Ok, I know I have to preface this with I work for IBM. So know that all disclaimers are out lets start. If they do come out with 2.5TB HDDs, and you put that drive into a RAID array, say a drive fails. Sure, you're protected against this with RAID protection right? Ok, so you have a hotspare drive of the same size, do you know how long it takes to rebuild a drive of say 500GB in a RAID 5 array? Just to simplify it, it's so long, your starting to see disk manufacturers implement dual parity array's. This is directly because the drive rebuild times are getting so large you run a much higher risk in having a second drive in the array go out before the rebuild is complete. Another bad thing about extremely dense drives, performance. Can you imagine the random seek time on a drive of this capacity? What's the top spindle speed in the market today, 15krpm. And mind you on the 500GB SATA 2 drives you're still only getting 7.2krpm. This will kill performance until we find a much quicker way to access the data on the HDD's. So, what do you use these large capacity drives for? Primarily large sequential I/O's. What does (LTO) tape perform best at, large sequential I/O's. Also, what is the life span of a disk drive? I'll tell you, it's much less than a tape cartridge. So all these federal compliance regulations that state a company must keep data for x ammount of time (3 yrs, 7 yrs, 30 yrs...) disk just doesn't make sense. From IBM's side, sure, I would love for you to use disk for everything, it's more expensive, you have to buy more of it, and 3-5 years from now, you'll have to replace it. LTO has a standard that n-1 generation carts must be able to be read and written by the current version drives, and n-2 must be able to be read by the current drives.
Now will your small shops be interested in this, no, but if you're a large company that has data retention policies, then tape just makes good sense.
Again, I'm an IBM employee so you can take this as you will, but I just want you to know tape has been and will be around for a long time.
I know I may be docked for being slightly off point, but I have to ask.
After being on/. for some time now, I've noticed that many people have issues with IBM as a company. Be it a (insert vendor name here) bigot or just someone who happend to not like IBM as a vendor, the majority of the posts I have read show a strong dislike for IBM. I find it interesting the ThinkPad's have (had?) such a strong following and the same people who bash IBM for their servers/software/storage at the enterprise level seem to just love the Laptops and desktops they made. Is this the case in the/. community? Do we only love IBM for their PC business and not for everything else they do?
After reading through many of the posts, I find it alarming that people are focusing on external factors. Try looking inward. Are you truly happy doing the work you're doing?
I realize that many of the external factors contribute to how you feel about your job, but everyone has a different definition of happiness. Some people want more money, some want a quite workplace, some want free pens, some just want a place to go and earn a living that can pay their bills and allow them to not be bothered.
Get a grip on what YOU want. If some of the things in your company is not jiving with your personal needs, but the majority of it is, it may not be the right time to jump ship. Some people really enjoy working 14-16 hours a day because their job is the only time they get human interaction. If this makes you happy, then great! No one can tell you to leave your job (except your boss and perhaps security).
I'm also a big advocate of keeping your resume up to date and posted on job websites. Even though you are happy where you are, you need to keep your options open and your interview skills up to snuff.
The point is, look to what you want to do with your life and career, instead of looking for a list of reasons to leave a job.
If only more people would listen to you, the job market would be much better. As well as the existing employees getting better pay raises.
I'm 3 days away from leaving my first job and taking one with(you guessed it) IBM.
The problem started when I stopped and noticed my co-workers, most of them had been with the company for less than I had (under 2 years), were being treated like crap, and the turnover rate was astonishing. My company absolutly refused to hire anyone in with experience and ended up overworking any experienced employee.
So by looking for a new job, and getting a 40% pay increase without having to move, that was huge. And in these last 2 weeks I've been at work, 3 experienced employees have left the company as well to work for a direct competitor and half of my teammates came to me and confessed they were looking as well.
The individuals need to stop thinking "I'm lucky to have a job" and start thinking "what am I really worth" and get what you're worth. If the employees started to do this, corporations would realize the value a trained and loyal employee is worth and stop putting limits on their raises.
I thought you would be very interested in this. IBM just announced the IVM. It allows you to partition a single server without the need of an HMC. That functionallity has been moved internal to the system. Check out the latest announcement.
I agree. The HMC is definitely a bad part of the LPAR management. It will be interesting if IBM addresses this with the new POWER5+ launch slated for the next few weeks.
But the HMC does provide a very good way of supporting multiple systems from one console. I'm not sure if you're working with p4 or p5 architecture, but on the p5 they've moved it from a serial network to an IP network for managing the servers. Much better to have one CAT 5 cable out of that HMC than to have a few RAN's hanging off the HMC attached to servers directly.
The thing I like the most about the HMC is the firmware updates for the managed systems. Makes it very easy to do from one console.
I agree to a point. Some situations it makes more sense to fill up a rack with 1U 2way intel servers and run windows or linux as an OS. However, if some of the servers are running at 10-20% processor utilization and others are getting maxed out on processor utilization, how long does it take to redistribute your processing resouces? With virtualization, provided you have the processors assigned to a pool, the system automatically will move processing power from one LPAR that is not maxed on processor resources to an LPAR with high utilization. This happens every clock cycle. And if you run into a situation where this is happening often, you can go ahead and move over as small as a.01 of a processor from one LPAR to another. This grainularity can greatly increase your processor utlization.
Lets extend this to I/O resources. If you have a system that has a high I/O through put on the LAN and another system that has very low throughput, there isn't a way to balance that load is there? With a VIOS you can have as few as one ethernet adapter provide LAN connections for 100's of client partitions. Yes, this can put an increadible ammount of load on that one adapter, but if you have say 10 Gb LAN adapters assigned to the VIOS, you can aggregate them into one pipe, and carve that logical enet adapter into 100's of Shared Ethernet adapters across 20 VLAN's for the client partitions. This can get you to the point where your I/O bandwidth is spread across multiple LPAR's all while maintaining secure networks for each partition.
Well, the interesting thing is, with the i5 boxes, they dumped the manditory host partition for linux or AIX partitions. On the p5 systems, you can still have dedicated resource partitions (own disk adapters and such), but they also have the option of running a host partition for shared resources like ethernet or disk. It's called the VIOS. It's basically a skinnied down version of AIX and all it does is manage the physical resources that are being virtualized to the client partitions.
If the linux kernel used is v2.6, you'll probably be ok. However, IBM won't help you out if it doesn't work. From what I understand, it has to be SLES 9 or RHEL 4.
While AIX isn't "free" (you're charged per active processor), almost all pSeries (soon to be IBM system p5) have AIX included with the system purchase. This does increase the value of using AIX in micropartitions instead of linux.
I wouldn't say POWER is the way everyone is going. I would instead say "virtualization" is the way everyone is going. While POWER architecture and IBM has a big lead in this, Microsoft, HP-UX, Sun Solaris, Intel, and AMD are making headway. With the success of VMWare, hardware and OS vendors are looking for ways to capitolize on this trend of system utilization.
POWER 4 systems and AIX 5.1 was the first LPAR capable systems. Even 5.1 didn't support DLPAR operations. Anytime you wanted to rearrange your resources, you had to bounce the partitions affected. AIX 5.2 was the first OS to support DLPAR operations. Linux just started to support this with the 2.6 kernel as well.
That's exactly what the Virtual I/O Server is. You can get it with any p5 system that has APV (Advanced Power Virtualization). However, it's a skinnied down version of AIX instead of Linux.
The VIOS acts as a broker of disk and communication resources. You can have one ethernet adapter assigned to a VIOS and create upto 20 virtual LAN's and basically an unlimited number of SEA's (Shared Ethernet Adapters) for client partitions.
As for disk, you can have one SCSI controller and create vSCSI adapters on the client partitions so the clients can utilize the same SCSI controller as other partitions. You can break it down to the device level (each pysical disk) or to the lv level (a section of a volume group).
For those of you who think this is just an IBM thing, I hear Intel is planning to support virtualization shortly as well for Windows systems. AMD is also on the bandwagon. Not to mention that HP has vPAR's and nPAR's and Sun is working at it a different way with containers.
Bottom line is virtualization is getting huge fast. It's been proven to decrease cost and increase system utilization and availability.
This document just touches on the capabilities. If you want to see a little bit more detail regarding running linux LPAR's on a POWER 5 system, I suggest heading here.
This is a good technology, and if there are people wanting to get LPAR capabilities without having to purchase all that extra IBM OS's (AIX, i5/OS), you might look into the OpenPower line. 2 way or 4 way POWER 5 systems that run only linux and can create upto 40 LPAR's on one system. That's bascially like having 40 different Linux servers all running at the same time on 4 total processors.
I agree this technology has some limitations as of right now, but it may not be a bad idea to look at it. And remember, this is PPC Linux, not your standard Intel Linux. While your boss won't know the difference, you should.
Don't forget about the IBM DB2 Content Management portfolio. It provides a lot of features from access restriction, peer approval, and a nice easy to program interface (document manager). And with all the government regulations popping up, a company may need to make certain documents a part of the company records, which can then not be altered.
There are several comparable products that are less expensive as well, like FileNet that can do similar type of functions.
My bother attended Indiana State University for undergrad in Physics (full ride). Afterwards he was accepted to Boston College in their Physics masters program (again, full ride). Immediately after graduating, he started pursuing his PhD in Physics at University of South Carolina (and again, full ride). He has recently transferred to Iowa State Univeristy to finish his PhD (you guessed it, full ride).
When it comes down to it, he will have a PhD in Physics for no tuition or housing out of pocket. He is very intelligent, but didn't earn the best grades in High School. He worked his butt of pursuing his desires. There are plenty of schools dying for good talent and willing to pay for it.
Fortunately, I decided to go to Indiana State and pursue a Computer Science degree. The education fallout in that area is actually helping me in my career. Companys veiw a degree as a degree, and that's the truth. Of course you may have the individual HR person who had a bad experience with someone from a specific school's program, but that is easily overcome in the interview.
Bottom line is, from my experience, it doesn't matter where you go to school. It's how you use that education to your advantage that makes all the difference.
Ok, so an 8 core processor to function at the level of a 4 way xeon processor. Hmmm, I'm sure Oracle users will be sure to run their apps on this architecture!
So, instead of paying $80k in licensing, they can pay $160k! (at about $20k per core for Enterprise Oracle DB).
With most enterprise level apps going to a per core licensing structure (and if per user, they usually limit that to 4 cores to a system), I don't see the benefit in having a really powerful and possibly expensive http server.
I've know more managers that are distracted by shiny things than geeks. But most of the time, those shiny things are coins in their pockets rather than the good of the business...
A manager is responsible for coordinating people and processes. While it would help for the manager to have some knowledge of the work the people he/she manages does on a day to day basis, it is more important that the manager understands the needs of the team. A good manager should be able to identify individuals who consistantly out perform their peers. They could be someone who cooks french fries to just the right crispness, or a programmer who always comes through in a crunch.
So, in my opinion it isn't as important that they understand the technology, but that they understand the business and people involved.
More information would be great! What applications are you running? What hardware is running it? How much do you spend yearly in maintenance costs? What is your storage architecture like? How many employees does your IT staff support? What product or service does your company provide?
These are all very important questions. You may be running on old hardware that requires 8 processor cores to run Oracle 9.2 database. If you upgrade to newer hardware, you could probably cut the processors need in half or more to do the same job. If you use multiple different storage products, this can really eat up time in systems management. If you go to a centralized storage pool and allocate resources off that pool, you may be able to cut Management costs in half. Depending upon the industry you're in, their may also be industry specific solutions that a tailor made to your needs.
This vague question can not be answered in a chat room. Contact a IT infrastructure architect in your area to do an evaluation of your IT infrastructure. Often times this service is free. They will be able to point out inefficiencies in your IT dept, provide solutions to your problems, and do a cost/benefit annalysis to get an idea as to your ROI.
Yes I understand people will disagree, however the whole idea of copyrighting is getting rediculous in my opinion.
Do While (copyright_laws != knowledge_exchange){
distance_to_utopian_society-- }
Slashdot Mirror
Ok, I know I have to preface this with I work for IBM. So know that all disclaimers are out lets start. If they do come out with 2.5TB HDDs, and you put that drive into a RAID array, say a drive fails. Sure, you're protected against this with RAID protection right? Ok, so you have a hotspare drive of the same size, do you know how long it takes to rebuild a drive of say 500GB in a RAID 5 array? Just to simplify it, it's so long, your starting to see disk manufacturers implement dual parity array's. This is directly because the drive rebuild times are getting so large you run a much higher risk in having a second drive in the array go out before the rebuild is complete. Another bad thing about extremely dense drives, performance. Can you imagine the random seek time on a drive of this capacity? What's the top spindle speed in the market today, 15krpm. And mind you on the 500GB SATA 2 drives you're still only getting 7.2krpm. This will kill performance until we find a much quicker way to access the data on the HDD's. So, what do you use these large capacity drives for? Primarily large sequential I/O's. What does (LTO) tape perform best at, large sequential I/O's. Also, what is the life span of a disk drive? I'll tell you, it's much less than a tape cartridge. So all these federal compliance regulations that state a company must keep data for x ammount of time (3 yrs, 7 yrs, 30 yrs...) disk just doesn't make sense. From IBM's side, sure, I would love for you to use disk for everything, it's more expensive, you have to buy more of it, and 3-5 years from now, you'll have to replace it. LTO has a standard that n-1 generation carts must be able to be read and written by the current version drives, and n-2 must be able to be read by the current drives.
Now will your small shops be interested in this, no, but if you're a large company that has data retention policies, then tape just makes good sense.
Again, I'm an IBM employee so you can take this as you will, but I just want you to know tape has been and will be around for a long time.
I know I may be docked for being slightly off point, but I have to ask.
/. for some time now, I've noticed that many people have issues with IBM as a company. Be it a (insert vendor name here) bigot or just someone who happend to not like IBM as a vendor, the majority of the posts I have read show a strong dislike for IBM. I find it interesting the ThinkPad's have (had?) such a strong following and the same people who bash IBM for their servers/software/storage at the enterprise level seem to just love the Laptops and desktops they made. Is this the case in the /. community? Do we only love IBM for their PC business and not for everything else they do?
After being on
After reading through many of the posts, I find it alarming that people are focusing on external factors. Try looking inward. Are you truly happy doing the work you're doing?
I realize that many of the external factors contribute to how you feel about your job, but everyone has a different definition of happiness. Some people want more money, some want a quite workplace, some want free pens, some just want a place to go and earn a living that can pay their bills and allow them to not be bothered.
Get a grip on what YOU want. If some of the things in your company is not jiving with your personal needs, but the majority of it is, it may not be the right time to jump ship. Some people really enjoy working 14-16 hours a day because their job is the only time they get human interaction. If this makes you happy, then great! No one can tell you to leave your job (except your boss and perhaps security).
I'm also a big advocate of keeping your resume up to date and posted on job websites. Even though you are happy where you are, you need to keep your options open and your interview skills up to snuff.
The point is, look to what you want to do with your life and career, instead of looking for a list of reasons to leave a job.
If only more people would listen to you, the job market would be much better. As well as the existing employees getting better pay raises.
I'm 3 days away from leaving my first job and taking one with(you guessed it) IBM.
The problem started when I stopped and noticed my co-workers, most of them had been with the company for less than I had (under 2 years), were being treated like crap, and the turnover rate was astonishing. My company absolutly refused to hire anyone in with experience and ended up overworking any experienced employee.
So by looking for a new job, and getting a 40% pay increase without having to move, that was huge. And in these last 2 weeks I've been at work, 3 experienced employees have left the company as well to work for a direct competitor and half of my teammates came to me and confessed they were looking as well.
The individuals need to stop thinking "I'm lucky to have a job" and start thinking "what am I really worth" and get what you're worth.
If the employees started to do this, corporations would realize the value a trained and loyal employee is worth and stop putting limits on their raises.
bigredradio,
I thought you would be very interested in this. IBM just announced the IVM. It allows you to partition a single server without the need of an HMC. That functionallity has been moved internal to the system. Check out the latest announcement.
I agree. The HMC is definitely a bad part of the LPAR management. It will be interesting if IBM addresses this with the new POWER5+ launch slated for the next few weeks.
But the HMC does provide a very good way of supporting multiple systems from one console. I'm not sure if you're working with p4 or p5 architecture, but on the p5 they've moved it from a serial network to an IP network for managing the servers. Much better to have one CAT 5 cable out of that HMC than to have a few RAN's hanging off the HMC attached to servers directly.
The thing I like the most about the HMC is the firmware updates for the managed systems. Makes it very easy to do from one console.
I agree to a point. Some situations it makes more sense to fill up a rack with 1U 2way intel servers and run windows or linux as an OS. However, if some of the servers are running at 10-20% processor utilization and others are getting maxed out on processor utilization, how long does it take to redistribute your processing resouces? With virtualization, provided you have the processors assigned to a pool, the system automatically will move processing power from one LPAR that is not maxed on processor resources to an LPAR with high utilization. This happens every clock cycle. And if you run into a situation where this is happening often, you can go ahead and move over as small as a .01 of a processor from one LPAR to another. This grainularity can greatly increase your processor utlization.
Lets extend this to I/O resources. If you have a system that has a high I/O through put on the LAN and another system that has very low throughput, there isn't a way to balance that load is there? With a VIOS you can have as few as one ethernet adapter provide LAN connections for 100's of client partitions. Yes, this can put an increadible ammount of load on that one adapter, but if you have say 10 Gb LAN adapters assigned to the VIOS, you can aggregate them into one pipe, and carve that logical enet adapter into 100's of Shared Ethernet adapters across 20 VLAN's for the client partitions. This can get you to the point where your I/O bandwidth is spread across multiple LPAR's all while maintaining secure networks for each partition.
Well, the interesting thing is, with the i5 boxes, they dumped the manditory host partition for linux or AIX partitions. On the p5 systems, you can still have dedicated resource partitions (own disk adapters and such), but they also have the option of running a host partition for shared resources like ethernet or disk. It's called the VIOS. It's basically a skinnied down version of AIX and all it does is manage the physical resources that are being virtualized to the client partitions.
If the linux kernel used is v2.6, you'll probably be ok. However, IBM won't help you out if it doesn't work. From what I understand, it has to be SLES 9 or RHEL 4.
While AIX isn't "free" (you're charged per active processor), almost all pSeries (soon to be IBM system p5) have AIX included with the system purchase. This does increase the value of using AIX in micropartitions instead of linux.
I wouldn't say POWER is the way everyone is going. I would instead say "virtualization" is the way everyone is going. While POWER architecture and IBM has a big lead in this, Microsoft, HP-UX, Sun Solaris, Intel, and AMD are making headway. With the success of VMWare, hardware and OS vendors are looking for ways to capitolize on this trend of system utilization.
POWER 4 systems and AIX 5.1 was the first LPAR capable systems. Even 5.1 didn't support DLPAR operations. Anytime you wanted to rearrange your resources, you had to bounce the partitions affected. AIX 5.2 was the first OS to support DLPAR operations. Linux just started to support this with the 2.6 kernel as well.
That's exactly what the Virtual I/O Server is. You can get it with any p5 system that has APV (Advanced Power Virtualization). However, it's a skinnied down version of AIX instead of Linux.
The VIOS acts as a broker of disk and communication resources. You can have one ethernet adapter assigned to a VIOS and create upto 20 virtual LAN's and basically an unlimited number of SEA's (Shared Ethernet Adapters) for client partitions.
As for disk, you can have one SCSI controller and create vSCSI adapters on the client partitions so the clients can utilize the same SCSI controller as other partitions. You can break it down to the device level (each pysical disk) or to the lv level (a section of a volume group).
For those of you who think this is just an IBM thing, I hear Intel is planning to support virtualization shortly as well for Windows systems. AMD is also on the bandwagon. Not to mention that HP has vPAR's and nPAR's and Sun is working at it a different way with containers.
Bottom line is virtualization is getting huge fast. It's been proven to decrease cost and increase system utilization and availability.
This document just touches on the capabilities. If you want to see a little bit more detail regarding running linux LPAR's on a POWER 5 system, I suggest heading here.
This is a good technology, and if there are people wanting to get LPAR capabilities without having to purchase all that extra IBM OS's (AIX, i5/OS), you might look into the OpenPower line. 2 way or 4 way POWER 5 systems that run only linux and can create upto 40 LPAR's on one system. That's bascially like having 40 different Linux servers all running at the same time on 4 total processors.
I agree this technology has some limitations as of right now, but it may not be a bad idea to look at it. And remember, this is PPC Linux, not your standard Intel Linux. While your boss won't know the difference, you should.
Don't forget about the IBM DB2 Content Management portfolio. It provides a lot of features from access restriction, peer approval, and a nice easy to program interface (document manager). And with all the government regulations popping up, a company may need to make certain documents a part of the company records, which can then not be altered.
There are several comparable products that are less expensive as well, like FileNet that can do similar type of functions.
vi In Soviet Russia
/have
:wq!
cw had
Agreed.
My bother attended Indiana State University for undergrad in Physics (full ride). Afterwards he was accepted to Boston College in their Physics masters program (again, full ride). Immediately after graduating, he started pursuing his PhD in Physics at University of South Carolina (and again, full ride). He has recently transferred to Iowa State Univeristy to finish his PhD (you guessed it, full ride).
When it comes down to it, he will have a PhD in Physics for no tuition or housing out of pocket. He is very intelligent, but didn't earn the best grades in High School. He worked his butt of pursuing his desires. There are plenty of schools dying for good talent and willing to pay for it.
Fortunately, I decided to go to Indiana State and pursue a Computer Science degree. The education fallout in that area is actually helping me in my career. Companys veiw a degree as a degree, and that's the truth. Of course you may have the individual HR person who had a bad experience with someone from a specific school's program, but that is easily overcome in the interview.
Bottom line is, from my experience, it doesn't matter where you go to school. It's how you use that education to your advantage that makes all the difference.
Ok, so an 8 core processor to function at the level of a 4 way xeon processor. Hmmm, I'm sure Oracle users will be sure to run their apps on this architecture!
So, instead of paying $80k in licensing, they can pay $160k! (at about $20k per core for Enterprise Oracle DB).
With most enterprise level apps going to a per core licensing structure (and if per user, they usually limit that to 4 cores to a system), I don't see the benefit in having a really powerful and possibly expensive http server.
Well, I think you're right.
Looking at the definition of "Human" and "Neanderthal" on http://www.dictionary.com/ they would be considered "human."
I say, write your right winged representative today to start a war about it!
Is everyone overlooking the obvious underlying opjective of this project?
Create a new German Army made up of very strong, sturdy, and stupid soldiers to take over the world.
I think I saw this on a "Pinky and the Brain" episode...
I've know more managers that are distracted by shiny things than geeks. But most of the time, those shiny things are coins in their pockets rather than the good of the business...
A manager is responsible for coordinating people and processes. While it would help for the manager to have some knowledge of the work the people he/she manages does on a day to day basis, it is more important that the manager understands the needs of the team. A good manager should be able to identify individuals who consistantly out perform their peers. They could be someone who cooks french fries to just the right crispness, or a programmer who always comes through in a crunch.
So, in my opinion it isn't as important that they understand the technology, but that they understand the business and people involved.
Ok,
More information would be great! What applications are you running? What hardware is running it? How much do you spend yearly in maintenance costs? What is your storage architecture like? How many employees does your IT staff support? What product or service does your company provide?
These are all very important questions. You may be running on old hardware that requires 8 processor cores to run Oracle 9.2 database. If you upgrade to newer hardware, you could probably cut the processors need in half or more to do the same job. If you use multiple different storage products, this can really eat up time in systems management. If you go to a centralized storage pool and allocate resources off that pool, you may be able to cut Management costs in half. Depending upon the industry you're in, their may also be industry specific solutions that a tailor made to your needs.
This vague question can not be answered in a chat room. Contact a IT infrastructure architect in your area to do an evaluation of your IT infrastructure. Often times this service is free. They will be able to point out inefficiencies in your IT dept, provide solutions to your problems, and do a cost/benefit annalysis to get an idea as to your ROI.
Of course, you could always go to http://www.monster.com/ and get a new job.
I thought we were computer nerds...not art * (insert favorite artist slang term here).
Yes I understand people will disagree, however the whole idea of copyrighting is getting rediculous in my opinion.
Do While (copyright_laws != knowledge_exchange){
distance_to_utopian_society--
}