What the ISP's could instead do is actually start using IPv6. 1. It removes all the difficulties of NAT, making the concept of P2P a non-issue (all peers will be servers with no port-forwarding-mumbo-jumbo).
The bandwidth-sucking of P2P is still just as much an issue with IPv6.
2. It will add multicast which will enable TV and other streaming media to be very effective.
If ISPs wanted multicast, they would have enabled it already. Multicast is not coming.
It's putting more weight on on the root name servers, how long until there are 10,000 TLDs, 100,000 of them? a million? I think tests were done showing that the root servers can handle much more load than they currently serve.
Then there's all the people running the TLDs who may or may not have the infrastructure, technical expertise or long-term stability to properly run one. ICANN won't let idiots create TLDs. Most of them will probably outsource their registries to VeriSign or Afilias (like the "non-profit".org).
I don't know why people keep getting hung up on legal vs. illegal content; the law clearly says that ISPs have no copyright liability for their caches:
Except that IPv6 uses multicast for pretty much everything. On the local link, sure. Besides that, IPv6 doesn't use multicast any more than IPv4 and it certainly isn't required.
Yeah, wouldn't it be great if Apple waited for VMware and Parallels to perfect their products and then kicked them in the head? Now that's developer relations.
No but seriously, whats the deal with this being available for common distros? It's not going to happen.
Also if I add a new external HDD to my 'z-pool' and then lose it, do I lose data from my internal hdd as well as the external? If you use RAID-0 (striping) mode you'll lose data.
Anyone know how many drives can fail at once in a RAID-Z2 before you are 100% SOL? RAID-Z2 can survive two drive failures; three failures will kill the pool.
ZFS uses super-paranoidal checksumming which can detect drive problems in advance. No, checksumming cannot detect drive problems in advance; for that you need SMART. Once your drive has been corrupted ZFS will kick in and prevent you from accessing any corrupt data.
High-end SSDs have a RAM write buffer, but it complicates the controller significantly. I expect sophisticated controllers to trickle down to all SSDs eventually.
I thought the chip has been out for a few months; I feel bad for anyone who has been trying to use the processor with no development tools.
Also, it looks like the tools have been released to Tilera's customers, not to the public. A shame, since I'm sure a lot of Slashdotters would like to at least gawk at the docs for this chip.
Slashdot Mirror
What the ISP's could instead do is actually start using IPv6.
1. It removes all the difficulties of NAT, making the concept of P2P a non-issue (all peers will be servers with no port-forwarding-mumbo-jumbo).
The bandwidth-sucking of P2P is still just as much an issue with IPv6.
2. It will add multicast which will enable TV and other streaming media to be very effective.
If ISPs wanted multicast, they would have enabled it already. Multicast is not coming.
If you use P2P instead of centralized server to move the same total amount of data, what's the problem?
The problem for some ISPs is upstream congestion causing light users to complain about VoIP dropouts.
You're missing SLC vs. MLC and high-performance controllers.
Putting a server processor in PCs was tried; it was called the G5. It turned out OK, although having no laptop version was annoying.
Look at the heatsink in a PS3 and you have your answer.
Maybe you missed the recent news that several large ISPs are shutting down Usenet service. You can always pay for Usenet, but why pay for warez?
I don't know why people keep getting hung up on legal vs. illegal content; the law clearly says that ISPs have no copyright liability for their caches:
http://www.bitlaw.com/source/17usc/512.html
And plugging in three cables is so much work that it negates the advantages of the Mac? I "dock" my MBP in my office all the time.
Yeah, wouldn't it be great if Apple waited for VMware and Parallels to perfect their products and then kicked them in the head? Now that's developer relations.
I don't see any coverage of NDA sessions there.
Red Hat is now pushing KVM, see http://ovirt.org/
That's why Neuros/TI ripped out all the GPL codecs and replaced them with proprietary ones.
They ripped all the codecs out of VLC and replaced them with legally licensed versions. So yes, they will be paying a lot of license fees.
So use O_DIRECT like some databases do.
High-end SSDs have a RAM write buffer, but it complicates the controller significantly. I expect sophisticated controllers to trickle down to all SSDs eventually.
Try this list: http://www.storagesearch.com/ssd-fastest.html
Intel tried that experiment with XScale and eventually sold it off to Marvell.
Multicast is a good idea, but it isn't related to IPv6. There's IPv4, IPv4 with multicast, IPv6, and IPv6 with multicast.
As I understand it, if ISPs enabled multicast their routers would explode due to the memory requirements.
Whoa, you've posted the same question three times in this thread. Relax a little.
In the absence of any guidance from Adobe, we have to assume that player developers will have to pay license fees to On2 and MPEG LA.
I thought the chip has been out for a few months; I feel bad for anyone who has been trying to use the processor with no development tools.
Also, it looks like the tools have been released to Tilera's customers, not to the public. A shame, since I'm sure a lot of Slashdotters would like to at least gawk at the docs for this chip.