Qt is okay for networking applications, but in my experience Boost has much, much better performance, not to mention better support for things like multicast without creating some hacks. Qt ends up using a lot of Qt specific classes internally to create buffers and network functions, so it ends up being slower than Boost which seems to act more as a wrapper than anything.
This is an electron scanning microscope, not a toaster. Why would you use some proprietary OS on an embedded system? Even a lot of new oscilloscopes are running Windows now and work quite well. Good luck getting all your proprietary commercial scientific libraries to compile on some random dedicated operating system in flash memory.
I get pretty upset at work when people save freaking.BMP files onto FLOPPY disks from oscilloscopes. Two formats that should be dead dead dead by now. PNG please!
I agree. When I build a new system I first: memtest86+ cpu test with something like prime95 CPU+GPU test with prime95 and then another 3D game running in the background.
If it survives that last test, then it's good. I've found overheating of my system to be the main cause of crashes. I've actually had to underclock my RAM to get it stable. If something does fail, I swap that component or add more fans and try again.
Windows 7 it's even easier than that. You just click and drag the title bar towards the top of the screen you want it to maximize too. Or, you can click the maximize button, to maximize it to the monitor the window is currently on. This is coming from someone who uses 3 monitors.
That funny you mention that game, because it included an extra RAM module to upgrade the graphics quality. How many console games force you to install RAM before you play?
I'm having a hard time finding any new phones that support tethering. It's like they want the fact that the feature even existed to slowly disappear. It's one of the only reasons I stay with T-Mobile having their super cheap $20/month internet plan.
I using tethering on my T-Mobile Wing when I need it. It's not very fast, in the bay area I at least get Edge speeds, but things like Youtube video and large downloads usually end up timing out.
I like the tethering option because it's unlimited internet on my phone and my laptop ($20/month). If I was with any other carrier, it would be a separate $60/month plan (yikes). And for occasional use, I don't need the speed.
My guess is that G3 networks are really not ready yet for the kind of use that laptop users want.
RAID0 with MLC is nice. 0.1ms access time and 300Mbyte/sec read/write throughput. It's the access time I think you would worry about with compilers and lots of random reads.
The benchmarks I've seen on 1TB drives show about 80MB/sec average, and it goes from 60MB to 100MB/sec depending on the location of the read on the drive, SSD's don't have this non-linearity. Also, the 350MB/sec is reaching the limitations of the RAID controller, a single drive is about 150MB/sec, so it starts scaling down a little when you add more. I will probably try a PCI express adapter that has more bandwidth in the future.
Still, the main speed boost is in the latency. 0.2ms vs 8ms is a huge leap. Also, I like my system as silent as possible, so I'm willing to pay a premium for that.
I save additional files on an external 1TB drive when needed.
As far as price, if you avoid the big name brand Samsung and Intel parts, you can get fairly good prices.
Okay, I just ran this benchmark on my 3 RAID0 SSD array....
From 0.5KB to 128KB write performance (in KB/sec) 3928 7368 12579 19931 48306 83492 143772 233510 252352
The reason for the low performance on small block sizes is the option called "Direct I/O" on ATTO Disk Benchmark. What this probably does is turns of your system's caching capability, so of course you are going to get ridiculously slow rates. It's good for comparison, but to say you're system is going to be slow because of it is ridiculous because in the real world your OS will cache everything. If you look around, you'll see that 7200 RPM HD also do bad on these write benchmarks. Maybe better on read, because HD have a RAM buffer, but that shouldn't matter in real world if you're using the OS's cache.
And ATTO tech is more interested in selling disk controllers anyway, so really this is more of a disk controller benchmark, not real world HD performance usage.
It would be the equivalent of turning L2 cache off on your CPU and publishing those benchmarks as real world performance.
I think a more accurate benchmark would be some type of MySQL database test.
I believe there is so much misconception out there about flash memory performance, it's astonishing. There just isn't a good understanding of how all the layers of cache in the OS work.
SSD's are not slow, do not "die young". I just built a new system with 3 SSD's in RAID0 and I'm getting 350MB/sec sequential read performance, and nearly 250MB/sec sequential write. In fact, I'm less worried adding additional drives in RAID0, because they fail by total wear, not a single point of a failure, and if the wear is being spread out, it should be less of a concern. I have not done benchmarks on random write performance yet, but I'm guessing it will not be that bad.
100% of the problems now are related to some of the controllers and how the OS caches data before writes. For example, why would you write thousands of small 1k blocks, and not cache those in memory first if the write is going to occur a second later? In fact, most OS's will intelligently do this.
So here's the real problem, a bunch of the early SSD's that came out were incredibly cheap and used really really bad controllers. Most of the new new SSD's now have moved beyond these deficiencies. Because of the past products though, it's creating a huge confusion in the market and people just don't "trust" these new products.
Natural rubber might be a bad choice. It tends to harden and get brittle with age and heat. I think some rubber washers, like I've seen in some cases, would work better.
Can anyone explain why Canadian data is so expensive? is there like a magic gnome sitting on the border the U.S. directing interwebs traffic through the fiber and demanding a high toll fee? Does it cost anymore to lay fiber from Montana to British Columbia than it would from California to New York?
Seriously, charging international roaming in most cases is just an excuse to charge you more with surprise bills.
And why shouldn't they be forced to inform you? Technologically, it's simple and feasible. The only reason they don't is because they wouldn't make as much as a profit that way if they actually informed you of the cost of their service. Bait and switch...
And how many users will write over 320 terrabytes to their hard drive during it's lifetime? That's 190 days of continuous writing at 20MByte/sec. I wish people would stop citing write cycle limits, I have yet to hear from anyone who's actually failed a drive this way.
It's called... wear leveling algorithms.
The future is actually probably going to be a hybrid of SLC and MLC. I read a paper recently on this. They got about the same performance as SLC only, using only a small amount of SLC.
Good question. Nintendo is losing quite a bit of money by not raising the price of the Wii to match market demand. I think in the U.S. people are too used to seeing the price of electronics fall yearly, but with our rapid inflation rate, that's not going to happen anymore.
Nintendo should just go ahead and silently raise the price a little. Sure, there will be some anger but I don't think it would hurt their brand very much. They could always just say "because of the weakening U.S. dollar..." and I think people would get the point. Heck, even U.S. companies are doing that now.
Wow, can we get this guy to decode some of the Bluray keys used? Break HDCP? His method is pretty straight forward, easy to follow, and looks fool proof. Expose layers in the chip and read the data directly. I don't see how manufactures can stop this. As long as the key is physically somewhere in the hardware, it should be possible to access it. I guess the reason this isn't done more often is because of the expense of the high powered microscope, toxic chemicals, and fume hood.
And why would you need a floppy drive in the year 2008? Looking at the pictures, it looks like that would consume over 50% of it's volume. I would be surprised if it even had a DVD-ROM drive.
Slashdot Mirror
Qt is okay for networking applications, but in my experience Boost has much, much better performance, not to mention better support for things like multicast without creating some hacks. Qt ends up using a lot of Qt specific classes internally to create buffers and network functions, so it ends up being slower than Boost which seems to act more as a wrapper than anything.
This is an electron scanning microscope, not a toaster. Why would you use some proprietary OS on an embedded system? Even a lot of new oscilloscopes are running Windows now and work quite well. Good luck getting all your proprietary commercial scientific libraries to compile on some random dedicated operating system in flash memory.
I get pretty upset at work when people save freaking .BMP files onto FLOPPY disks from oscilloscopes. Two formats that should be dead dead dead by now. PNG please!
I agree. When I build a new system I first:
memtest86+
cpu test with something like prime95
CPU+GPU test with prime95 and then another 3D game running in the background.
If it survives that last test, then it's good. I've found overheating of my system to be the main cause of crashes. I've actually had to underclock my RAM to get it stable. If something does fail, I swap that component or add more fans and try again.
Applications limited to 2GB of RAM forever? No thanks.
How many people write drivers? And will this actually hurt hobbyists who want to write their own?
Windows 7 it's even easier than that. You just click and drag the title bar towards the top of the screen you want it to maximize too. Or, you can click the maximize button, to maximize it to the monitor the window is currently on. This is coming from someone who uses 3 monitors.
My point was, even back then there was a push to improve graphics quality. I don't see why that shouldn't change now.
Would a company that big actually insure against theft loss from a single store? I would think it would be cheaper for them to insure themselves.
That funny you mention that game, because it included an extra RAM module to upgrade the graphics quality. How many console games force you to install RAM before you play?
I'm having a hard time finding any new phones that support tethering. It's like they want the fact that the feature even existed to slowly disappear. It's one of the only reasons I stay with T-Mobile having their super cheap $20/month internet plan.
I using tethering on my T-Mobile Wing when I need it. It's not very fast, in the bay area I at least get Edge speeds, but things like Youtube video and large downloads usually end up timing out.
I like the tethering option because it's unlimited internet on my phone and my laptop ($20/month). If I was with any other carrier, it would be a separate $60/month plan (yikes). And for occasional use, I don't need the speed.
My guess is that G3 networks are really not ready yet for the kind of use that laptop users want.
RAID0 with MLC is nice. 0.1ms access time and 300Mbyte/sec read/write throughput. It's the access time I think you would worry about with compilers and lots of random reads.
The OS would not be responsible for re-issuing the write. The wear leveling of the SSD should do this automatically and mark the sector as bad.
What should happen is a SMART status update telling the host OS that the drive is running out of writable sectors due to a high % of bad sectors.
The benchmarks I've seen on 1TB drives show about 80MB/sec average, and it goes from 60MB to 100MB/sec depending on the location of the read on the drive, SSD's don't have this non-linearity. Also, the 350MB/sec is reaching the limitations of the RAID controller, a single drive is about 150MB/sec, so it starts scaling down a little when you add more. I will probably try a PCI express adapter that has more bandwidth in the future.
Still, the main speed boost is in the latency. 0.2ms vs 8ms is a huge leap. Also, I like my system as silent as possible, so I'm willing to pay a premium for that.
I save additional files on an external 1TB drive when needed.
As far as price, if you avoid the big name brand Samsung and Intel parts, you can get fairly good prices.
Okay, I just ran this benchmark on my 3 RAID0 SSD array....
From 0.5KB to 128KB write performance (in KB/sec)
3928
7368
12579
19931
48306
83492
143772
233510
252352
The reason for the low performance on small block sizes is the option called "Direct I/O" on ATTO Disk Benchmark. What this probably does is turns of your system's caching capability, so of course you are going to get ridiculously slow rates. It's good for comparison, but to say you're system is going to be slow because of it is ridiculous because in the real world your OS will cache everything. If you look around, you'll see that 7200 RPM HD also do bad on these write benchmarks. Maybe better on read, because HD have a RAM buffer, but that shouldn't matter in real world if you're using the OS's cache.
And ATTO tech is more interested in selling disk controllers anyway, so really this is more of a disk controller benchmark, not real world HD performance usage.
It would be the equivalent of turning L2 cache off on your CPU and publishing those benchmarks as real world performance.
I think a more accurate benchmark would be some type of MySQL database test.
I believe there is so much misconception out there about flash memory performance, it's astonishing. There just isn't a good understanding of how all the layers of cache in the OS work.
SSD's are not slow, do not "die young". I just built a new system with 3 SSD's in RAID0 and I'm getting 350MB/sec sequential read performance, and nearly 250MB/sec sequential write. In fact, I'm less worried adding additional drives in RAID0, because they fail by total wear, not a single point of a failure, and if the wear is being spread out, it should be less of a concern. I have not done benchmarks on random write performance yet, but I'm guessing it will not be that bad.
100% of the problems now are related to some of the controllers and how the OS caches data before writes. For example, why would you write thousands of small 1k blocks, and not cache those in memory first if the write is going to occur a second later? In fact, most OS's will intelligently do this.
So here's the real problem, a bunch of the early SSD's that came out were incredibly cheap and used really really bad controllers. Most of the new new SSD's now have moved beyond these deficiencies. Because of the past products though, it's creating a huge confusion in the market and people just don't "trust" these new products.
Except the fonts are still unreadable, even 13 years later, unlike windows. In fact, this problem still exists on most distros I've tried.
Natural rubber might be a bad choice. It tends to harden and get brittle with age and heat. I think some rubber washers, like I've seen in some cases, would work better.
Did you try once every second too see what would happen? Maybe you could have single handendly bankrupted AT&T. :)
Can anyone explain why Canadian data is so expensive? is there like a magic gnome sitting on the border the U.S. directing interwebs traffic through the fiber and demanding a high toll fee? Does it cost anymore to lay fiber from Montana to British Columbia than it would from California to New York?
Seriously, charging international roaming in most cases is just an excuse to charge you more with surprise bills.
And why shouldn't they be forced to inform you? Technologically, it's simple and feasible. The only reason they don't is because they wouldn't make as much as a profit that way if they actually informed you of the cost of their service. Bait and switch...
And how many users will write over 320 terrabytes to their hard drive during it's lifetime? That's 190 days of continuous writing at 20MByte/sec. I wish people would stop citing write cycle limits, I have yet to hear from anyone who's actually failed a drive this way.
It's called... wear leveling algorithms.
The future is actually probably going to be a hybrid of SLC and MLC. I read a paper recently on this. They got about the same performance as SLC only, using only a small amount of SLC.
Good question. Nintendo is losing quite a bit of money by not raising the price of the Wii to match market demand. I think in the U.S. people are too used to seeing the price of electronics fall yearly, but with our rapid inflation rate, that's not going to happen anymore.
Nintendo should just go ahead and silently raise the price a little. Sure, there will be some anger but I don't think it would hurt their brand very much. They could always just say "because of the weakening U.S. dollar..." and I think people would get the point. Heck, even U.S. companies are doing that now.
Wow, can we get this guy to decode some of the Bluray keys used? Break HDCP? His method is pretty straight forward, easy to follow, and looks fool proof. Expose layers in the chip and read the data directly. I don't see how manufactures can stop this. As long as the key is physically somewhere in the hardware, it should be possible to access it. I guess the reason this isn't done more often is because of the expense of the high powered microscope, toxic chemicals, and fume hood.
And why would you need a floppy drive in the year 2008? Looking at the pictures, it looks like that would consume over 50% of it's volume. I would be surprised if it even had a DVD-ROM drive.