Networker

Re: [Networker] Too many open files

2004-07-08 09:30:39
Subject: Re: [Networker] Too many open files
From: Arun Sondhi <asondhi AT RA.ROCKWELL DOT COM>
To: NETWORKER AT LISTMAIL.TEMPLE DOT EDU
Date: Thu, 8 Jul 2004 08:30:28 -0500
You should start looking at the number of network connections in TIME_WAIT
state also. The default for tcp_time_wait _interval is pretty high reduce
that to 60000 or lower, but that would alleviate some problems ...
Sincerely,

Arun Sondhi
CCNP,CCDP

Ph  : +1 414.382.0206
Pg  : +1 414.341.8650
Mo : +1 414.213.1540
Extn: 20206




Thorsten Linow <Linow.Thorsten AT TALKLINE DOT DE>
Sent by: Legato NetWorker discussion <NETWORKER AT LISTMAIL.TEMPLE DOT EDU>
07/08/2004 08:11 AM
Please respond to Legato NetWorker discussion; Please respond to Thorsten
Linow


        To:     NETWORKER AT LISTMAIL.TEMPLE DOT EDU
        cc:
        Subject:        [Networker] Too many open files


Hi,
After upgrading Legato Networker 6.1.3 towards 7.1.2 we got lots of
"service at 0.0.0.0/5833error from accept call: Too many open files"
messages in the daemon.log, during heavy load caused by obviously
too many client connection requests.
The Legato Networker Server was busy near death, nsrd occupied
one CPU by 100% but the Server was more or less idle.
We had semilar situations several times in the past but we got no clue
why.
Just since we upgraded we got this detailed messages in the daemon.log,
so now we know where to start to investigate.

Our LNS is a Sun V880 based on 8 gigs of RAM and 4 times 750 MHz cpu's.
As recommended by our service-partner we increased the /etc/system
parameter

rlim_fd_cur

and

rlim_fd_max

towards 4096 (old value was 1024)

My question is if there are any recommended values, and/or any dependency
based on the number of clients or server-parallelism or what ever...

About our environment:
140 clients, 7 Solaris based Storage nodes, LNS and Alphastor Server
running together on one Host,
Tapedrive-environment connected via SAN: 20 * STK9840 plus 6 * STK9940B,
located in Powderhorn, controlled by ACSLS.

Any help would be appreciated.

Regards Thorsten Linow

--
Note: To sign off this list, send a "signoff networker" command via email
to listserv AT listmail.temple DOT edu or visit the list's Web site at
http://listmail.temple.edu/archives/networker.html where you can
also view and post messages to the list.
=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=



--
Note: To sign off this list, send a "signoff networker" command via email
to listserv AT listmail.temple DOT edu or visit the list's Web site at
http://listmail.temple.edu/archives/networker.html where you can
also view and post messages to the list.
=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=

<Prev in Thread] Current Thread [Next in Thread>