9fans - fans of the OS Plan 9 from Bell Labs
 help / color / mirror / Atom feed
* [9fans] leaks?
@ 2003-06-05 18:35 Fco.J.Ballesteros
  2003-06-06 15:26 ` rog
  0 siblings, 1 reply; 3+ messages in thread
From: Fco.J.Ballesteros @ 2003-06-05 18:35 UTC (permalink / raw)
  To: 9fans

I've been monitoring the memory usage in our file server and it seems
to steadily increase.  This script shows the growing memory usage from
our last reboot (but it seems to keep on growing according to the
records for other periods of (up)time).

The numbers have been collected by cron at 3am, when there's almost no
system activity.

#!/bin/rc
# w swapstats
cat $0 | grep '^[0-9]' | awk -F/ '{print $1}' | graph -a | plot
exit ''
53150/110163 memory 0/160000 swap
53350/110163 memory 0/160000 swap
53857/110163 memory 0/160000 swap
54082/110163 memory 0/160000 swap
54583/110163 memory 0/160000 swap

A ps reveals that it might be both venti and fossil the ones eating memory.

For example, these are fossil and venti initially:
elf              34    0:00   0:00   11872K Rendez   venti
elf              41    0:00   0:00  190132K Rendez   fossil [cons]


these are the numbers after four days:
elf              34    0:00   0:00   12384K Rendez   venti
elf              41    0:00   0:00  190480K Rendez   fossil [cons]


Does this happen at other sites?
It's not a big deal, but might be of concern if we want to leave the
machine unattended for a long period of time.
I didnt try leak w/ them (anyone did?)

thanks a lot

PS: BTW, both venti and fossil work just great and rock solid here. We had
no problem at all.



^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [9fans] leaks?
  2003-06-05 18:35 [9fans] leaks? Fco.J.Ballesteros
@ 2003-06-06 15:26 ` rog
  2003-06-06 15:30   ` Fco.J.Ballesteros
  0 siblings, 1 reply; 3+ messages in thread
From: rog @ 2003-06-06 15:26 UTC (permalink / raw)
  To: 9fans

> I've been monitoring the memory usage in our file server and it seems
> to steadily increase.  This script shows the growing memory usage from
> our last reboot (but it seems to keep on growing according to the
> records for other periods of (up)time).

the increases are 4% (venti) and 0.1% (fossil) over 4 days.
does it keep growing at that rate?
might it just be heap fragmentation?



^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [9fans] leaks?
  2003-06-06 15:26 ` rog
@ 2003-06-06 15:30   ` Fco.J.Ballesteros
  0 siblings, 0 replies; 3+ messages in thread
From: Fco.J.Ballesteros @ 2003-06-06 15:30 UTC (permalink / raw)
  To: 9fans

[-- Attachment #1: Type: text/plain, Size: 98 bytes --]

Yes, it keeps growing. And it could indeed be fragmentation; I didnt trace
the problem.

thanks

[-- Attachment #2: Type: message/rfc822, Size: 1537 bytes --]

From: rog@vitanuova.com
To: 9fans@cse.psu.edu
Subject: Re: [9fans] leaks?
Date: Fri, 6 Jun 2003 16:26:32 +0100
Message-ID: <4afa5a2591051e5f5bf833735cd263e9@vitanuova.com>

> I've been monitoring the memory usage in our file server and it seems
> to steadily increase.  This script shows the growing memory usage from
> our last reboot (but it seems to keep on growing according to the
> records for other periods of (up)time).

the increases are 4% (venti) and 0.1% (fossil) over 4 days.
does it keep growing at that rate?
might it just be heap fragmentation?

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2003-06-06 15:30 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2003-06-05 18:35 [9fans] leaks? Fco.J.Ballesteros
2003-06-06 15:26 ` rog
2003-06-06 15:30   ` Fco.J.Ballesteros

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).