the medium to long term implications for the z series? The i and p series? Haha! Good question! IBM has proven it will sue even without grounds or standing. The legality of zPrime appeared to be air-tight, based on how the IBM Customer Agreement was worded, but that didn't stop IBM from suing NEON anyway. (Of course, IBM later changed the ICA for new machines and for z/OS V2 to plug those loopholes.) I imagine they've taken additional precautions this time around ... -- Edward E Jaffe Phoenix Software International, Inc 831 Parkview Drive North El Segundo, CA 90245 http://www.phoenixsoftware.com/ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
dcrayf...@gmail.com (David Crayford) writes: > Emulex sells an HBA that handles over 1M IOPS on a single port. IIRC, > x86 Xeon class servers have something called DDIO which facilitates > writes directly to processor cache. > It's not too dissimilar to offloading I/O to SAPs. I've got old > colleagues that work on distributed now and they are of the opinion > that I/O bandwidth is not an issue on x86 systems, > but it's not exactly commodity hardware. They're all hooked up using > 16Gbs fiber connected to a SAN using PCIe, the same as z Systems. > > I would question the RAS capabilities rather than I/O. Last published mainframe I/O I've seen was peak I/O benchmark for z196 which got 2M IOPS using 104 FICON (running over 104 fibre-channel). Also that all 14 SAPs would run 100% busy getting 2.2M SSCHs/sec but recommendation was keeping SAPs to 75% or 1.5M SSCHs/sec. About the same time of the z196 peak I/O benchmark there was fibre-channel announced for e5-2600 blade claiming over million IOPS, two such fibre-channel getting more throughput than 104 FICON (running over 104 fibre-channel) ... aka FICON is enormously heavy-weight protocol that drastically cuts the native throughput of fibre-channel. disclaimer: 1980 I was asked to do the support for channel extender for STL (now IBM Silicon Valley Lab), they were moving 300 people from the IMS group to offsite bldg. with access back to the STL datacenter; they had tried remote 3270 but found the human factors intolerable. The channel extender support put channel attached 3270 controllers out at the offsite bldg ... and resulted in response indistinguishable from channel attach 3270 controllers within the STL bldg. The vendor they tried to get approval from IBM to release the support, but there was a group in POK that was playing with some serial stuff and they got it blocked because they were afraid it might interfer with getting their stuff released. In 1988, I'm asked to help standardize some serial stuff that LLNL was playing with which quickly becomes fibre channel standard ... one of the issues is that protocol latency effects increases with increase in bandwidth ... so that it becomes apparent at relatively short distances. One of the features with the 1980 work is that it localized the enormous IBM channel protocol latency at the offsite bldg and then used much more efficient protocol the longer distance. For fibre-channel used the much more efficient protocol for everything. In 1990, the POK group finally get their stuff release as ESCON when it is already obsolete. Then some POK engineers become involved with fibre channel standard and define a protocol that enormously cuts the native throughput ... that is eventually released as FICON. Note that the more recent zHPF/TCW work for FICON looks a little more like the work that I had done back in 1980. Besides the peak I/O benchmark FICON throughput issue (compared to native fibre channel issue) there is also the overhead of CKD simulation. There hasn't been any real CKD disks built for decades, current CKD disks are all simulation on industry standard commodity disks. Other tivia, when I moved to San Jose Research in the 70s, they let me wander around. At the time the disk engineering lab (bldg 14) and disk product test lab (bldg 15) they were running pre-scheduled standalone mainframe around the clock, 7x24. At one point they had tried to us MVS for concurrent testing, but found that MVS had 15mins MTBF in that environment. I offerred to rewrite I/O supervisor that made it bullet proof and never fail ... being able to do ondemand, anytime concurrent testing, greatly improving productivity. I happened to mention that MVS 15min MTBF in an internal-only report on the work ... which brings down the wrath of the MVS group on my head (not that it was untrue, but that it exposed the information to the rest of the company). When they found that they couldn't get me fired, they then were to make sure they made my career as unpleasant as possible (blocking promotions and awards whenever they could). z900, 16 processors, 2.5BIPS (156MIPS/proc), Dec2000 z990, 32 processors, 9BIPS, (281MIPS/proc), 2003 z9, 54 processors, 18BIPS (333MIPS/proc), July2005 z10, 64 processors, 30BIPS (469MIPS/proc), Feb2008 z196, 80 processors, 50BIPS (625MIPS/proc), Jul2010 EC12, 101 processors, 75BIPS (743MIPS/proc), Aug2012 z13 published refs is 30% move throughput than EC12 (or about 100BIPS) with 40% more processors ... or about 710MIPS/proc z196 era e5-2600v1 blade rated at 400-500+BIPS depending on model, e5-2600v4 blades are three-four times that, around 1.5TIPS (1500BIPS). i.e. since the start of the century, commodity processors have increased their processing power significantly more aggresively than mainframe. They have also come to dominate the wafer-chip manufacturing technology ... and essentially mainframe chips have converged to use the same technology (in much the same way mainframe has converged to use
Re: CeBIT and mainframes
I just read the article. Interestin, but, really, EBSDIC? Twice?!? On Fri, Mar 18, 2016 at 1:00 PM, Clark Morriswrote: > On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: > > >no recompile involved. Just relink to replace IBM's LE modules. > So what processor(s) is this code running on? What exactly is being > done? > > Clark Morris > > > >Itschak > > > > > > > >On Fri, Mar 18, 2016 at 12:01 PM, Mark Regan > wrote: > > > >> There is a ComputerWeekly article on this product at > >> > >> > http://www.computerweekly.com/blogs/quocirca-insights/2016/03/the-software-defined-mainframe.html > >> . > >> I noticed that the article author needs to know how to spell the acronym > >> for EBCDIC correctly. He spells it 'EBSDIC' and did it twice. > >> > >> > >> On Fri, Mar 18, 2016 at 4:04 AM Elardus Engelbrecht < > >> elardus.engelbre...@sita.co.za> wrote: > >> > >> > Joel C. Ewing wrote: > >> > > >> > >I notice they also claim "no need for recompilation of Cobol or PL/1 > >> > application programmes, no source code changes, or changes to > operational > >> > procedures". > >> > > >> > I am really struggling to swallow that claim... > >> > > >> > and Dave_Craig wrote: > >> > > >> > >Queue the IP lawyers, and action! > >> > > >> > This is why I said this is 'interesting development'. I am very sure > big > >> > blue and their lawyers won't like that one bit unless there is an > >> agreement. > >> > > >> > > I'll be slow to migrate off that proven decades-old > mission-critical > >> > platform, that's for sure. > >> > > >> > I will also be slow to get off the mainframes. > >> > > >> > Joel C. Ewing wrote: > >> > > >> > >Color me skeptical. > >> > > >> > With all the colors of the rainbow! ;-) > >> > > >> > Groete / Greetings > >> > Elardus Engelbrecht > >> > > >> > -- > >> > For IBM-MAIN subscribe / signoff / archive access instructions, > >> > send email to lists...@listserv.ua.edu with the message: INFO > IBM-MAIN > >> > > >> > >> -- > >> For IBM-MAIN subscribe / signoff / archive access instructions, > >> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > >> > > > >-- > >For IBM-MAIN subscribe / signoff / archive access instructions, > >send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- A fail-safe circuit will destroy others. -- Klipstein Maranatha! <>< John McKown -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Joel C. Ewing wrote: >I notice they also claim "no need for recompilation of Cobol or PL/1 >application programmes, no source code changes, or changes to operational >procedures". I am really struggling to swallow that claim... and Dave_Craig wrote: >Queue the IP lawyers, and action! This is why I said this is 'interesting development'. I am very sure big blue and their lawyers won't like that one bit unless there is an agreement. > I'll be slow to migrate off that proven decades-old mission-critical > platform, that's for sure. I will also be slow to get off the mainframes. Joel C. Ewing wrote: >Color me skeptical. With all the colors of the rainbow! ;-) Groete / Greetings Elardus Engelbrecht -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: LzLabs (Was: CeBIT and mainframes)
>Can we expect this product to be the subject of a court battle if it >is successful in doing what it claims? What are the medium to long >term implications for the z series? The i and p series? > >Clark Morris Well i and p both use proprietary hardware so no effect. For the "z Series"I don't see a major impact, certainly immediately, but I have been wrong before and will be wrong again. Emulating the central CPU Channel Subsystem and API's isn't too hard, folks have been doing it for a long time. Most of the folks involved understand the issues. Replicating the entire environment is much harder. I believe that folks like my ex-employer (I am retired) are probably the likely takers, but not sure how many of them are left. Up until around five years ago they had an MP3000 running traditional DOS/VSE CICS really had no place to go. They started out down the LANMANAGER, OS/2 path which became NT Servers because IBM pulled the plug on OS/2. This left them with an small Mainframe running VM/ESA & DOS/CICS and 200 or so NT servers. Given no upgrade path to a modern Mainframe at an affordable price, they ditched it the Mainframe. I don't believe IBM wants such customers unless they move to a mixed Traditional (VM/DOS/zOS) and Linux farm running on a large "Z" box. My employer had lots of commodity software in use that was tied to Windows it wasn't an option, perhaps for the same reasons LzLabs won't take the world by storm. They now have replaced the 250 NT servers with 30 IBM x3650 2 x 6 Core boxes running VMWARE ESXi and various flavours of Windows Server. Performance isn't really a problem. That's not to say there aren't performance problems, so there is one database app where they were the first site to buy. The developers decided to switch from Oracle to SQL server to save costs, and really didn't know how to tune the code. When I left it was improving as they tuned the indexing, but these issues used to occur on Mainframes... ... it will be interesting to see how many takers there are... Dave Wade -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 20/03/2016 10:50 AM, Tom Marchant wrote: I'm skeptical of all that but assuming all that, where are they going to get the I/O bandwidth needed? Emulex sells an HBA that handles over 1M IOPS on a single port. IIRC, x86 Xeon class servers have something called DDIO which facilitates writes directly to processor cache. It's not too dissimilar to offloading I/O to SAPs. I've got old colleagues that work on distributed now and they are of the opinion that I/O bandwidth is not an issue on x86 systems, but it's not exactly commodity hardware. They're all hooked up using 16Gbs fiber connected to a SAN using PCIe, the same as z Systems. I would question the RAS capabilities rather than I/O. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: LzLabs (Was: CeBIT and mainframes)
On Sat, Mar 19, 2016 at 8:35 PM, Clark Morriswrote: > On 19 Mar 2016 14:53:09 -0700, in bit.listserv.ibm-main you wrote: > > >On 3/18/2016 6:30 AM, Bill Woodger wrote: > >> A google-translate of part of the final article in French from the > media section of the LzLabs website. > >> > >> "Lzlabs technology leans on a container system which embeds the > mainframe application and data. The application and its lines of code are > included and the native format of the original data is kept - all without > recompilation. "The only thing we are changing is the APIs. We take the old > APIs, and replace them with ours, "said Thilo Rockmann." > > > >This is what happens when a billionaire loses a court battle with IBM. > > Can we expect this product to be the subject of a court battle if it > is successful in doing what it claims? Especially considering the on-going legal battle between Oracle and Google about the Java API specification itself being copyrighted so that Google cannot legally create a separate product (Android) which implements a "clean room" implementation of a "work alike" which mirrors the Java API. To write Android code, you basically write and compile Java into Java byte code. The Java byte code is the translated from JVM byte code to ART (earlier Dalvik) byte code. The ART virtual machine runs this, different, byte code. But the "calling sequence", i.e. API, is the same as the "calling sequence" (API) that the JVM uses. Which Oracle insists is illegal copying. What LzLabs appears to have done is write two things: 1) an instruction emulator for zArch "problem state" instructions and 2) an alternate LE implementation which uses the identical API as z/OS LE. This latter, if Oracle wins, will most totally kill the LzLabs product. Um, assuming that IBM as copyrighted the API. If, indeed, such a thing can even be copyrighted. That is what is being fought over. The above reminds me of the "UNIX wars" where ever UNIX vendor decided to "extend" UNIX in such a way as to cause "vendor lock in". There are many reasons why I like FOSS and the FSF. I understand wanting to make money. > What are the medium to long > term implications for the z series? The i and p series? > > Clark Morris > >He strikes back! > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- A fail-safe circuit will destroy others. -- Klipstein Maranatha! <>< John McKown -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Sat, Mar 19, 2016 at 9:50 PM, Tom Marchant < 000a2a8c2020-dmarc-requ...@listserv.ua.edu> wrote: > > > > I'm skeptical of all that but assuming all that, where are they going to > get the I/O > bandwidth needed? > I wonder that myself. But then, there are now SSD devices which run directly on the PCIe bus at PCIe bus speeds. I could envision a purpose built system (likely way too expensive) which has an Intel Xeon class CPU for regular instructions, a GPU array using CUDA for numeric intensive work, and "channels" made up of ARM processors, each controlling only a few SSD (SATA 3 or PCIe attached) drives sharing memory with the main system memory for I/O. > > -- > Tom Marchant > -- A fail-safe circuit will destroy others. -- Klipstein Maranatha! <>< John McKown -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Mar 19, 2016, at 11:04 PM, Joel C. Ewing wrote: On 03/19/2016 03:13 PM, Ed Gould wrote: On Mar 19, 2016, at 2:42 PM, Joel C. Ewing wrote: On 03/18/2016 11:14 PM, Ed Gould wrote: On Mar 18, 2016, at 1:00 PM, Clark Morris wrote: On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: no recompile involved. Just relink to replace IBM's LE modules. So what processor(s) is this code running on? What exactly is being done? Clark Morris --SNIP So ... how do you know when an LE module changes? Manual effort? Ed I'm pretty sure he means re-link to replace any IBM-licensed LE modules within application load modules with non-IBM functional replacement modules that are either part of or interface to whatever replaces the LE run time in the new environment. If that is successful, the resulting load module is no longer associated with IBM's LE and you could care less if IBM makes subsequent LE changes. In the unlikely event that fixes/enhancements to the LzLabs run time environment might have versioning issues that require re-linking to change their interface modules at some later time, that would be an issue independent from any changes in IBM's LE. I may have missed something in the thread. However, When you get a mixed LE module (PTF type) level all bets are off when it comes to LE. Execution platform comes with its own issues and complicates debugging beyond anything I would be willing to support and I suspect other on here would have the same issues. At one time Amdahl had issues and with the coming of OCO came the demise and I suspect IBM saw (caused) the issue as well. I suspect any OEM would have similar issues without source. IIRC some modules are semi public source available in JES2 although some modules in JES2 are OCO. I don't know about JES3 but I suspect its close to being the same. LE is an example of all OCO and seeing as they (LE) can't get their act together any other vendor IMO would be stupid if they think they can emulate LE . Ed Unless he relinks the module(s) to pick up any changed LE modules each time maintenance is applied he will be in for a big surprise. LE is *KNOWN* for changing the rules without telling anyone. LE is the *WORST* IBM product ever delivered, IMO. Ed Ed, As I understand it, in a context where there would be NO IBM LE modules, your comment simply doesn't make sense: the context being executing legacy mainframe application object code on non-mainframe hardware, in a non-IBM operating environment that has NO IBM run time libraries or code, an environment that supposedly runs application load modules designed for CICS and batch environments by replicating the functionality of application interfaces that would be needed by such load modules previously generated by COBOL and PL/I compilers for those environments. Surely a customer owns the rights to object modules generated by compiling customer source code, but just as surely IBM owns the rights to any modules generated solely from IBM source code. The LE run time environment is part of IBM's licensed code on z/OS. Unless you believe IBM is going to reverse its Hercules policy and start licensing IBM software to run in non-IBM-sanctioned hardware environments, that means the LzLabs implementation must not depend on an IBM LE modules or any other IBM code for providing LE-like functionality in its execution environment, and any IBM code modules that were linked into the application load modules for run time support would likely need to be functionally replaced to legally run the application under an LzLabs environment. Dynamic linking to IBM LE run time library routines would also be unavailable. We are talking here about an environment to execute functionally-frozen mainframe application code -- there are no claims of support for application development or use of COBOL and PL/I compilers under LzLabs. Once an application successfully makes the jump to the LZLabs environment, that of necessity means it is no longer running any LE or other IBM restricted-license code and that all LE-like functionality provided by LzLabs code at the time of that jump must be compatible with what the application load module needs. IT MAKES NO DIFFERENCE AFTER THAT POINT IF IBM CHANGES ANY LE CODE OR ANY OF THE RULES FOR LE OR FOR THE IBM COMPILERS. The old application modules under LzLabs are unchanged so their requirements that are being satisfied by LzLabs code are also unchanged. The stable application load module is at that point running in the LzLabs environment with the IBM LE run time environment code and IBM COBOL and PL/I compilers totally out of the picture! Whether LzLabs can successfully provide the claimed support, and whether they can do it without some illegal reverse engineering and without violation of IBM patents or other intellectual property rights are separate
Re: CeBIT and mainframes
On 03/19/2016 03:13 PM, Ed Gould wrote: > On Mar 19, 2016, at 2:42 PM, Joel C. Ewing wrote: > >> On 03/18/2016 11:14 PM, Ed Gould wrote: >>> On Mar 18, 2016, at 1:00 PM, Clark Morris wrote: >>> On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: > no recompile involved. Just relink to replace IBM's LE modules. So what processor(s) is this code running on? What exactly is being done? Clark Morris >>> >>> --SNIP >>> >>> So ... how do you know when an LE module changes? >>> >>> Manual effort? >>> >>> Ed >>> >> I'm pretty sure he means re-link to replace any IBM-licensed LE modules >> within application load modules with non-IBM functional replacement >> modules that are either part of or interface to whatever replaces the LE >> run time in the new environment. If that is successful, the resulting >> load module is no longer associated with IBM's LE and you could care >> less if IBM makes subsequent LE changes. In the unlikely event that >> fixes/enhancements to the LzLabs run time environment might have >> versioning issues that require re-linking to change their interface >> modules at some later time, that would be an issue independent from any >> changes in IBM's LE. > > Unless he relinks the module(s) to pick up any changed LE modules each > time maintenance is applied he will be in for a big surprise. > LE is *KNOWN* for changing the rules without telling anyone. LE is the > *WORST* IBM product ever delivered, IMO. > > Ed > > Ed, As I understand it, in a context where there would be NO IBM LE modules, your comment simply doesn't make sense: the context being executing legacy mainframe application object code on non-mainframe hardware, in a non-IBM operating environment that has NO IBM run time libraries or code, an environment that supposedly runs application load modules designed for CICS and batch environments by replicating the functionality of application interfaces that would be needed by such load modules previously generated by COBOL and PL/I compilers for those environments. Surely a customer owns the rights to object modules generated by compiling customer source code, but just as surely IBM owns the rights to any modules generated solely from IBM source code. The LE run time environment is part of IBM's licensed code on z/OS. Unless you believe IBM is going to reverse its Hercules policy and start licensing IBM software to run in non-IBM-sanctioned hardware environments, that means the LzLabs implementation must not depend on an IBM LE modules or any other IBM code for providing LE-like functionality in its execution environment, and any IBM code modules that were linked into the application load modules for run time support would likely need to be functionally replaced to legally run the application under an LzLabs environment. Dynamic linking to IBM LE run time library routines would also be unavailable. We are talking here about an environment to execute functionally-frozen mainframe application code -- there are no claims of support for application development or use of COBOL and PL/I compilers under LzLabs. Once an application successfully makes the jump to the LZLabs environment, that of necessity means it is no longer running any LE or other IBM restricted-license code and that all LE-like functionality provided by LzLabs code at the time of that jump must be compatible with what the application load module needs. IT MAKES NO DIFFERENCE AFTER THAT POINT IF IBM CHANGES ANY LE CODE OR ANY OF THE RULES FOR LE OR FOR THE IBM COMPILERS. The old application modules under LzLabs are unchanged so their requirements that are being satisfied by LzLabs code are also unchanged. The stable application load module is at that point running in the LzLabs environment with the IBM LE run time environment code and IBM COBOL and PL/I compilers totally out of the picture! Whether LzLabs can successfully provide the claimed support, and whether they can do it without some illegal reverse engineering and without violation of IBM patents or other intellectual property rights are separate issues beyond my skill set. -- Joel C. Ewing,Bentonville, AR jcew...@acm.org -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Fri, 18 Mar 2016 13:46:55 -0500, Mike Schwabwrote: >It has a small proof-of-concept box that it can make available to >those running mainframe apps where they can see how it works and try >out some of their own applications. This box, based on an Intel NUC >running an i7 CPU, is smaller than the size of a hardback book, but >can run workloads as if it was a reasonable-sized mainframe. Right. Assuming that they can interpret the z/Architecture instructions at a reasonable rate, since they don't recompile. And assuming that they can provide emulation for all of the things that real systems do, including serialization of accesses. And ssuming that they can lash together enough commodity x86 systems to perform significant real work. I'm skeptical of all that but assuming all that, where are they going to get the I/O bandwidth needed? -- Tom Marchant -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: LzLabs (Was: CeBIT and mainframes)
On 19 Mar 2016 14:53:09 -0700, in bit.listserv.ibm-main you wrote: >On 3/18/2016 6:30 AM, Bill Woodger wrote: >> A google-translate of part of the final article in French from the media >> section of the LzLabs website. >> >> "Lzlabs technology leans on a container system which embeds the mainframe >> application and data. The application and its lines of code are included and >> the native format of the original data is kept - all without recompilation. >> "The only thing we are changing is the APIs. We take the old APIs, and >> replace them with ours, "said Thilo Rockmann." > >This is what happens when a billionaire loses a court battle with IBM. Can we expect this product to be the subject of a court battle if it is successful in doing what it claims? What are the medium to long term implications for the z series? The i and p series? Clark Morris >He strikes back! -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
It has a small proof-of-concept box that it can make available to those running mainframe apps where they can see how it works and try out some of their own applications. This box, based on an Intel NUC running an i7 CPU, is smaller than the size of a hardback book, but can run workloads as if it was a reasonable-sized mainframe. On Fri, Mar 18, 2016 at 1:00 PM, Clark Morriswrote: > On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: > >>no recompile involved. Just relink to replace IBM's LE modules. > So what processor(s) is this code running on? What exactly is being > done? > > Clark Morris >> >>Itschak >> >> >> >>On Fri, Mar 18, 2016 at 12:01 PM, Mark Regan wrote: >> >>> There is a ComputerWeekly article on this product at >>> >>> http://www.computerweekly.com/blogs/quocirca-insights/2016/03/the-software-defined-mainframe.html -- Mike A Schwab, Springfield IL USA Where do Forest Rangers go to get away from it all? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
IMHO they don't run compiled code. They recompile source code. Clue: Raincode is their technology partner. Raincode makes COBOL compiler. -- Radoslaw Skorupka Lodz, Poland -- Treść tej wiadomości może zawierać informacje prawnie chronione Banku przeznaczone wyłącznie do użytku służbowego adresata. Odbiorcą może być jedynie jej adresat z wyłączeniem dostępu osób trzecich. Jeżeli nie jesteś adresatem niniejszej wiadomości lub pracownikiem upoważnionym do jej przekazania adresatowi, informujemy, że jej rozpowszechnianie, kopiowanie, rozprowadzanie lub inne działanie o podobnym charakterze jest prawnie zabronione i może być karalne. Jeżeli otrzymałeś tę wiadomość omyłkowo, prosimy niezwłocznie zawiadomić nadawcę wysyłając odpowiedź oraz trwale usunąć tę wiadomość włączając w to wszelkie jej kopie wydrukowane lub zapisane na dysku. This e-mail may contain legally privileged information of the Bank and is intended solely for business use of the addressee. This e-mail may only be received by the addressee and may not be disclosed to any third parties. If you are not the intended addressee of this e-mail or the employee authorized to forward it to the addressee, be advised that any dissemination, copying, distribution or any other similar activity is legally prohibited and may be punishable. If you received this e-mail by mistake please advise the sender immediately by using the reply facility in your e-mail software and delete permanently this e-mail including any copies of it either printed or saved to hard drive. mBank S.A. z siedzibą w Warszawie, ul. Senatorska 18, 00-950 Warszawa, www.mBank.pl, e-mail: kont...@mbank.pl Sąd Rejonowy dla m. st. Warszawy XII Wydział Gospodarczy Krajowego Rejestru Sądowego, nr rejestru przedsiębiorców KRS 025237, NIP: 526-021-50-88. Według stanu na dzień 01.01.2016 r. kapitał zakładowy mBanku S.A. (w całości wpłacony) wynosi 168.955.696 złotych. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
LzLabs (Was: CeBIT and mainframes)
On 3/18/2016 6:30 AM, Bill Woodger wrote: A google-translate of part of the final article in French from the media section of the LzLabs website. "Lzlabs technology leans on a container system which embeds the mainframe application and data. The application and its lines of code are included and the native format of the original data is kept - all without recompilation. "The only thing we are changing is the APIs. We take the old APIs, and replace them with ours, "said Thilo Rockmann." This is what happens when a billionaire loses a court battle with IBM. He strikes back! -- Edward E Jaffe Phoenix Software International, Inc 831 Parkview Drive North El Segundo, CA 90245 http://www.phoenixsoftware.com/ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
CeBIT and mainframes
Hi I played around the CeBIT website and came across this interesting thing: http://www.cebit.de/exhibitor/lzlabs/E363469 http://www.bankingtech.com/454942/lzlabs-unveils-worlds-first-software-defined-mainframe/ I see this note: LzLabs Software Defined Mainframe (TM) enables both Red Hat Linux and Cloud infrastructure such as Microsoft's Azure to process thousands of transactions per second, while maintaining enterprise requirements for reliability, scalability, serviceability and security. This software solution includes a faithful re-creation of the primary online, batch and database environments, which enables unrivaled compatibility and exceptional performance, to dramatically reduce IT costs. Wonder what is big blue saying of this interesting development? PS: I am NOT with CeBIT or LzLabs or anything with them. Groete / Greetings Elardus Engelbrecht -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 03/17/2016 08:01 AM, Elardus Engelbrecht wrote: > Hi > > I played around the CeBIT website and came across this interesting thing: > > http://www.cebit.de/exhibitor/lzlabs/E363469 > > http://www.bankingtech.com/454942/lzlabs-unveils-worlds-first-software-defined-mainframe/ > > > I see this note: > > LzLabs Software Defined Mainframe (TM) enables both Red Hat Linux and Cloud > infrastructure such as Microsoft's Azure to process thousands of transactions > per second, while maintaining enterprise requirements for reliability, > scalability, serviceability and security. This software solution includes a > faithful re-creation of the primary online, batch and database environments, > which enables unrivaled compatibility and exceptional performance, to > dramatically reduce IT costs. > > Wonder what is big blue saying of this interesting development? > > PS: I am NOT with CeBIT or LzLabs or anything with them. > > Groete / Greetings > Elardus Engelbrecht > > ... I notice they also claim "no need for recompilation of Cobol or PL/1 application programmes, no source code changes, or changes to operational procedures". So they have somehow managed to replicate the functional behavior of all the SVC and PC interfaces and control blocks that application code might be using in z/OS batch and CICS environments, to replicate the functional behavior of I/O to data sets that batch jobs and CICS transactions might be doing, to replicate all the CICS APIs and CICS control blocks CICS applications might be using, to replicate all the LE run time support needed to execute COBOL and PL/I programs in batch and CICS, to replicate all the related DB2 functional APIs, and to emulate the execution of z-architecture application program code in batch and CICS environments, and to replicate operational interfaces. And since security was "maintained", that implies they have also managed to replicate the functionality of RACF for their batch, CICS, and DB2 environments, and integrated that security somehow into the supporting physical operating environment to secure the "mainframe" data from external tampering. In other words, to do what they seem to claim, they have re-implemented a significant portion of z/OS and some major subsystems of z/OS for another hardware platform. All correctly and without infringing on any IBM patents or licensing restrictions? And have achieved reasonable transaction rates without sacrificing "reliability, scalability, serviceability, and security" on hardware platforms that have historically been less robust than z-architecture? Color me skeptical. They don't say no re-linking of load modules, which makes me suspect that to be legal you would have to re-link and somehow replace any linked-in LE run time modules, since those modules would be IBM-licensed code. Even "stabilized" applications may require occasional minor changes --e.g.,to adapt to trivial changes in local sales tax rates. Without a mainframe compiler even a trivial change becomes a difficult load module patch. -- Joel C. Ewing,Bentonville, AR jcew...@acm.org -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
no recompile involved. Just relink to replace IBM's LE modules. Itschak On Fri, Mar 18, 2016 at 12:01 PM, Mark Reganwrote: > There is a ComputerWeekly article on this product at > > http://www.computerweekly.com/blogs/quocirca-insights/2016/03/the-software-defined-mainframe.html > . > I noticed that the article author needs to know how to spell the acronym > for EBCDIC correctly. He spells it 'EBSDIC' and did it twice. > > > On Fri, Mar 18, 2016 at 4:04 AM Elardus Engelbrecht < > elardus.engelbre...@sita.co.za> wrote: > > > Joel C. Ewing wrote: > > > > >I notice they also claim "no need for recompilation of Cobol or PL/1 > > application programmes, no source code changes, or changes to operational > > procedures". > > > > I am really struggling to swallow that claim... > > > > and Dave_Craig wrote: > > > > >Queue the IP lawyers, and action! > > > > This is why I said this is 'interesting development'. I am very sure big > > blue and their lawyers won't like that one bit unless there is an > agreement. > > > > > I'll be slow to migrate off that proven decades-old mission-critical > > platform, that's for sure. > > > > I will also be slow to get off the mainframes. > > > > Joel C. Ewing wrote: > > > > >Color me skeptical. > > > > With all the colors of the rainbow! ;-) > > > > Groete / Greetings > > Elardus Engelbrecht > > > > -- > > For IBM-MAIN subscribe / signoff / archive access instructions, > > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > > > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Mar 19, 2016, at 2:42 PM, Joel C. Ewing wrote: On 03/18/2016 11:14 PM, Ed Gould wrote: On Mar 18, 2016, at 1:00 PM, Clark Morris wrote: On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: no recompile involved. Just relink to replace IBM's LE modules. So what processor(s) is this code running on? What exactly is being done? Clark Morris --SNIP So ... how do you know when an LE module changes? Manual effort? Ed I'm pretty sure he means re-link to replace any IBM-licensed LE modules within application load modules with non-IBM functional replacement modules that are either part of or interface to whatever replaces the LE run time in the new environment. If that is successful, the resulting load module is no longer associated with IBM's LE and you could care less if IBM makes subsequent LE changes. In the unlikely event that fixes/enhancements to the LzLabs run time environment might have versioning issues that require re-linking to change their interface modules at some later time, that would be an issue independent from any changes in IBM's LE. Unless he relinks the module(s) to pick up any changed LE modules each time maintenance is applied he will be in for a big surprise. LE is *KNOWN* for changing the rules without telling anyone. LE is the *WORST* IBM product ever delivered, IMO. Ed -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 03/18/2016 11:14 PM, Ed Gould wrote: > On Mar 18, 2016, at 1:00 PM, Clark Morris wrote: > >> On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: >> >>> no recompile involved. Just relink to replace IBM's LE modules. >> So what processor(s) is this code running on? What exactly is being >> done? >> >> Clark Morris > > --SNIP > > So ... how do you know when an LE module changes? > > Manual effort? > > Ed > I'm pretty sure he means re-link to replace any IBM-licensed LE modules within application load modules with non-IBM functional replacement modules that are either part of or interface to whatever replaces the LE run time in the new environment. If that is successful, the resulting load module is no longer associated with IBM's LE and you could care less if IBM makes subsequent LE changes. In the unlikely event that fixes/enhancements to the LzLabs run time environment might have versioning issues that require re-linking to change their interface modules at some later time, that would be an issue independent from any changes in IBM's LE. -- Joel C. Ewing,Bentonville, AR jcew...@acm.org -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
There is a ComputerWeekly article on this product at http://www.computerweekly.com/blogs/quocirca-insights/2016/03/the-software-defined-mainframe.html. I noticed that the article author needs to know how to spell the acronym for EBCDIC correctly. He spells it 'EBSDIC' and did it twice. On Fri, Mar 18, 2016 at 4:04 AM Elardus Engelbrecht < elardus.engelbre...@sita.co.za> wrote: > Joel C. Ewing wrote: > > >I notice they also claim "no need for recompilation of Cobol or PL/1 > application programmes, no source code changes, or changes to operational > procedures". > > I am really struggling to swallow that claim... > > and Dave_Craig wrote: > > >Queue the IP lawyers, and action! > > This is why I said this is 'interesting development'. I am very sure big > blue and their lawyers won't like that one bit unless there is an agreement. > > > I'll be slow to migrate off that proven decades-old mission-critical > platform, that's for sure. > > I will also be slow to get off the mainframes. > > Joel C. Ewing wrote: > > >Color me skeptical. > > With all the colors of the rainbow! ;-) > > Groete / Greetings > Elardus Engelbrecht > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
dave.g4...@gmail.com (Dave Wade) writes: > In fact its a bit like SVC's in VM/370. The code which handles them is > very different to that in the OS world, but the code still runs there was joke about the time MVS came out with 8mbyte kernel image in every virtual address space ... that the 32kbyte os/360 system services simulation in VM/CMS was a lot more efficient than the 8mbyte os/360 system services simulation in MVS. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Nah, not letting him off that easily! The word "coded" is the same in both languages, and BCD ¬= BSD. Like us Brits tend to say "kicks" and the Americans tend to say "see, eye, see, ess" but it's still actually CICS :-) Cheers, Mick. On 18 March 2016 at 18:35, Tom Brennanwrote: > Maybe EBSDIC is just like colour vs. color, spanner vs. wrench. > > John McKown wrote: >> >> I just read the article. Interestin, but, really, EBSDIC? Twice?!? >> > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
CeBIT and mainframes
A google-translate of part of the final article in French from the media section of the LzLabs website. "Lzlabs technology leans on a container system which embeds the mainframe application and data. The application and its lines of code are included and the native format of the original data is kept - all without recompilation. "The only thing we are changing is the APIs. We take the old APIs, and replace them with ours, "said Thilo Rockmann." They have a little video which shows the running of the NIST compiler-validation suite, compiled on a Mainframe, and run in their container. With 260 JCL steps (they proudly point out that this is more steps than the Mainframe supports...). The NIST suite is doing nothing fancy, it is for validating COBOL compilers to the 1985 Standard. Running the compiled code would show that all COBOL statements work. "we take the old APIs, and replace them" in this case seems to mean "taking the COBOL runtime (Language Environment) and replacing its functionality". In the video there is a brief simple mention of "ported" without explanation. This could mean, effectively, a "relink" as suggested earlier in this thread. There is a mention of COBOL-IT in the French article for programs which do need to be recompiled. Raincode has experience, and tools, although directed at .Net, but including an alleged DFSORT-compatible product. On Friday, 18 March 2016 09:59:47 UTC, R.S. wrote: > IMHO they don't run compiled code. They recompile source code. > Clue: Raincode is their technology partner. Raincode makes COBOL compiler. > > -- > Radoslaw Skorupka > Lodz, Poland -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
I noticed that the CEO of LzLabs is the ex CEO of NEON. Wasn't NEON working on something similar? CIT | Ken Porowski | VP Mainframe Engineering | Information Technology | +1 973 740 5459 (tel) | ken.porow...@cit.com This email message and any accompanying materials may contain proprietary, privileged and confidential information of CIT Group Inc. or its subsidiaries or affiliates (collectively, “CIT”), and are intended solely for the recipient(s) named above. If you are not the intended recipient of this communication, any use, disclosure, printing, copying or distribution, or reliance on the contents, of this communication is strictly prohibited. CIT disclaims any liability for the review, retransmission, dissemination or other use of, or the taking of any action in reliance upon, this communication by persons other than the intended recipient(s). If you have received this communication in error, please reply to the sender advising of the error in transmission, and immediately delete and destroy the communication and any accompanying materials. To the extent permitted by applicable law, CIT and others may inspect, review, monitor, analyze, copy, record and retain any communications sent from or received at this email address. -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Joel C. Ewing Sent: Thursday, March 17, 2016 11:38 AM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Re: [IBM-MAIN] CeBIT and mainframes On 03/17/2016 08:01 AM, Elardus Engelbrecht wrote: > Hi > > I played around the CeBIT website and came across this interesting thing: > > http://www.cebit.de/exhibitor/lzlabs/E363469 > > http://www.bankingtech.com/454942/lzlabs-unveils-worlds-first-software > -defined-mainframe/ > > I see this note: > > LzLabs Software Defined Mainframe (TM) enables both Red Hat Linux and Cloud > infrastructure such as Microsoft's Azure to process thousands of transactions > per second, while maintaining enterprise requirements for reliability, > scalability, serviceability and security. This software solution includes a > faithful re-creation of the primary online, batch and database environments, > which enables unrivaled compatibility and exceptional performance, to > dramatically reduce IT costs. > > Wonder what is big blue saying of this interesting development? > > PS: I am NOT with CeBIT or LzLabs or anything with them. > > Groete / Greetings > Elardus Engelbrecht > > ... I notice they also claim "no need for recompilation of Cobol or PL/1 application programmes, no source code changes, or changes to operational procedures". So they have somehow managed to replicate the functional behavior of all the SVC and PC interfaces and control blocks that application code might be using in z/OS batch and CICS environments, to replicate the functional behavior of I/O to data sets that batch jobs and CICS transactions might be doing, to replicate all the CICS APIs and CICS control blocks CICS applications might be using, to replicate all the LE run time support needed to execute COBOL and PL/I programs in batch and CICS, to replicate all the related DB2 functional APIs, and to emulate the execution of z-architecture application program code in batch and CICS environments, and to replicate operational interfaces. And since security was "maintained", that implies they have also managed to replicate the functionality of RACF for their batch, CICS, and DB2 environments, and integrated that security somehow into the supporting physical operating environment to secure the "mainframe" data from external tampering. In other words, to do what they seem to claim, they have re-implemented a significant portion of z/OS and some major subsystems of z/OS for another hardware platform. All correctly and without infringing on any IBM patents or licensing restrictions? And have achieved reasonable transaction rates without sacrificing "reliability, scalability, serviceability, and security" on hardware platforms that have historically been less robust than z-architecture? Color me skeptical. They don't say no re-linking of load modules, which makes me suspect that to be legal you would have to re-link and somehow replace any linked-in LE run time modules, since those modules would be IBM-licensed code. Even "stabilized" applications may require occasional minor changes --e.g.,to adapt to trivial changes in local sales tax rates. Without a mainframe compiler even a trivial change becomes a difficult load module patch. -- Joel C. Ewing,Bentonville, AR jcew...@acm.org -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Please note I have no connection with lzlabs, other than I know some people who work there from other things I have dabbled in 1) On that note its worth doing a LinkedIn search and seeing who say they work for LZLABS. I notice a couple I know from the Hercules that I didn't know worked there, plus Laurence Wilkinson who built an FPGA 360/30 clone, so folks how have been down the battle field with IBM and know a little bit about mainframes. 2) The approach isn't totally new or original. The original Don Higgins MS-DOS IBM 370 Assembler and Emulator took a similar approach, emulating the hardware for the problem state code and implementing the SVC's as shims in X86 code that call the MS-DOS APIs. This is still downloadable freeware. Then there was the MicroFocus Cobol which evolved from this. More recently Don wrote the Z390 Java emulator, which provides support for a number API's including parts of CICS and some access methods. This product continues to be available at www.z390.org. although Don no longer takes an active part in working on the project. In fact its a bit like SVC's in VM/370. The code which handles them is very different to that in the OS world, but the code still runs 3) I always thought the LE API's were, like most IBM mainframe backwards compatible. So if they changed in a way which would break code running on the LzLabs software defined mainframe, they would break the same code on a real mainframe. 4) Of course the challenge is to have an emulation which is both accurate and complete. Oh and of course is cheap enough to be cost effective. If we are talking legacy code, then LE is possibly irrelevant and its basic access methods such as QSAM and VSAM that would be critical. Also how do you provide RACF protection. What really is the scope of this project. Of course this sort of question probably won't get answered because the journalists don't know enough to ask it. I wonder if the current testing phase is also about defining the scope needed. Dave Wade -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 16Mar17:1037-0500, Joel C. Ewing wrote: > I notice they also claim > "no need for recompilation of Cobol or PL/1 application programmes, no > source code changes, or changes to operational procedures". > > So they have somehow managed to replicate the functional behavior of all > the SVC and PC interfaces and control blocks that application code might > be using in z/OS batch and CICS environments, to replicate the > functional behavior of I/O to data sets that batch jobs and CICS > transactions might be doing, to replicate all the CICS APIs and CICS > control blocks CICS applications might be using, to replicate all the LE > run time support needed to execute COBOL and PL/I programs in batch and > CICS, to replicate all the related DB2 functional APIs, and to emulate > the execution of z-architecture application program code in batch and > CICS environments, and to replicate operational interfaces. And since > security was "maintained", that implies they have also managed to > replicate the functionality of RACF for their batch, CICS, and DB2 > environments, and integrated that security somehow into the supporting > physical operating environment to secure the "mainframe" data from > external tampering. In other words, to do what they seem to claim, they > have re-implemented a significant portion of z/OS and some major > subsystems of z/OS for another hardware platform. All correctly and > without infringing on any IBM patents or licensing restrictions? And > have achieved reasonable transaction rates without sacrificing > "reliability, scalability, serviceability, and security" on hardware > platforms that have historically been less robust than z-architecture? > > Color me skeptical. > > They don't say no re-linking of load modules, which makes me suspect > that to be legal you would have to re-link and somehow replace any > linked-in LE run time modules, since those modules would be IBM-licensed > code. > > Even "stabilized" applications may require occasional minor changes > --e.g.,to adapt to trivial changes in local sales tax rates. Without a > mainframe compiler even a trivial change becomes a difficult load module > patch. Queue the IP lawyers, and action! This looks to me a firm built to be acquired for a tidy lump sum payoff by the competition with subsequent euthanasia. I'll be slow to migrate off that proven decades-old mission-critical platform, that's for sure. -- May the LORD God bless you exceedingly abundantly! Dave_Craig__ "So the universe is not quite as you thought it was. You'd better rearrange your beliefs, then. Because you certainly can't rearrange the universe." __--from_Nightfall_by_Asimov/Silverberg_ -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Maybe EBSDIC is just like colour vs. color, spanner vs. wrench. John McKown wrote: I just read the article. Interestin, but, really, EBSDIC? Twice?!? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On Mar 18, 2016, at 1:00 PM, Clark Morris wrote: On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: no recompile involved. Just relink to replace IBM's LE modules. So what processor(s) is this code running on? What exactly is being done? Clark Morris --SNIP So ... how do you know when an LE module changes? Manual effort? Ed -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
Sounds a lot like http://www.z390.org/ . It took about 5 years for one guy to develop. It emulates hardware instructions and operating system calls. No IBM software (other than macro definitions for the system calls). On Thu, Mar 17, 2016 at 10:37 AM, Joel C. Ewingwrote: > On 03/17/2016 08:01 AM, Elardus Engelbrecht wrote: >> Hi >> >> I played around the CeBIT website and came across this interesting thing: >> >> http://www.cebit.de/exhibitor/lzlabs/E363469 >> >> http://www.bankingtech.com/454942/lzlabs-unveils-worlds-first-software-defined-mainframe/ >> >> I see this note: >> >> LzLabs Software Defined Mainframe (TM) enables both Red Hat Linux and Cloud >> infrastructure such as Microsoft's Azure to process thousands of >> transactions per second, while maintaining enterprise requirements for >> reliability, scalability, serviceability and security. This software >> solution includes a faithful re-creation of the primary online, batch and >> database environments, which enables unrivaled compatibility and exceptional >> performance, to dramatically reduce IT costs. >> >> Wonder what is big blue saying of this interesting development? >> >> PS: I am NOT with CeBIT or LzLabs or anything with them. >> >> Groete / Greetings >> Elardus Engelbrecht >> >> ... > I notice they also claim > "no need for recompilation of Cobol or PL/1 application programmes, no > source code changes, or changes to operational procedures". > > So they have somehow managed to replicate the functional behavior of all > the SVC and PC interfaces and control blocks that application code might > be using in z/OS batch and CICS environments, to replicate the > functional behavior of I/O to data sets that batch jobs and CICS > transactions might be doing, to replicate all the CICS APIs and CICS > control blocks CICS applications might be using, to replicate all the LE > run time support needed to execute COBOL and PL/I programs in batch and > CICS, to replicate all the related DB2 functional APIs, and to emulate > the execution of z-architecture application program code in batch and > CICS environments, and to replicate operational interfaces. And since > security was "maintained", that implies they have also managed to > replicate the functionality of RACF for their batch, CICS, and DB2 > environments, and integrated that security somehow into the supporting > physical operating environment to secure the "mainframe" data from > external tampering. In other words, to do what they seem to claim, they > have re-implemented a significant portion of z/OS and some major > subsystems of z/OS for another hardware platform. All correctly and > without infringing on any IBM patents or licensing restrictions? And > have achieved reasonable transaction rates without sacrificing > "reliability, scalability, serviceability, and security" on hardware > platforms that have historically been less robust than z-architecture? > > Color me skeptical. > > They don't say no re-linking of load modules, which makes me suspect > that to be legal you would have to re-link and somehow replace any > linked-in LE run time modules, since those modules would be IBM-licensed > code. > > Even "stabilized" applications may require occasional minor changes > --e.g.,to adapt to trivial changes in local sales tax rates. Without a > mainframe compiler even a trivial change becomes a difficult load module > patch. > > -- > Joel C. Ewing,Bentonville, AR jcew...@acm.org > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- Mike A Schwab, Springfield IL USA Where do Forest Rangers go to get away from it all? -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: CeBIT and mainframes
On 18 Mar 2016 07:27:09 -0700, in bit.listserv.ibm-main Itschak wrote: >no recompile involved. Just relink to replace IBM's LE modules. So what processor(s) is this code running on? What exactly is being done? Clark Morris > >Itschak > > > >On Fri, Mar 18, 2016 at 12:01 PM, Mark Reganwrote: > >> There is a ComputerWeekly article on this product at >> >> http://www.computerweekly.com/blogs/quocirca-insights/2016/03/the-software-defined-mainframe.html >> . >> I noticed that the article author needs to know how to spell the acronym >> for EBCDIC correctly. He spells it 'EBSDIC' and did it twice. >> >> >> On Fri, Mar 18, 2016 at 4:04 AM Elardus Engelbrecht < >> elardus.engelbre...@sita.co.za> wrote: >> >> > Joel C. Ewing wrote: >> > >> > >I notice they also claim "no need for recompilation of Cobol or PL/1 >> > application programmes, no source code changes, or changes to operational >> > procedures". >> > >> > I am really struggling to swallow that claim... >> > >> > and Dave_Craig wrote: >> > >> > >Queue the IP lawyers, and action! >> > >> > This is why I said this is 'interesting development'. I am very sure big >> > blue and their lawyers won't like that one bit unless there is an >> agreement. >> > >> > > I'll be slow to migrate off that proven decades-old mission-critical >> > platform, that's for sure. >> > >> > I will also be slow to get off the mainframes. >> > >> > Joel C. Ewing wrote: >> > >> > >Color me skeptical. >> > >> > With all the colors of the rainbow! ;-) >> > >> > Groete / Greetings >> > Elardus Engelbrecht >> > >> > -- >> > For IBM-MAIN subscribe / signoff / archive access instructions, >> > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN >> > >> >> -- >> For IBM-MAIN subscribe / signoff / archive access instructions, >> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN >> > >-- >For IBM-MAIN subscribe / signoff / archive access instructions, >send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN