You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@spamassassin.apache.org by Bernd Petrovitsch <be...@petrovitsch.priv.at> on 2013/03/07 19:04:22 UTC
Re: fork is vfork?
On Don, 2013-03-07 at 12:14 -0500, David F. Skoll wrote:
> On Thu, 7 Mar 2013 18:56:45 +0200
> Henrik K <he...@hege.li> wrote:
>
> > You provide no data how you end up with the 4MB etc. And MD is not
> > SA, it might do all sorts of funky stuff.
>
> I wrote MD, so I'm pretty sure it's not doing any funky stuff.
MD forks the worker process and the worker process initializes libperl
and loads the perl script.
To share more memory on a fork, it should initialize libperl and load
the perl script before forking off the worker processes.
BTW switching to vfork() won't speed up anything significantly IMHO as
processes are (re)started quite seldom - it is not that one starts a
process for each mail .....
Bernd
--
Bernd Petrovitsch Email : bernd@petrovitsch.priv.at
LUGA : http://www.luga.at
Re: fork is vfork?
Posted by Henrik K <he...@hege.li>.
On Fri, Mar 08, 2013 at 07:09:12PM +0200, Henrik K wrote:
> On Fri, Mar 08, 2013 at 11:55:43AM -0500, David F. Skoll wrote:
> > On Fri, 8 Mar 2013 18:44:54 +0200
> > Henrik K <he...@hege.li> wrote:
> >
> > > Virgin childs:
> > 79MB private; 2GB shared (~40MB shared/child)
> >
> > > Used childs:
> > 1.2GB private; 1.2GB shared (~24MB shared/child)
> >
> > This is roughly what I am seeing with MIMEDefang also: Only 50%
> > shared. It's better than nothing, but not nearly as good as one might
> > have hoped. On my system, about 3.5MB of the shared memory is the
> > text portion of libraries such as libperl.so and libc.so which you'd
> > expect to be shared anyway, so really only about 20.5MB/46.5MB of Perl
> > memory is shared for each slave.
>
> But atleast ~10-20MB of private data per spamd child is the per message scan
> data/blobs etc (can be seen as 20mb heap allocation). This should not be
> calculated in any memory ratio conclusions.
Also to be noted that these "shared" values are completely vague anyway.
All that matters is how much real system memory is taken. As seen by my
previous free reports, master + 50 virgin childs only take total of 137MB.
At full blast everything take ~1.2GB.
So the real ratio per child might be something like 4MB bogus perl data,
20MB of per-message data. If the master process takes 50MB memory, this
means the child ratio is _much_ better than 50% (4MB/50MB). I might dig
deeper into this later with some tools.
Re: fork is vfork?
Posted by Henrik K <he...@hege.li>.
On Fri, Mar 08, 2013 at 11:55:43AM -0500, David F. Skoll wrote:
> On Fri, 8 Mar 2013 18:44:54 +0200
> Henrik K <he...@hege.li> wrote:
>
> > Virgin childs:
> 79MB private; 2GB shared (~40MB shared/child)
>
> > Used childs:
> 1.2GB private; 1.2GB shared (~24MB shared/child)
>
> This is roughly what I am seeing with MIMEDefang also: Only 50%
> shared. It's better than nothing, but not nearly as good as one might
> have hoped. On my system, about 3.5MB of the shared memory is the
> text portion of libraries such as libperl.so and libc.so which you'd
> expect to be shared anyway, so really only about 20.5MB/46.5MB of Perl
> memory is shared for each slave.
But atleast ~10-20MB of private data per spamd child is the per message scan
data/blobs etc (can be seen as 20mb heap allocation). This should not be
calculated in any memory ratio conclusions.
Re: fork is vfork?
Posted by "David F. Skoll" <df...@roaringpenguin.com>.
On Fri, 8 Mar 2013 18:44:54 +0200
Henrik K <he...@hege.li> wrote:
> Virgin childs:
79MB private; 2GB shared (~40MB shared/child)
> Used childs:
1.2GB private; 1.2GB shared (~24MB shared/child)
This is roughly what I am seeing with MIMEDefang also: Only 50%
shared. It's better than nothing, but not nearly as good as one might
have hoped. On my system, about 3.5MB of the shared memory is the
text portion of libraries such as libperl.so and libc.so which you'd
expect to be shared anyway, so really only about 20.5MB/46.5MB of Perl
memory is shared for each slave.
Regards,
David.
Re: fork is vfork?
Posted by Henrik K <he...@hege.li>.
On Fri, Mar 08, 2013 at 11:26:39AM -0500, David F. Skoll wrote:
> On Fri, 8 Mar 2013 17:42:58 +0200
> Henrik K <he...@hege.li> wrote:
>
> > $ pgrep -f 'spamd child' | while read p; do grep Private_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Private_/ {p> += $2;} END {print p;}'
>
> I would be interested in seeing the output of:
>
> pgrep -f 'spamd child' | while read p; do grep Shared_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Shared_/ {p> += $2;} END {print p;}'
Here's a new run..
Virgin childs:
$ pgrep -f 'spamd child' | while read p; do grep Private_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Private_/ {p += $2;} END {print p;}'
79364
$ pgrep -f 'spamd child' | while read p; do grep Shared_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Shared_/ {p += $2;} END {print p;}'
2057688
Used childs:
$ pgrep -f 'spamd child' | while read p; do grep Private_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Private_/ {p += $2;} END {print p;}'
1348048
$ pgrep -f 'spamd child' | while read p; do grep Shared_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Shared_/ {p += $2;} END {print p;}'
1271252
Re: fork is vfork?
Posted by "David F. Skoll" <df...@roaringpenguin.com>.
On Fri, 8 Mar 2013 17:42:58 +0200
Henrik K <he...@hege.li> wrote:
> $ pgrep -f 'spamd child' | while read p; do grep Private_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Private_/ {p> += $2;} END {print p;}'
I would be interested in seeing the output of:
pgrep -f 'spamd child' | while read p; do grep Shared_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Shared_/ {p> += $2;} END {print p;}'
Regards,
David.
Re: fork is vfork?
Posted by Henrik K <he...@hege.li>.
On Fri, Mar 08, 2013 at 09:09:27AM -0500, David F. Skoll wrote:
>
> I think that's what I said originally... but was met with skepticism from
> some.
There is a difference in saying something and actually providing some data.
I'm sorry but this sounds like "True Believers" (no need to prove anything)
vs "Scepticists" (no matter what you prove, it doesn't matter to them). :-)
Here is my full documentation. I don't really care if you are on sa-users
list and claim to not even have access to spamd, but if we keep going, let's
base the claims on hard data? If MD behaves differently, that's another
matter and not relevant to SA.
$ uname -a
Linux ubuntu 3.2.0-35-generic #55-Ubuntu SMP Wed Dec 5 17:42:16 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux
$ /usr/local/perl/bin/perl -v
This is perl 5, version 16, subversion 2 (v5.16.2) built for x86_64-linux
$ free
total used free shared buffers cached
Mem: 4049584 3593572 456012 0 290380 1636144
-/+ buffers/cache: 1667048 2382536
Swap: 0 0 0
(even disabled swap so it doesn't interfere)
$ /usr/local/perl/bin/spamd -4 -p 1234 -m 50 --min-children=50 --min-spare=40 --max-conn-per-child=1000 --round-robin -L -d
$ pgrep -f spamd |wc -l
51
$ free
total used free shared buffers cached
Mem: 4049584 3730644 318940 0 290396 1636152
-/+ buffers/cache: 1804096 2245488
Swap: 0 0 0
(memory difference to before spamd running: 137MB)
$ pgrep -f 'spamd child' | while read p; do grep Private_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Private_/ {p += $2;} END {print p;}'
78700
(smaps claims virgin childs are using 78MB / 50 = ~1.5MB/child)
$ find ham.old -type f | while read f; do spamc -p 1234 < $f; done
(zzz..... about 25 messages processed per child)
$ ps axu |grep spamd
hege 23755 0.2 1.0 121608 44244 ? Ss 17:23 0:01 /usr/local/perl/bin/spamd -4 -p 1234 -m 50 --min-children=50 --min-spare=40 --max-conn-per-child=1000 --round-robin -L -d
hege 23756 2.1 1.2 129400 52400 ? S 17:23 0:09 spamd child
hege 23757 2.0 1.3 130432 53284 ? S 17:23 0:09 spamd child
hege 23758 1.0 1.2 127168 50244 ? S 17:23 0:04 spamd child
hege 23759 0.9 1.2 129636 52628 ? S 17:23 0:04 spamd child
hege 23760 1.0 1.2 127984 50960 ? S 17:23 0:04 spamd child
hege 23761 1.2 1.3 130204 53080 ? S 17:23 0:05 spamd child
hege 23762 1.1 1.2 128312 51324 ? S 17:23 0:05 spamd child
hege 23763 1.4 1.2 126356 49512 ? S 17:23 0:06 spamd child
hege 23764 0.9 1.2 128636 51408 ? S 17:23 0:04 spamd child
hege 23765 1.2 1.2 129112 52056 ? S 17:23 0:05 spamd child
hege 23766 1.1 1.2 128048 51068 ? S 17:23 0:05 spamd child
hege 23767 1.0 1.2 127604 50588 ? S 17:23 0:04 spamd child
hege 23768 1.2 1.2 129244 52376 ? S 17:23 0:05 spamd child
hege 23769 0.9 1.2 128680 51632 ? S 17:23 0:04 spamd child
hege 23770 1.8 1.3 133168 56184 ? S 17:23 0:08 spamd child
hege 23771 0.8 1.2 129112 52096 ? S 17:23 0:03 spamd child
hege 23772 0.6 1.2 128268 51220 ? S 17:23 0:03 spamd child
hege 23773 2.4 1.3 132232 55132 ? S 17:23 0:11 spamd child
hege 23774 1.3 1.2 129260 52288 ? S 17:23 0:06 spamd child
hege 23775 1.0 1.3 130308 53360 ? S 17:23 0:04 spamd child
hege 23776 1.8 1.2 126960 49876 ? S 17:23 0:08 spamd child
hege 23777 1.0 1.2 128608 51692 ? S 17:23 0:04 spamd child
hege 23778 0.9 1.2 127232 50248 ? S 17:23 0:04 spamd child
hege 23779 1.5 1.2 128808 51936 ? S 17:23 0:07 spamd child
hege 23780 1.1 1.3 131680 54504 ? S 17:23 0:05 spamd child
hege 23781 1.5 1.2 126596 49760 ? S 17:23 0:07 spamd child
hege 23782 1.0 1.3 130636 53632 ? S 17:23 0:04 spamd child
hege 23783 1.0 1.3 130816 53716 ? S 17:23 0:04 spamd child
hege 23784 1.7 1.3 132872 55820 ? S 17:23 0:08 spamd child
hege 23785 0.8 1.3 131696 54608 ? S 17:23 0:03 spamd child
hege 23786 2.1 1.3 130104 53208 ? S 17:23 0:10 spamd child
hege 23787 1.1 1.3 130940 53892 ? S 17:23 0:05 spamd child
hege 23788 1.0 1.3 130116 52932 ? S 17:23 0:04 spamd child
hege 23789 1.3 1.3 132556 55388 ? S 17:23 0:06 spamd child
hege 23790 0.8 1.2 127744 50784 ? S 17:23 0:04 spamd child
hege 23791 1.1 1.2 125812 48984 ? S 17:23 0:05 spamd child
hege 23792 1.6 1.3 129812 52804 ? S 17:23 0:07 spamd child
hege 23793 0.8 1.3 132040 55036 ? S 17:23 0:04 spamd child
hege 23794 0.6 1.3 129804 52684 ? S 17:23 0:02 spamd child
hege 23795 0.7 1.2 126640 49556 ? S 17:23 0:03 spamd child
hege 23796 1.3 1.3 130160 53064 ? S 17:23 0:06 spamd child
hege 23797 1.1 1.3 131008 53920 ? S 17:23 0:05 spamd child
hege 23798 1.1 1.3 131016 54120 ? S 17:23 0:05 spamd child
hege 23799 0.8 1.2 127944 50912 ? S 17:23 0:03 spamd child
hege 23800 1.3 1.3 132756 55668 ? S 17:23 0:06 spamd child
hege 23801 1.4 1.2 128584 51584 ? S 17:23 0:06 spamd child
hege 23802 1.2 1.2 127664 50620 ? S 17:23 0:05 spamd child
hege 23803 1.0 1.3 131188 54052 ? S 17:23 0:04 spamd child
hege 23804 1.4 1.3 132212 55240 ? S 17:23 0:06 spamd child
hege 23805 0.9 1.1 125060 48076 ? S 17:23 0:04 spamd child
$ free
total used free shared buffers cached
Mem: 4049584 3944384 105200 0 268060 653584
-/+ buffers/cache: 3022740 1026844
Swap: 0 0 0
(memory difference to before spamd running: 1220MB)
$ pgrep -f 'spamd child' | while read p; do grep Private_ /proc/$p/smaps; done | awk 'BEGIN {p=0;} $1 ~ /Private_/ {p += $2;} END {print p;}'
1350324
(so smaps reports slightly little higher usage, ~27MB per child)
$ pkill -f spamd
$ free
total used free shared buffers cached
Mem: 4049584 2536460 1513124 0 268172 653612
-/+ buffers/cache: 1614676 2434908
Swap: 0 0 0
Re: fork is vfork?
Posted by "David F. Skoll" <df...@roaringpenguin.com>.
On Fri, 08 Mar 2013 13:26:50 +0100
Bernd Petrovitsch <be...@petrovitsch.priv.at> wrote:
> Hmm, I had the impression ages ago with md-2.56 - did this change
> since then?
> [ And I mean with embedded-perl compiled-in and activated. ]
No, I think it's been that way for ages.
> Then I have no idea, why the mimedefang-multiplexor processes have
> next to nothing shared - except that perl actually changes a lot in
> the internal data structures killing any copy-on-write benefits.
I think that's what I said originally... but was met with skepticism from
some.
Regards,
David.
Re: fork is vfork?
Posted by Bernd Petrovitsch <be...@petrovitsch.priv.at>.
On Don, 2013-03-07 at 13:12 -0500, David F. Skoll wrote:
> On Thu, 07 Mar 2013 19:04:22 +0100
> Bernd Petrovitsch <be...@petrovitsch.priv.at> wrote:
> > MD forks the worker process and the worker process initializes libperl
> > and loads the perl script.
>
> Nope.
Hmm, I had the impression ages ago with md-2.56 - did this change since
then?
[ And I mean with embedded-perl compiled-in and activated. ]
> > To share more memory on a fork, it should initialize libperl and load
> > the perl script before forking off the worker processes.
>
> That's what it does.
Then I have no idea, why the mimedefang-multiplexor processes have next
to nothing shared - except that perl actually changes a lot in the
internal data structures killing any copy-on-write benefits.
Hmm, perl probably does not separate code from data internally that
much .....
Bernd
--
Bernd Petrovitsch Email : bernd@petrovitsch.priv.at
LUGA : http://www.luga.at
Re: fork is vfork?
Posted by "David F. Skoll" <df...@roaringpenguin.com>.
On Thu, 07 Mar 2013 19:04:22 +0100
Bernd Petrovitsch <be...@petrovitsch.priv.at> wrote:
> MD forks the worker process and the worker process initializes libperl
> and loads the perl script.
Nope.
> To share more memory on a fork, it should initialize libperl and load
> the perl script before forking off the worker processes.
That's what it does.
Regards,
DAvid.