subject:"\[OpenAFS\] File systems on Linux, again."

Re: [OpenAFS] File systems on Linux, again.

2007-12-04 Thread Dirk Heinrichs

Am Montag, 3. Dezember 2007 schrieb ext John Lockard:

> I'm curious about those using ext3...  Are you running
> ext3 with or without journaling?

w/o journaling it's called ext2 :-)

Bye...

Dirk
-- 
Dirk Heinrichs  | Tel:  +49 (0)162 234 3408
Configuration Manager   | Fax:  +49 (0)211 47068 111
Capgemini Deutschland   | Mail: [EMAIL PROTECTED]
Wanheimerstraße 68  | Web:  http://www.capgemini.com
D-40468 Düsseldorf  | ICQ#: 110037733
GPG Public Key C2E467BB | Keyserver: www.keyserver.net


signature.asc
Description: This is a digitally signed message part.

Re: [OpenAFS] File systems on Linux, again.

2007-12-04 Thread Steve Simmons



On Dec 3, 2007, at 9:53 AM, John Lockard wrote:


I'm curious about those using ext3...  Are you running
ext3 with or without journaling?


With.
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

RE: [OpenAFS] File systems on Linux, again. Numbers

2007-12-04 Thread Jerry Normandin

Cool!  Your file create times are on par with NFS. 

I am planning on starting to upgrade servers today.

-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Martin Ginkel
Sent: Monday, December 03, 2007 3:25 PM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again. Numbers

On Friday 30 November 2007 02:52:06 pm Jerry Normandin wrote:
> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for
this.
> I inherited a mess here that I am fixing.  My predecessor built is
using
> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
> create,
> Delete, or rename files.  I tested with Bonnie++... here are my stats:
>
> Initial file performance baselines taken from ENG02 with 4096kbyte
> cache:
>
> > recommendation for which file system to use on Linux AFS file
servers.
> > Ext3, XFS, JFS, something else?

Here are my numbers:
Boundary-conditions:
 Client: 5G disk cache (ext2) openafs 1.4.5 Core Duo 2.7GHz
Bonnie++ with 4G files
 Server: openafs 1.4.5 on 2x Dual Xeon 3.2
Disk: Dell Perc 4 Raid 5 
Connection via switched 1Gbit Ethernet, 0.125ms Roundtrip

server partitions:
EXT3:
Version 1.01d   --Sequential Output-- --Sequential Input-
--Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
pc5334G  7615  39  7362  36  4607  31 12005  14  8932   1
36.5  18
--Sequential Create-- Random
Create
-Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
 16   717  38  6705  80  1079  33   743  38  2735  55
1269  27

XFS:
Version 1.01d   --Sequential Output-- --Sequential Input-
--Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
pc5334G  7575  43  7393  40  4650  33 11804  13  8949   1
37.9  21
--Sequential Create-- Random
Create
-Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
 16   659  35  6738  82  1000  30   695  36  2711  55
1172  24

REISER:
Version 1.01d   --Sequential Output-- --Sequential Input-
--Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
pc5334G  7552  39  7599  36  4645  31 11817  13  8784   1
37.6  20
--Sequential Create-- Random
Create
-Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
 16   679  34  6670  83  1048  33   721  38  2697  53
1072  22

HTH
Martin
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again. Numbers

2007-12-03 Thread Martin Ginkel

On Friday 30 November 2007 02:52:06 pm Jerry Normandin wrote:
> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for this.
> I inherited a mess here that I am fixing.  My predecessor built is using
> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
> create,
> Delete, or rename files.  I tested with Bonnie++... here are my stats:
>
> Initial file performance baselines taken from ENG02 with 4096kbyte
> cache:
>
> > recommendation for which file system to use on Linux AFS file servers.
> > Ext3, XFS, JFS, something else?

Here are my numbers:
Boundary-conditions:
 Client: 5G disk cache (ext2) openafs 1.4.5 Core Duo 2.7GHz
Bonnie++ with 4G files
 Server: openafs 1.4.5 on 2x Dual Xeon 3.2
Disk: Dell Perc 4 Raid 5 
Connection via switched 1Gbit Ethernet, 0.125ms Roundtrip

server partitions:
EXT3:
Version 1.01d   --Sequential Output-- --Sequential Input- --Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP
pc5334G  7615  39  7362  36  4607  31 12005  14  8932   1  36.5  18
--Sequential Create-- Random Create
-Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
 16   717  38  6705  80  1079  33   743  38  2735  55  1269  27

XFS:
Version 1.01d   --Sequential Output-- --Sequential Input- --Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP
pc5334G  7575  43  7393  40  4650  33 11804  13  8949   1  37.9  21
--Sequential Create-- Random Create
-Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
 16   659  35  6738  82  1000  30   695  36  2711  55  1172  24

REISER:
Version 1.01d   --Sequential Output-- --Sequential Input- --Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP
pc5334G  7552  39  7599  36  4645  31 11817  13  8784   1  37.6  20
--Sequential Create-- Random Create
-Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
 16   679  34  6670  83  1048  33   721  38  2697  53  1072  22

HTH
Martin
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

RE: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Jerry Normandin

Would you like me to upload my openafs 4.5.1 32bit rpms for redhat
enterprise 3.0 that I just built to the openafs website?

From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Derrick Brashear
Sent: Monday, December 03, 2007 2:55 PM
To: OpenAFS-Info
Subject: Re: [OpenAFS] File systems on Linux, again.

On Dec 3, 2007 2:50 PM, Jerry Normandin <[EMAIL PROTECTED]>
wrote:

ah.. sorry about that I intended to post to the group.  I thought I hit
reply-all.

Here's where I got the SRPM:

http://www.openafs.org/dl/openafs/1.4.5/rhel3/SRPMS/openafs-1.4.5-rhel3.
1.src.rpm 

openafs-buildall.sh fails.

Derrick,

Do you still have a copy of the srpm that you built openafs 1.4.5 on
redhat enterprise 3 with?

i uploaded it.  the srpm, like the rpms, came from me. you never
answered what was on the line in the spec file it complained about.

RE: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Jerry Normandin

I thought I did.  What release did you build the srpm on?  

 

I have:

[EMAIL PROTECTED] SOURCES]# more /etc/issue

Red Hat Enterprise Linux ES release 3 (Taroon Update 8)

 

Here's how the buildall script bombs:

 

Processing files: openafs-kernel-hugemem-1.4.5-2.4.21_47.EL_1

error: File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*

 

 

RPM build errors:

File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*

[EMAIL PROTECTED] SOURCES]#

 

the kernel directory is NOT in /var/tmp  so it's
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/fs/openafs/o
penafs.*

 

That is the first error.

 

That's a no-brainer. I fixed the spec file and built the openafs kernel
rpms.

--define "build_modules 1" \   is  now --define "build_userspace 1" \

 

All I did was to select to build the userspace tools instead of the
modules.  

 

It fails with:
[EMAIL PROTECTED] SOURCES]# ./openafs-buildall.sh

Building OpenAFS for rhel3

rpmbuild -ba --define osvers rhel3 /usr/src/redhat/SPECS/openafs.spec

Building for /usr/src/linux-2.4.21-47.EL, 2.4.21-47.EL, i686

Building target platforms: i686

Building for target i686

error: parse error in expression

error: /usr/src/redhat/SPECS/openafs.spec:349: parseExpressionBoolean
returns -1

Checking for unpackaged file(s): /usr/lib/rpm/check-files
/var/tmp/openafs-1.4.5-root

Building for /usr/src/linux-2.4.21-47.EL, 2.4.21-47.EL, athlon

Building target platforms: athlon

Building for target athlon

error: parse error in expression

error: /usr/src/redhat/SPECS/openafs.spec:349: parseExpressionBoolean
returns -1

Checking for unpackaged file(s): /usr/lib/rpm/check-files
/var/tmp/openafs-1.4.5-root

 

It appears that there's a problem with the openafs.spec file 

 

From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Derrick Brashear
Sent: Monday, December 03, 2007 2:55 PM
To: OpenAFS-Info
Subject: Re: [OpenAFS] File systems on Linux, again.

 

 

On Dec 3, 2007 2:50 PM, Jerry Normandin <[EMAIL PROTECTED]>
wrote:

ah.. sorry about that I intended to post to the group.  I thought I hit
reply-all.

 

Here's where I got the SRPM:

 

http://www.openafs.org/dl/openafs/1.4.5/rhel3/SRPMS/openafs-1.4.5-rhel3.
1.src.rpm 

 

openafs-buildall.sh fails.

 

Derrick,

 

Do you still have a copy of the srpm that you built openafs 1.4.5 on
redhat enterprise 3 with?

  

i uploaded it.  the srpm, like the rpms, came from me. you never
answered what was on the line in the spec file it complained about.

Re: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Derrick Brashear

On Dec 3, 2007 2:50 PM, Jerry Normandin <[EMAIL PROTECTED]> wrote:

>  ah.. sorry about that I intended to post to the group.  I thought I hit
> reply-all.
>
>
>
> Here's where I got the SRPM:
>
>
>
>
> http://www.openafs.org/dl/openafs/1.4.5/rhel3/SRPMS/openafs-1.4.5-rhel3.1.src.rpm
>
>
>
> openafs-buildall.sh fails.
>
>
>
> Derrick,
>
>
>
> Do you still have a copy of the srpm that you built openafs 1.4.5 on
> redhat enterprise 3 with?
>
>
>
i uploaded it.  the srpm, like the rpms, came from me. you never answered
what was on the line in the spec file it complained about.

RE: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Jerry Normandin

ah.. sorry about that I intended to post to the group.  I thought I hit
reply-all.

 

Here's where I got the SRPM:

 

http://www.openafs.org/dl/openafs/1.4.5/rhel3/SRPMS/openafs-1.4.5-rhel3.
1.src.rpm

 

openafs-buildall.sh fails.

 

Derrick,

 

Do you still have a copy of the srpm that you built openafs 1.4.5 on
redhat enterprise 3 with?

 

 

 

From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Derrick Brashear
Sent: Monday, December 03, 2007 2:32 PM
To: OpenAFS-Info
Subject: Re: [OpenAFS] File systems on Linux, again.

 

Keep it on the list.

Anyway, this is really the RHEL3 srpm? The hugemem error should have
been fixed in that specfile.

and, 
error: /usr/src/redhat/SPECS/openafs.spec:346: parseExpressionBoolean
returns -1

what's on line 346?

On Dec 3, 2007 2:21 PM, Jerry Normandin <[EMAIL PROTECTED] >
wrote:

OK.. I am running

 

 

This is the first error I get:

Processing files: openafs-kernel-hugemem-1.4.5-2.4.21_47.EL_1

error: File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*

 

 

RPM build errors:

File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*

[EMAIL PROTECTED] SOURCES]#

 

I managed to fix this manually by editing the spec file.  The reason why
there is an error is because there kernel direcory does not exit..

the direcory fs/openafs is directly under :
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem

 

The Second error .. 

 

I modified line 112, I now have:

for arch in $archlist ; do

  echo "Building for $kerndir, $kvers, $arch"

rpmbuild -bb $buildopts \

  --define "fedorakmod 0" \

  --define "osvers $osvers" \

  --define "kernvers $kvers" \

  --define "ksrcdir $kerndir" \

  --define "build_modules 1" \

  --define "build_userspace 1" \

  --target=$arch \

  $specdir/openafs.spec || exit 1

done

  fi

 

openafs-buildall.sh I get :

[EMAIL PROTECTED] SOURCES]# ./openafs-buildall.sh

Building OpenAFS for rhel3

rpmbuild -ba --define osvers rhel3 /usr/src/redhat/SPECS/openafs.spec

Building for /usr/src/linux-2.4.21-47.EL, 2.4.21-47.EL, i686

Building target platforms: i686

Building for target i686

error: parse error in expression

error: /usr/src/redhat/SPECS/openafs.spec:346: parseExpressionBoolean
returns -1

Checking for unpackaged file(s): /usr/lib/rpm/check-files
/var/tmp/openafs-1.4.5-root

error: Installed (but unpackaged) file(s) found:

   /lib/modules/2.4.21-47.EL/fs/openafs/openafs.o

   /lib/modules/2.4.21-47.ELhugemem/fs/openafs/openafs.o

   /lib/modules/2.4.21-47.ELsmp/fs/openafs/openafs.o

 

 

RPM build errors:

parse error in expression

/usr/src/redhat/SPECS/openafs.spec:346: parseExpressionBoolean
returns -1

Installed (but unpackaged) file(s) found:

   /lib/modules/2.4.21-47.EL/fs/openafs/openafs.o

   /lib/modules/2.4.21-47.ELhugemem/fs/openafs/openafs.o

   /lib/modules/2.4.21-47.ELsmp/fs/openafs/openafs.o

[EMAIL PROTECTED] SOURCES]# vi openafs-buildall.sh

[EMAIL PROTECTED] SOURCES]# ls

 

From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Derrick Brashear
Sent: Monday, December 03, 2007 1:54 PM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

 

 

On Dec 3, 2007 1:52 PM, Jerry Normandin <[EMAIL PROTECTED]>
wrote:

Has anyone tried to build the openafs userspace code on Redhat ver 3?

the rpm build scripts fail.

This is sort of news, in the sense that the RPMs on the web site were
built by me on RHEL3. 

Get the RHEL3 srpm from the web site and 
rpm -ivh 
then cd /usr/src/redhat/SOURCES/
./openafs-buildall.sh

Report any errors.

Re: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Derrick Brashear

Redirected to the list.

On Dec 3, 2007 2:34 PM, Jerry Normandin <[EMAIL PROTECTED]> wrote:

>  Hmm my beginning of my email should of read
>
>
>
> OK I am running:
>
> [EMAIL PROTECTED] SOURCES]# more /etc/issue
>
> Red Hat Enterprise Linux ES release 3 (Taroon Update 8)
>
> Kernel \r on an \m
>
>
>
> I'm not running 1.4.5 as of yet.
>
>
>
> Were you running AS or ES 3? Is there a difference?
>

No difference. And, I don't remember what's in 1.4.4, and I don't especially
care at this point simply because it's "in the can" so to speak. I'm talking
about the SRPM for rhel3 for 1.4.5.

Re: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Derrick Brashear

Keep it on the list.

Anyway, this is really the RHEL3 srpm? The hugemem error should have been
fixed in that specfile.

and,
error: /usr/src/redhat/SPECS/openafs.spec:346: parseExpressionBoolean
returns -1

what's on line 346?

On Dec 3, 2007 2:21 PM, Jerry Normandin <[EMAIL PROTECTED]> wrote:

>  OK.. I am running
>
>
>
>
>
> This is the first error I get:
>
> Processing files: openafs-kernel-hugemem-1.4.5-2.4.21_47.EL_1
>
> error: File not found by glob: /var/tmp/openafs-1.4.5-root
> /lib/modules/2.4.21-47.ELhugemem/kernel/fs/openafs/openafs.*
>
>
>
>
>
> RPM build errors:
>
> File not found by glob: /var/tmp/openafs-1.4.5-root
> /lib/modules/2.4.21-47.ELhugemem/kernel/fs/openafs/openafs.*
>
> [EMAIL PROTECTED] SOURCES]#
>
>
>
> I managed to fix this manually by editing the spec file.  The reason why
> there is an error is because there kernel direcory does not exit..
>
> the direcory fs/openafs is directly under : /var/tmp/openafs-1.4.5-root
> /lib/modules/2.4.21-47.ELhugemem
>
>
>
> The Second error ..
>
>
>
> I modified line 112, I now have:
>
> for arch in $archlist ; do
>
>   echo "Building for $kerndir, $kvers, $arch"
>
> rpmbuild -bb $buildopts \
>
>   --define "fedorakmod 0" \
>
>   --define "osvers $osvers" \
>
>   --define "kernvers $kvers" \
>
>   --define "ksrcdir $kerndir" \
>
>   --define "build_modules 1" \
>
>   --define "build_userspace 1" \
>
>   --target=$arch \
>
>   $specdir/openafs.spec || exit 1
>
> done
>
>   fi
>
>
>
> openafs-buildall.sh I get :
>
> [EMAIL PROTECTED] SOURCES]# ./openafs-buildall.sh
>
> Building OpenAFS for rhel3
>
> rpmbuild -ba --define osvers rhel3 /usr/src/redhat/SPECS/openafs.spec
>
> Building for /usr/src/linux-2.4.21-47.EL, 2.4.21-47.EL, i686
>
> Building target platforms: i686
>
> Building for target i686
>
> error: parse error in expression
>
> error: /usr/src/redhat/SPECS/openafs.spec:346: parseExpressionBoolean
> returns -1
>
> Checking for unpackaged file(s): /usr/lib/rpm/check-files
> /var/tmp/openafs-1.4.5-root
>
> error: Installed (but unpackaged) file(s) found:
>
>/lib/modules/2.4.21-47.EL/fs/openafs/openafs.o
>
>/lib/modules/2.4.21-47.ELhugemem/fs/openafs/openafs.o
>
>/lib/modules/2.4.21-47.ELsmp/fs/openafs/openafs.o
>
>
>
>
>
> RPM build errors:
>
> parse error in expression
>
> /usr/src/redhat/SPECS/openafs.spec:346: parseExpressionBoolean returns
> -1
>
> Installed (but unpackaged) file(s) found:
>
>/lib/modules/2.4.21-47.EL/fs/openafs/openafs.o
>
>    /lib/modules/2.4.21-47.ELhugemem/fs/openafs/openafs.o
>
>/lib/modules/2.4.21-47.ELsmp/fs/openafs/openafs.o
>
> [EMAIL PROTECTED] SOURCES]# vi openafs-buildall.sh
>
> [EMAIL PROTECTED] SOURCES]# ls
>
>
>
> *From:* [EMAIL PROTECTED] [mailto:
> [EMAIL PROTECTED] *On Behalf Of *Derrick Brashear
> *Sent:* Monday, December 03, 2007 1:54 PM
> *To:* openafs-info@openafs.org
> *Subject:* Re: [OpenAFS] File systems on Linux, again.
>
>
>
>
>
> On Dec 3, 2007 1:52 PM, Jerry Normandin <[EMAIL PROTECTED]> wrote:
>
> Has anyone tried to build the openafs userspace code on Redhat ver 3?
>
> the rpm build scripts fail.
>
> This is sort of news, in the sense that the RPMs on the web site were
> built by me on RHEL3.
>
> Get the RHEL3 srpm from the web site and
> rpm -ivh
> then cd /usr/src/redhat/SOURCES/
> ./openafs-buildall.sh
>
> Report any errors.
>
>
>

Re: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Derrick Brashear

On Dec 3, 2007 1:52 PM, Jerry Normandin <[EMAIL PROTECTED]> wrote:

>  Has anyone tried to build the openafs userspace code on Redhat ver 3?
>
> the rpm build scripts fail.
>
> This is sort of news, in the sense that the RPMs on the web site were
built by me on RHEL3.

Get the RHEL3 srpm from the web site and
rpm -ivh
then cd /usr/src/redhat/SOURCES/
./openafs-buildall.sh

Report any errors.

RE: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Jerry Normandin

Has anyone tried to build the openafs userspace code on Redhat ver 3?

the rpm build scripts fail.

 

I'm attempting to build the source manually.

I'd prefer to build the rpms to manage the 6 nodes.

 

 

 

From: Derrick Brashear [mailto:[EMAIL PROTECTED] 
Sent: Monday, December 03, 2007 10:13 AM
To: Jerry Normandin
Cc: John Lockard; openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

 

the spec file is fixed in CVS and will be in thenext version also.



On Dec 3, 2007 10:02 AM, Jerry Normandin <[EMAIL PROTECTED]>
wrote: 

with.  I was asked to upgrade to 1.4.5 and then gather some Bonnie++
bencmarks again before I resort to changing the underlying filesystem to

xfs.


So I'm working on getting afs 1.4.5 to build on redhat 3 AS (yes I am
locked into redhat 3 for now)
I'm currently working on fixing the rpm build because there must be some
typos in the rpm spec: 

Processing files: openafs-kernel-hugemem-1.4.5-2.4.21_47.EL_1
error: File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*


RPM build errors: 
   File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*/kernel/fs/openafs/openafs.*

The problem is that a kernel direcictory does not exist under 
2.4.21-47.ELhugemem
I'm fixing it now and will attempt again.




-Original Message-
From: [EMAIL PROTECTED] 

[mailto:[EMAIL PROTECTED] On Behalf Of John Lockard
Sent: Monday, December 03, 2007 9:54 AM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

I'm curious about those using ext3...  Are you running
ext3 with or without journaling?

-John

On Fri, Nov 30, 2007 at 06:59:29PM -0800, Jerry Normandin wrote: 
>
> Please send me a Bonnie++ report regarding your AFS setup.
> Our setup "works".. but.. it could be much faster.
> Bonnie show's me that file creation, deletion, and rename takes
forever
> read/writes are fine.
> Please send me your report so I can compare. And what version of
open-afs are you running.
>
> -Original Message-
> From: [EMAIL PROTECTED] on behalf of Mike Garrison
> Sent: Fri 11/30/2007 4:41 PM
> To: openafs-info@openafs.org
> Subject: Re: [OpenAFS] File systems on Linux, again. 
>
>
> On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:
>
> > "Jerry Normandin" <[EMAIL PROTECTED]> writes:
> > 
> >> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for

> >> this.
> >> I inherited a mess here that I am fixing.  My predecessor built is

> >> using 
> >> Ext3 for the /vicepa filesystems.  It takes a hell of a long time
to
> >> create, Delete, or rename files.
> >
> > *shrug*.  It works just fine for us.
>
> Works fine for us at UMich too. 

--
Brain: Pinky, Are you pondering what I'm pondering?
Pinky: I think so, but what if the chicken won't wear the nylons?
---
John M. Lockard |  U of Michigan - School of Information 
 Unix and Security Admin |  1214 SI Norsth - 1075 Beal Ave.
 [EMAIL PROTECTED] |Ann Arbor, MI  48109-2112
  www.umich.edu/~jlockard <http://www.umich.edu/%7Ejlockard>  |
734-615-8776 | 734-647-8045 FAX
---
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info
___ 
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Derrick Brashear

the spec file is fixed in CVS and will be in thenext version also.


On Dec 3, 2007 10:02 AM, Jerry Normandin <[EMAIL PROTECTED]> wrote:

> with.  I was asked to upgrade to 1.4.5 and then gather some Bonnie++
> bencmarks again before I resort to changing the underlying filesystem to
> xfs.
>
>
> So I'm working on getting afs 1.4.5 to build on redhat 3 AS (yes I am
> locked into redhat 3 for now)
> I'm currently working on fixing the rpm build because there must be some
> typos in the rpm spec:
>
> Processing files: openafs-kernel-hugemem-1.4.5-2.4.21_47.EL_1
> error: File not found by glob:
> /var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
> enafs/openafs.*
>
>
> RPM build errors:
>File not found by glob:
> /var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
> enafs/openafs.*/kernel/fs/openafs/openafs.*
>
> The problem is that a kernel direcictory does not exist under
> 2.4.21-47.ELhugemem
> I'm fixing it now and will attempt again.
>
>
>
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of John Lockard
> Sent: Monday, December 03, 2007 9:54 AM
> To: openafs-info@openafs.org
> Subject: Re: [OpenAFS] File systems on Linux, again.
>
> I'm curious about those using ext3...  Are you running
> ext3 with or without journaling?
>
> -John
>
> On Fri, Nov 30, 2007 at 06:59:29PM -0800, Jerry Normandin wrote:
> >
> > Please send me a Bonnie++ report regarding your AFS setup.
> > Our setup "works".. but.. it could be much faster.
> > Bonnie show's me that file creation, deletion, and rename takes
> forever
> > read/writes are fine.
> > Please send me your report so I can compare. And what version of
> open-afs are you running.
> >
> > -Original Message-
> > From: [EMAIL PROTECTED] on behalf of Mike Garrison
> > Sent: Fri 11/30/2007 4:41 PM
> > To: openafs-info@openafs.org
> > Subject: Re: [OpenAFS] File systems on Linux, again.
> >
> >
> > On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:
> >
> > > "Jerry Normandin" <[EMAIL PROTECTED]> writes:
> > >
> > >> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for
>
> > >> this.
> > >> I inherited a mess here that I am fixing.  My predecessor built is
>
> > >> using
> > >> Ext3 for the /vicepa filesystems.  It takes a hell of a long time
> to
> > >> create, Delete, or rename files.
> > >
> > > *shrug*.  It works just fine for us.
> >
> > Works fine for us at UMich too.
>
> --
> Brain: Pinky, Are you pondering what I'm pondering?
> Pinky: I think so, but what if the chicken won't wear the nylons?
> ---
> John M. Lockard |  U of Michigan - School of Information
>  Unix and Security Admin |  1214 SI Norsth - 1075 Beal Ave.
>  [EMAIL PROTECTED] |Ann Arbor, MI  48109-2112
>  www.umich.edu/~jlockard <http://www.umich.edu/%7Ejlockard> |
> 734-615-8776 | 734-647-8045 FAX
> ---
> ___
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
> ___
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
>

RE: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread Jerry Normandin

with.  I was asked to upgrade to 1.4.5 and then gather some Bonnie++
bencmarks again before I resort to changing the underlying filesystem to
xfs.


So I'm working on getting afs 1.4.5 to build on redhat 3 AS (yes I am
locked into redhat 3 for now)
I'm currently working on fixing the rpm build because there must be some
typos in the rpm spec:

Processing files: openafs-kernel-hugemem-1.4.5-2.4.21_47.EL_1
error: File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*


RPM build errors:
File not found by glob:
/var/tmp/openafs-1.4.5-root/lib/modules/2.4.21-47.ELhugemem/kernel/fs/op
enafs/openafs.*/kernel/fs/openafs/openafs.*

The problem is that a kernel direcictory does not exist under
2.4.21-47.ELhugemem
I'm fixing it now and will attempt again.



-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of John Lockard
Sent: Monday, December 03, 2007 9:54 AM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

I'm curious about those using ext3...  Are you running
ext3 with or without journaling?

-John

On Fri, Nov 30, 2007 at 06:59:29PM -0800, Jerry Normandin wrote:
> 
> Please send me a Bonnie++ report regarding your AFS setup.
> Our setup "works".. but.. it could be much faster.
> Bonnie show's me that file creation, deletion, and rename takes
forever
> read/writes are fine.
> Please send me your report so I can compare. And what version of
open-afs are you running.
> 
> -Original Message-
> From: [EMAIL PROTECTED] on behalf of Mike Garrison
> Sent: Fri 11/30/2007 4:41 PM
> To: openafs-info@openafs.org
> Subject: Re: [OpenAFS] File systems on Linux, again.
>  
> 
> On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:
> 
> > "Jerry Normandin" <[EMAIL PROTECTED]> writes:
> >
> >> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for

> >> this.
> >> I inherited a mess here that I am fixing.  My predecessor built is

> >> using
> >> Ext3 for the /vicepa filesystems.  It takes a hell of a long time
to
> >> create, Delete, or rename files.
> >
> > *shrug*.  It works just fine for us.
> 
> Works fine for us at UMich too.

-- 
Brain: Pinky, Are you pondering what I'm pondering?
Pinky: I think so, but what if the chicken won't wear the nylons?
---
 John M. Lockard |  U of Michigan - School of Information
 Unix and Security Admin |  1214 SI Norsth - 1075 Beal Ave.
  [EMAIL PROTECTED] |Ann Arbor, MI  48109-2112
 www.umich.edu/~jlockard | 734-615-8776 | 734-647-8045 FAX
---
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-12-03 Thread John Lockard

I'm curious about those using ext3...  Are you running
ext3 with or without journaling?

-John

On Fri, Nov 30, 2007 at 06:59:29PM -0800, Jerry Normandin wrote:
> 
> Please send me a Bonnie++ report regarding your AFS setup.
> Our setup "works".. but.. it could be much faster.
> Bonnie show's me that file creation, deletion, and rename takes forever
> read/writes are fine.
> Please send me your report so I can compare. And what version of open-afs are 
> you running.
> 
> -Original Message-
> From: [EMAIL PROTECTED] on behalf of Mike Garrison
> Sent: Fri 11/30/2007 4:41 PM
> To: openafs-info@openafs.org
> Subject: Re: [OpenAFS] File systems on Linux, again.
>  
> 
> On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:
> 
> > "Jerry Normandin" <[EMAIL PROTECTED]> writes:
> >
> >> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for  
> >> this.
> >> I inherited a mess here that I am fixing.  My predecessor built is  
> >> using
> >> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
> >> create, Delete, or rename files.
> >
> > *shrug*.  It works just fine for us.
> 
> Works fine for us at UMich too.

-- 
Brain: Pinky, Are you pondering what I'm pondering?
Pinky: I think so, but what if the chicken won't wear the nylons?
---
 John M. Lockard |  U of Michigan - School of Information
 Unix and Security Admin |  1214 SI Norsth - 1075 Beal Ave.
  [EMAIL PROTECTED] |Ann Arbor, MI  48109-2112
 www.umich.edu/~jlockard | 734-615-8776 | 734-647-8045 FAX
---
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

RE: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Jerry Normandin

Please send me a Bonnie++ report regarding your AFS setup.
Our setup "works".. but.. it could be much faster.
Bonnie show's me that file creation, deletion, and rename takes forever
read/writes are fine.
Please send me your report so I can compare. And what version of open-afs are 
you running.

-Original Message-
From: [EMAIL PROTECTED] on behalf of Mike Garrison
Sent: Fri 11/30/2007 4:41 PM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:

> "Jerry Normandin" <[EMAIL PROTECTED]> writes:
>
>> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for  
>> this.
>> I inherited a mess here that I am fixing.  My predecessor built is  
>> using
>> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
>> create, Delete, or rename files.
>
> *shrug*.  It works just fine for us.

Works fine for us at UMich too.

--
Mike Garrison
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

RE: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Jerry Normandin

did you see my Bonnie++ report? Can you please send me a copy of yours and what 
version of Open-AFS are you running


-Original Message-
From: [EMAIL PROTECTED] on behalf of Steve Devine
Sent: Fri 11/30/2007 5:22 PM
To: Mike Garrison
Cc: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.
 
Mike Garrison wrote:
>
> On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:
>
>> "Jerry Normandin" <[EMAIL PROTECTED]> writes:
>>
>>> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for
>>> this.
>>> I inherited a mess here that I am fixing.  My predecessor built is
>>> using
>>> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
>>> create, Delete, or rename files.
>>
>> *shrug*.  It works just fine for us.
>
> Works fine for us at UMich too.
>
> -- 
> Mike Garrison
> ___
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
Not to "Pile On" but we use ext3 as well and its very solid.
/sd

-- 
Steve Devine
Network Storage and Printing
Academic Computing & Network Services
Michigan State University

506 Computer Center
East Lansing, MI 48824-1042
1-517-432-7327

Baseball is ninety percent mental; the other half is physical.
- Yogi Berra 

___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Steve Devine

Mike Garrison wrote:
>
> On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:
>
>> "Jerry Normandin" <[EMAIL PROTECTED]> writes:
>>
>>> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for
>>> this.
>>> I inherited a mess here that I am fixing.  My predecessor built is
>>> using
>>> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
>>> create, Delete, or rename files.
>>
>> *shrug*.  It works just fine for us.
>
> Works fine for us at UMich too.
>
> -- 
> Mike Garrison
> ___
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
Not to "Pile On" but we use ext3 as well and its very solid.
/sd

-- 
Steve Devine
Network Storage and Printing
Academic Computing & Network Services
Michigan State University

506 Computer Center
East Lansing, MI 48824-1042
1-517-432-7327

Baseball is ninety percent mental; the other half is physical.
- Yogi Berra 

___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Mike Garrison



On Nov 30, 2007, at 2:17 PM, Russ Allbery wrote:


"Jerry Normandin" <[EMAIL PROTECTED]> writes:

AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for  
this.
I inherited a mess here that I am fixing.  My predecessor built is  
using

Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
create, Delete, or rename files.


*shrug*.  It works just fine for us.


Works fine for us at UMich too.

--
Mike Garrison
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Jeffrey Altman

Jerry Normandin wrote:
> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for this.
> I inherited a mess here that I am fixing.  My predecessor built is using
> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
> create,
> Delete, or rename files.  I tested with Bonnie++... here are my stats:
> 
> Initial file performance baselines taken from ENG02 with 4096kbyte
> cache:
> 
> read performance on disk is 6.7 x faster than AFS
> read performance on nfs is 2.0 x faser than AFS
> 
> write performance is actually impressive.  file creation and deletion
> are very slow on afs.
> 
> file creation and deletion times is horrible.  I will be working on a
> solution to solve this.  Once file creation and deletion times are
> comparable to NFS, then AFS should perform well.

Upgrade to 1.4.5 and check your performance again.  You should see a
measurable improvement on EXT3.

Jeffrey Altman


smime.p7s
Description: S/MIME Cryptographic Signature

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Dj Merrill

Russ Allbery wrote:
> "Jerry Normandin" <[EMAIL PROTECTED]> writes:
> 
>> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for this.
>> I inherited a mess here that I am fixing.  My predecessor built is using
>> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
>> create, Delete, or rename files.
> 
> *shrug*.  It works just fine for us.
> 

We've been using ext3 for /vicepX partitions for over 3 years.  Works
just fine for us, too.

Jerry, any chance there might be something else that is causing your
slowness?

-Dj
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Russ Allbery

"Jerry Normandin" <[EMAIL PROTECTED]> writes:

> AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for this.
> I inherited a mess here that I am fixing.  My predecessor built is using
> Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
> create, Delete, or rename files.

*shrug*.  It works just fine for us.

-- 
Russ Allbery ([EMAIL PROTECTED]) 
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Matt Benjamin

-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256

woot, chas :)

chas williams - CONTRACTOR wrote:
> no i dont think rx locking is the problem.  the rx locking is
> actually pretty good.  i had tracked this down with fstrace
> at one point but i seem to have lost the trace at the moment.
> i will dig around and see if i can find it.
> 
> In message <[EMAIL PROTECTED]>,Matt Benjamin writes:
> Hey, Chas,
> 


- --

Matt Benjamin

The Linux Box
206 South Fifth Ave. Suite 150
Ann Arbor, MI  48104

http://linuxbox.com

tel. 734-761-4689
fax. 734-769-8938
cel. 734-216-5309

-BEGIN PGP SIGNATURE-
Version: GnuPG v1.4.7 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org

iD8DBQFHUFNgJiSUUSaRdSURCH7/AJ9eTtSta1JCYEcL4jt2kaPH4rm25QCePpXS
8ozxvvFRngC1EMZz1vXY/0E=
=koC6
-END PGP SIGNATURE-
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread chas williams - CONTRACTOR

no i dont think rx locking is the problem.  the rx locking is
actually pretty good.  i had tracked this down with fstrace
at one point but i seem to have lost the trace at the moment.
i will dig around and see if i can find it.

In message <[EMAIL PROTECTED]>,Matt Benjamin writes:
>-BEGIN PGP SIGNED MESSAGE-
>Hash: SHA256
>
>Hey, Chas,
>
>Sorry to bug.
>
>I've been looking at this, tangentially, because I've been working with
>bypassing dcache/memcache, writing direct into page cache.  Pretty far
>along on that side of things.  Is rx locking so coarse that in general
>only one read makes progress even independent of the cache--to your
>knowledge?
>
>Matt
>
>chas williams - CONTRACTOR wrote:
>> In message <[EMAIL PROTECTED]
>med
>> ia.net>,"Jerry Normandin" writes:
>>> write performance is actually impressive.  file creation and deletion
>>> are very slow on afs.
>> 
>> because writing is easier than reading.  the afs cache manager can
>> group the outgoing writes together and send them in a single message.
>> while the cache manager has readahead it doesnt work because the afs
>> global locks blocks any progress the readahead thread might make.
>> ___
>> OpenAFS-info mailing list
>> OpenAFS-info@openafs.org
>> https://lists.openafs.org/mailman/listinfo/openafs-info
>
>
>
>
>- --
>
>Matt Benjamin
>
>The Linux Box
>206 South Fifth Ave. Suite 150
>Ann Arbor, MI  48104
>
>http://linuxbox.com
>
>tel. 734-761-4689
>fax. 734-769-8938
>cel. 734-216-5309
>
>-BEGIN PGP SIGNATURE-
>Version: GnuPG v1.4.7 (GNU/Linux)
>Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
>
>iD8DBQFHUEJRJiSUUSaRdSURCA2lAJ4p19x8OH8y2cYO3WERwapwdZ9gYwCffFeR
>t96QUFYv5yHK6wlFTbn9TSE=
>=BAnD
>-END PGP SIGNATURE-
>___
>OpenAFS-info mailing list
>OpenAFS-info@openafs.org
>https://lists.openafs.org/mailman/listinfo/openafs-info
>
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Matt Benjamin

-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256

Hey, Chas,

Sorry to bug.

I've been looking at this, tangentially, because I've been working with
bypassing dcache/memcache, writing direct into page cache.  Pretty far
along on that side of things.  Is rx locking so coarse that in general
only one read makes progress even independent of the cache--to your
knowledge?

Matt

chas williams - CONTRACTOR wrote:
> In message <[EMAIL PROTECTED]
> ia.net>,"Jerry Normandin" writes:
>> write performance is actually impressive.  file creation and deletion
>> are very slow on afs.
> 
> because writing is easier than reading.  the afs cache manager can
> group the outgoing writes together and send them in a single message.
> while the cache manager has readahead it doesnt work because the afs
> global locks blocks any progress the readahead thread might make.
> ___
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info




- --

Matt Benjamin

The Linux Box
206 South Fifth Ave. Suite 150
Ann Arbor, MI  48104

http://linuxbox.com

tel. 734-761-4689
fax. 734-769-8938
cel. 734-216-5309

-BEGIN PGP SIGNATURE-
Version: GnuPG v1.4.7 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org

iD8DBQFHUEJRJiSUUSaRdSURCA2lAJ4p19x8OH8y2cYO3WERwapwdZ9gYwCffFeR
t96QUFYv5yHK6wlFTbn9TSE=
=BAnD
-END PGP SIGNATURE-
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread chas williams - CONTRACTOR

In message <[EMAIL PROTECTED]
ia.net>,"Jerry Normandin" writes:
>write performance is actually impressive.  file creation and deletion
>are very slow on afs.

because writing is easier than reading.  the afs cache manager can
group the outgoing writes together and send them in a single message.
while the cache manager has readahead it doesnt work because the afs
global locks blocks any progress the readahead thread might make.
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

RE: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Stephen Joyce

When you have bonnie++ numbers for xfs /vicep partitions, please post them. 
Mine are currently ext3, but I've warmed considerably to xfs since they 
were installed.


On Fri, 30 Nov 2007, Jerry Normandin wrote:


AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for this.
I inherited a mess here that I am fixing.  My predecessor built is using
Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
create,
Delete, or rename files.  I tested with Bonnie++... here are my stats:

Initial file performance baselines taken from ENG02 with 4096kbyte
cache:

read performance on disk is 6.7 x faster than AFS
read performance on nfs is 2.0 x faser than AFS

write performance is actually impressive.  file creation and deletion
are very slow on afs.

file creation and deletion times is horrible.  I will be working on a
solution to solve this.  Once file creation and deletion times are
comparable to NFS, then AFS should perform well.

Bonnie++ Benchmarks

ENG02   AFS:
Version  1.03   --Sequential Output-- --Sequential Input-
--Random-
   -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
eng02.dafca.loca 8G  5296  47  6115  40  4074  34 19518  63 22494   7
125.6   4
   --Sequential Create-- Random
Create
   -Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
 files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
1623   1    7923   023   1  4546  66
18   0
eng02.dafca.local,8G,5296,47,6115,40,4074,34,19518,63,22494,7,125.6,4,16
,23,1,,79,23,0,23,1,4546,66,18,0



ENG02 Local Disk:

Version  1.03   --Sequential Output-- --Sequential Input-
--Random-
   -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
eng02.dafca.loca 8G 35438  95 42686  23 16027   6 13516  31 24135   4
604.7   1
   --Sequential Create-- Random
Create
   -Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
 files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
16  2046  77 + +++ + +++  2230  84 + +++
1461  17
eng02.dafca.local,8G,35438,95,42686,23,16027,6,13516,31,24135,4,604.7,1,
16,2046,77,+,+++,+,+++,2230,84,+,+++,1461,17



ENG02  NFS:
Version  1.03   --Sequential Output-- --Sequential Input-
--Random-
   -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
eng02.dafca.loca 8G 11051  27 11126   3  8944   5 11179  27 11186   2
118.1   0
   --Sequential Create-- Random
Create
   -Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
 files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
16   934   4  6092  12  2951   6   949   4  7922  12
2359   5
eng02.dafca.local,8G,11051,27,11126,3,8944,5,11179,27,11186,2,118.1,0,16
,934,4,6092,12,2951,6,949,4,7922,12,2359,5

So I have to backup the vicepa filesystems.  Create a xfs filesystem.
And restore.  I've got 3TB of data to deal with.

Trust me you do not want to use ext3 for the /vicepa file system!

-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Russ Allbery
Sent: Thursday, November 29, 2007 2:36 PM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

"Smith, Matt" <[EMAIL PROTECTED]> writes:


After the recent thread "openafs upgrade from 1.4.1 to 1.5.7", and a
review of a thread[1] from July, I'm wondering if there is a

definitive

recommendation for which file system to use on Linux AFS file servers.
Ext3, XFS, JFS, something else?


It shouldn't make much of a difference, so I think you're safe choosing
your file system on whatever basis you'd choose a file system for any
other file server.  We use ext3 because of the stability, reliability,
and
"center of the mainstream" support in the kernel, which we always
considered more important than a bit of additional speed, but your
mileage
may vary.

XFS is probably the next most common choice.

I would be very leery of ReiserFS.  It has nice features, but the
recovery
tools are fairly horrific.

--
Russ Allbery ([EMAIL PROTECTED])
<http://www.eyrie.org/~eagle/>
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

RE: [OpenAFS] File systems on Linux, again.

2007-11-30 Thread Jerry Normandin

AFS on EXT3?  No there are Metadata issues.  EXT3 was intended for this.
I inherited a mess here that I am fixing.  My predecessor built is using
Ext3 for the /vicepa filesystems.  It takes a hell of a long time to
create,
Delete, or rename files.  I tested with Bonnie++... here are my stats:

Initial file performance baselines taken from ENG02 with 4096kbyte
cache:

read performance on disk is 6.7 x faster than AFS
read performance on nfs is 2.0 x faser than AFS

write performance is actually impressive.  file creation and deletion
are very slow on afs.

file creation and deletion times is horrible.  I will be working on a
solution to solve this.  Once file creation and deletion times are
comparable to NFS, then AFS should perform well.

Bonnie++ Benchmarks

ENG02   AFS:
Version  1.03   --Sequential Output-- --Sequential Input-
--Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
eng02.dafca.loca 8G  5296  47  6115  40  4074  34 19518  63 22494   7
125.6   4
--Sequential Create-- Random
Create
-Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
 1623   1    7923   023   1  4546  66
18   0
eng02.dafca.local,8G,5296,47,6115,40,4074,34,19518,63,22494,7,125.6,4,16
,23,1,,79,23,0,23,1,4546,66,18,0

ENG02 Local Disk:

Version  1.03   --Sequential Output-- --Sequential Input-
--Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
eng02.dafca.loca 8G 35438  95 42686  23 16027   6 13516  31 24135   4
604.7   1
--Sequential Create-- Random
Create
-Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
 16  2046  77 + +++ + +++  2230  84 + +++
1461  17
eng02.dafca.local,8G,35438,95,42686,23,16027,6,13516,31,24135,4,604.7,1,
16,2046,77,+,+++,+,+++,2230,84,+,+++,1461,17

ENG02  NFS:
Version  1.03   --Sequential Output-- --Sequential Input-
--Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
--Seeks--
MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
/sec %CP
eng02.dafca.loca 8G 11051  27 11126   3  8944   5 11179  27 11186   2
118.1   0
--Sequential Create-- Random
Create
-Create-- --Read--- -Delete-- -Create-- --Read---
-Delete--
  files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
/sec %CP
 16   934   4  6092  12  2951   6   949   4  7922  12
2359   5
eng02.dafca.local,8G,11051,27,11126,3,8944,5,11179,27,11186,2,118.1,0,16
,934,4,6092,12,2951,6,949,4,7922,12,2359,5

So I have to backup the vicepa filesystems.  Create a xfs filesystem.
And restore.  I've got 3TB of data to deal with.

Trust me you do not want to use ext3 for the /vicepa file system!

-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Russ Allbery
Sent: Thursday, November 29, 2007 2:36 PM
To: openafs-info@openafs.org
Subject: Re: [OpenAFS] File systems on Linux, again.

"Smith, Matt" <[EMAIL PROTECTED]> writes:

> After the recent thread "openafs upgrade from 1.4.1 to 1.5.7", and a
> review of a thread[1] from July, I'm wondering if there is a
definitive
> recommendation for which file system to use on Linux AFS file servers.
> Ext3, XFS, JFS, something else?

It shouldn't make much of a difference, so I think you're safe choosing
your file system on whatever basis you'd choose a file system for any
other file server.  We use ext3 because of the stability, reliability,
and
"center of the mainstream" support in the kernel, which we always
considered more important than a bit of additional speed, but your
mileage
may vary.

XFS is probably the next most common choice.

I would be very leery of ReiserFS.  It has nice features, but the
recovery
tools are fairly horrific.

-- 
Russ Allbery ([EMAIL PROTECTED])
<http://www.eyrie.org/~eagle/>
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-29 Thread Hartmut Reuter


Smith, Matt wrote:

After the recent thread "openafs upgrade from 1.4.1 to 1.5.7", and a
review of a thread[1] from July, I'm wondering if there is a definitive
recommendation for which file system to use on Linux AFS file servers.
Ext3, XFS, JFS, something else?

Thanks all,
-Matt

[1] http://www.openafs.org/pipermail/openafs-info/2007-July/026798.html


We are using exclusively xfs since many years. It is performant and you 
can enlarge partitions on the fly doing "lvextend" and "xfs_growfs".


Hartmut
-
Hartmut Reuter   e-mail [EMAIL PROTECTED]
   phone +49-89-3299-1328
RZG (Rechenzentrum Garching)   fax   +49-89-3299-1301
Computing Center of the Max-Planck-Gesellschaft (MPG) and the
Institut fuer Plasmaphysik (IPP)
-
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

Re: [OpenAFS] File systems on Linux, again.

2007-11-29 Thread Russ Allbery

"Smith, Matt" <[EMAIL PROTECTED]> writes:

> After the recent thread "openafs upgrade from 1.4.1 to 1.5.7", and a
> review of a thread[1] from July, I'm wondering if there is a definitive
> recommendation for which file system to use on Linux AFS file servers.
> Ext3, XFS, JFS, something else?

It shouldn't make much of a difference, so I think you're safe choosing
your file system on whatever basis you'd choose a file system for any
other file server.  We use ext3 because of the stability, reliability, and
"center of the mainstream" support in the kernel, which we always
considered more important than a bit of additional speed, but your mileage
may vary.

XFS is probably the next most common choice.

I would be very leery of ReiserFS.  It has nice features, but the recovery
tools are fairly horrific.

-- 
Russ Allbery ([EMAIL PROTECTED]) 
___
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info

[OpenAFS] File systems on Linux, again.

2007-11-29 Thread Smith, Matt

After the recent thread "openafs upgrade from 1.4.1 to 1.5.7", and a
review of a thread[1] from July, I'm wondering if there is a definitive
recommendation for which file system to use on Linux AFS file servers.
Ext3, XFS, JFS, something else?

Thanks all,
-Matt

[1] http://www.openafs.org/pipermail/openafs-info/2007-July/026798.html
-- 
Matt Smith
[EMAIL PROTECTED]
University Information Technology Services (UITS)
University of Connecticut
PGP Key ID: 0xE9C5244E


signature.asc
Description: This is a digitally signed message part

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again. Numbers

Re: [OpenAFS] File systems on Linux, again. Numbers

RE: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

RE: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

Re: [OpenAFS] File systems on Linux, again.

[OpenAFS] File systems on Linux, again.

31 matches

Site Navigation

Mail list logo

Footer information