On 5 Jul, Georg-W. Koltermann wrote:
> Am Mi, 2002-07-03 um 17.31 schrieb David O'Brien:
>> On a 27-June-2002 23:02:00 UTC system (just before ipfw2 went in,
>> pre-KSE3), dump will not complete dumping more than 5GB. At that point
>> it stops responding properly to ^T, which should give "DUMP: 47.52% done,
>> finished in 1:19". At the 5GB mark, ^T gives:
>>
>> load: 0.00 cmd: dump 3981 [physstr] 2.11u 43.06s 0% 1536k
>>
>> and never changes. The user and system times never advance. Anybody
>> have any ideas?
>
> For me it is broken in a different way. For a small FS like / it works,
> but dumping my /home, which is 4G, I get
>
> DUMP: read error from /dev/ad0s5e: Invalid argument: [sector -1054739789]:
>count=-1
> DUMP: read error from /dev/ad0s5e: Invalid argument: [sector -1054739788]:
>count=-1
> DUMP: read error from /dev/ad0s5e: Invalid argument: [sector -1054739787]:
>count=-1
> DUMP: read error from /dev/ad0s5e: Invalid argument: [sector -1054739786]:
>count=-1
>
> and on and on.
>
> Maybe a 32 bit <--> 64 bit mismatch caused by UFS2? My -current is of
> date=2002.06.27.22.00.00.
I was finally finally able to reproduce this by creating a large file
before doing the dump. Dump(8) is *very* hosed. The UFS2 import broke
it's ability to follow multiple levels of indirect blocks.
Here's a patch that fixed the problem along with a bunch of print format
mismatches:
Index: tape.c
===================================================================
RCS file: /home/ncvs/src/sbin/dump/tape.c,v
retrieving revision 1.20
diff -u -r1.20 tape.c
--- tape.c 21 Jun 2002 06:17:57 -0000 1.20
+++ tape.c 7 Jul 2002 03:56:31 -0000
@@ -204,7 +204,7 @@
quit("Cannot recover\n");
/* NOTREACHED */
}
- msg("write error %d blocks into volume %d\n", blocksthisvol, tapeno);
+ msg("write error %ld blocks into volume %d\n", blocksthisvol, tapeno);
broadcast("DUMP WRITE ERROR!\n");
if (!query("Do you want to restart?"))
dumpabort(0);
Index: traverse.c
===================================================================
RCS file: /home/ncvs/src/sbin/dump/traverse.c,v
retrieving revision 1.19
diff -u -r1.19 traverse.c
--- traverse.c 21 Jun 2002 06:17:57 -0000 1.19
+++ traverse.c 7 Jul 2002 04:24:14 -0000
@@ -275,9 +275,9 @@
{
int ret = 0;
int i;
- static caddr_t idblk;
+ caddr_t idblk;
- if (idblk == NULL && (idblk = malloc(sblock->fs_bsize)) == NULL)
+ if ((idblk = malloc(sblock->fs_bsize)) == NULL)
quit("dirindir: cannot allocate indirect memory.\n");
bread(fsbtodb(sblock, blkno), idblk, (int)sblock->fs_bsize);
if (ind_level <= 0) {
@@ -294,6 +294,7 @@
else
*filesize -= sblock->fs_bsize;
}
+ free(idblk);
return (ret);
}
ind_level--;
@@ -306,6 +307,7 @@
ret |= dirindir(ino, blkno, ind_level, filesize,
tapesize, nodump);
}
+ free(idblk);
return (ret);
}
@@ -501,9 +503,9 @@
dmpindir(ino_t ino, ufs2_daddr_t blk, int ind_level, off_t *size)
{
int i, cnt;
- static caddr_t idblk;
+ caddr_t idblk;
- if (idblk == NULL && (idblk = malloc(sblock->fs_bsize)) == NULL)
+ if ((idblk = malloc(sblock->fs_bsize)) == NULL)
quit("dmpindir: cannot allocate indirect memory.\n");
if (blk != 0)
bread(fsbtodb(sblock, blk), idblk, (int) sblock->fs_bsize);
@@ -519,6 +521,7 @@
ufs1_blksout((ufs1_daddr_t *)idblk, cnt, ino);
else
ufs2_blksout((ufs2_daddr_t *)idblk, cnt, ino);
+ free(idblk);
return;
}
ind_level--;
@@ -529,9 +532,12 @@
else
dmpindir(ino, ((ufs2_daddr_t *)idblk)[i], ind_level,
size);
- if (*size <= 0)
+ if (*size <= 0) {
+ free(idblk);
return;
+ }
}
+ free(idblk);
}
/*
@@ -705,13 +711,13 @@
goto loop;
}
if (cnt == -1)
- msg("read error from %s: %s: [block %d]: count=%d\n",
+ msg("read error from %s: %s: [block %qd]: count=%d\n",
disk, strerror(errno), blkno, size);
else
- msg("short read error from %s: [block %d]: count=%d, got=%d\n",
+ msg("short read error from %s: [block %qd]: count=%d, got=%d\n",
disk, blkno, size, cnt);
if (++breaderrors > BREADEMAX) {
- msg("More than %d block read errors from %d\n",
+ msg("More than %d block read errors from %s\n",
BREADEMAX, disk);
broadcast("DUMP IS AILING!\n");
msg("This is an unrecoverable error.\n");
@@ -730,11 +736,11 @@
((off_t)blkno << dev_bshift))) == dev_bsize)
continue;
if (cnt == -1) {
- msg("read error from %s: %s: [sector %d]: count=%d\n",
+ msg("read error from %s: %s: [sector %qd]: count=%d\n",
disk, strerror(errno), blkno, dev_bsize);
continue;
}
- msg("short read error from %s: [sector %d]: count=%d, got=%d\n",
+ msg("short read error from %s: [sector %qd]: count=%d, got=%d\n",
disk, blkno, dev_bsize, cnt);
}
}
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message
