DBMail 1.2 (released October 13th) changed some stuff in the
send_message_lines function (dbmysql.c
and dbpgsql.c) which could explain the drop (when compared with dbmail 1.1):
the function uses a smaller buffer (which is cleared more quickly) and
uses a direct access method (an array) for putting characters into the
buffer instead of using the snprintf() function, which needs
to an internal strlen() call on every addition of a character.
cheers,
Ilja
Bret Baptist wrote:
Weird, well the only other thing it could be is an update to 1.2.1 than. Was
anything done since Oct 8th that would explain the drop in CPU usage?
Bret.
On Tuesday 28 October 2003 5:33 am, Eelco van Beek - IC&S wrote:
-fomit-frame-pointer
Don't keep the frame pointer in a register for functions that don't
need one. This avoids the instructions to save, set up and restore
frame pointers; it also makes an extra register available in many
functions. It also makes debugging impossible on some machines.
On some machines, such as the VAX, this flag has no effect, because the
standard calling sequence automatically handles the frame pointer and
nothing is saved by pretending it doesn't exist. The
machine-description macro FRAME_POINTER_REQUIRED controls whether a
target machine supports this flag. See Register Usage.
Enabled at levels -O, -O2, -O3, -Os.
As being told in the gcc man :)
Eelco
On 28-okt-03, at 10:20, Shih Ming-Wei wrote:
I don't think -O -O1 and -O2 impliciet -fomit-fram-pointer
not sure about -O3
Ming-Wei
-----Original Message-----
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] Behalf
Of Eelco van Beek - IC&S
Sent: Tuesday, October 28, 2003 9:37 AM
To: [email protected]
Subject: Re: [Dbmail] 100% cpu usage with dbmail-pop3d --
SOLVED, for me
at least
I thought the stable version was compiled with -O which automatically
enables the omission of frame pointer usage?
Best regards,
Eelco
On 27-okt-03, at 23:08, Bret Baptist wrote:
On Friday 24 October 2003 5:35 am, Shih Ming-Wei wrote:
hi,
I have solve the 99% CPU usage on Linux/sparc systems that
we are using, apparently changing CFLAGS from "-O2 -pipe" to
"-march=v8 -mtune=v9 -O2 -pipe -fomit-frame-pointer" cahnges
the CPU usage from 99% to max 1.8% (avg 0.4 %). So my
conclusion is this is not a dbmail bug but dbmail must trigger
some bug in platform/compiler/glibc,
Just my 2 cents
Hope this might help someone else
Ming-Wei
After more testing I have found that the important bit here is the
-fomit-frame-pointer. If I define that I don't get the
excessive CPU
usage.
Is there any reason for not making this a standard compile flag?
I am running debian testing (sarge):
Which has:
gcc-3.3.1-2
kernel: 2.4.18-bf2.4 #1 Son Apr 14 09:53:28 CEST 2002 i686
GNU/Linux
libc6-2.3.2-7
mysql-client-4.0.13-3
Anything else relevant?
--
Bret Baptist
Systems and Technical Support Specialist
[EMAIL PROTECTED]
Internet Exposure, Inc.
http://www.iexposure.com
(612)676-1946 x17
Web Development-Web Marketing-ISP Services
------------------------------------------
Today is the tomorrow you worried about yesterday.
_______________________________________________
Dbmail mailing list
[email protected]
https://mailman.fastxs.nl/mailman/listinfo/dbmail
_________________________
E.J.A. van Beek
ICT Manager
IC&S
T: +31 30 2322878
F: +31 30 2322305
PGP-key:
www.ic-s.nl/keys/eelco.txt
_______________________________________________
Dbmail mailing list
[email protected]
https://mailman.fastxs.nl/mailman/listinfo/dbmail
_________________________
E.J.A. van Beek
ICT Manager
IC&S
T: +31 30 2322878
F: +31 30 2322305
PGP-key:
www.ic-s.nl/keys/eelco.txt
_______________________________________________
Dbmail mailing list
[email protected]
https://mailman.fastxs.nl/mailman/listinfo/dbmail
--
IC&S
Koningsweg 4
3582 GE UTRECHT
PGP-key:
http://www.ic-s.nl/keys/ilja.txt
