mirror/freebsd
1
0
Fork 0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-25 11:37:56 +00:00
Code Issues Releases Activity
49d3a95692
freebsd/sys/kern/kern_subr.c
Kirk McKusick ad8ac923fa These changes appear to give us benefits with both small (32MB) and 
large (1G) memory machine configurations.  I was able to run 'dbench 32'
on a 32MB system without bring the machine to a grinding halt.

    * buffer cache hash table now dynamically allocated.  This will
      have no effect on memory consumption for smaller systems and
      will help scale the buffer cache for larger systems.

    * minor enhancement to pmap_clearbit().  I noticed that
      all the calls to it used constant arguments.  Making
      it an inline allows the constants to propogate to
      deeper inlines and should produce better code.

    * removal of inherent vfs_ioopt support through the emplacement
      of appropriate #ifdef's, with John's permission.  If we do not
      find a use for it by the end of the year we will remove it entirely.

    * removal of getnewbufloops* counters & sysctl's - no longer
      necessary for debugging, getnewbuf() is now optimal.

    * buffer hash table functions removed from sys/buf.h and localized
      to vfs_bio.c

    * VFS_BIO_NEED_DIRTYFLUSH flag and support code added
      ( bwillwrite() ), allowing processes to block when too many dirty
      buffers are present in the system.

    * removal of a softdep test in bdwrite() that is no longer necessary
      now that bdwrite() no longer attempts to flush dirty buffers.

    * slight optimization added to bqrelse() - there is no reason
      to test for available buffer space on B_DELWRI buffers.

    * addition of reverse-scanning code to vfs_bio_awrite().
      vfs_bio_awrite() will attempt to locate clusterable areas
      in both the forward and reverse direction relative to the
      offset of the buffer passed to it.  This will probably not
      make much of a difference now, but I believe we will start
      to rely on it heavily in the future if we decide to shift
      some of the burden of the clustering closer to the actual
      I/O initiation.

    * Removal of the newbufcnt and lastnewbuf counters that Kirk
      added.  They do not fix any race conditions that haven't already
      been fixed by the gbincore() test done after the only call
      to getnewbuf().  getnewbuf() is a static, so there is no chance
      of it being misused by other modules.  ( Unless Kirk can think
      of a specific thing that this code fixes.  I went through it
      very carefully and didn't see anything ).

    * removal of VOP_ISLOCKED() check in flushbufqueues().  I do not
      think this check is necessary, the buffer should flush properly
      whether the vnode is locked or not. ( yes? ).

    * removal of extra arguments passed to getnewbuf() that are not
      necessary.

    * missed cluster_wbuild() that had to be a cluster_wbuild_wb() in
      vfs_cluster.c

    * vn_write() now calls bwillwrite() *PRIOR* to locking the vnode,
      which should greatly aid flushing operations in heavy load
      situations - both the pageout and update daemons will be able
      to operate more efficiently.

    * removal of b_usecount.  We may add it back in later but for now
      it is useless.  Prior implementations of the buffer cache never
      had enough buffers for it to be useful, and current implementations
      which make more buffers available might not benefit relative to
      the amount of sophistication required to implement a b_usecount.
      Straight LRU should work just as well, especially when most things
      are VMIO backed.  I expect that (even though John will not like
      this assumption) directories will become VMIO backed some point soon.

Submitted by:	Matthew Dillon <dillon@backplane.com>
Reviewed by:	Kirk McKusick <mckusick@mckusick.com>
1999-07-08 06:06:00 +00:00

432 lines
9.4 KiB
C
Raw Blame History

/*
* Copyright (c) 1982, 1986, 1991, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, Inc.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)kern_subr.c 8.3 (Berkeley) 1/21/94
* $Id: kern_subr.c,v 1.28 1999/03/12 03:09:29 julian Exp $
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/proc.h>
#include <sys/malloc.h>
#include <sys/lock.h>
#include <sys/resourcevar.h>
#include <sys/vnode.h>
#include <vm/vm.h>
#include <vm/vm_prot.h>
#include <vm/vm_page.h>
#include <vm/vm_map.h>
static void uio_yield __P((void));
int
uiomove(cp, n, uio)
register caddr_t cp;
register int n;
register struct uio *uio;
{
register struct iovec *iov;
u_int cnt;
int error = 0;
int save = 0;
KASSERT(uio->uio_rw == UIO_READ || uio->uio_rw == UIO_WRITE,
("uiomove: mode"));
KASSERT(uio->uio_segflg != UIO_USERSPACE || uio->uio_procp == curproc,
("uiomove proc"));
if (curproc) {
save = curproc->p_flag & P_DEADLKTREAT;
curproc->p_flag |= P_DEADLKTREAT;
}
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
switch (uio->uio_segflg) {
case UIO_USERSPACE:
case UIO_USERISPACE:
if (ticks - switchticks >= hogticks)
uio_yield();
if (uio->uio_rw == UIO_READ)
error = copyout(cp, iov->iov_base, cnt);
else
error = copyin(iov->iov_base, cp, cnt);
if (error)
break;
break;
case UIO_SYSSPACE:
if (uio->uio_rw == UIO_READ)
bcopy((caddr_t)cp, iov->iov_base, cnt);
else
bcopy(iov->iov_base, (caddr_t)cp, cnt);
break;
case UIO_NOCOPY:
break;
}
iov->iov_base += cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
cp += cnt;
n -= cnt;
}
if (curproc)
curproc->p_flag = (curproc->p_flag & ~P_DEADLKTREAT) | save;
return (error);
}
int
uiomoveco(cp, n, uio, obj)
caddr_t cp;
int n;
struct uio *uio;
struct vm_object *obj;
{
struct iovec *iov;
u_int cnt;
int error;
KASSERT(uio->uio_rw == UIO_READ || uio->uio_rw == UIO_WRITE,
("uiomoveco: mode"));
KASSERT(uio->uio_segflg != UIO_USERSPACE || uio->uio_procp == curproc,
("uiomoveco proc"));
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
switch (uio->uio_segflg) {
case UIO_USERSPACE:
case UIO_USERISPACE:
if (ticks - switchticks >= hogticks)
uio_yield();
if (uio->uio_rw == UIO_READ) {
#ifdef ENABLE_VFS_IOOPT
if (vfs_ioopt && ((cnt & PAGE_MASK) == 0) &&
((((intptr_t) iov->iov_base) & PAGE_MASK) == 0) &&
((uio->uio_offset & PAGE_MASK) == 0) &&
((((intptr_t) cp) & PAGE_MASK) == 0)) {
error = vm_uiomove(&curproc->p_vmspace->vm_map, obj,
uio->uio_offset, cnt,
(vm_offset_t) iov->iov_base, NULL);
} else
#endif
{
error = copyout(cp, iov->iov_base, cnt);
}
} else {
error = copyin(iov->iov_base, cp, cnt);
}
if (error)
return (error);
break;
case UIO_SYSSPACE:
if (uio->uio_rw == UIO_READ)
bcopy((caddr_t)cp, iov->iov_base, cnt);
else
bcopy(iov->iov_base, (caddr_t)cp, cnt);
break;
case UIO_NOCOPY:
break;
}
iov->iov_base += cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
cp += cnt;
n -= cnt;
}
return (0);
}
#ifdef ENABLE_VFS_IOOPT
int
uioread(n, uio, obj, nread)
int n;
struct uio *uio;
struct vm_object *obj;
int *nread;
{
int npagesmoved;
struct iovec *iov;
u_int cnt, tcnt;
int error;
*nread = 0;
if (vfs_ioopt < 2)
return 0;
error = 0;
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
if ((uio->uio_segflg == UIO_USERSPACE) &&
((((intptr_t) iov->iov_base) & PAGE_MASK) == 0) &&
((uio->uio_offset & PAGE_MASK) == 0) ) {
if (cnt < PAGE_SIZE)
break;
cnt &= ~PAGE_MASK;
if (ticks - switchticks >= hogticks)
uio_yield();
error = vm_uiomove(&curproc->p_vmspace->vm_map, obj,
uio->uio_offset, cnt,
(vm_offset_t) iov->iov_base, &npagesmoved);
if (npagesmoved == 0)
break;
tcnt = npagesmoved * PAGE_SIZE;
cnt = tcnt;
if (error)
break;
iov->iov_base += cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
*nread += cnt;
n -= cnt;
} else {
break;
}
}
return error;
}
#endif
/*
* Give next character to user as result of read.
*/
int
ureadc(c, uio)
register int c;
register struct uio *uio;
{
register struct iovec *iov;
again:
if (uio->uio_iovcnt == 0 || uio->uio_resid == 0)
panic("ureadc");
iov = uio->uio_iov;
if (iov->iov_len == 0) {
uio->uio_iovcnt--;
uio->uio_iov++;
goto again;
}
switch (uio->uio_segflg) {
case UIO_USERSPACE:
if (subyte(iov->iov_base, c) < 0)
return (EFAULT);
break;
case UIO_SYSSPACE:
*iov->iov_base = c;
break;
case UIO_USERISPACE:
if (suibyte(iov->iov_base, c) < 0)
return (EFAULT);
break;
case UIO_NOCOPY:
break;
}
iov->iov_base++;
iov->iov_len--;
uio->uio_resid--;
uio->uio_offset++;
return (0);
}
#ifdef vax /* unused except by ct.c, other oddities XXX */
/*
* Get next character written in by user from uio.
*/
int
uwritec(uio)
struct uio *uio;
{
register struct iovec *iov;
register int c;
if (uio->uio_resid <= 0)
return (-1);
again:
if (uio->uio_iovcnt <= 0)
panic("uwritec");
iov = uio->uio_iov;
if (iov->iov_len == 0) {
uio->uio_iov++;
if (--uio->uio_iovcnt == 0)
return (-1);
goto again;
}
switch (uio->uio_segflg) {
case UIO_USERSPACE:
c = fubyte(iov->iov_base);
break;
case UIO_SYSSPACE:
c = *(u_char *) iov->iov_base;
break;
case UIO_USERISPACE:
c = fuibyte(iov->iov_base);
break;
}
if (c < 0)
return (-1);
iov->iov_base++;
iov->iov_len--;
uio->uio_resid--;
uio->uio_offset++;
return (c);
}
#endif /* vax */
/*
* General routine to allocate a hash table.
*/
void *
hashinit(elements, type, hashmask)
int elements;
struct malloc_type *type;
u_long *hashmask;
{
long hashsize;
LIST_HEAD(generic, generic) *hashtbl;
int i;
if (elements <= 0)
panic("hashinit: bad elements");
for (hashsize = 1; hashsize <= elements; hashsize <<= 1)
continue;
hashsize >>= 1;
hashtbl = malloc((u_long)hashsize * sizeof(*hashtbl), type, M_WAITOK);
for (i = 0; i < hashsize; i++)
LIST_INIT(&hashtbl[i]);
*hashmask = hashsize - 1;
return (hashtbl);
}
static int primes[] = { 1, 13, 31, 61, 127, 251, 509, 761, 1021, 1531, 2039,
2557, 3067, 3583, 4093, 4603, 5119, 5623, 6143, 6653,
7159, 7673, 8191, 12281, 16381, 24571, 32749 };
#define NPRIMES (sizeof(primes) / sizeof(primes[0]))
/*
* General routine to allocate a prime number sized hash table.
*/
void *
phashinit(elements, type, nentries)
int elements;
struct malloc_type *type;
u_long *nentries;
{
long hashsize;
LIST_HEAD(generic, generic) *hashtbl;
int i;
if (elements <= 0)
panic("phashinit: bad elements");
for (i = 1, hashsize = primes[1]; hashsize <= elements;) {
i++;
if (i == NPRIMES)
break;
hashsize = primes[i];
}
hashsize = primes[i - 1];
hashtbl = malloc((u_long)hashsize * sizeof(*hashtbl), type, M_WAITOK);
for (i = 0; i < hashsize; i++)
LIST_INIT(&hashtbl[i]);
*nentries = hashsize;
return (hashtbl);
}
static void
uio_yield()
{
struct proc *p;
int s;
p = curproc;
p->p_priority = p->p_usrpri;
s = splhigh();
setrunqueue(p);
p->p_stats->p_ru.ru_nivcsw++;
mi_switch();
splx(s);
}
Reference in New Issue View Git Blame Copy Permalink