The reason why nfsd consumes 850% CPU is that measurement is per CPU core, and it currently uses more than 8 CPU cores. It does that by running more than 8 threads (LWPs).
Unfortunately the HP-UX ps command does not show the process threads (where Linux and Solaris have the -L option for ps).
You can see the NFS statistics:
Code:
nfsstat -ns
Further, if you have tpcdump installed, you can see which NFS client is currently accessing:
Can anybody please help me on how to optimize following command as it use up a lot of CPU :
tail -f $DIR3$DATE4.log |\
while read line
do echo $line | egrep "Processing incoming SMS message" | sed 's/\,/ /g' \
| awk '{print $2}' >> $DIR2/LIST1.$DATE4.log && echo... (6 Replies)
hi guys
I installed NFS server and everything started out fine but I don't have /proc/fs/nfsd entry and so I can't mount nfsd. Therefore I can't start my nfs service.
Why don't I have /proc/fs/nfsd? How do I create that?
Thanks (1 Reply)
Dear Friends,
we are using HP-UX B.11.31 U ia64 HP-UX server. Can you check bellow the top command output whether can point out any abnormality. Becoz i suspect something wrong there,
Load averages: 2.40, 2.73, 2.99
711 processes: 287 sleeping, 424 running
Cpu states:
CPU LOAD USER ... (4 Replies)
Hi i recently observed my cpu being used 100% due to which load average on machine get increased to < 5.
I have no idea what the process is?
Appreciate any help in this regard.
root 15859 99.9 0.0 5668 1592 pts/4 R+ 12:28 660:06 \_ pvs
root 7334 99.9 ... (2 Replies)
Hello,
what is the relation between portmap and nfsd and how communication between them looks like. Does the nfsclient contact with the portmap or nfsd first.
Many thanks in advance for helping me to understand this :)
BR,
p (3 Replies)
Hi all,
I am having a following problem. Trying to run PXE boot server on my OpenBSD machine I have ended up on making NFSd daemon works. On all machines I get an error msg. nfsd : nfsd count is invalid: (null) no matter what computer I run it on. Everything works just well on FreeBSD and linux.... (1 Reply)
We are using oracle database on solaris 10 sparc 64 bit on M5000 machine. we facing performance related issues.
We diagnose using prstat -a command that oracle user not utilizing the ram more than 30 gb total we have 64 gb ram available as in project max-shm-memory set to 42 gb . We are running... (2 Replies)
Use and complete the template provided. The entire template must be completed. If you don't, your post may be deleted!
1. The problem statement, all variables and given/known data:
Compile cpp2html.c to produce cpp2html.o.
( Important: the source code in these files is C, not C++, and so... (8 Replies)
Use and complete the template provided. The entire template must be completed. If you don't, your post may be deleted!
1. The problem statement, all variables and given/known data:
]Compile cpp2html.c to produce cpp2html.o.
( Important: the source code in these files is C, not C++, and so... (1 Reply)
Hi.
Using debian 8.0 on a raspberryPI SERVER, accessing nfs from another raspberry gives quick reply.
But from a slackware 14.1 SERVER on a Celeron 2Ghz dual core, is painfully slow and i cannot figure out why.
Can anyone guide me? (2 Replies)
Discussion started by: dimples
2 Replies
LEARN ABOUT CENTOS
nfsstat
nfsstat(8) System Manager's Manual nfsstat(8)NAME
nfsstat - list NFS statistics
SYNOPSIS
nfsstat [OPTION]...
DESCRIPTION
The nfsstat displays statistics kept about NFS client and server activity.
OPTIONS -s, --server
Print only server-side statistics. The default is to print both server and client statistics.
-c, --client
Print only client-side statistics.
-n, --nfs
Print only NFS statistics. The default is to print both NFS and RPC information.
-2 Print only NFS v2 statistics. The default is to only print information about the versions of NFS that have non-zero counts.
-3 Print only NFS v3 statistics. The default is to only print information about the versions of NFS that have non-zero counts.
-4 Print only NFS v4 statistics. The default is to only print information about the versions of NFS that have non-zero counts.
-m, --mounts
Print information about each of the mounted NFS file systems.
If this option is used, all other options are ignored.
-r, --rpc
Print only RPC statistics.
-o facility
Display statistics for the specified facility, which must be one of:
nfs NFS protocol information, split up by RPC call.
rpc General RPC information.
net Network layer statistics, such as the number of received packets, number of TCP connections, etc.
fh Usage information on the server's file handle cache, including the total number of lookups, and the number of hits and
misses.
rc Usage information on the server's request reply cache, including the total number of lookups, and the number of hits and
misses.
all Display all of the above facilities.
-v, --verbose
This is equivalent to -o all.
-l, --list
Print information in list form.
-S, --since file
Instead of printing current statistics, nfsstat imports statistics from file and displays the difference between those and the cur-
rent statistics. Valid input files may be in the form of /proc/net/rpc/nfs (raw client stats), /proc/net/rpc/nfsd (raw server
stats), or saved output from nfsstat itself (client and/or server stats). Any statistics missing from a saved nfsstat output file
are treated as zeroes.
-Z[interval], --sleep=[interval]
Instead of printing current statistics and immediately exiting, nfsstat takes a snapshot of the current statistics and pauses until
it receives SIGINT (typically from Ctrl-C), at which point it takes another snapshot and displays the difference between the two.
If interval is specified, nfsstat will print the number of NFS calls made since the previous report. Stats will be printed repeat-
edly every interval seconds.
EXAMPLES
nfsstat -o all -234
Show all information about all versions of NFS.
nfsstat --verbose -234
Same as above.
nfsstat -o all
Show all information about active versions of NFS.
nfsstat --nfs --server -3
Show statistics for NFS version 3 server.
nfsstat -m
Show information about mounted NFS filesystems.
DISPLAY
The Flags output from the -m option is the same as the flags give to the mount command.
FILES
/proc/net/rpc/nfsd
procfs-based interface to kernel NFS server statistics.
/proc/net/rpc/nfs
procfs-based interface to kernel NFS client statistics.
/proc/mounts
procfs-based interface to the mounted filesystems.
SEE ALSO rpc.nfsd(8). nfs(5).
BUGS
The default output has been changed. To get the old default output you must run nfsstat --auto -2.
The function of the -v and -a options have changed. The -a option is now reserved for future use. The -v does what the -a option used to
do, and the new -[234] options replace the -v option.
The Display section should be more complete.
Further bugs can be found or reported at http://nfs.sf.net/.
AUTHOR
Olaf Kirch, <okir@suse.de>
7 Aug 2007 nfsstat(8)