I agree, but optimizing CPU utilization by reducing interrupts (and thus context switches) needs to be done carefully in order to avoid the latency problems mentioned by the previous poster. The proper heuristics for this require more information that older NICs and drivers provided to one another.
It actually pretty nice seeing evolution of some fairly fundamental things like interface definitions as these can really impact the performacne of the final product. A poor NIC interface design (from the host's memory and OS perspectives) can cripple an otherwise good design.
After re-reading what I just wrote, I think I may have just justified your comment.:-)
You make a good point about interrupt coalescing affecting latency, but that was mostly on first generation gig-e products. It also had a lot to do with how the products were built. Newer NIC architectures have learned to balance this better.
During heavy loads, with interrupt coalescing enabled, latency is not an issue, getting the most throughput per cpu cycle is. If the NIC and driver together can determine system and network load, then it can make an intelligent decision when to delay presenting an interrupt to the host and when it should do so right away. To do this correctly, the NIC should also be able to determine when the host is in the interrupt service routine, so work can just be placed on the queue without requiring any interrupt. In cases like this, the work gets done almost for free.
The problem is integration of multiple MACs and PHYs into a single chip. If you take apart a 4 or 8 port 10/100 switch, you will find that you have a singe chip product with some small components surrounding it. If you take a multiport 10/100/1000 switch apart, you will find many more chips because the integration hasn't happened there yet. Give it a few more years for the technology to mature.
When I hear the word hub, I think of half duplex shared medium. Although the gig-e spec (802.3z) contains support for half duplex, I don't know of any vendor that has implemented and tested it, espicially in a hub product.
Coolness aside, the market for gigabit ethernet is a lot larger for the corporate user than it is for the home user. One of the primary drivers for the fast adoption of gig-e in corporate environments is the ability to use the existing copper infrastucture by using an additional 2 pairs (copper gig-e uses 4 pairs).
The problem with fiber vs copper isn't really the cost of the medium, it is the cost of laying the infrastructure. If I remember correctly, the cost of the cable is about 1/10 of the total cost.
Part of the reason gig-e has become so cheap so quickly is that it has been able to ride the ethernet adoption curve to make the MACs and copper transcievers cheap because of the huge volumes. These volumes will never be reached by fiber.
In your argument, you make the implicit assumption that an IP address equals a person. In my house, I have 1 IP address, running through a NAT box that supports 4 people. I can download the mail for everyone (using fetchmail), but that in no way implies that any of the people using this IP address has received their mail, or that they even have been notified that new mail has arrived.
This leads back to my original point- unless the downloading of mail is coupled with biometric authentication, you can contrive many instances where the mail may seem to be delivered when it has not.
Getting the pop logs only shows that the email has been downloaded. It does not show who downloaded them, If *I* retrieved them, or if it was done by a proxy on my behalf. Of course, If the act of retrieving mail becomes equated with receiving mail, my email downloading habits will have to adapt accordingly...
My mailer is not allowed to initiate connections without my express permission. I firewall everything, on the way in and the way out. Unless the reciept mechanism is coupled to the delivery mechanism, I fail to see how this can work. The problem with coupling the reciept mechanism to the delivery mechanism, is that many mailers will pull the email, without human intervention. I believe to make this work, you need a bioauthenticated pull that is coupled to the reciept. The email pull cannot happen without the bioauthenticated individual being present and because the individual is present, the act of the pull can be construed as delivery and a reciept of the subpoena (or whatever).
Now that we have figured out how to make this work, would you use this as a reliable, authenticated email delivery mechanism?
The act of a mail user agent receiving the email, does not equate to the intended individual receiving it. Nor does an unauthenticated user. The only way this makes sense is if the intended recipient uses some form of biometric authentication.
I am making an assumption that the entity in question is in fact a human and not a virtual entity. As long as we are dealing with people, we should maintain the same high level of bioauthentication that we use today. Handing a subpoena to the identified individual relys on human based bioauthentication. That has been the legal standard. Not being able to find the person has not been an excuse to serve a subpoena without this level of bioauthentication. I don't believe that it is permissable to deliver a subpoena via the telephone.
I'm still waiting for a bioauthentication scheme as ubiquitous as human recognition...
I can see it now. The first time someone puts this in a magazine, it will come infected with a virus. Figuring a first run of 500K copies, some could get into machines otherwise firewalled off or just not connected to the net.
I'm guessing that an adapter could be made from cardboard and also included in a magazine distribution. Or as a special bonus when you "sign up now and recieve a free gift"...
I can see it now, cdrom and audio magazine inserts. I remember a long time ago getting magazine inserts in the form of records. You rip them out and play them on your turntable. The one I remember most was a recording of whale songs that came in a National Geographic.
The 802.11b uses 2.4GHz portion of the spectrum also known as the ISM band. ISM stands for Industrual, Scientific and Medical. When the ISM band was opened up for communications purposes in 1985, the deal was that communications equipment had to accept and tolerate other non-communications equipment that radiate in the same band. ISM communications gear is not allowed to force non-communications gear to change to enable or enhance ISM band communications. Examples of non-communications users of the ISM band include microwave ovens and some high efficiency industrial lights. The net of this is that ISM band communications, including 802.11b, is already regulated by a strict set of requirements mostly to preserve the rights of the previous and current non-communications users. Placing additional restrictions on 802.11b users would also affect the non-communications users of the ISM band.
It is easy to see why digital photography has given Polariod's instant camera technology a challenge in the marketplace. Both live on removing the need for an outside processing lab. Digital photography gives the additional features of being able to send and manipulate the photographs. I see some areas where the polaroid technology still has some advantages- Cheaper upfront equipment cost, disposable equipment and comes with a built in printer. I have both a couple of polaroids and a digital camera. The polaroid is kept for emergencies. My digital camera has replaced my 35MM camera.
I hope that polaroid stays afloat enough to keep its basic product line alive, but they definitely need to make changes to respond to the changing marketplace. I'm thinking of emergency cameras or survival cameras. If they can make a completely disposable instant camera along the lines of the disposable 35MM, they might have a sustainable niche.
Another issue that has been overlooked is the size of the resulting RAMdrive. You can buy 3.5" drives at 75 gigs. All of the current products that I have seen are at least full sized PCI cards, or a PCI card controller connected to a seperate RAMdrive frame.
The amazing thing about this is, the spinning storage is smaller that RAM drives. This is quite counter intuitive, but I believe that it demonstrates what engineering marvels a state of the art disk drive really is.
I do believe that RAM drive/ RAM storage technology can achieve mich higher packaging densities, but not using today's off the shelf memory chips.
Slashdot Mirror
I agree, but optimizing CPU utilization by reducing interrupts (and thus context switches) needs to be done carefully in order to avoid the latency problems mentioned by the previous poster. The proper heuristics for this require more information that older NICs and drivers provided to one another.
:-)
It actually pretty nice seeing evolution of some fairly fundamental things like interface definitions as these can really impact the performacne of the final product. A poor NIC interface design (from the host's memory and OS perspectives) can cripple an otherwise good design.
After re-reading what I just wrote, I think I may have just justified your comment.
-tpg.
You make a good point about interrupt coalescing affecting latency, but that was mostly on first generation gig-e products. It also had a lot to do with how the products were built. Newer NIC architectures have learned to balance this better.
During heavy loads, with interrupt coalescing enabled, latency is not an issue, getting the most throughput per cpu cycle is. If the NIC and driver together can determine system and network load, then it can make an intelligent decision when to delay presenting an interrupt to the host and when it should do so right away. To do this correctly, the NIC should also be able to determine when the host is in the interrupt service routine, so work can just be placed on the queue without requiring any interrupt. In cases like this, the work gets done almost for free.
A similar thing occurs in TCP with delayed ACKs.
-tpg
The problem is integration of multiple MACs and PHYs into a single chip. If you take apart a 4 or 8 port 10/100 switch, you will find that you have a singe chip product with some small components surrounding it. If you take a multiport 10/100/1000 switch apart, you will find many more chips because the integration hasn't happened there yet. Give it a few more years for the technology to mature.
-tpg
When I hear the word hub, I think of half duplex shared medium. Although the gig-e spec (802.3z) contains support for half duplex, I don't know of any vendor that has implemented and tested it, espicially in a hub product.
-tpg
Coolness aside, the market for gigabit ethernet is a lot larger for the corporate user than it is for the home user. One of the primary drivers for the fast adoption of gig-e in corporate environments is the ability to use the existing copper infrastucture by using an additional 2 pairs (copper gig-e uses 4 pairs).
The problem with fiber vs copper isn't really the cost of the medium, it is the cost of laying the infrastructure. If I remember correctly, the cost of the cable is about 1/10 of the total cost.
Part of the reason gig-e has become so cheap so quickly is that it has been able to ride the ethernet adoption curve to make the MACs and copper transcievers cheap because of the huge volumes. These volumes will never be reached by fiber.
-tpg
In your argument, you make the implicit assumption that an IP address equals a person. In my house, I have 1 IP address, running through a NAT box that supports 4 people. I can download the mail for everyone (using fetchmail), but that in no way implies that any of the people using this IP address has received their mail, or that they even have been notified that new mail has arrived.
This leads back to my original point- unless the downloading of mail is coupled with biometric authentication, you can contrive many instances where the mail may seem to be delivered when it has not.
-tpg
Getting the pop logs only shows that the email has been downloaded. It does not show who downloaded them, If *I* retrieved them, or if it was done by a proxy on my behalf. Of course, If the act of retrieving mail becomes equated with receiving mail, my email downloading habits will have to adapt accordingly...
-tpg
My mailer is not allowed to initiate connections without my express permission. I firewall everything, on the way in and the way out. Unless the reciept mechanism is coupled to the delivery mechanism, I fail to see how this can work. The problem with coupling the reciept mechanism to the delivery mechanism, is that many mailers will pull the email, without human intervention. I believe to make this work, you need a bioauthenticated pull that is coupled to the reciept. The email pull cannot happen without the bioauthenticated individual being present and because the individual is present, the act of the pull can be construed as delivery and a reciept of the subpoena (or whatever).
Now that we have figured out how to make this work, would you use this as a reliable, authenticated email delivery mechanism?
-tpg
I see a couple of problem-
The act of a mail user agent receiving the email, does not equate to the intended individual receiving it. Nor does an unauthenticated user. The only way this makes sense is if the intended recipient uses some form of biometric authentication.
I am making an assumption that the entity in question is in fact a human and not a virtual entity. As long as we are dealing with people, we should maintain the same high level of bioauthentication that we use today. Handing a subpoena to the identified individual relys on human based bioauthentication. That has been the legal standard. Not being able to find the person has not been an excuse to serve a subpoena without this level of bioauthentication. I don't believe that it is permissable to deliver a subpoena via the telephone.
I'm still waiting for a bioauthentication scheme as ubiquitous as human recognition...
-tpg
I can see it now. The first time someone puts this in a magazine, it will come infected with a virus. Figuring a first run of 500K copies, some
could get into machines otherwise firewalled off or just not connected to the net.
I'm not a pessimist, really, I'm not...
I'm guessing that an adapter could be made from cardboard and also included in a magazine distribution. Or as a special bonus when you "sign up now and recieve a free gift"...
I can see it now, cdrom and audio magazine inserts. I remember a long time ago getting magazine inserts in the form of records. You rip them out and play them on your turntable. The one I remember most was a recording of whale songs that came in a National Geographic.
The 802.11b uses 2.4GHz portion of the spectrum also known as the ISM band. ISM stands for Industrual, Scientific and Medical. When the ISM band was opened up for communications purposes in 1985, the deal was that communications equipment had to accept and tolerate other non-communications equipment that radiate in the same band. ISM communications gear is not allowed to force non-communications gear to change to enable or enhance ISM band communications. Examples of non-communications users of the ISM band include microwave ovens and some high efficiency industrial lights. The net of this is that ISM band communications, including 802.11b, is already regulated by a strict set of requirements mostly to preserve the rights of the previous and current non-communications users. Placing additional restrictions on 802.11b users would also affect the non-communications users of the ISM band.
It is easy to see why digital photography has given Polariod's instant camera technology a challenge in the marketplace. Both live on removing the need for an outside processing lab. Digital photography gives the additional features of being able to send and manipulate the photographs. I see some areas where the polaroid technology still has some advantages- Cheaper upfront equipment cost, disposable equipment and comes with a built in printer. I have both a couple of polaroids and a digital camera. The polaroid is kept for emergencies. My digital camera has replaced my 35MM camera.
I hope that polaroid stays afloat enough to keep its basic product line alive, but they definitely need to make changes to respond to the changing marketplace. I'm thinking of emergency cameras or survival cameras. If they can make a completely disposable instant camera along the lines of the disposable 35MM, they might have a sustainable niche.
-tpg
Another issue that has been overlooked is the size of the resulting RAMdrive. You can buy 3.5" drives at 75 gigs. All of the current products that I have seen are at least full sized PCI cards, or a PCI card controller connected to a seperate RAMdrive frame.
The amazing thing about this is, the spinning storage is smaller that RAM drives. This is quite counter intuitive, but I believe that it demonstrates what engineering marvels a state of the art disk drive really is.
I do believe that RAM drive/ RAM storage technology can achieve mich higher packaging densities, but not using today's off the shelf memory chips.
-tpg.