Re: Is it worth considering compling a generic MPPF kernel for user convenience
so this is about setting MULTIPROCESSOR, WITH_PF_LOCK and NET_TASKQ ? or something else? i been using it since a while and as in basic router all seem fine. __ kolargol Sent with ProtonMail Secure Email. ‐‐‐ Original Message ‐‐‐ On Tuesday, April 2, 2019 6:28 PM, Tom Smyth wrote: > Hi, you can re-compile the BSD kernel to allow multi Processor PF, > (but it is deemd by people who know more about PF and Programming > than my self that it is not fully up to OpenBSD standards for Release yet > > I was referring to it as BSDMPPF as a continuation of the BSD vs BSDMP > kernel ... > > sorry for the confusion that I have caused in this case... > > On Tue, 2 Apr 2019 at 17:25, kolargol kolar...@protonmail.com wrote: > > > MPPF is multi processor for pf or what? Where can i learn more about it? I > > was searching sources but could not find anything related to "MPPF", any > > clue? > > thanks, > > __ > > kolargol > > Sent with ProtonMail Secure Email. > > ‐‐‐ Original Message ‐‐‐ > > On Tuesday, April 2, 2019 1:30 PM, Tom Smyth tom.sm...@wirelessconnect.eu > > wrote: > > > > > Hello, > > > I was wondering what devs / more experienced users think about > > > having BSDMPPF kernel as an option in the upcoming release > > > so that users could opt to test that by selecting alternate BSDMPPF kernel > > > (without having to re-compile the kernel) > > > the tested benefits on a PC engines apuc2 is at least 2x performance > > > from my lab testing here > > > I think having a higher install base of consistently complied generic > > > kernels with > > > pf enabled would be beneficial > > > what do the more experienced users of OpenBSD think about this? > > > are there any down sides with this approach ? > > > Thanks, > > > Tom Smyth > > -- > > Kindest regards, > Tom Smyth > > The information contained in this E-mail is intended only for the > confidential use of the named recipient. If the reader of this message > is not the intended recipient or the person responsible for > delivering it to the recipient, you are hereby notified that you have > received this communication in error and that any review, > dissemination or copying of this communication is strictly prohibited. > If you have received this in error, please notify the sender > immediately by telephone at the number above and erase the message > You are requested to carry out your own virus check before > opening any attachment.
Re: Is it worth considering compling a generic MPPF kernel for user convenience
Hi, you can re-compile the BSD kernel to allow multi Processor PF, (but it is deemd by people who know more about PF and Programming than my self that it is not fully up to OpenBSD standards for Release yet I was referring to it as BSDMPPF as a continuation of the BSD vs BSDMP kernel ... sorry for the confusion that I have caused in this case... On Tue, 2 Apr 2019 at 17:25, kolargol wrote: > > MPPF is multi processor for pf or what? Where can i learn more about it? I > was searching sources but could not find anything related to "MPPF", any clue? > > thanks, > > __ > kolargol > > Sent with ProtonMail Secure Email. > > ‐‐‐ Original Message ‐‐‐ > On Tuesday, April 2, 2019 1:30 PM, Tom Smyth > wrote: > > > Hello, > > > > I was wondering what devs / more experienced users think about > > having BSDMPPF kernel as an option in the upcoming release > > so that users could opt to test that by selecting alternate BSDMPPF kernel > > (without having to re-compile the kernel) > > > > the tested benefits on a PC engines apuc2 is at least 2x performance > > from my lab testing here > > > > I think having a higher install base of consistently complied generic > > kernels with > > pf enabled would be beneficial > > > > what do the more experienced users of OpenBSD think about this? > > > > are there any down sides with this approach ? > > > > Thanks, > > > > Tom Smyth > > -- Kindest regards, Tom Smyth The information contained in this E-mail is intended only for the confidential use of the named recipient. If the reader of this message is not the intended recipient or the person responsible for delivering it to the recipient, you are hereby notified that you have received this communication in error and that any review, dissemination or copying of this communication is strictly prohibited. If you have received this in error, please notify the sender immediately by telephone at the number above and erase the message You are requested to carry out your own virus check before opening any attachment.
Re: Is it worth considering compling a generic MPPF kernel for user convenience
MPPF is multi processor for pf or what? Where can i learn more about it? I was searching sources but could not find anything related to "MPPF", any clue? thanks, __ kolargol Sent with ProtonMail Secure Email. ‐‐‐ Original Message ‐‐‐ On Tuesday, April 2, 2019 1:30 PM, Tom Smyth wrote: > Hello, > > I was wondering what devs / more experienced users think about > having BSDMPPF kernel as an option in the upcoming release > so that users could opt to test that by selecting alternate BSDMPPF kernel > (without having to re-compile the kernel) > > the tested benefits on a PC engines apuc2 is at least 2x performance > from my lab testing here > > I think having a higher install base of consistently complied generic > kernels with > pf enabled would be beneficial > > what do the more experienced users of OpenBSD think about this? > > are there any down sides with this approach ? > > Thanks, > > Tom Smyth
Re: Is it worth considering compling a generic MPPF kernel for user convenience
Ok, under stood re ,prototype code... thought the Project was being extra conservative :) and that more people trying MPPF would be helpful, but if it aint ready for release it aint ready for release re PF going away... I thought that was a Calendar Coincidence... now im feeling a slight up tick in my blood pressure :) On Tue, 2 Apr 2019 at 12:33, Theo de Raadt wrote: > > No, this is not our style, it very much doesn't fit the development > process to have users running prototype code for 6 months. > > And anyways why do you want this, since pf is going away. > > Tom Smyth wrote: > > > I was wondering what devs / more experienced users think about > > having BSDMPPF kernel as an option in the upcoming release > > so that users could opt to test that by selecting alternate BSDMPPF kernel > > (without having to re-compile the kernel) > > > > the tested benefits on a PC engines apuc2 is at least 2x performance > > from my lab testing here > > > > I think having a higher install base of consistently complied generic > > kernels with > > pf enabled would be beneficial > > > > what do the more experienced users of OpenBSD think about this? > > > > are there any down sides with this approach ? > > > > Thanks, > > > > Tom Smyth > > -- Kindest regards, Tom Smyth The information contained in this E-mail is intended only for the confidential use of the named recipient. If the reader of this message is not the intended recipient or the person responsible for delivering it to the recipient, you are hereby notified that you have received this communication in error and that any review, dissemination or copying of this communication is strictly prohibited. If you have received this in error, please notify the sender immediately by telephone at the number above and erase the message You are requested to carry out your own virus check before opening any attachment.
Re: Is it worth considering compling a generic MPPF kernel for user convenience
With MPPF it can go away almost ~5x as fast on a 6-core machine. Den tis 2 apr. 2019 kl 13:35 skrev Theo de Raadt : > No, this is not our style, it very much doesn't fit the development > process to have users running prototype code for 6 months. > > And anyways why do you want this, since pf is going away. > > Tom Smyth wrote: > > > I was wondering what devs / more experienced users think about > > having BSDMPPF kernel as an option in the upcoming release > > so that users could opt to test that by selecting alternate BSDMPPF > kernel > > (without having to re-compile the kernel) > > > > the tested benefits on a PC engines apuc2 is at least 2x performance > > from my lab testing here > > > > I think having a higher install base of consistently complied generic > > kernels with > > pf enabled would be beneficial > > > > what do the more experienced users of OpenBSD think about this? > > > > are there any down sides with this approach ? > > > > Thanks, > > > > Tom Smyth > > > > -- May the most significant bit of your life be positive.
Re: Is it worth considering compling a generic MPPF kernel for user convenience
No, this is not our style, it very much doesn't fit the development process to have users running prototype code for 6 months. And anyways why do you want this, since pf is going away. Tom Smyth wrote: > I was wondering what devs / more experienced users think about > having BSDMPPF kernel as an option in the upcoming release > so that users could opt to test that by selecting alternate BSDMPPF kernel > (without having to re-compile the kernel) > > the tested benefits on a PC engines apuc2 is at least 2x performance > from my lab testing here > > I think having a higher install base of consistently complied generic > kernels with > pf enabled would be beneficial > > what do the more experienced users of OpenBSD think about this? > > are there any down sides with this approach ? > > Thanks, > > Tom Smyth >
Is it worth considering compling a generic MPPF kernel for user convenience
Hello, I was wondering what devs / more experienced users think about having BSDMPPF kernel as an option in the upcoming release so that users could opt to test that by selecting alternate BSDMPPF kernel (without having to re-compile the kernel) the tested benefits on a PC engines apuc2 is at least 2x performance from my lab testing here I think having a higher install base of consistently complied generic kernels with pf enabled would be beneficial what do the more experienced users of OpenBSD think about this? are there any down sides with this approach ? Thanks, Tom Smyth