5.1 PAE testing results: 2 panics
Cagle, John (ISS-Houston)
john.cagle at hp.com
Thu May 22 18:11:39 PDT 2003
I am testing -current on a ProLiant DL560 4P with 8.25 GB of RAM.
I have enabled PAE and SMP+APIC in my kernel config.
I initially had problems with the ciss and bge drivers, but Paul
Saab has added PAE support to those drivers and they have been
checked into CVS (Thanks Paul!).
I am now running into a reproduceable panic when doing a single
SSH session doing a "find . -print" on an NFS file share:
panic: kmem_malloc(4096): kmem_map too small: 96624640 total allocated
I tried lowering kern.maxvnodes from 536130 (default) to 200000,
but that did not alleviate the panic.
If anyone has any ideas of what might be the problem, please let
me know. I have attached a stack trace and some statistics
captured just before the panic that may be helpful.
Also, I get a different panic whenever mounting /dev/fd0:
root at bigdaddy:~> mount /dev/fd0 /mnt
panic: isa_dmastart: bad bounce buffer
cpuid = 2; lapic.id = 02000000
Debugger("panic")
Stopped at Debugger+0x55: xchgl %ebx,in_Debugger.0
db> trace
Debugger(c0429eec,2000000,c0442f3a,e44abbe0,1) at Debugger+0x55
panic(c0442f3a,200,2,dc,8) at panic+0x11f
isa_dmastart(100000,d5787000,200,2,c042ae33) at isa_dmastart+0x78
fdstate(d27b4700,7,e44abcb4,c03ef591,d27b4700) at fdstate+0x4df
fdc_intr(d27b4700,e44abce0,c028f62c,d27b4700,0) at fdc_intr+0x18
fd_pseudointr(d27b4700,0,c042ae33,bf,c51c) at fd_pseudointr+0x11
softclock(0,0,c0427d36,233,ce8391e0) at softclock+0x19c
ithread_loop(ce823200,e44abd48,c0427be7,2f8,0) at ithread_loop+0x182
fork_exit(c026ca00,ce823200,e44abd48) at fork_exit+0xc0
fork_trampoline() at fork_trampoline+0x1a
--- trap 0x1, eip = 0, esp = 0xe44abd7c, ebp = 0 ---
Thanks,
John
--------------------------------
John Cagle john.cagle at hp.com
Principal Member Technical Staff
Industry Standard Servers
Hewlett-Packard Company
panic: kmem_malloc(4096): kmem_map too small: 96624640 total allocated
cpuid = 0; lapic.id = 00000000
Debugger("panic")
Stopped at Debugger+0x55: xchgl %ebx,in_Debugger.0
db> trace
Debugger(c041b6da,0,c042cea5,e8d49774,1) at Debugger+0x55
panic(c042cea5,1000,5c26000,e8d497a0,c04886a8) at panic+0x11f
kmem_malloc(c062e0b0,1000,102,e8d497fc,c0398072) at kmem_malloc+0x124
page_alloc(c063a9c0,1000,e8d497ef,102,c042e75d) at page_alloc+0x27
slab_zalloc(c063a9c0,2,c045388c,c048e920,c063aa98) at slab_zalloc+0x112
uma_zone_slab(c063a9c0,2,163,d41fddb0,c063aa98) at uma_zone_slab+0xd8
uma_zalloc_bucket(c063a9c0,2,c042e754,586,0) at uma_zalloc_bucket+0x17d
uma_zalloc_arg(c063a9c0,0,2,c042ec5c,2d498b4) at uma_zalloc_arg+0x307
vm_object_allocate_wait(2,1,0,2,e8d498e4) at
vm_object_allocate_wait+0x38
vm_object_allocate(2,1,0,88,c04867a0) at vm_object_allocate+0x28
vnode_pager_alloc(d41fddb0,200,0,0,0) at vnode_pager_alloc+0x192
vop_stdcreatevobject(e8d499cc,e8d499e0,c02d541a,e8d499cc,1) at
vop_stdcreatevobject+0x175
vop_defaultop(e8d499cc,1,c04227e5,cb1,c046eca0) at vop_defaultop+0x18
vfs_object_create(d41fddb0,d346a4c0,d3826b00,a4,d346a4c0) at
vfs_object_create+0x5a
namei(e8d49bd8,e8d49a74,c02a0c3b,c0487c08,d346a4c0) at namei+0x2f6
vn_open_cred(e8d49bd8,e8d49cd8,1,d3826b00,e8d49cc4) at
vn_open_cred+0x258
vn_open(e8d49bd8,e8d49cd8,1,2ab,c02a0ca3) at vn_open+0x29
kern_open(d346a4c0,80559c8,0,5,1) at kern_open+0x13d
open(d346a4c0,e8d49d10,c0432e37,3fb,3) at open+0x30
syscall(805002f,bf7f002f,bf7f002f,8055980,8053040) at syscall+0x26e
Xint0x80_syscall() at Xint0x80_syscall+0x1d
--- syscall (5, FreeBSD ELF32, open), eip = 0x280bc6f3, esp =
0xbf7ff8cc, ebp = 0xbf7ffa98 ---
db>
mbuf usage:
GEN cache: 0/0 (in use/in pool)
CPU #0 cache: 388/448 (in use/in pool)
CPU #1 cache: 0/64 (in use/in pool)
CPU #2 cache: 4/64 (in use/in pool)
CPU #3 cache: 0/64 (in use/in pool)
CPU #4 cache: 0/288 (in use/in pool)
CPU #5 cache: 0/64 (in use/in pool)
CPU #6 cache: 1/64 (in use/in pool)
CPU #7 cache: 0/64 (in use/in pool)
Total: 393/1120 (in use/in pool)
Mbuf cache high watermark: 512
Mbuf cache low watermark: 128
Maximum possible: 51200
Allocated mbuf types:
393 mbufs allocated to data
2% of mbuf map consumed
mbuf cluster usage:
GEN cache: 0/0 (in use/in pool)
CPU #0 cache: 382/392 (in use/in pool)
CPU #1 cache: 0/64 (in use/in pool)
CPU #2 cache: 1/64 (in use/in pool)
CPU #3 cache: 0/64 (in use/in pool)
CPU #4 cache: 0/128 (in use/in pool)
CPU #5 cache: 0/64 (in use/in pool)
CPU #6 cache: 1/64 (in use/in pool)
CPU #7 cache: 0/64 (in use/in pool)
Total: 384/904 (in use/in pool)
Cluster cache high watermark: 128
Cluster cache low watermark: 16
Maximum possible: 25600
3% of cluster map consumed
2088 KBytes of wired memory reserved (41% in use)
0 requests for memory denied
0 requests for memory delayed
0 calls to protocol drain routines
Type InUse MemUse HighUse Requests Size(s)
atkbddev 2 1K 1K 2 32
MSDOSFS mount 1 1024K 1024K 1
nexusdev 3 1K 1K 3 16
memdesc 1 4K 4K 1 4096
DEVFS 104 16K 16K 104 16,32,128,4096
VM pgdata 1 64K 64K 1 65536
UFS mount 12 25K 60K 24 64,256,1024,2048,4096,32768
UFS ihash 1 2048K 2048K 1
UFS dirhash 21 4K 4K 21 16,32,64,512
dirrem 0 0K 1K 26 32
diradd 0 0K 1K 28 32
freefile 0 0K 1K 17 32
freeblks 0 0K 3K 16 256
freefrag 0 0K 1K 7 32
allocindir 0 0K 29K 489 64
indirdep 0 0K 867K 244 32,16384
allocdirect 0 0K 2K 46 128
bmsafemap 0 0K 2K 74 32
newblk 1 1K 1K 536 64,256
inodedep 1 2048K 2054K 66 128,256
pagedep 1 256K 257K 12 64
p1003.1b 1 1K 1K 1 16
NFS daemon 1 1K 1K 1 256
NFS hash 1 2048K 2048K 1
NFSV3 diroff 12 6K 6K 12 512
NFS req 0 0K 1K 38698 64
in6_multi 6 1K 1K 6 64
syncache 1 8K 8K 1 8192
in_multi 2 1K 1K 2 32
igmp 1 1K 1K 1 16
routetbl 52 8K 8K 77 16,32,64,128,256
lo 1 1K 1K 1 512
clone 4 16K 16K 4 4096
ether_multi 28 2K 2K 28 16,32,64
ifaddr 58 11K 11K 59 32,256,512,2048
BPF 10 10K 10K 10 128,256,4096
mount 13 4K 4K 17 16,32,128,512
ATA DMA 1 1K 1K 1 64
vnodes 26 7K 7K 151 16,32,64,128,256
cluster_save buffer 0 0K 1K 2 32,64
vfscache 10702 4766K 4766K 11121 64,128
BIO buffer 20 40K 68K 62 2048
pcb 12 5K 5K 54 16,32,64,2048
soname 2 1K 1K 247 16,32,128
ptys 2 1K 1K 2 512
ttys 1108 142K 142K 2368 128,512
shm 1 16K 16K 1 16384
sem 4 7K 7K 4 1024,4096
msg 4 25K 25K 4 512,4096,16384
ioctlops 0 0K 1K 22 512,1024
ATA generic 2 1K 1K 3 16,512
acpidev 50 1K 1K 50 16
acpisem 20 3K 3K 20 128
acpitask 0 0K 1K 6 16,32
taskqueue 3 1K 1K 3 128
sbuf 0 0K 13K 138
16,32,64,128,256,512,1024,2048,4096,8192
rman 116 8K 8K 453 16,64
mbufmgr 169 141K 141K 169 32,64,256,8192,16384
kobj 126 504K 504K 126 4096
eventhandler 34 2K 2K 34 32,128
devstat 4 9K 9K 4 16,4096
bus 732 125K 233K 4150
16,32,64,128,256,512,1024,2048,4096,8192,16384,32768
SWAP 2 2189K 2189K 2 64
sysctltmp 0 0K 4K 999
16,32,64,128,256,512,2048,4096
sysctloid 134 5K 5K 134 16,32,64
sysctl 0 0K 1K 934 16,32,64
uidinfo 3 2K 2K 9 32,1024
ciss_data 4 2K 2K 5 32,128,512,1024
cred 19 3K 3K 1148 128
subproc 84 8K 9K 675 64,256
proc 2 8K 8K 2 4096
session 19 3K 3K 24 128
pgrp 23 3K 3K 159 128
acpica 1638 85K 86K 14047 16,32,64,128,256,512,1024
module 176 12K 12K 176 64,128
ip6ndp 3 1K 1K 4 64,128,512
temp 8 117K 117K 3193
16,32,64,128,256,512,1024,2048,4096,8192,32768
devbuf 2530 975K 1007K 3166
16,32,64,128,256,512,1024,2048,4096,16384
lockf 1 1K 1K 5 64
linker 34 2K 2K 54 16,32,256
ACD driver 1 1K 1K 1 1024
KTRACE 100 13K 13K 100 128
ithread 44 4K 4K 44 64,128
zombie 0 0K 1K 575 128
proc-args 23 2K 2K 609 16,32,64,128,256
kqueue 4 4K 6K 47 256,1024
kenv 108 6K 6K 109 16,32,64,2048
sigio 1 1K 1K 1 32
file desc 70 18K 20K 645 256
dev_t 31 8K 8K 31 256
ATAPI generic 1 1K 1K 2 32,128
ISOFS mount 1 2048K 2048K 1
isadev 22 2K 2K 22 64
GEOM 47 6K 8K 175 16,32,64,128,256,512,1024
pfs_fileno 1 32K 32K 1 32768
pfs_nodes 20 3K 3K 20 128
More information about the freebsd-current
mailing list