Hi All
 
I have really slow working nfs.
Server is build on:
- dual pentium Xeon 2GHz,
- 2 3ware 7500 controllers,
- raid 5 on 7 160GB discs on controler 1 
- raid 5 on 6 160GB disks on cotroller 2 
 
Serwer is used for ~500k maildirs,
all clients (~20) are freebsd boxes, when nfs transfer is around 1MB/s for writing and 1.5MB/s for reading
listing user directories even with very few file stakes up to 15 seconds.
 
I tried nfs-ALL patch, but it didn' t help.
 
I run 256 nfs daemons,
 
echo 2097152 > /proc/sys/net/core/rmem_max
echo 2097152 > /proc/sys/net/core/rmem_default
 
nsfstat output:
 
Server rpc stats:
calls      badcalls   badauth    badclnt    xdrcall
25271043   17885061   0          17885061   0
Server nfs v3:
null       getattr    setattr    lookup     access     readlink
25      0% 1159    0% 89718   0% 11702395 46% 10953437 43% 34868   0%
read       write      create     mkdir      symlink    mknod
925727  3% 226250  0% 44964   0% 1089    0% 2299    0% 0       0%
remove     rmdir      rename     link       readdir    readdirplus
35040   0% 42      0% 121064  0% 535     0% 534720  2% 0       0%
fsstat     fsinfo     pathconf   commit
585179  2% 36      0% 0       0% 12493   0%
mount over tcp gives frequent errors on freebsd clients side:
kernel: nfs send error 32 from nfs server xxx.xxx.xxx.xxx:/export
 
thanks for any help,
 
rafal