9c7f8050f4
Kernel: * Add runtime quantity lfs_ravail, the number of disk-blocks reserved for writing. Writes to the filesystem first reserve a maximum amount of blocks before their write is allowed to proceed; after the blocks are allocated the reserved total is reduced by a corresponding amount. If the lfs_reserve function cannot immediately reserve the requested number of blocks, the inode is unlocked, and the thread sleeps until the cleaner has made enough space available for the blocks to be reserved. In this way large files can be written to the filesystem (or, smaller files can be written to a nearly-full but thoroughly clean filesystem) and the cleaner can still function properly. * Remove explicit switching on dlfs_minfreeseg from the kernel code; it is now merely a fs-creation parameter used to compute dlfs_avail and dlfs_bfree (and used by fsck_lfs(8) to check their accuracy). Its former role is better assumed by a properly computed dlfs_avail. * Bounds-check inode numbers submitted through lfs_bmapv and lfs_markv. This prevents a panic, but, if the cleaner is feeding the filesystem the wrong data, you are still in a world of hurt. * Cleanup: remove explicit references of DEV_BSIZE in favor of btodb()/dbtob(). lfs_cleanerd: * Make -n mean "send N segments' blocks through a single call to lfs_markv". Previously it had meant "clean N segments though N calls to lfs_markv, before looking again to see if more need to be cleaned". The new behavior gives better packing of direct data on disk with as little metadata as possible, largely alleviating the problem that the cleaner can consume more disk through inefficient use of metadata than it frees by moving dirty data away from clean "holes" to produce entirely clean segments. * Make -b mean "read as many segments as necessary to write N segments of dirty data back to disk", rather than its former meaning of "read as many segments as necessary to free N segments worth of space". The new meaning, combined with the new -n behavior described above, further aids in cleaning storage efficiency as entire segments can be written at once, using as few blocks as possible for segment summaries and inode blocks. * Make the cleaner take note of segments which could not be cleaned due to error, and not attempt to clean them until they are entirely free of dirty blocks. This prevents the case in which a cleanerd running with -n 1 and without -b (formerly the default) would spin trying repeatedly to clean a corrupt segment, while the remaining space filled and deadlocked the filesystem. * Update the lfs_cleanerd manual page to describe all the options, including the changes mentioned here (in particular, the -b and -n flags were previously undocumented). fsck_lfs: * Check, and optionally fix, lfs_avail (to an exact figure) and lfs_bfree (within a margin of error) in pass 5. newfs_lfs: * Reduce the default dlfs_minfreeseg to 1/20 of the total segments. * Add a warning if the sgs disklabel field is 16 (the default for FFS' cpg, but not usually desirable for LFS' sgs: 5--8 is a better range). * Change the calculation of lfs_avail and lfs_bfree, corresponding to the kernel changes mentioned above. mount_lfs: * Add -N and -b options to pass corresponding -n and -b options to lfs_cleanerd. * Default to calling lfs_cleanerd with "-b -n 4". [All of these changes were largely tested in the 1.5 branch, with the idea that they (along with previous un-pulled-up work) could be applied to the branch while it was still in ALPHA2; however my test system has experienced corruption on another filesystem (/dev/console has gone missing :^), and, while I believe this unrelated to the LFS changes, I cannot with good conscience request that the changes be pulled up.]
286 lines
8.9 KiB
C
286 lines
8.9 KiB
C
/* $NetBSD: lfs_subr.c,v 1.17 2000/09/09 04:49:55 perseant Exp $ */
|
|
|
|
/*-
|
|
* Copyright (c) 1999, 2000 The NetBSD Foundation, Inc.
|
|
* All rights reserved.
|
|
*
|
|
* This code is derived from software contributed to The NetBSD Foundation
|
|
* by Konrad E. Schroder <perseant@hhhh.org>.
|
|
*
|
|
* 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 NetBSD
|
|
* Foundation, Inc. and its contributors.
|
|
* 4. Neither the name of The NetBSD Foundation 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 NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
|
|
*/
|
|
/*
|
|
* Copyright (c) 1991, 1993
|
|
* The Regents of the University of California. All rights reserved.
|
|
*
|
|
* 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.
|
|
*
|
|
* @(#)lfs_subr.c 8.4 (Berkeley) 5/8/95
|
|
*/
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/namei.h>
|
|
#include <sys/vnode.h>
|
|
#include <sys/buf.h>
|
|
#include <sys/mount.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/proc.h>
|
|
|
|
#include <ufs/ufs/quota.h>
|
|
#include <ufs/ufs/inode.h>
|
|
#include <ufs/lfs/lfs.h>
|
|
#include <ufs/lfs/lfs_extern.h>
|
|
|
|
/*
|
|
* Return buffer with the contents of block "offset" from the beginning of
|
|
* directory "ip". If "res" is non-zero, fill it in with a pointer to the
|
|
* remaining space in the directory.
|
|
*/
|
|
int
|
|
lfs_blkatoff(v)
|
|
void *v;
|
|
{
|
|
struct vop_blkatoff_args /* {
|
|
struct vnode *a_vp;
|
|
off_t a_offset;
|
|
char **a_res;
|
|
struct buf **a_bpp;
|
|
} */ *ap = v;
|
|
struct lfs *fs;
|
|
struct inode *ip;
|
|
struct buf *bp;
|
|
ufs_daddr_t lbn;
|
|
int bsize, error;
|
|
|
|
ip = VTOI(ap->a_vp);
|
|
fs = ip->i_lfs;
|
|
lbn = lblkno(fs, ap->a_offset);
|
|
bsize = blksize(fs, ip, lbn);
|
|
|
|
*ap->a_bpp = NULL;
|
|
if ((error = bread(ap->a_vp, lbn, bsize, NOCRED, &bp)) != 0) {
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
if (ap->a_res)
|
|
*ap->a_res = (char *)bp->b_data + blkoff(fs, ap->a_offset);
|
|
*ap->a_bpp = bp;
|
|
return (0);
|
|
}
|
|
|
|
|
|
/*
|
|
* lfs_seglock --
|
|
* Single thread the segment writer.
|
|
*/
|
|
void
|
|
lfs_seglock(fs, flags)
|
|
struct lfs *fs;
|
|
unsigned long flags;
|
|
{
|
|
struct segment *sp;
|
|
int s;
|
|
|
|
if (fs->lfs_seglock) {
|
|
if (fs->lfs_lockpid == curproc->p_pid) {
|
|
++fs->lfs_seglock;
|
|
fs->lfs_sp->seg_flags |= flags;
|
|
return;
|
|
} else while (fs->lfs_seglock)
|
|
(void)tsleep(&fs->lfs_seglock, PRIBIO + 1,
|
|
"lfs seglock", 0);
|
|
}
|
|
|
|
fs->lfs_seglock = 1;
|
|
fs->lfs_lockpid = curproc->p_pid;
|
|
|
|
sp = fs->lfs_sp = malloc(sizeof(struct segment), M_SEGMENT, M_WAITOK);
|
|
sp->bpp = malloc(((LFS_SUMMARY_SIZE - sizeof(SEGSUM)) /
|
|
sizeof(ufs_daddr_t) + 1) * sizeof(struct buf *),
|
|
M_SEGMENT, M_WAITOK);
|
|
sp->seg_flags = flags;
|
|
sp->vp = NULL;
|
|
(void) lfs_initseg(fs);
|
|
|
|
/*
|
|
* Keep a cumulative count of the outstanding I/O operations. If the
|
|
* disk drive catches up with us it could go to zero before we finish,
|
|
* so we artificially increment it by one until we've scheduled all of
|
|
* the writes we intend to do.
|
|
*/
|
|
s = splbio();
|
|
++fs->lfs_iocount;
|
|
splx(s);
|
|
}
|
|
|
|
/*
|
|
* lfs_segunlock --
|
|
* Single thread the segment writer.
|
|
*/
|
|
void
|
|
lfs_segunlock(fs)
|
|
struct lfs *fs;
|
|
{
|
|
struct segment *sp;
|
|
unsigned long sync, ckp;
|
|
int s;
|
|
struct vnode *vp;
|
|
struct mount *mp;
|
|
extern int lfs_dirvcount;
|
|
|
|
sp = fs->lfs_sp;
|
|
|
|
if (fs->lfs_seglock == 1 && !(sp->seg_flags & SEGM_PROT)) {
|
|
|
|
mp = fs->lfs_ivnode->v_mount;
|
|
/*
|
|
* Go through and unmark all DIROP vnodes, possibly
|
|
* calling VOP_INACTIVE (through vrele). This is
|
|
* delayed until now in order not to accidentally
|
|
* write a DIROP node through lfs_flush.
|
|
*/
|
|
#ifndef LFS_NO_BACKVP_HACK
|
|
/* BEGIN HACK */
|
|
#define VN_OFFSET (((caddr_t)&vp->v_mntvnodes.le_next) - (caddr_t)vp)
|
|
#define BACK_VP(VP) ((struct vnode *)(((caddr_t)VP->v_mntvnodes.le_prev) - VN_OFFSET))
|
|
#define BEG_OF_VLIST ((struct vnode *)(((caddr_t)&mp->mnt_vnodelist.lh_first) - VN_OFFSET))
|
|
|
|
/* Find last vnode. */
|
|
loop: for (vp = mp->mnt_vnodelist.lh_first;
|
|
vp && vp->v_mntvnodes.le_next != NULL;
|
|
vp = vp->v_mntvnodes.le_next);
|
|
for (; vp && vp != BEG_OF_VLIST; vp = BACK_VP(vp)) {
|
|
#else
|
|
loop:
|
|
for (vp = mp->mnt_vnodelist.lh_first;
|
|
vp != NULL;
|
|
vp = vp->v_mntvnodes.le_next) {
|
|
#endif
|
|
if (vp->v_mount != mp)
|
|
goto loop;
|
|
if (vp->v_type == VNON)
|
|
continue;
|
|
if (lfs_vref(vp))
|
|
continue;
|
|
if (VOP_ISLOCKED(vp) &&
|
|
vp->v_lock.lk_lockholder != curproc->p_pid) {
|
|
lfs_vunref(vp);
|
|
continue;
|
|
}
|
|
if ((vp->v_flag & VDIROP) &&
|
|
!(VTOI(vp)->i_flag & IN_ADIROP)) {
|
|
--lfs_dirvcount;
|
|
vp->v_flag &= ~VDIROP;
|
|
wakeup(&lfs_dirvcount);
|
|
fs->lfs_unlockvp = vp;
|
|
lfs_vunref(vp);
|
|
vrele(vp);
|
|
fs->lfs_unlockvp = NULL;
|
|
} else {
|
|
lfs_vunref(vp);
|
|
}
|
|
}
|
|
}
|
|
|
|
if (fs->lfs_seglock == 1) {
|
|
sync = sp->seg_flags & SEGM_SYNC;
|
|
ckp = sp->seg_flags & SEGM_CKP;
|
|
if (sp->bpp != sp->cbpp) {
|
|
/* Free allocated segment summary */
|
|
fs->lfs_offset -= btodb(LFS_SUMMARY_SIZE);
|
|
lfs_freebuf(*sp->bpp);
|
|
} else
|
|
printf ("unlock to 0 with no summary");
|
|
|
|
free(sp->bpp, M_SEGMENT);
|
|
free(sp, M_SEGMENT);
|
|
|
|
/*
|
|
* If the I/O count is non-zero, sleep until it reaches zero.
|
|
* At the moment, the user's process hangs around so we can
|
|
* sleep.
|
|
*/
|
|
s = splbio();
|
|
--fs->lfs_iocount;
|
|
/*
|
|
* We let checkpoints happen asynchronously. That means
|
|
* that during recovery, we have to roll forward between
|
|
* the two segments described by the first and second
|
|
* superblocks to make sure that the checkpoint described
|
|
* by a superblock completed.
|
|
*/
|
|
while (sync && fs->lfs_iocount)
|
|
(void)tsleep(&fs->lfs_iocount, PRIBIO + 1,
|
|
"lfs vflush", 0);
|
|
splx(s);
|
|
if (ckp) {
|
|
fs->lfs_nactive = 0;
|
|
/* If we *know* everything's on disk, write both sbs */
|
|
if(sync)
|
|
lfs_writesuper(fs,fs->lfs_sboffs[fs->lfs_activesb]);
|
|
fs->lfs_activesb = 1 - fs->lfs_activesb;
|
|
lfs_writesuper(fs,fs->lfs_sboffs[fs->lfs_activesb]);
|
|
}
|
|
--fs->lfs_seglock;
|
|
fs->lfs_lockpid = 0;
|
|
wakeup(&fs->lfs_seglock);
|
|
} else if (fs->lfs_seglock == 0) {
|
|
panic ("Seglock not held");
|
|
} else {
|
|
--fs->lfs_seglock;
|
|
}
|
|
}
|