into uipc_mbuf.c. This reduces three sets of identical tunable code to
one set, and puts the initialisation with the mbuf code proper.
Make NMBUFs tunable as well.
Move the nmbclusters sysctl here as well.
Move the initialisation of maxsockets from param.c to uipc_socket2.c,
next to its corresponding sysctl.
Use the new tunable macros for the kern.vm.kmem.size tunable (this should have
been in a separate commit, whoops).
print_AMD_info(), L2 internal cache is shown, as are AMD's special CPUID
infos:
CPU: AMD-K6(tm) 3D processor (350.81-MHz 586-class CPU)
Origin = "AuthenticAMD" Id = 0x58c Stepping=12
Features=0x8021bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8,PGE,MMX>
AMD Features=0x808029bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8,SYSCALL,PGE,MMX,3DNow!>
PR: kern/12512
Submitted by: Louis A. Mamakos <louie@TransSys.COM>
frames (or just insane received packet lengths generated due to errors
reading from the NIC's internal buffers). Anything too large to fit
safely into an mbuf cluster buffer is discarded and an error logged.
I have not observed this problem with my own cards, but on user has
reported it and adding the sanity test seems reasonable in any case.
Problem noted and patch provided by: Per Andersson <per@cdg.chalmers.se>
we will never use more memory than this value (if specified), but will always
check memory for validity up to this amount.
Get rid of the speculative_mprobe option; the memory amount can now be
specified by hw.physmem.
QUEUE_AGE, QUEUE_LRU, and QUEUE_EMPTY we instead have QUEUE_CLEAN,
QUEUE_DIRTY, QUEUE_EMPTY, and QUEUE_EMPTYKVA. With this patch clean
and dirty buffers have been separated. Empty buffers with KVM
assignments have been separated from truely empty buffers. getnewbuf()
has been rewritten and now operates in a 100% optimal fashion. That is,
it is able to find precisely the right kind of buffer it needs to
allocate a new buffer, defragment KVM, or to free-up an existing buffer
when the buffer cache is full (which is a steady-state situation for
the buffer cache).
Buffer flushing has been reorganized. Previously buffers were flushed
in the context of whatever process hit the conditions forcing buffer
flushing to occur. This resulted in processes blocking on conditions
unrelated to what they were doing. This also resulted in inappropriate
VFS stacking chains due to multiple processes getting stuck trying to
flush dirty buffers or due to a single process getting into a situation
where it might attempt to flush buffers recursively - a situation that
was only partially fixed in prior commits. We have added a new daemon
called the buf_daemon which is responsible for flushing dirty buffers
when the number of dirty buffers exceeds the vfs.hidirtybuffers limit.
This daemon attempts to dynamically adjust the rate at which dirty buffers
are flushed such that getnewbuf() calls (almost) never block.
The number of nbufs and amount of buffer space is now scaled past the
8MB limit that was previously imposed for systems with over 64MB of
memory, and the vfs.{lo,hi}dirtybuffers limits have been relaxed
somewhat. The number of physical buffers has been increased with the
intention that we will manage physical I/O differently in the future.
reassignbuf previously attempted to keep the dirtyblkhd list sorted which
could result in non-deterministic operation under certain conditions,
such as when a large number of dirty buffers are being managed. This
algorithm has been changed. reassignbuf now keeps buffers locally sorted
if it can do so cheaply, and otherwise gives up and adds buffers to
the head of the dirtyblkhd list. The new algorithm is deterministic but
not perfect. The new algorithm greatly reduces problems that previously
occured when write_behind was turned off in the system.
The P_FLSINPROG proc->p_flag bit has been replaced by the more descriptive
P_BUFEXHAUST bit. This bit allows processes working with filesystem
buffers to use available emergency reserves. Normal processes do not set
this bit and are not allowed to dig into emergency reserves. The purpose
of this bit is to avoid low-memory deadlocks.
A small race condition was fixed in getpbuf() in vm/vm_pager.c.
Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
Reviewed by: Kirk McKusick <mckusick@mckusick.com>
behavior slightly.
If machine/bus.h is included, but neither bus_memio.h nor bus_pio.h
are included, then behave as if both were included.
This won't change existing drivers, all of which include one or more
of bus_{p,mem}io.h, but will allow drivers from other systems to come
over with fewer changes. I freely admit that this might not be
optimal for some drivers, but those drivers can be optimized for
FreeBSD after the initial bringup happens.
Without the change, there is a bug that preclude drivers from
compiling with strange warning/errors.
I've been running this here for a while now w/o ill effects.
Reviewed by: gibbs
Not objected to by: bde, arch@ list.
On the VAX, it used to be used for special compilation to avoid the
optimizer which would mess with memory mapped devices etc. These days
we use 'volatile'.
- The kernel environment variable 'hw.physmem' can be used to set the
amount of physical memory space, based at 0, that FreeBSD will use.
Any memory detected over this limit is ignored. Documentation for
this is available under 'help set tunables' in the loader.
- In the case where system memory size can't be accurately determined,
hw.physmem is used as a best-guess memory size, but speculative
probing will be used to determine actual memory size if any of the
guesses or hints are 16M or more.
- If RB_VERBOSE, we list the memory regions as we test them.
- The compile-time option MAXMEM supplies a default value for
'hw.physmem'.
specified in the kernel config file - but setting options MAXMEM works
exactly the same. Userconfig overrides of this have not worked for
ages.
Also, change the getenv for the loader override to hw.physmem based on a
prior suggestion from Mike Smith. I think he still wants to change this
some, but this shouldn't get in his way. This is a forced setting of
the memory size, not a "cap". We probably should have a plain 'maxmem'
variable as well which does do a cap, without loosing the bios memory
configuration data.
memory size. If somebody wants to change the name, fine - I used this
since it's consistant with the config variable it replaces.
This is intended to replace the npx0 msize hack (which no longer works).
SYSINIT_KT() etc (which is a static, compile-time procedure), use a
NetBSD-style kthread_create() interface. kproc_start is still available
as a SYSINIT() hook. This allowed simplification of chunks of the
sysinit code in the process. This kthread_create() is our old kproc_start
internals, with the SYSINIT_KT fork hooks grafted in and tweaked to work
the same as the NetBSD one.
One thing I'd like to do shortly is get rid of nfsiod as a user initiated
process. It makes sense for the nfs client code to create them on the
fly as needed up to a user settable limit. This means that nfsiod
doesn't need to be in /sbin and is always "available". This is a fair bit
easier to do outside of the SYSINIT_KT() framework.
surrounding critical sections that consist of (1) a single read or
(2) a single locked RMW operation.
(Thanks to thomma@slip.net (Tamiji Homma) for helping to test
these changes.)
- Do not try to allocate a keyboard in pccnprobe() when probing the vt
driver for the kernel console. Rather, allocate a keyboard when
initializing the vt driver in pccninit().
- Release the keyboard in pccnterm().
- Don't try to read from the keyboard, if it is not present.
