Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Comments

top

Black Holes Not Black After All, Theorize Physicists

Bengie Re:Wait (204 comments)

If, however, time slows as it approached the blackhole and the particle never actually crossed the event horizon

Can someone please explain this. It seems to be accepted that not only does the object's time slows down as it approaches the event horizon, but it's velocity does also. I don't get that. If an object is moving away from me at 0.9999c, I could expect is to actually be moving away from me at that speed, not slowing down relative to me. If from my perspective an object has stopped moving, then it is no longer moving relative to me and its time should be pretty much the same to my reference.

I seem to be missing something. I assume it has to do with gravitational fields instead of "proper" velocity.

9 hours ago
top

Black Holes Not Black After All, Theorize Physicists

Bengie Re:What about existing evidence? (204 comments)

Another orthogonal explanation.

Any light emitted from the "black hole" itself could also be dwarfed by the noise of all the other em coming from the accretion disk, making it nearly impossible to detected remotely.

10 hours ago
top

Black Holes Not Black After All, Theorize Physicists

Bengie Re:Why is information movement a paradox? (204 comments)

Time must be reversible. Once information falls into a blackhole, there is no way to reverse time and get the same information out because the information becomes ambiguous in something that in infinitely dense.

10 hours ago
top

For Half, Degrees In Computing, Math, Or Stats Lead To Other Jobs

Bengie Re:well rounded cool but not at today's price leve (169 comments)

Why are you comparing "PE" in a 4 year degree to a fitness club? It's a full on class where you spend most of your time learning in a lecture hall. As for "hands on" skills, so many people that learn these "skills", but only know exactly what they were taught and nothing more. Those "hands on" skills have expiration dates when the technology changes. If you really want to learn something useful, learn they theory behind those skills. While theory and "hands on" skills can both be learned, most places tend to focus on one or the other and theory is much more important.

yesterday
top

'Just Let Me Code!'

Bengie Re:Go work for a bigger company (367 comments)

He doesn't want to use frameworks, he wants to reinvent the wheel, poorly. This is a mix of sarcasm and opinion.

2 days ago
top

'Just Let Me Code!'

Bengie Re: Just let me do brain surgery! (367 comments)

I think what he meant is if brain surgery was as bureaucratic as many projects, it would take too long and would be a botched job almost every time. But yes, lots of pre-op stuff to do.

2 days ago
top

Verizon Boosts FiOS Uploads To Match Downloads

Bengie Re:Thank Google, not Verizon (230 comments)

I personally don't see the point of more than using 200watts at home. Just enough for two light bulbs.

Wait, if you have enough power to the house, you can have ovens, refrigerators, and air conditioning units?! Wow, who would have thought about the new awesome ideas 100 years ago when power was limited?

Unless you're God and can see the future, stop acting like you know that there is absolutely no benefit to improving technology.

3 days ago
top

Verizon Boosts FiOS Uploads To Match Downloads

Bengie Re:Symmetrical? (230 comments)

80/20 rule would most definitely apply on average. When reading about Netflix' caching servers, something like 10% of the data represents about 70% of the hits.

Netflix' SSD servers only have about 10TB of storage, and they have about a 70% hit rate, while the rust-bucket servers have 100TB of storage and have about an 80%-90% hit rate. Their entire catalog is about 1PB.

P2P would work best for flash-mobs. It would reduce the number of cache servers they need deployed in other ISPs.

3 days ago
top

Verizon Boosts FiOS Uploads To Match Downloads

Bengie Re:Symmetrical? (230 comments)

The 80/20 rule is a great rule.

Assuming decent buffering, you can start streaming the video live at the beginning, and the P2P can start buffering the later part of the video. Just use the normal servers for starting the buffer, but then use P2P to populate as much buffer as you can. I'm sure the 80/20 rule would apply.

3 days ago
top

Verizon Boosts FiOS Uploads To Match Downloads

Bengie Re:What about (230 comments)

So it makes little sense to have asymmetric fiber service other than for marketing purposes.

Most fiber deployments use GPON, which shares bandwidth. High speed sending optics are more expensive than high speed receiving optics. Most ONTs can receive up to 2.5gb/s, but can only send 1.25gb/s.. If using Active Ethernet, then it'll be completely symmetrical, and you'll have 1gb up/down. But in GPON mode, you have 2.5 down and 1.25 up.

Google Fiber uses WDM-GPON, which has 32 lamdas of 1.25gb/1.25gb, so it's all symmetrical, but they were an early adopter and used the draft version.

The other question that comes up. Since the fiber is already dedicated, why use GPON? Well, you get higher port densities and less power consumption, but quite a bit. There is a good benefit of having 32 customers per port instead of one customer per port.

3 days ago
top

Verizon Boosts FiOS Uploads To Match Downloads

Bengie Re:What about (230 comments)

A 100mb interface that can get 112mb/s? That's impressive.

3 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:complex application example (160 comments)

The point is that each and every component involved, from hardware through firmware to software, is designed under the premiss that it is okay to drop a packet at any time for any reason, or to duplicate or reorder packets.

That entire sentence is damn near a lie. Those issue can happen, but they shouldn't happen. You almost have to go out of your way to make those situations happen. Dropping a packet should NEVER happen except when going past line rate. Packets should NEVER be duplicated or reordered except in the case of a misconfiguration of a network. Networks are FIFO and they don't just duplicate packets for the fun of it.

As for error rates, many high end network devices can upwards of an error rate of 10E-18, which puts it at one error every 111petabytes. I assume you'd have to divide that error rate by the number of hops.

I've seen enough system designs where they send data as UDP packets and they require incredibly low packet-loss rates, border-lining never. It can be done, but you're not going to be using dlink switches. You can purchase L4 switches now with multi-gigabyte buffers. They're meant to handle potentially massive throughput spikes and not drop packets.

I assume this is all intra-datacenter traffic or at least an entirely reserved network.

3 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:Where is the market demand? (160 comments)

The whole point of QoS is to not have to add more hardware, but to make better use of your current hardware while not having large amounts of jitter. Mainframes don't need to worry about interactive processes, but many modern day work loads do. What they want is a good average throughput with a maximum latency.

4 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:complex application example (160 comments)

* the UDP traffic contains multiple data packets (call them "jobs") each of which requires minimal decoding and processing

anything _above_ that rate and the UDP buffers overflow and there is no way to know if the data has been dropped. the data is *not* repeated, and there is no back-communication channel.

How are you planning on handling UDP checksum errors without a backchannel or EC? The physical ethernet layer is lossy, so you're screwed even before the packet hits the NIC.

Lossy?

I just logged into my switch at home and it has 146 days of uptime with 20,154,030,043 frames processed and 0 frame errors. I can even do a 1gb/1gb, for a total of just under 2gb/s at once, iperf, and have 0 packets dropped.

Let the network group worry about QoS. But yes, errors will eventually happen, they're just very rare. But when they do happen, it's probably pathological and you'll get a lot of them. But I wouldn't go so far to say "the physical ethernet layer is lossy", as a general statement.

4 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:complex application example (160 comments)

What kind of crappy network equipment does your job use that has packet loss at anything less than line rate? He's talking about near 1mbit/sec of UDP. I can get 0% packet-loss around the world for only 1mb/s

4 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:complex application example (160 comments)

But if done correctly, you can do line rate UDP with 0% loss. Routers can do line rate without loss all the time. He's talking about thousands of packets per second, not the millions to tens of millions a modern NIC can handle.

4 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:complex application example (160 comments)

When you handling lots of little messages/jobs/tasks that are coming in quickly, passing data between processes is a horrible idea. Between context switching and system calls, you're destroying your performance.

You need to make larger batches.

1) UDP/Job comes in, write to single-writer many reader queue(large circular queues can be good for this) and the order number, maybe a 64bit incrementing integer. If the run time per job is quite constant, then you could use several single reader/writer queues and just round robin them. This would reduce potential lock contention, but would come at the cost of variable work loads could cause a bias towards a single worker.

1.a) You're not receiving packets fast enough to worry about threading reading from the NIC. If you had to look into making this part faster, like millions of Packets Per Second, the first thing I would find out is if this packets are coming from multiple data sources and if jobs need to be processing in order relative to all sources or to themselves. If themselves, then you could have a load balancer trying to round-robin and sticky by Source IP.

2) Worker sees jobs in queue(since this is a speed sensitive dedicated matching, polling could work, but may want event based), grabs N jobs, where those N Jobs can be reliably completed in a timely fashion, this may be 1 or may be 100, who knows until you test. Note the order number of your Jobs. You don't really need to grab N jobs if using a single reader/writer queue since there is no real contention, but reading in batches is good for high contention queues like multi-readers.

3) Your worker will now loop through each job running each script, hopefully all on the same worker/thread.

4) Write out the completed jobs to a single reader single writer queue. If you don't use a single reader/writer queue and instead have a multi-writer queue, you may want to commit finished jobs in batches to reduce contention.

5) Have another worker poll/event each of queues for each worker. This worker can make sure the jobs are put back in order. This process I assume to be relatively lite, so probably a single worker to handle all of the worker queues, but could also be threaded. You just need to manage the ordering somehow.

You should have no more than N number of workers per core, where N is probably a small number, like 2. Lots of threads is bad.

I love single reader/writer queues, they can be lock-less.

Your problem sounds close to what Disruptor handles (Google: disruptor ring buffer)(fun read: http://mechanitis.blogspot.com...). May want to also look into that kind of design. It's an interesting project that runs on Java and .Net, and I think C or something, but I can't remember. Still a good read.

4 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:complex application example (160 comments)

He said the CPU is mostly idle. He's trying to set up his system to handle lots of tiny tasks and Linux isn't playing well with the regular tools.

4 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:mainframe is old crap for geezers (160 comments)

If you got a 2x increase in single threaded performance on a 100k node cluster, you could probably get rid of quite a bit more than 50k nodes because of scaling issues.

5 days ago
top

Linux Needs Resource Management For Complex Workloads

Bengie Re:This obsession with everything in RAM needs to (160 comments)

Earlier 64-bit AMD CPUs did not have a 64bit atomic compare-and-swap instruction, so Microsoft limited their OSes at those times to 8TB. If only Microsoft supported compiling for your arch. Stupid closed source OS.

5 days ago

Submissions

top

Resolving IP to MAC address across a router

Bengie Bengie writes  |  more than 6 years ago

Bengie (1121981) writes "From what I know about networks, you can't find out the MAC of an IP across a router. At some point I stumbled across a program that does just this. The only google hits I get talk about Netbios. Being able to do this would help out IT dept because our back-up registration page pulls MAC info from our DHCP server, but the DHCP database only syncs with our back-up database every 24 hours. If we build a new computer to replace an old one, our registration page can't get the new MAC for the Wake-on-LAN info until 24 hours later. We could use netbios if we had to, but that's kind of shady and won't work for our Mac computers since they don't have netbios. Is there a way of resolving the MAC of an IP across routers?"

Journals

Bengie has no journal entries.

Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...