Re: Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (net/file IO) How much is it a relevant prio?
On 2016-02-25 19:05, Jiri B wrote: On Thu, Feb 25, 2016 at 06:14:40PM +0700, Tinker wrote: Any guess about when might it actually become usable, 6.1, 6.2, this year, next? I would be very curious to see if-what limits there are on file IO activity when you do it full-on completely RW on 10-20 cores and a ton of SSD:s. If you have any guess about what probably would happen feel free to share. :) Read cvs commit messages and you will see they are hard working on it. Lot of work has been done by sasha@ in PF as he's one of those responsible for porting PF to Solaris as main FW in next major release. If you by some chance think they are slow, your mails won't change much anyway. Send money, so the project could use them to free some developers from coding something else for living and work instead on OpenBSD. Or... OpenBSD was first open-source OS which had anonymous access to sources. So you know other way too speed up the things. j. Just wanted to understand where it is at. No complaining, just grateful for this great OS. Yes all with you that proper contributions are money, code and hardware. Thanks.
Re: Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (net/file IO) How much is it a relevant prio?
On Thu, Feb 25, 2016 at 06:14:40PM +0700, Tinker wrote: > Any guess about when might it actually become usable, 6.1, 6.2, this year, > next? > > > I would be very curious to see if-what limits there are on file IO activity > when you do it full-on completely RW on 10-20 cores and a ton of SSD:s. > > If you have any guess about what probably would happen feel free to share. > :) Read cvs commit messages and you will see they are hard working on it. Lot of work has been done by sasha@ in PF as he's one of those responsible for porting PF to Solaris as main FW in next major release. If you by some chance think they are slow, your mails won't change much anyway. Send money, so the project could use them to free some developers from coding something else for living and work instead on OpenBSD. Or... OpenBSD was first open-source OS which had anonymous access to sources. So you know other way too speed up the things. j.
Re: Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (net/file IO) How much is it a relevant prio?
On 2016 Feb 25 (Thu) at 18:14:40 +0700 (+0700), Tinker wrote: :On 2016-02-25 06:04, Chris Cappuccio wrote: :>Tinker [ti...@openmailbox.org] wrote: :>>First, Thank you for this fantastically awesome OS. :>> :>> :>>Just curious, what are approx plans for kernel-multicore-ness next 1-2 :>>years? (Network IO, file/disk IO) :>> :> :>Network SMP (and other subsystems required to support it) is the heaviest :>area right now. :> :>> :>>Are there any relevant cases today where the singlecore architecture :>>actually is limiting? Say on a 20-core machine doing random file and :>>network :>>IO full-on. :>> :> :>Many, especially once you go past 4 or 8 cores. : :Regarding the network, yes I heard about the multicore-ization work too. :(Also I talked to someone whose router had a 700Mbps limit on his crappy :hardware because of the same constraint - not too bad though haha :) ) : :Any guess about when might it actually become usable, 6.1, 6.2, this year, :next? : The plan is "make it better". And the timeframe is "when it is ready". This is pretty much always the plan and timeframe we have. Obviously we hope "sooner" rather than "later", but hopes don't make it ready. -- You know it's going to be a bad day when you want to put on the clothes you wore home from the party and there aren't any.
Re: Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (net/file IO) How much is it a relevant prio?
On 2016-02-25 06:04, Chris Cappuccio wrote: Tinker [ti...@openmailbox.org] wrote: First, Thank you for this fantastically awesome OS. Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (Network IO, file/disk IO) Network SMP (and other subsystems required to support it) is the heaviest area right now. Are there any relevant cases today where the singlecore architecture actually is limiting? Say on a 20-core machine doing random file and network IO full-on. Many, especially once you go past 4 or 8 cores. Regarding the network, yes I heard about the multicore-ization work too. (Also I talked to someone whose router had a 700Mbps limit on his crappy hardware because of the same constraint - not too bad though haha :) ) Any guess about when might it actually become usable, 6.1, 6.2, this year, next? I would be very curious to see if-what limits there are on file IO activity when you do it full-on completely RW on 10-20 cores and a ton of SSD:s. If you have any guess about what probably would happen feel free to share. :) Thanks, have a great day.
Re: Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (net/file IO) How much is it a relevant prio?
Tinker [ti...@openmailbox.org] wrote: > First, Thank you for this fantastically awesome OS. > > > Just curious, what are approx plans for kernel-multicore-ness next 1-2 > years? (Network IO, file/disk IO) > Network SMP (and other subsystems required to support it) is the heaviest area right now. > > Are there any relevant cases today where the singlecore architecture > actually is limiting? Say on a 20-core machine doing random file and network > IO full-on. > Many, especially once you go past 4 or 8 cores.
Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (net/file IO) How much is it a relevant prio?
First, Thank you for this fantastically awesome OS. Just curious, what are approx plans for kernel-multicore-ness next 1-2 years? (Network IO, file/disk IO) Are there any relevant cases today where the singlecore architecture actually is limiting? Say on a 20-core machine doing random file and network IO full-on. Just curious. Thanks.
