вс, 11 мая 2025 г., 18:03 Paul Goyette :
> You're asking for a lot, and I am not prepared to spend the time it
> would require. I have already updated x86/boot(8) and added a Xr
> for mk.conf(5), and if someone wants to write a wiki page I will
> happily review/edit it. wiz@ has already created
You're asking for a lot, and I am not prepared to spend the time it
would require. I have already updated x86/boot(8) and added a Xr
for mk.conf(5), and if someone wants to write a wiki page I will
happily review/edit it. wiz@ has already created a wiki page (see
https://wiki.netbsd.org/kernel_d
> Date: Sun, 11 May 2025 06:39:42 -0700 (PDT)
> From: Paul Goyette
>
> On Sun, 11 May 2025, Greg Troxel wrote:
>
> > Thus I suspect I am missing something.
>
> Yup, I think you're missing the fact that all of this relates to the
> ratther new-ish KERNEL_DIR option, support for which was only re
On Sun, 11 May 2025, Greg Troxel wrote:
Paul Goyette writes:
Yup, I think you're missing the fact that all of this relates to the
ratther new-ish KERNEL_DIR option, support for which was only recently
completed (by myself). KERNEL_DIR is described briefly in options(4),
and it is noted in bo
Paul Goyette writes:
>> Yup, I think you're missing the fact that all of this relates to the
>> ratther new-ish KERNEL_DIR option, support for which was only recently
>> completed (by myself). KERNEL_DIR is described briefly in options(4),
>> and it is noted in both CHANGES and UPDATING.
>
> Cor
On Sun, 11 May 2025, Paul Goyette wrote:
On Sun, 11 May 2025, Greg Troxel wrote:
Paul Goyette writes:
With the recent changes, specifying /onetbsd will only look for a
kernel in /onetbsd and /onetbsd.gz (both being regular files); it
will not look in /onetbsd/kernel or /onetbsd/kernel.gz a
On Sun, 11 May 2025, Greg Troxel wrote:
Paul Goyette writes:
With the recent changes, specifying /onetbsd will only look for a
kernel in /onetbsd and /onetbsd.gz (both being regular files); it
will not look in /onetbsd/kernel or /onetbsd/kernel.gz as might be
expected.
If one is accustomed
Paul Goyette writes:
> With the recent changes, specifying /onetbsd will only look for a
> kernel in /onetbsd and /onetbsd.gz (both being regular files); it
> will not look in /onetbsd/kernel or /onetbsd/kernel.gz as might be
> expected.
>
> If one is accustomed to booting with the leading slash
e...@math.uni-bonn.de (Edgar =?iso-8859-1?B?RnXf?=) writes:
>For instance, when reconstructing (I manually failed a component to test
>this), top shows the "system" process to use 80-90% of CPU time, so I guess
>the EXORing done during reconstruction is attributed to the kernel. But
>during nor
> With a smaller stdio buffer, you do more read/write syscalls and add more
> overhead.
Ah yes, I see, thanks.
> The [time spent] in a syscall is attributed to the process. But the
> actual I/O is often deferred to kernel threads and handled in
> interrupts. Interrupt time is not accounted to user
This patch https://imil.net/NetBSD/tslog.patch is a port of FreeBSD's
tslog(4) which permits to ease pinpointing parts of the kernel and
userland where the most time is spent.
This tracing facility is what allowed to reduce NetBSD kernel boot
time as it gives the ability to produce flamegraphs
11 matches
Mail list logo
