SCIENTIFIC-LINUX-DEVEL Archives

June 2016

SCIENTIFIC-LINUX-DEVEL@LISTSERV.FNAL.GOV

Options: Use Monospaced Font
Show HTML Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
"Patrick J. LoPresti" <[log in to unmask]>
Reply To:
Patrick J. LoPresti
Date:
Fri, 3 Jun 2016 14:08:20 -0700
Content-Type:
multipart/alternative
Parts/Attachments:
text/plain (934 bytes) , text/html (1417 bytes)
On Fri, Jun 3, 2016 at 7:43 AM, Valentin B <[log in to unmask]> wrote:

>
> This line here:
>
> rw,relatime,vers=3,rsize=8192,wsize=8192,namlen=255,hard,proto=tcp,timeo=600,retrans=2,sec=sys,mountaddr=10.0.6.9,mountvers=3,mountport=35079,mountproto=udp,fsc,local_lock=none,addr=10.0.6.9
>
> is handled by autofs which is configured through (FreeIPA).
>
> I could increase the wsize and rsize though but not sure what value to
> define.
>

Yes, that is what I am suggesting you try. I am suggesting you use the
largest value you can. Assuming the client and server are both Linux and
SL6 or newer, that value will be 1 megabyte.

Your "dd" experiments are doing something completely different... That is
just affecting how much data userspace is trying to read/write at a time.
The NFS request payload size is controlled by these rsize/wsize settings,
and for a "proto=tcp" mount you want to make them as large as possible
(assuming a fast network).

 - Pat


ATOM RSS1 RSS2