Just to recap, the system is running but cannot fork anymore procs.  This
means I can't login.  Cron does a make -j3 buildworld each night and it
appears this is triggering it.  Sys is uniprocessor.  Please let me know
if you need more info.

db> ps
  pid   proc     addr    uid  ppid  pgrp  flag   stat  wmesg    wchan  cmd
66984 c24efa80 cddf7000    0     1     1 8000000 norm[SLPQ  thrd_sleep
c0b740b4][SLP] init
66983 c24efc40 cddf8000    2 66982 66983 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66982 c24efe00 cddf9000    0   420   420 0000000 norm[SLPQ  ppwait
c24efe00][SLP] cron
66981 c24d5e00 cdca7000    2 66980 66981 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66980 c24d5c40 cdca6000    0   420   420 0000000 norm[SLPQ  ppwait
c24d5c40][SLP] cron
66979 c24d6000 cdca8000    2 66978 66979 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66978 c24c3540 cdb4a000    0   420   420 0000000 norm[SLPQ  ppwait
c24c3540][SLP] cron
66977 c24c3700 cdb4b000    2 66976 66977 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66976 c24c38c0 cdb4c000    0   420   420 0000000 norm[SLPQ  ppwait
c24c38c0][SLP] cron
66975 c24c3a80 cdb4d000    2 66973 66975 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66974 c24c3c40 cdb4e000    0 66972 66974 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66973 c24c3e00 cdb4f000    0   420   420 0000000 norm[SLPQ  ppwait
c24c3e00][SLP] cron
66972 c24d1000 cdc24000    0   420   420 0000000 norm[SLPQ  ppwait
c24d1000][SLP] cron
66971 c24d11c0 cdc25000    2 66970 66971 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66970 c24d1380 cdc98000    0   420   420 0000000 norm[SLPQ  ppwait
c24d1380][SLP] cron
66969 c24d1540 cdc99000    2 66968 66969 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66968 c24d1700 cdc9a000    0   420   420 0000000 norm[SLPQ  ppwait
c24d1700][SLP] cron
66967 c24d18c0 cdc9b000    2 66966 66967 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66966 c24d1a80 cdc9c000    0   420   420 0000000 norm[SLPQ  ppwait
c24d1a80][SLP] cron
66965 c24d1c40 cdc9d000    2 66964 66965 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
[... more pages of the same ...]
66780 c1a21000 cd37d000    0   420   420 0000000 norm[SLPQ  ppwait
c1a21000][SLP] cron
66779 c1a2cc40 cd2f8000    2 66778 66779 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66778 c1b62e00 cd3c7000    0   420   420 0000000 norm[SLPQ  ppwait
c1b62e00][SLP] cron
66777 c1a2c380 cd2f3000    2 66776 66777 8000110 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cron
66776 c19d1700 cd334000    0   420   420 0000000 norm[SLPQ  ppwait
c19d1700][SLP] cron
66775 c1e62c40 cd45e000    0 66768  1431 0004000 norm[SLPQ  thrd_sleep
c0b740b4][SLP] as
66774 c1a21a80 cd3bc000    0 66768  1431 8000000 norm[SLPQ     ufs
c226168c][SLP] cc
66773 c19cda80 cd319000    0 66769  1431 0004000 norm[SLPQ     ufs
c220d1ec][SLP] as
66772 c19d1380 cd332000    0 66769  1431 0004000 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cc1
66771 c1a2ca80 cd2f7000    0 66767  1431 8000000 norm[SLPQ  thrd_sleep
c0b740b4][SLP] cc
66770 c19cd8c0 cd318000    0 66767  1431 0004000 norm[SLPQ     ufs
c226168c][SLP] cc1
66769 c19271c0 cce49000    0 66766  1431 0004000 norm[SLPQ    wait
c19271c0][SLP] cc
66768 c1a2ce00 cd2f9000    0 66764  1431 0004000 norm[SLPQ    wait
c1a2ce00][SLP] cc
66767 c19d1540 cd333000    0 66765  1431 0004000 norm[SLPQ    wait
c19d1540][SLP] cc
66766 c1b62000 cd3bf000    0 66763  1431 0004000 norm[SLPQ    wait
c1b62000][SLP] sh
66765 c1e62e00 cd45f000    0 66763  1431 0004000 norm[SLPQ    wait
c1e62e00][SLP] sh
66764 c1a21c40 cd3bd000    0 66763  1431 0004000 norm[SLPQ    wait
c1a21c40][SLP] sh
66763 c1e62540 cd45a000    0 42503  1431 0004000 norm[CVQ  select
c03c4fc4][SLP] make
42503 c19d18c0 cd335000    0 42502  1431 0004000 norm[SLPQ    wait
c19d18c0][SLP] sh
42502 c1b621c0 cd3c0000    0 37343  1431 0004000 norm[CVQ  select
c03c4fc4][SLP] make
37343 c1927380 cce4a000    0 37337  1431 0004000 norm[SLPQ    wait
c1927380][SLP][SWAP] sh
37337 c19d1c40 cd337000    0 17464  1431 0004000 norm[CVQ  select
c03c4fc4][SLP] make
17464 c19cd700 cd317000    0 17459  1431 0004000 norm[SLPQ    wait
c19cd700][SLP][SWAP] sh
17459 c19cd380 cd309000    0 17458  1431 0004000 norm[CVQ  select
c03c4fc4][SLP]
17458 c1a21e00 cd3be000    0  1451  1431 0004000 norm[SLPQ    wait
c1a21e00][SLP][SWAP] sh
 1451 c19cd1c0 cd308000    0  1450  1431 0004000 norm[CVQ  select
c03c4fc4][SLP] make
 1450 c19d11c0 cd329000    0  1436  1431 0004000 norm[SLPQ    wait
c19d11c0][SLP][SWAP] sh
 1436 c19d1000 cd328000    0  1433  1431 0004000 norm[CVQ  select
c03c4fc4][SLP] make
 1433 c1a2c540 cd2f4000    0  1431  1431 0004000 norm[SLPQ    wait
c1a2c540][SLP][SWAP] sh
 1431 c1924380 cce08000    0  1429  1431 0004000 norm[SLPQ    wait
c1924380][SLP][SWAP] sh
 1429 c19cde00 cd327000    0   420   420 0000000 norm[SLPQ  piperd
c18aaa50][SLP] cron
  420 c19241c0 cce07000    0     1   420 0000000 norm[SLPQ  nanslp
c03f9bd4][SLP] cron

db> tr 66770
mi_switch(c1a2d410,50,c037b496,cc,1) at mi_switch+0x1e1
msleep(c226168c,c03f8010,50,c038b03e,0) at msleep+0x453
acquire(c226168c,1000040,700,101,104d2) at acquire+0xa7
lockmgr(c226168c,1030041,c22615c8,c1a2d410,cd2cab34) at lockmgr+0x16d
vop_stdlock(cd2cab50,cd2cab70,c028902b,cd2cab50,c0382bd2) at
vop_stdlock+0x2c
ufs_vnoperate(cd2cab50,c0382bd2,815,cd2cab70,c0220731) at
ufs_vnoperate+0x18
vn_lock(c22615c8,1030041,c1a2d410,815,18b) at vn_lock+0xeb
vget(c22615c8,1020041,c1a2d410,432,18b) at vget+0xd6
vnode_pager_lock(c1f5e5b0,8230000,1,cd2cac60,cd2cac50) at
vnode_pager_lock+0x95
vm_fault(c19c4b28,8230000,1,0,c1a2d410) at vm_fault+0x2cb
trap_pfault(cd2cad48,1,8230ab0,299,8230ab0) at trap_pfault+0xef
trap(2f,2f,2f,bfbff664,2d) at trap+0x287
calltrap() at calltrap+0x5
--- trap 0xc, eip = 0x8230ab0, esp = 0xbfbff640, ebp = 0xbfbff65c ---

db> tr 66984
mi_switch(c24eba90,44,c037b496,cc,cdda6a38) at mi_switch+0x1e1
msleep(c0b740b4,c03f7928,44,c038c5d9,0) at msleep+0x453
acquire(c0b740b4,1000000,600,e3,105a8) at acquire+0xa7
lockmgr(c0b740b4,2,0,c24eba90,246) at lockmgr+0x378
_vm_map_lock(c0b74078,c038c47c,1d0,c02207e0,c24efae8) at _vm_map_lock+0x5b
kmem_alloc_wait(c0b74078,11000,c03784b8,cb,c03fa420) at
kmem_alloc_wait+0x38
kern_execve(c24eba90,80a188d,bfbffca0,bfbffe04,0) at kern_execve+0x1de
execve(c24eba90,cdda6d10,c039575a,409,3) at execve+0x30
syscall(2f,2f,2f,bfbffdf8,0) at syscall+0x28e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (59, FreeBSD ELF32, execve), eip = 0x80524af, esp =
0xbfbffbbc, ebp = 0xbfbffbd8 ---

db> tr 66983
mi_switch(c24eb9c0,44,c037b496,cc,c03fc118) at mi_switch+0x1e1
msleep(c0b740b4,c03f7928,44,c038c5d9,0) at msleep+0x453
acquire(c0b740b4,1000000,600,e3,105a7) at acquire+0xa7
lockmgr(c0b740b4,2,0,c24eb9c0,246) at lockmgr+0x378
_vm_map_lock(c0b74078,c038c47c,1d0,c02207e0,c24efca8) at _vm_map_lock+0x5b
kmem_alloc_wait(c0b74078,11000,c03784b8,cb,0) at kmem_alloc_wait+0x38
kern_execve(c24eb9c0,80590c6,bfbff6ec,8052160,0) at kern_execve+0x1de
execve(c24eb9c0,cdda3d10,c039575a,409,3) at execve+0x30
syscall(2f,2f,2f,805213a,bfbff6ec) at syscall+0x28e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (59, FreeBSD ELF32, execve), eip = 0x280c1343, esp =
0xbfbff6dc, ebp = 0xbfbff708 ---

db> tr 66982
mi_switch(c24eb8f0,5c,c037b496,cc,c24f21b0) at mi_switch+0x1e1
msleep(c24efe00,c24efca8,5c,c0378708,0) at msleep+0x453
fork1(c24eb8f0,80000034,0,cdda0cd4,c24efe68) at fork1+0x11bb
vfork(c24eb8f0,cdda0d10,c039575a,409,0) at vfork+0x52
syscall(2f,2f,2f,0,8052040) at syscall+0x28e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (66, FreeBSD ELF32, vfork), eip = 0x2809e52c, esp =
0xbfbff710, ebp = 0xbfbffcd8 ---

db> tr 66981
mi_switch(c24d28f0,44,c037b496,cc,c03fc118) at mi_switch+0x1e1
msleep(c0b740b4,c03f7928,44,c038c5d9,0) at msleep+0x453
acquire(c0b740b4,1000000,600,e3,105a5) at acquire+0xa7
lockmgr(c0b740b4,2,0,c24d28f0,246) at lockmgr+0x378
_vm_map_lock(c0b74078,c038c47c,1d0,c02207e0,c24d5e68) at _vm_map_lock+0x5b
kmem_alloc_wait(c0b74078,11000,c03784b8,cb,0) at kmem_alloc_wait+0x38
kern_execve(c24d28f0,80590c6,bfbff6ec,8052160,0) at kern_execve+0x1de
execve(c24d28f0,cdc49d10,c039575a,409,3) at execve+0x30
syscall(2f,2f,2f,805213a,bfbff6ec) at syscall+0x28e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (59, FreeBSD ELF32, execve), eip = 0x280c1343, esp =
0xbfbff6dc, ebp = 0xbfbff708 ---

db> tr 66980
mi_switch(c24d29c0,5c,c037b496,cc,c24d4360) at mi_switch+0x1e1
msleep(c24d5c40,c24d5e68,5c,c0378708,0) at msleep+0x453
fork1(c24d29c0,80000034,0,cdc4ccd4,c24d5ca8) at fork1+0x11bb
vfork(c24d29c0,cdc4cd10,c039575a,409,0) at vfork+0x52
syscall(2f,2f,2f,0,8052040) at syscall+0x28e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (66, FreeBSD ELF32, vfork), eip = 0x2809e52c, esp =
0xbfbff710, ebp = 0xbfbffcd8 ---

db> tr 66772
mi_switch(c1926750,44,c037b496,cc,c03fc208) at mi_switch+0x1e1
msleep(c0b740b4,c03f7928,44,c038c5d9,0) at msleep+0x453
acquire(c0b740b4,1000000,600,e3,104d4) at acquire+0xa7
lockmgr(c0b740b4,2,0,c1926750,c1926750) at lockmgr+0x378
_vm_map_lock(c0b74078,c038c47c,1ed,c1b95800,c1926750) at _vm_map_lock+0x5b
kmem_free_wakeup(c0b74078,c7f0a000,11000,0,0) at kmem_free_wakeup+0x2a
kern_execve(c1926750,806b300,8073400,8070300,0) at kern_execve+0xd57
execve(c1926750,cce29d10,c039575a,409,3) at execve+0x30
syscall(2f,2f,2f,0,0) at syscall+0x28e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (0, FreeBSD ELF32, nosys), eip = 0x80480c0, esp = 0xbfbff630,
ebp = 0 ---


To me, it looks like 66772 (in kmem_free_wakeup/vm_map_lock()) and the
others (in kmem_alloc_wait/vm_map_lock()) are the problem.  But I have no
idea who has the lock.  "show locks" just shows Giant locked by the intr
handler for ddb.

I can leave the box in ddb for a while if anyone needs more info.

-Nate


To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message

Reply via email to