Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 1 Jul 2010 11:51:28 -0700 (PDT)
From:      alan bryan <alan.bryan@yahoo.com>
To:        Garrett Cooper <yanefbsd@gmail.com>
Cc:        freebsd-stable@freebsd.org
Subject:   Re: NFS 75 second stall
Message-ID:  <538823.39365.qm@web50508.mail.re2.yahoo.com>
In-Reply-To: <AANLkTilNvy3FYUNjjiJ85eWrF7jTAvJJ9E7Q2eqhhQj6@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
=0A=0A--- On Thu, 7/1/10, Garrett Cooper <yanefbsd@gmail.com> wrote:=0A=0A>=
 From: Garrett Cooper <yanefbsd@gmail.com>=0A> Subject: Re: NFS 75 second s=
tall=0A> To: "alan bryan" <alan.bryan@yahoo.com>=0A> Cc: freebsd-stable@fre=
ebsd.org=0A> Date: Thursday, July 1, 2010, 11:13 AM=0A> On Thu, Jul 1, 2010=
 at 11:01 AM, alan=0A> bryan <alan.bryan@yahoo.com>=0A> wrote:=0A> > Setup:=
=0A> >=0A> > server - FreeBSD 8-stable from today.=A0 2 UFS dirs=0A> export=
ed via NFS.=0A> > client - FreeBSD 8.0-Release. =A0Running a test php=0A> s=
cript that copies around various files to/from 2 separate=0A> NFS mounts.=
=0A> >=0A> > Situation:=0A> >=0A> > script is started (forked to do 20 simu=
ltaneous runs)=0A> and 20 1GB files are copied to the NFS dir which works=
=0A> fine.=A0 When it then switches to reading those files back=0A> and sim=
ultaneously writing to the other NFS mount I see a=0A> hang of 75 seconds.=
=A0 If I do an "ls -l" on the NFS mount it=0A> hangs too.=A0 After 75 secon=
ds the client has reported:=0A> >=0A> > nfs server 192.168.10.133:/usr/loca=
l/export1: not=0A> responding=0A> > nfs server 192.168.10.133:/usr/local/ex=
port1: is alive=0A> again=0A> > nfs server 192.168.10.133:/usr/local/export=
1: not=0A> responding=0A> > nfs server 192.168.10.133:/usr/local/export1: i=
s alive=0A> again=0A> >=0A> > and then things start working again.=A0 The s=
erver was=0A> originally FreeBSD 8.0-Release also but was upgraded to the=
=0A> latest stable to see if this issue could be avoided.=0A> >=0A> > # nfs=
stat -s -W -w 1=0A> > =A0GtAttr Lookup Rdlink=A0=A0=A0Read=A0 Write Rename=
=0A> Access=A0 Rddir=0A> > =A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 2=
22=A0 =A0 257=A0 =A0=0A> =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> > =A0 =A0 =A0 =
0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 178=A0 =A0 135=A0 =A0=0A> =A0 0=A0 =A0 =
=A0 0=A0 =A0 =A0 0=0A> > =A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0=A0=
=A085=A0 =A0 127=A0=0A> =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> > =A0 =A0 =
=A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0=0A> =A0 =A0 0=
=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> > =A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0=
 =A0 =A0 0=A0 =A0 =A0 0=A0=0A> =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> > =
=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0=0A> =
=A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> > =A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0=
 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0=0A> =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=
=0A> > =A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0=
=0A> =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> >=0A> > ... for 75 rows of all=
 zeros=0A> >=0A> > =A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=A0 =A0 272=A0 =
=A0 266=A0 =A0=0A> =A0 0=A0 =A0 =A0 0=A0 =A0 =A0 0=0A> > =A0 =A0 =A0 0=A0 =
=A0 =A0 0=A0 =A0 =A0 0=A0 =A0 167=A0 =A0 165=A0 =A0=0A> =A0 0=A0 =A0 =A0 0=
=A0 =A0 =A0 0=0A> >=0A> > I also tried runs with 15 simultaneous processes =
and=0A> 25. =A015 processes gave only about a 5 second stall but 25=0A> gav=
e again the same 75 second stall.=0A> >=0A> > Further, I tested with 2 moun=
ts to the same server but=0A> from ZFS filesytems with the exact same stall=
/timeout=0A> periods. =A0So, it doesn't appear to matter what the=0A> under=
lying filesystem is - it's something in NFS or=0A> networking code.=0A> >=
=0A> > Any ideas on what's going on here? =A0What's causing=0A> the complet=
e stall period of zero NFS activity? =A0 Any flaws=0A> with my testing meth=
ods?=0A> >=0A> > Thanks for any and all help/ideas.=0A> =0A> What network d=
river are you using? Have you tried=0A> tcpdumping the packets?=0A> -Garret=
t=0A> =0A=0AI'm using igb currently but have also used em.  I have not trie=
d tcpdumping the packets yet on this test.  Any suggestions on things to lo=
ok out for (I'm not that familiar with that whole process).=0A=0AWhich brin=
gs up another point - I'm using TCP connections for NFS, not UDP.  =0A=0A--=
Alan=0A=0A=0A=0A      



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?538823.39365.qm>