Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 12 Aug 2018 10:32:48 -0700
From:      John Kennedy <warlock@phouka.net>
To:        bob prohaska <fbsd@www.zefox.net>
Cc:        freebsd-arm <freebsd-arm@freebsd.org>
Subject:   Re: RPI3 swap experiments ["was killed: out of swap space" with: "v_free_count: 5439, v_inactive_count: 1"]
Message-ID:  <20180812173248.GA81324@phouka1.phouka.net>
In-Reply-To: <20180809175802.GA32974@www.zefox.net>
References:  <6BFE7B77-A0E2-4FAF-9C68-81951D2F6627@yahoo.com> <20180802002841.GB99523@www.zefox.net> <20180802015135.GC99523@www.zefox.net> <EC74A5A6-0DF4-48EB-88DA-543FD70FEA07@yahoo.com> <20180806155837.GA6277@raichu> <20180808153800.GF26133@www.zefox.net> <20180808204841.GA19379@raichu> <2DC1A479-92A0-48E6-9245-3FF5CFD89DEF@yahoo.com> <20180809033735.GJ30738@phouka1.phouka.net> <20180809175802.GA32974@www.zefox.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Aug 09, 2018 at 10:58:02AM -0700, bob prohaska wrote:
> ... I've gathered up what I've been given and put it in
> http://www.zefox.net/~fbsd/rpi3/swaptests/tools/
> in hopes it'll be useful. ...

Bob, are you doing anything clever to track/graph resources over time?

I've got my box patched up to 12.0-ALPHA1 (r337589+2a27f5c34b07) + patches, and
haven't seen any logged output (assuming it'll end up in /var/log/messages)
although I'm certainly exercising things.  I typically beat things up with
a buildworld-then-buildkernel.

Patches I've applied:
	http://www.zefox.net/~fbsd/rpi3/swaptests/tools/pageout.patch
	http://www.zefox.net/~fbsd/rpi3/swaptests/tools/slow_swap.patch

I haven't used the CAM_IOSCHED_DYNAMIC option or adjusted vm.pageout_oom_seq.

Just using top isn't really going to help me go back in time and diagnose it
after the fact and capturing it's output (and all the screen codes) over an
extended period of time seems pretty ugly.

I can see why my ntpd tends to get whacked.  At ~18M, it's almost always in the
top 5 of memory-using processes.  Load seems lower than it normally does (~4
for a -j4) and it seems a bit more swappy than I remember it being (r337443).

I added a vfs.zfs.arc_max="450M" to /boot/loader.conf, but it didn't seen to
be anywhere near that originally and doesn't seem to have taken effect:

    [sysctl vfs.zfs.arc_max]
	vfs.zfs.arc_max: 195873280

AFAIK, that would take up more "wired" space, but wired is only ~197M and
ARC claims to only be ~50M so ZFS doesn't see to be too piggy.

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

[top -IatP -o res]

last pid: 75860;  load averages:  1.38,  1.72,  1.95                                      up 0+13:42:25  10:04:05
65 processes:  65 sleeping
CPU 0:  1.6% user,  0.0% nice,  5.1% system, 13.7% interrupt, 79.7% idle
CPU 1:  6.6% user,  0.0% nice,  9.0% system,  0.0% interrupt, 84.4% idle
CPU 2:  2.7% user,  0.0% nice,  9.0% system,  2.7% interrupt, 85.5% idle
CPU 3: 16.0% user,  0.0% nice,  7.0% system,  0.4% interrupt, 76.6% idle
Mem: 596M Active, 31M Inact, 51M Laundry, 197M Wired, 32K Buf, 19M Free 
ARC: 50M Total, 14M MFU, 16M MRU, 2758K Anon, 558K Header, 17M Other
     6757K Compressed, 26M Uncompressed, 3.99:1 Ratio
Swap: 3584M Total, 820M Used, 2764M Free, 22% Inuse, 3736K In, 5568K Out
 
  PID USERNAME    THR PRI NICE   SIZE    RES STATE    C   TIME    WCPU COMMAND
75841 root          1  35    0   373M    55M swread   2   2:27  14.35% /usr/bin/c++ -cc1 -triple aarch64-unknown- 
75844 root          1  39    0   423M    46M swread   3   2:45  21.76% /usr/bin/c++ -cc1 -triple aarch64-unknown-
  821 ntpd          1  20    0    18M    18M select   3   0:16   0.02% /usr/sbin/ntpd -p /var/db/ntp/ntpd.pid -c
75811 root          1  22    0   346M    14M swread   1   2:41   2.05% /usr/bin/c++ -cc1 -triple aarch64-unknown- 
75815 root          1  21    0   389M  7252K swread   1   3:09   1.86% /usr/bin/c++ -cc1 -triple aarch64-unknown- 
 2308 warlock       1  20    0    14M  2748K select   2   7:30   0.78% top -IatP -o cpu
75749 warlock       1  20    0    14M  2744K select   2   0:18   0.79% top -IatP -o cpu
 2515 root          1  20    0    11M  1828K kqread   0   0:27   0.06% tail -F /var/log/messages
  930 warlock       1  20    0    20M  1460K select   2  16:36   0.07% sshd: warlock@pts/0 (sshd)
  935 warlock       1  20    0    19M  1288K select   3  46:14   0.38% screen



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20180812173248.GA81324>