From owner-freebsd-fs Mon Apr 22 16:12: 7 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from mail.fibertel.com.ar (mta4.fibertel.com.ar [24.232.0.164])
by hub.freebsd.org (Postfix) with ESMTP id BFE0637B9D3
for ; Mon, 22 Apr 2002 16:00:35 -0700 (PDT)
Received: from OL101-181.fibertel.com.ar (24.232.181.101) by mail.fibertel.com.ar (5.5.034)
id 3CC0AEA0000DC849 for freebsd-fs@FreeBSD.org; Mon, 22 Apr 2002 15:15:25 -0300
Message-ID: <4178-220024122181356340@cyco>
To: "Lina Avellaneda"
From: "PromocionaTuShow"
Subject: Tango Argentino: Cantante Lina Avellaneda
Date: Mon, 22 Apr 2002 15:13:56 -0300
MIME-Version: 1.0
Content-Type: multipart/alternative;
boundary="----=_NextPart_84815C5ABAF209EF376268C8"
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
------=_NextPart_84815C5ABAF209EF376268C8
Content-type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
*Gacetilla de Prensa - Se Agradece su Difusion* *No utilice RESPONDER o RE=
PLY para conestar este mensaje* =20
www=2Elinaavellaneda=2Ecom=2Ear
Lina Avellaneda tiene nuevo sitio oficial en la Web, en el mismo hay mucha=
mas informacion, fotos, mp3, producciones de sus alumnos, y en breve se i=
naugurara una nueva seccion: "Cantando bajo la ducha, pero =2E=2E=2EBIEN!!=
!"=20
Este nuevo espacio apunta a cubrir las necesidades de quienes quieren cant=
ar no profesionalmente pero sin fatigas vocales o disfonias, intentando ad=
emas brindarles conocimientos minimos de registro y de afinacion, de maner=
a muy sencilla y apta para todo publico=2E
Lina viene trabajando hace muchos a=F1os bajo la consigna "CANTAR HACE BIE=
N"=2E
En pocos meses los sitios de Lina han sido visitados por mas de 10=2E000 p=
ersonas=2E
Consultas de canto, bajadas de mp3, pedidos de nuevos tangos=2E=2E=2E=2E=2E=
GRACIAS!!!!!
En el orden profesional el mencionado sitio nos ha puesto en contacto con =
las siguientes personalidades del quehacer artistico vinculado al TANGO AR=
GENTINO EN EL MUNDO=2E
"TANGOLINA" se esta difundiendo merced a:
ENRIQUE TELLER=CDA, BARCELONA
RICARDO SAYALERO GARCIA, VENEZUELA
SALVADOR ENRIQUEZ, MADRID
GONZALO ANDINO, MADRID
SUSAN GILLIES, AUSTRALIA
ANDREW MCKINNON, SIDNEY
CARLOS GONZALEZ VILCHES, TIJUANA MEXICO
ERIK VANVLIET, HOLANDA
LUIS MONT, MOCTEZUMA, MEXICO
DANIEL GALLO, VIRGINIA, U=2ES=2EA=2E
WITHGARBOPRODUCTION, CALIFORNIA, U=2ES=2EA=2E
CARLOS GROPPA, CALIFORNIA, U=2ES=2EA=2E
ELEVEN MEDIA, TORONTO, ONTARIO, CANAD=C1
VINCE CICCARELLO, AUSTRALIA=2E
JUSTIN Mc DONNELL, AUSTRALIA=2E
MARGUERITE PEPPAR, AUSTRALIA=2E
LYRIC PROMOTIONS, AUSTRALIA=2E
INTERNATIONAL MANAGEMENT GROUP, AUSTRALIA=2E
"Ciudadana" y "Tangolina" a disposici=F3n de la prensa=2E
Clips y show en vivo para insert TV=2E Gracias por difundir la presente=2E=
Contacto: casalina@fibertel=2Ecom=2Ear =20
Para ser removido de nuestra lista enviar un e-mail a bloquearenvios@fiber=
tel=2Ecom=2Ear escribiendo s=F3lo Remover en Subject
------=_NextPart_84815C5ABAF209EF376268C8
Content-Type: text/html; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
*Gacetilla de Pre=
nsa - Se Agradece su Difusion* *No=20
utilice RESPONDER o REPLY para conestar este mensaje* =20
www=2Elinaavellaneda=2Ecom=2Ear
Lina=20
Avellaneda tiene nuevo sitio=
oficial=20
en la Web, en el mismo hay mucha mas informacion, fotos, m=
p3,=20
producciones de sus alumnos, y en=20
breve se inaugurara una nuev=
a=20
seccion: "Cantando bajo la ducha, pero=20
=2E=2E=2E=2EBIEN!!!"
Este nuevo espacio apunta a cubrir las necesidades de quienes quieren cantar =
no=20
profesionalmente pero sin fatigas vocales o disfonias,=20
intentando ademas brindarles conocimientos m=
inimos=20
de registro y de afinacion, de manera muy sencilla y apta =
para=20
todo publico=2E
Lina viene trabajando hace muchos a=F1=
os bajo la=20
consigna "CANTAR HACE BIEN"=2E
=
En pocos meses=20
los sitios de Lina han sido visitados por mas de 10=2E000=20
personas=2E
=
Consultas de=20
canto, bajadas de mp3, pedidos de nuevos tangos=2E=2E=2E=2E=2E GRACIAS!!!!=
!
En el orden profesional el mencionado=
sitio nos=20
ha puesto en contacto con las siguientes personalidades del quehacer artis=
tico=20
vinculado al TANGO ARGENTINO EN EL MUNDO=2E
"TANGOLINA" se=20
esta difundiendo merced a:
ENRIQUE TELLER=CDA, BARCELONA
RICARDO SAYALERO GARCIA, VENEZUELA
<=
/FONT>
SALVADOR ENRIQUEZ, MADRID
GONZALO ANDINO, MADRID
SUSAN GILLIES, AUSTRALIA
ANDREW MCKINNON, SIDNEY
CARLOS GONZALEZ VILCHES, TIJUANA=20
MEXICO
ERIK VANVLIET, HOLANDA
LUIS MONT, MOCTEZUMA, MEXICO
=
DANIEL GALLO, VIRGINIA, U=2ES=2EA=2E
WITHGARBOPRODUCTION, CALIFORNIA,=20
U=2ES=2EA=2E
CARLOS GROPPA, CALIFORNIA, U=2ES=2EA=2E
=
ELEVEN MEDIA, TORONTO, ONTARIO,=20
CANAD=C1
VINCE CICCARELLO, AUSTRALIA=2E
JUSTIN Mc DONNELL, AUSTRALIA=2E
MARGUERITE PEPPAR, AUSTRALIA=2E<=
/P>
LYRIC PROMOTIONS, AUSTRALIA=2E
INTERNATIONAL MANAGEMENT GROUP,=20
AUSTRALIA=2E
"Ciudadana" y "Tangolina" a disposici=F3n de la prensa=2E=
Clips y show en vivo para insert TV=2E Gracias por difun=
dir la=20
presente=2E
Contacto: casalina@fibertel=2Ecom=2Ear =20
Para ser removido de nuestra =
lista enviar=20
un e-mail a <=
FONT=20
face=3DArial color=3D#000000 size=3D1>bloquearenvios@fibertel=
=2Ecom=2Ear escribiendo s=F3lo Remover=
en=20
Subject
------=_NextPart_84815C5ABAF209EF376268C8--
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Thu Apr 25 1:39:42 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from obsecurity.dyndns.org (adsl-64-165-226-18.dsl.lsan03.pacbell.net [64.165.226.18])
by hub.freebsd.org (Postfix) with ESMTP
id 8BC0737B41D; Thu, 25 Apr 2002 01:39:26 -0700 (PDT)
Received: by obsecurity.dyndns.org (Postfix, from userid 1000)
id 439C766B8A; Thu, 25 Apr 2002 01:39:23 -0700 (PDT)
Date: Thu, 25 Apr 2002 01:39:22 -0700
From: Kris Kennaway
To: current@FreeBSD.org, fs@FreeBSD.org
Subject: 4 panics under 5.0 on ports cluster
Message-ID: <20020425013922.A27152@xor.obsecurity.org>
Mime-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-md5;
protocol="application/pgp-signature"; boundary="Q68bSM7Ycu6FN28Q"
Content-Disposition: inline
User-Agent: Mutt/1.2.5.1i
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
--Q68bSM7Ycu6FN28Q
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
I've had 4 panics on the ports cluster in the past couple of days.
They're running kernels from March 31 which have been very stable
since then, but on the other hand I've been building packages
intensively for the past few days. Is there anything interesting
here? I have the cores if more information is needed.
Kris
panic: ffs_valloc: dup alloc
Uptime: 3d6h42m19s
(kgdb) bt
#0 dumpsys () at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:506
#1 0xc0207cb0 in boot (howto=260) at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:338
#2 0xc020814f in panic (fmt=0xc037f781 "ffs_valloc: dup alloc")
at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:648
#3 0xc02cb682 in ffs_valloc (pvp=0xdb4d7000, mode=16832, cred=0xdcc4b180, vpp=0xd9627ac8)
at /local0/scratch/usr/src/sys/ufs/ffs/ffs_alloc.c:639
#4 0xc02e0b15 in ufs_mkdir (ap=0xd9627c14) at /local0/scratch/usr/src/sys/ufs/ufs/ufs_vnops.c:1380
#5 0xc02e1d85 in ufs_vnoperate (ap=0xd9627c14)
at /local0/scratch/usr/src/sys/ufs/ufs/ufs_vnops.c:2660
#6 0xc024a06a in vn_mkdir (path=0x804f3e0 "./share/doc/ja", mode=448, segflg=UIO_USERSPACE,
td=0xd9414a00) at vnode_if.h:537
#7 0xc0249e90 in mkdir (td=0xd9414a00, uap=0xd9627d20)
at /local0/scratch/usr/src/sys/kern/vfs_syscalls.c:3647
#8 0xc0326d8f in syscall (frame={tf_fs = 47, tf_es = 47, tf_ds = 47, tf_edi = 0, tf_esi = 134580224,
tf_ebp = -1077938244, tf_isp = -647856780, tf_ebx = 134542315, tf_edx = 134535775,
tf_ecx = 672225016, tf_eax = 136, tf_trapno = 12, tf_err = 2, tf_eip = 671827427, tf_cs = 31,
tf_eflags = 647, tf_esp = -1077938384, tf_ss = 47})
at /local0/scratch/usr/src/sys/i386/i386/trap.c:1033
#9 0xc0317b1d in syscall_with_err_pushed ()
#10 0x804c4c1 in ?? ()
#11 0x804c4c1 in ?? ()
#12 0x804c4c1 in ?? ()
#13 0x804bfa3 in ?? ()
#14 0x804b511 in ?? ()
#15 0x80493c9 in ?? ()
(kgdb)
panicstr: ffs_valloc: dup alloc
panic messages:
---
dmesg: kvm_read:
---
#0 dumpsys () at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:506
506 /local0/scratch/usr/src/sys/kern/kern_shutdown.c: No such file or directory.
(kgdb) bt
#0 dumpsys () at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:506
#1 0xd933b14c in ?? ()
#2 0xc0207cb0 in boot (howto=260) at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:338
#3 0xc020814f in panic (fmt=0xc037f781 "ffs_valloc: dup alloc")
at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:648
#4 0xc02cb682 in ffs_valloc (pvp=0xd99d3b2c, mode=16895, cred=0xdb1f2600, vpp=0xdb4ccac8)
at /local0/scratch/usr/src/sys/ufs/ffs/ffs_alloc.c:639
#5 0xc02e0b15 in ufs_mkdir (ap=0xdb4ccc14) at /local0/scratch/usr/src/sys/ufs/ufs/ufs_vnops.c:1380
#6 0xc02e1d85 in ufs_vnoperate (ap=0xdb4ccc14)
at /local0/scratch/usr/src/sys/ufs/ufs/ufs_vnops.c:2660
#7 0xc024a06a in vn_mkdir (path=0x8093040 , mode=511,
segflg=UIO_USERSPACE, td=0xdb483100) at vnode_if.h:537
#8 0xc0249e90 in mkdir (td=0xdb483100, uap=0xdb4ccd20)
at /local0/scratch/usr/src/sys/kern/vfs_syscalls.c:3647
#9 0xc0326d8f in syscall (frame={tf_fs = 47, tf_es = 47, tf_ds = 47, tf_edi = 0, tf_esi = 134819904,
tf_ebp = -1077938120, tf_isp = -615723660, tf_ebx = 134819914, tf_edx = -1, tf_ecx = 47,
tf_eax = 136, tf_trapno = 12, tf_err = 2, tf_eip = 134605092, tf_cs = 31, tf_eflags = 647,
tf_esp = -1077938164, tf_ss = 47}) at /local0/scratch/usr/src/sys/i386/i386/trap.c:1033
#10 0xc0317b1d in syscall_with_err_pushed ()
Cannot access memory at address 0xbfbff838.
panic: sleeping thread owns a mutex
Uptime: 8h52m59s
(kgdb) bt
#0 dumpsys () at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:506
#1 0xc0207cb0 in boot (howto=260) at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:338
#2 0xc020814f in panic (fmt=0xc0367580 "sleeping thread owns a mutex")
at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:648
#3 0xc0200a35 in propagate_priority (td=0xcd23d400)
at /local0/scratch/usr/src/sys/kern/kern_mutex.c:110
#4 0xc0200ffb in _mtx_lock_sleep (m=0xc767866c, opts=0,
file=0xc03858e0 "/local0/scratch/usr/src/sys/vm/uma_core.c", line=1489)
at /local0/scratch/usr/src/sys/kern/kern_mutex.c:389
#5 0xc0200c6b in _mtx_lock_flags (m=0xc767866c, opts=0,
file=0xc03858e0 "/local0/scratch/usr/src/sys/vm/uma_core.c", line=1489)
at /local0/scratch/usr/src/sys/kern/kern_mutex.c:208
#6 0xc02f3017 in uma_zfree_arg (zone=0xc76785a0, item=0xd0dc2000, udata=0xcfa75678)
at /local0/scratch/usr/src/sys/vm/uma_core.c:1489
#7 0xc01ffb5d in free (addr=0xd0dc2000, type=0xc03c5280)
at /local0/scratch/usr/src/sys/kern/kern_malloc.c:232
#8 0xc02d61e2 in softdep_disk_write_complete (bp=0xc772b650)
at /local0/scratch/usr/src/sys/ufs/ffs/ffs_softdep.c:3550
#9 0xc023b011 in bufdone (bp=0xc772b650) at /local0/scratch/usr/src/sys/sys/buf.h:405
#10 0xc023aedf in bufdonebio (bp=0xc772b650) at /local0/scratch/usr/src/sys/kern/vfs_bio.c:2805
#11 0xc017e571 in ad_interrupt (request=0xcf21fb40) at /local0/scratch/usr/src/sys/sys/bio.h:115
#12 0xc01725b9 in ata_intr (data=0xc7686a00) at /local0/scratch/usr/src/sys/dev/ata/ata-all.c:596
#13 0xc01fa7e7 in ithread_loop (arg=0xcdd09e80) at /local0/scratch/usr/src/sys/kern/kern_intr.c:533
#14 0xc01f9cc6 in fork_exit (callout=0xc01fa6b8 , arg=0xcdd09e80, frame=0xcdd32d48)
at /local0/scratch/usr/src/sys/kern/kern_fork.c:799
panic: pipe buffer gone
Uptime: 3d13h4m20s
(kgdb) bt
#0 dumpsys () at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:506
#1 0xc0207cb0 in boot (howto=260) at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:338
#2 0xc020814f in panic (fmt=0xc036bbc0 "pipe buffer gone")
at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:648
#3 0xc02228cc in pipe_write (fp=0xda7c12d0, uio=0xdabfec90, cred=0xdaad6a00, flags=0, td=0xdabca700)
at /local0/scratch/usr/src/sys/kern/sys_pipe.c:887
#4 0xc021fe46 in dofilewrite (td=0xdabca700, fp=0xda7c12d0, fd=1, buf=0x80a6d80, nbyte=8192,
offset=-1, flags=0) at /local0/scratch/usr/src/sys/sys/file.h:186
#5 0xc021fce4 in write (td=0xdabca700, uap=0xdabfed20)
at /local0/scratch/usr/src/sys/kern/sys_generic.c:332
#6 0xc0326d8f in syscall (frame={tf_fs = 47, tf_es = 47, tf_ds = 47, tf_edi = 134901120,
tf_esi = 8192, tf_ebp = -1077937820, tf_isp = -624956044, tf_ebx = 971, tf_edx = 184,
tf_ecx = 0, tf_eax = 4, tf_trapno = 0, tf_err = 2, tf_eip = 134592700, tf_cs = 31,
tf_eflags = 663, tf_esp = -1077937864, tf_ss = 47})
at /local0/scratch/usr/src/sys/i386/i386/trap.c:1033
#7 0xc0317b1d in syscall_with_err_pushed ()
#8 0x804e693 in ?? ()
#9 0x804e445 in ?? ()
#10 0x804cb5f in ?? ()
#11 0x8048a66 in ?? ()
#12 0x804882d in ?? ()
#13 0x8048135 in ?? ()
--Q68bSM7Ycu6FN28Q
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.0.6 (FreeBSD)
Comment: For info see http://www.gnupg.org
iD8DBQE8x8C6Wry0BWjoQKURAofqAKCBypIjQc5o/oN2ExpAWn6x/JICBQCgmjEc
KDJz4wbRdJpdvv1DQRc70dY=
=xxK1
-----END PGP SIGNATURE-----
--Q68bSM7Ycu6FN28Q--
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Thu Apr 25 10:12:11 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from mail.speakeasy.net (mail17.speakeasy.net [216.254.0.217])
by hub.freebsd.org (Postfix) with ESMTP id 384EC37B43F
for ; Thu, 25 Apr 2002 10:11:44 -0700 (PDT)
Received: (qmail 31637 invoked from network); 25 Apr 2002 17:11:42 -0000
Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender )
by mail17.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP
for ; 25 Apr 2002 17:11:42 -0000
Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1])
by server.baldwin.cx (8.11.6/8.11.6) with ESMTP id g3PHBgv11006;
Thu, 25 Apr 2002 13:11:42 -0400 (EDT)
(envelope-from jhb@FreeBSD.org)
Message-ID:
X-Mailer: XFMail 1.5.2 on FreeBSD
X-Priority: 3 (Normal)
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 8bit
MIME-Version: 1.0
In-Reply-To: <20020425013922.A27152@xor.obsecurity.org>
Date: Thu, 25 Apr 2002 13:10:50 -0400 (EDT)
From: John Baldwin
To: Kris Kennaway
Subject: RE: 4 panics under 5.0 on ports cluster
Cc: fs@FreeBSD.org, current@FreeBSD.org
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
On 25-Apr-2002 Kris Kennaway wrote:
> panic: sleeping thread owns a mutex
> Uptime: 8h52m59s
> (kgdb) bt
>#0 dumpsys () at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:506
>#1 0xc0207cb0 in boot (howto=260) at
>#/local0/scratch/usr/src/sys/kern/kern_shutdown.c:338
>#2 0xc020814f in panic (fmt=0xc0367580 "sleeping thread owns a mutex")
> at /local0/scratch/usr/src/sys/kern/kern_shutdown.c:648
>#3 0xc0200a35 in propagate_priority (td=0xcd23d400)
> at /local0/scratch/usr/src/sys/kern/kern_mutex.c:110
Can you go to this frame, then dump the contents of 'm' to find the misbehaving
mutex? WITNESS should have warned about this but I guess getting people to run
WITNESS is too much to ask.
--
John Baldwin <>< http://www.FreeBSD.org/~jhb/
"Power Users Use the Power to Serve!" - http://www.FreeBSD.org/
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Fri Apr 26 10:15:44 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from mk-smarthost-1.mail.uk.tiscali.com (mk-smarthost-1.mail.uk.tiscali.com [212.74.112.71])
by hub.freebsd.org (Postfix) with ESMTP
id 7D69037B404; Fri, 26 Apr 2002 10:15:38 -0700 (PDT)
Received: from [212.139.129.126] (helo=bloodhound.uk.worldonline.com)
by mk-smarthost-1.mail.uk.tiscali.com with esmtp (Exim 3.35 #1)
id 1719JS-0000bE-00; Fri, 26 Apr 2002 18:15:14 +0100
Received: from brian by bloodhound.uk.worldonline.com with local (Exim 3.22 #1)
id 1719Jn-0000jD-00; Fri, 26 Apr 2002 18:15:35 +0100
Date: Fri, 26 Apr 2002 18:15:35 +0100
From: Brian Candler
To: freebsd-fs@freebsd.org, freebsd-net@freebsd.org
Subject: NFS clearing attribute cache in nfs_open
Message-ID: <20020426181535.B2748@linnet.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
User-Agent: Mutt/1.2.5i
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
I have been tracing some performance problems on diskless systems. In
particular, the following test program:
perl -e 'for ($i=0;$i<1000;$i++) { open F,"; close F;}'
generates 1000 'access' transactions, and hence an exchange of 2000 UDP
packets, just from repeatedly opening the same file.
After some digging around, I have found the cause: the NFS attribute cache
for a file is explicitly invalidated every time the file is opened.
[sys/nfs/nfs_vnops.c]
static int
nfs_open(ap)
...
if ((nmp->nm_flag & NFSMNT_NQNFS) == 0)
np->n_attrstamp = 0; /* For Open/Close consistency */
return (0);
}
For test purposes I changed this to
if ((nmp->nm_flag & NFSMNT_NQNFS) == 0 && (np->n_flag & NMODIFIED))
np->n_attrstamp = 0; /* For Open/Close consistency */
return (0);
and suddenly the problem went away - attributes were being cached happily,
and NFS traffic dropped to virtually zero.
Now, there is obviously some "consistency" issue to beware of. Are there any
NFS gurus out there who can say why it is necessary to clear the attribute
cache on _every_ open? Could it safely be made less restrictive, e.g. don't
clear the cache when opening a file for read? I think there are some
potentially large performance gains for diskless server clusters, where the
same file is being repeatedly exec()'d.
I see that the code in nfs_close doesn't invalidate the cache unless the
file has been modified. However that doesn't help much if the cache is going
to get invalidated anyway the next time the file is opened :-)
Many thanks,
Brian Candler.
P.S. I am working to FreeBSD-4.5-STABLE-20020426
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Fri Apr 26 10:54:54 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from elvis.mu.org (elvis.mu.org [192.203.228.196])
by hub.freebsd.org (Postfix) with ESMTP
id 7998737B41A; Fri, 26 Apr 2002 10:54:51 -0700 (PDT)
Received: by elvis.mu.org (Postfix, from userid 1192)
id 51A67AE28D; Fri, 26 Apr 2002 10:54:51 -0700 (PDT)
Date: Fri, 26 Apr 2002 10:54:51 -0700
From: Alfred Perlstein
To: Brian Candler
Cc: freebsd-fs@freebsd.org, freebsd-net@freebsd.org
Subject: Re: NFS clearing attribute cache in nfs_open
Message-ID: <20020426175451.GG1530@elvis.mu.org>
References: <20020426181535.B2748@linnet.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20020426181535.B2748@linnet.org>
User-Agent: Mutt/1.3.27i
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
* Brian Candler [020426 10:15] wrote:
>
> Now, there is obviously some "consistency" issue to beware of. Are there any
> NFS gurus out there who can say why it is necessary to clear the attribute
> cache on _every_ open? Could it safely be made less restrictive, e.g. don't
> clear the cache when opening a file for read? I think there are some
> potentially large performance gains for diskless server clusters, where the
> same file is being repeatedly exec()'d.
Open()s should be as consistant as possible, this requires a cache flush.
However, If you were to make this a tunable (defaults to off) I
would commit it.
If you can show that Solaris caches open()s as well I'd be ok with
turning it on by default. :)
--
-Alfred Perlstein [alfred@freebsd.org]
'Instead of asking why a piece of software is using "1970s technology,"
start asking why software is ignoring 30 years of accumulated wisdom.'
Tax deductible donations for FreeBSD: http://www.freebsdfoundation.org/
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Fri Apr 26 13: 5:40 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from OL101-181.fibertel.com.ar (OL101-181.fibertel.com.ar [24.232.181.101])
by hub.freebsd.org (Postfix) with SMTP id 46FCB37B417
for ; Fri, 26 Apr 2002 13:04:33 -0700 (PDT)
Message-ID: <41165-22002452620731770@cyco>
To: "Lina Avellaneda"
From: "PromocionaTuShow"
Subject: Tango Argentino: Prensa Especializada proclama a "TangoLina"
Date: Fri, 26 Apr 2002 17:07:32 -0300
MIME-Version: 1.0
Content-Type: multipart/alternative;
boundary="----=_NextPart_84815C5ABAF209EF376268C8"
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
------=_NextPart_84815C5ABAF209EF376268C8
Content-type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
*Gacetilla de Prensa - Se Agradece su Difusion* *No utilice RESPONDER o RE=
PLY para conestar este mensaje* =20
CRITICAS Y COMENTARIOS DEL C=2ED=2E "TANGOLINA"
Lina tiene el =E1ngel del barrio, la frescura de su lugar de origen, la be=
lleza interior provocada por el hecho de transcurrir ni=F1ez, adolescencia=
y adultez en el clima de las viejas casas con patio=2E Dif=EDcil es defin=
irla en su integridad: por un lado, autora y compositora de obras con el s=
abor indisimulable del tango, con el paisaje del barrio=2E Por otro, canta=
nte con voz profunda y sensible, int=E9rprete medida, con el gesto justo y=
el adem=E1n a tiempo=2E JORGE GOTTLING - CLARIN - 2001
En su flamante compact "TangoLina", afianza su relaci=F3n con la m=FAsica =
ciudadana=2E Puede apreciarse un hilo conductor que le da coherencia en su=
diversidad=2E Una versi=F3n propia, de estilo sobrio y despojado lejos de=
los esquemas estereotipados que el tango traz=F3 para las mujeres=2E FERN=
ANDO D ADDARIO - PAGINA 12 =962001
En los tangos tradicionales se recrea la fuerza interpretativa de Lina, ca=
paz de "recontar" esos tangos que forman parte de nuestro pasado=2E La otr=
a Lina, la que mira a su alrededor, se sensibiliza con aquello que nos pas=
a y lo vuelca en temas con fuerte impronta tanguera, de alto vuelo po=E9ti=
co y musical=2E Lina est=E1 llamada a ocupar un lugar prioritario entre la=
s grandes cantantes de nuestro Pa=EDs=2E WILMAR MERINO - DIARIO POPULAR - =
2001
Un "Se=F1or Disco"=2E Maduro, con unidad y l=EDnea tanguera, con estilo en=
cada surco=2E Lina se muestra como una verdadera cantante de tangos, bien=
modulada encastra en lo cl=E1sico del tango pero con un aire actual encan=
tador=2E Tiene arrabal, ternura, tono brav=EDo y sentimental=2E Sin desper=
dicio=2E Autora de Aquel Cielo, Despu=E9s e Insolaci=F3n, tangos que puede=
n adornar el repertorio de cualquier cantor contempor=E1neo=2E Un verdader=
o aporte al tango=2E CARLOS GROPPA - TANGOREPORTER - LOS ANGELES=2ECALIFOR=
NIA=2EEEUU=2E
Lina Avellaneda tiene una buena voz que maneja profesionalmente=2E Tiene a=
dem=E1s muy buen gusto para elegir repertorio=2E Es una mujer inquieta que=
no solo expresa cosas ajenas, canta con toda su potencia desplegando toda=
s las posibilidades que tienen sus cuerdas vocales=2E RICARDO SALTON - AMB=
ITO FINANCIERO - 2001
Lina Avellaneda es hoy una de las mejores cantantes de tango=2E Siguiendo =
los pasos de Susana Rinaldi, tiene algo tambi=E9n de Adriana Varela en cua=
nto a coraje, pasi=F3n y sensibilidad de las grandes artistas=2E Su voz es=
clara, melodiosa y sobre todo muy personal=2E SANDRA ANGEROSA - BUENOS AI=
RES HERALD - 2001
Due=F1a de un fraseo particular que destaca los mejores rasgos de su voz=2E=
PABLO WAISBERG - NOTICIAS ARGENTINAS - 2001
"Aquel cielo" es una exacta radiograf=EDa de esta =E9poca desesperada, esc=
rito y musicalizado por la propia Lina=2E La voz corajuda y de vibrante di=
cci=F3n de la Avellaneda encuentra su mejor momento=2E REVISTA LUNA - 2001=
AGRADECEMOS A LA GENTE DE "EL TANGAUTA", "EL CLUB DE TANGO", EL DIA (LA PL=
ATA), CRONICA, B=2EA=2ETANGO, VEA MAS, Y A LOS NUMEROSOS MEDIOS DEL INTERI=
OR DEL PA=CDS POR SUS GENEROSAS CR=CDTICAS=2E=20
"Ciudadana" y "Tangolina" a disposici=F3n de la prensa=2E Clips y show en =
vivo para insert TV=2E Gracias por difundir la presente
www=2Elinaavellaneda=2Ecom=2Ear
Para ser removido de nuestra lista enviar un e-mail a bloquearenvios@fiber=
tel=2Ecom=2Ear escribiendo s=F3lo Remover en Subject
------=_NextPart_84815C5ABAF209EF376268C8
Content-Type: text/html; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
*Gacetilla =
de Prensa - Se Agradece=20
su Difusion* *No utilice RESPONDER o REPLY para conestar este=20
mensaje* =20
=20
=
CRITICAS=20
Y COMENTARIOS DEL C=2ED=2E "TANGOLINA"
Lina tiene el =E1ngel del barri=
o, la=20
frescura de su lugar de origen, la belleza interior provocada por el hecho=
de=20
transcurrir ni=F1ez, adolescencia y adultez en el clima de las viejas casa=
s con=20
patio=2E Dif=EDcil es definirla en su integridad: por un lado, autora y co=
mpositora=20
de obras con el sabor indisimulable del tango, con el paisaje del barrio=2E=
Por=20
otro, cantante con voz profunda y sensible, int=E9rprete medida, con el ge=
sto=20
justo y el adem=E1n a tiempo=2E JORGE GOTTLING=
- CLARIN -=20
2001
En su flamante =
compact=20
"TangoLina", afianza su relaci=F3n con la m=FAsica ciudadana=2E Puede apre=
ciarse un=20
hilo conductor que le da coherencia en su diversidad=2E Una versi=F3n prop=
ia, de=20
estilo sobrio y despojado lejos de los esquemas estereotipados que el tang=
o=20
traz=F3 para las mujeres=2E FERNANDO D AD=
DARIO - PAGINA=20
12 =962001
En los tangos tradicionales se recrea la fuerza interpretativa de Lina,=
capaz=20
de "recontar" esos tangos que forman parte de nuestro pasado=2E La otra Li=
na, la=20
que mira a su alrededor, se sensibiliza con aquello que nos pasa y lo vuel=
ca en=20
temas con fuerte impronta tanguera, de alto vuelo po=E9tico y musical=2E L=
ina est=E1=20
llamada a ocupar un lugar prioritario entre las grandes cantantes de nuest=
ro=20
Pa=EDs=2E WILMAR MERINO - DIARIO POP=
ULAR -=20
2001
=
P>
Un "Se=F1or Disco"=2E Maduro, con unidad y l=EDnea tanguera, con estilo=
en cada=20
surco=2E Lina se muestra como una verdadera cantante de tangos, bien modul=
ada=20
encastra en lo cl=E1sico del tango pero con un aire actual encantador=2E T=
iene=20
arrabal, ternura, tono brav=EDo y sentimental=2E Sin desperdicio=2E Autora=
de Aquel=20
Cielo, Despu=E9s e Insolaci=F3n, tangos que pueden adornar el repertorio d=
e=20
cualquier cantor contempor=E1neo=2E Un verdadero aporte al tango=2E CARLOS GROPPA - TANGOREPORTER - LOS=20
ANGELES=2ECALIFORNIA=2EEEUU=2E
Lina Avellaneda tiene una buena voz que maneja profesionalmente=2E Tien=
e adem=E1s=20
muy buen gusto para elegir repertorio=2E Es una mujer inquieta que no solo=
expresa=20
cosas ajenas, canta con toda su potencia desplegando todas las posibilidad=
es que=20
tienen sus cuerdas vocales=2E RICARDO SAL=
TON - AMBITO=20
FINANCIERO - 2001
Lina Avellaneda es hoy una de las mejores cantantes de tango=2E Siguien=
do los=20
pasos de Susana Rinaldi, tiene algo tambi=E9n de Adriana Varela en cuanto =
a=20
coraje, pasi=F3n y sensibilidad de las grandes artistas=2E Su voz es clara=
,=20
melodiosa y sobre todo muy personal=2E SA=
NDRA ANGEROSA=20
- BUENOS AIRES HERALD - 2001
Due=F1a de un fraseo particular que destaca los mejores rasgos de su vo=
z=2E=20
PABLO WAISBERG - NOTICIAS ARGENTINAS -=20=
2001
"Aquel cielo" es una exacta radiograf=EDa de esta =E9poca desesperada, =
escrito y=20
musicalizado por la propia Lina=2E La voz corajuda y de vibrante dicci=F3n=
de la=20
Avellaneda encuentra su mejor momento=2E =
REVISTA LUNA=20
- 2001
AGRADECEMOS A LA GENTE DE "EL TANGAUTA", "EL CLUB=
DE=20
TANGO", EL DIA (LA PLATA), CRONICA, B=2EA=2ETANGO, VEA MAS, Y A LOS NUMERO=
SOS MEDIOS=20
DEL INTERIOR DEL PA=CDS POR SUS GENEROSAS CR=CDTICAS=2E
"Ciudadana" y "Tangolina"=
a=20
disposici=F3n de la prensa=2E Clips y show en vivo para insert TV=2E Graci=
as por=20
difundir la presente
www=2Elinaavellaneda=2Ecom=
=2Ear
Para se=
r removido de=20
nuestra lista enviar un e-mail a bloquearenvios@fibertel=
=2Ecom=2Ear escribiendo s=F3lo Remover=
en=20
Subject
------=_NextPart_84815C5ABAF209EF376268C8--
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Fri Apr 26 16:42:59 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from mail.allcaps.org (mail.allcaps.org [208.252.245.17])
by hub.freebsd.org (Postfix) with ESMTP
id 003E337B41A; Fri, 26 Apr 2002 16:42:54 -0700 (PDT)
Received: from mail.allcaps.org (localhost [127.0.0.1])
by mail.allcaps.org (Postfix) with ESMTP
id 6C7CC32601; Fri, 26 Apr 2002 16:42:49 -0700 (PDT)
Received: from localhost (bsder@localhost)
by mail.allcaps.org (8.12.3/8.12.3/Submit) with ESMTP id g3QNgmxo008721;
Fri, 26 Apr 2002 16:42:49 -0700 (PDT)
X-Authentication-Warning: mail.allcaps.org: bsder owned process doing -bs
Date: Fri, 26 Apr 2002 16:42:48 -0700 (PDT)
From: "Andrew P. Lentvorski"
To: Brian Candler
Cc: ,
Subject: Re: NFS clearing attribute cache in nfs_open
In-Reply-To: <20020426181535.B2748@linnet.org>
Message-ID: <20020426162442.N8693-100000@mail.allcaps.org>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
On Fri, 26 Apr 2002, Brian Candler wrote:
> perl -e 'for ($i=0;$i<1000;$i++) { open F,"; close F;}'
I will assume that you wrote this *only* to prove the point. However, if
you are using NFS, you need to check the status of both open *and* close.
Otherwise you are likely to start breeding *very* insidious bugs.
> ... Could it safely be made less restrictive, e.g. don't
> clear the cache when opening a file for read?
In a word, no. Why couldn't the sysadmin be running "make installworld"
on the NFS server while you're running that program? By definition, for
better or worse, NFS is "stateless". The only way in which NFS can know
that your file hasn't changed (been deleted, renamed, etc) is to make that
round trip to the server. Sorry.
> I think there are some
> potentially large performance gains for diskless server clusters, where the
> same file is being repeatedly exec()'d.
Yes, as long as you are willing to risk invalid data. If you are really
into clusters with low-latency, you might want to look into something like
NFS V4 (Is anybody working on that on FreeBSD, anymore?), AFS, CODA, or
something more specialized. Those networked filesystems have a
bidrectional characteristic and cached state protocols so that they can
minimize communication.
-a
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Sat Apr 27 7:20:35 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from internal.mail.telinco.net (internal.mail.telinco.net [212.1.128.4])
by hub.freebsd.org (Postfix) with ESMTP
id 2C80237B41B; Sat, 27 Apr 2002 07:20:30 -0700 (PDT)
Received: from ppp-dp1-mk-66.access.uk.worldonline.com ([212.74.113.66] helo=vaio.linnet.org)
by internal.mail.telinco.net with esmtp (Exim 3.22 #1)
id 171T3s-000CBP-00; Sat, 27 Apr 2002 15:20:28 +0100
Received: (from brian@localhost)
by vaio.linnet.org (8.9.3/8.9.3) id PAA16666;
Sat, 27 Apr 2002 15:27:19 +0100
Date: Sat, 27 Apr 2002 15:27:18 +0100
From: Brian Candler
To: "Andrew P. Lentvorski"
Cc: freebsd-fs@freebsd.org, freebsd-net@freebsd.org
Subject: Re: NFS clearing attribute cache in nfs_open
Message-ID: <20020427152718.A16634@linnet.org>
References: <20020426181535.B2748@linnet.org> <20020426162442.N8693-100000@mail.allcaps.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 1.0pre3us
In-Reply-To: <20020426162442.N8693-100000@mail.allcaps.org>
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
On Fri, Apr 26, 2002 at 04:42:48PM -0700, Andrew P. Lentvorski wrote:
> > ... Could it safely be made less restrictive, e.g. don't
> > clear the cache when opening a file for read?
>
> In a word, no. Why couldn't the sysadmin be running "make installworld"
> on the NFS server while you're running that program? By definition, for
> better or worse, NFS is "stateless". The only way in which NFS can know
> that your file hasn't changed (been deleted, renamed, etc) is to make that
> round trip to the server. Sorry.
Sounds fair. I was talking about the _attribute_ cache, but does re-fetching
the attributes also tell the client that the _content_ of a file has
changed? A version number, perhaps?
> If you are really
> into clusters with low-latency, you might want to look into something like
> NFS V4 (Is anybody working on that on FreeBSD, anymore?), AFS, CODA, or
> something more specialized. Those networked filesystems have a
> bidrectional characteristic and cached state protocols so that they can
> minimize communication.
Will do. For a diskless bootup I think I am restricted to either NFS or
ramdisk for the root filesystem though.
Is it possible to replace the root filesystem with a different one after the
system has started?
Regards,
Brian.
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Sat Apr 27 18:57:27 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from fledge.watson.org (fledge.watson.org [204.156.12.50])
by hub.freebsd.org (Postfix) with ESMTP
id 4DDC737B400; Sat, 27 Apr 2002 18:57:22 -0700 (PDT)
Received: from fledge.watson.org (fledge.pr.watson.org [192.0.2.3])
by fledge.watson.org (8.11.6/8.11.6) with SMTP id g3S1v7w19999;
Sat, 27 Apr 2002 21:57:08 -0400 (EDT)
(envelope-from robert@fledge.watson.org)
Date: Sat, 27 Apr 2002 21:57:07 -0400 (EDT)
From: Robert Watson
X-Sender: robert@fledge.watson.org
To: Brian Candler
Cc: freebsd-fs@freebsd.org, freebsd-net@freebsd.org
Subject: Re: NFS clearing attribute cache in nfs_open
In-Reply-To: <20020426181535.B2748@linnet.org>
Message-ID:
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
On Fri, 26 Apr 2002, Brian Candler wrote:
> I have been tracing some performance problems on diskless systems. In
> particular, the following test program:
>
> perl -e 'for ($i=0;$i<1000;$i++) { open F,"; close F;}'
>
> generates 1000 'access' transactions, and hence an exchange of 2000 UDP
> packets, just from repeatedly opening the same file.
Because access control is performed on the server with NFSv3, not the
client, you have to go to the server when you open a file. The attribute
cache caches information for stat(), not for evaluation during open().
Although open() might stat the file (vop_getattr()), that's really not the
same thing. Try instead a stat() rather than open() and see how the
results change in your performance test. Note that an important reason to
invoke the NFS RPC for access during open() is that the client may not
understand the protection semantics of the server. For example, the
server might support ACLs, but the client might not. Or the server might
support another access control model of another sort. The return from
GETATTR is generally just used for file information rendering as of NFSv3,
not actual evaluation.
If you cache data for open()'s, you risk problems during a revocation
operation. Also, you potentially allow opening files that will become
ESTALE, etc. NFSv2/3 isn't really intended to do this sort of caching.
You might want to investigate AFS, since AFS tends to perform operations
on close() rather than open() once a file is in the cache (and has a
"callback" model to invalidate cached files on meta-data changes of this
sort).
Robert N M Watson FreeBSD Core Team, TrustedBSD Project
robert@fledge.watson.org NAI Labs, Safeport Network Services
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Sat Apr 27 19:13:45 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from fledge.watson.org (fledge.watson.org [204.156.12.50])
by hub.freebsd.org (Postfix) with ESMTP
id 8CCA037B405; Sat, 27 Apr 2002 19:13:40 -0700 (PDT)
Received: from fledge.watson.org (fledge.pr.watson.org [192.0.2.3])
by fledge.watson.org (8.11.6/8.11.6) with SMTP id g3S2DIw21402;
Sat, 27 Apr 2002 22:13:18 -0400 (EDT)
(envelope-from robert@fledge.watson.org)
Date: Sat, 27 Apr 2002 22:13:17 -0400 (EDT)
From: Robert Watson
X-Sender: robert@fledge.watson.org
To: Brian Candler
Cc: "Andrew P. Lentvorski" ,
freebsd-fs@freebsd.org, freebsd-net@freebsd.org
Subject: Re: NFS clearing attribute cache in nfs_open
In-Reply-To: <20020427152718.A16634@linnet.org>
Message-ID:
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
On Sat, 27 Apr 2002, Brian Candler wrote:
> > If you are really
> > into clusters with low-latency, you might want to look into something like
> > NFS V4 (Is anybody working on that on FreeBSD, anymore?), AFS, CODA, or
> > something more specialized. Those networked filesystems have a
> > bidrectional characteristic and cached state protocols so that they can
> > minimize communication.
>
> Will do. For a diskless bootup I think I am restricted to either NFS or
> ramdisk for the root filesystem though.
>
> Is it possible to replace the root filesystem with a different one after
> the system has started?
The trick I've played in this situation is the one I think you're alluding
to with the ramdisk comment above -- I pxeboot a kernel, but have the
loader also pull over an mfsroot containing the root filesystem to md/ffs
mount. I then mounted other filesystems via NFS. A trick I've played a
few times, and I know is popular at certain large web-based providers, is
to then pull down the rest of the OS to a local file system at that point,
and use that for /usr (etc). Depends how much boot latency you can
accept vs. run-time latency. For crash boxes, I tend to lean to the
completely-NFS direction, for some other boxes I've used mixed
local/mfs/nfs. I tend not to use chroot() to change the rootfs, but I
imagine you could do that if you wanted.
One important observation is that newfs can be orders of magnitude faster
than fsck, and scales much better with disk size. Rather than allow a
machine that's pretty stateless to fsck, just rebuild the box. :-)
Our pxeboot loader (and normal loader) are incredibly flexible, and make
it easy to do a whole ton of different kinds of things. For both
experimentation and production service, they can dramatically lower admin
costs by making OS roll forward/back and stateless systems a reality.
Robert N M Watson FreeBSD Core Team, TrustedBSD Project
robert@fledge.watson.org NAI Labs, Safeport Network Services
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message
From owner-freebsd-fs Sat Apr 27 19:15:15 2002
Delivered-To: freebsd-fs@freebsd.org
Received: from cs.com (h195202140212.stp.cm.kabsi.at [195.202.140.212])
by hub.freebsd.org (Postfix) with SMTP
id 2B69D37B421; Sat, 27 Apr 2002 19:14:18 -0700 (PDT)
Received: from [106.212.56.170] by rly-xw05.oxyeli.com with asmtp; Sat, 27 Apr 2002 08:14:30 +1100
Received: from 169.97.210.127 ([169.97.210.127]) by anther.webhostingtotalk.com with SMTP; 27 Apr 2002 19:11:29 +1000
Received: from unknown (HELO asy100.as122.sol-superunderline.com) (96.123.223.178)
by mail.gimmixx.net with asmtp; Sun, 28 Apr 2002 05:08:28 -0300
Received: from sparc.zubilam.net ([21.172.243.140])
by mailout2-eri1.midmouth.com with SMTP; Sun, 28 Apr 2002 02:05:27 +0700
Received: from [85.15.174.48] by rly-xr02.nikavo.net with smtp; 28 Apr 2002 09:02:26 -0700
Reply-To:
Message-ID: <038e28d55b5d$6232d1b8$0cd84cd5@itdlgy>
From:
To:
Cc: , , ,
, , ,
, , ,
, , ,
, ,
,
Subject: Sell on eBay and Make a Fortune!
Date: Sun, 28 Apr 2002 12:04:27 -1000
MiME-Version: 1.0
Content-Type: multipart/mixed;
boundary="----=_NextPart_000_00C7_80E03A1C.C5823D85"
X-Priority: 3 (Normal)
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 6.00.2600.0000
Importance: Normal
Sender: owner-freebsd-fs@FreeBSD.ORG
Precedence: bulk
List-ID:
List-Archive: (Web Archive)
List-Help: (List Instructions)
List-Subscribe:
List-Unsubscribe:
X-Loop: FreeBSD.org
------=_NextPart_000_00C7_80E03A1C.C5823D85
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: base64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To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-fs" in the body of the message