Re: Help - Memory Leak Issue with SCSI Stack on Linux

From: John-Paul Stewart (jpstewart_at_binaryfoundry.ca)
Date: 08/28/04 

Date: Sat, 28 Aug 2004 11:15:45 -0400

L wrote:
> Hi,
>
> I think the following issue is memory leak related but not sure how to
> narrow it down. Your help and suggestion would be helpful.
>
> - Test Environment
> - RH Linux 9.0 (lk2.4) with patch 2.4.20-30.9
> - Dell 1U server with 2 SCSI disks. The first
> one hold OS and utilities, while the 2nd one
> (Seagate ST318453LC) is the target iometer
> sends I/O to.
> - 2GB memory
> - Linux 'Hardware Browser' -> 'SCSI devices'
> shows "LSI 53c1030, Driver: mptscsih". This
> is probably the built-in SCSI HBA but I'm not
> 100% sure. I can double check if some one
> tells me how.

If that's a Dell PowerEdge 1750, then yes, that is the built-in
controller. (Possibly applicable for other Dell models, too, but it
sure sounds like a 1750 to me.)

> - iometer (v. 2003.12.16) and dynamo (v. 2003.12.16)
>
> - Symptom
> run iometer on a different Windows machine, and
> dynamo (the iometer client for Linux) on the Dell
> server. Use 'top' utility on Linux to trace the
> memory usage. Here is what I observed:
>
> Time (min) Used Memory (MB)
> 0 305
> 1 461
> 2 589
> 3 679
> 4 787
> 5 894
> 6 898
> 7 973
> 10 1087
> 15 1087
> 20 1087
> 30 1087
>
> - Question
> Can we say there is a memory leak somewhere based on the above table? If

No.

> not, then why the amount of used memory keeps increasing within a certain
> period of time? If so, why the amount of used memory
> stops increasing after 10 mins, and how I can trace which layer or component
> causes it?

Look at the full output of 'top', especially the buffers and cache
figures. Or better yet, use free, and pay attention only to the
*second* line of figures. I'd guess that the cache is growing steadily
  size and then staying constant for whatever reason.

Moreover, I can assure you that there is no memory leak in the Linux
SCSI subsystem (including the Fusion MPT driver). If there is a leak i
your system, it would have to be within the iometer tools. And that's
also highly unlikely.

There simply isn't enough evidence to conclude that there is a memory
leak at this point in time.

Relevant Pages

  • Re: Linux v2.6.18-rc5
    ... Linus Torvalds wrote: ... > Linux 2.6.18-rc5 is out there now ... Possible memory leak in kernel/delayacct.c ... that the patch was merged yet so I suspect the problem is still there. ...
    (Linux-Kernel)
  • Re: Memory leak
    ... I'm looking for some tool to find the memory leak happening in one of ... running in in linux. ... The process is a very huge one with large chunk ...
    (comp.os.linux.development.system)
  • Re: Horrendous memory leak with TCP/IP Socket client, new to 5.8.0?
    ... The server works fine without a memory leak ... >> so I'm not showing it here. ... > I also have linux, but didn't try your script on that platform as I ...
    (comp.lang.perl.modules)
  • Re: Horrendous memory leak with TCP/IP Socket client, new to 5.8.0?
    ... The server works fine without a memory leak ... >> so I'm not showing it here. ... > I also have linux, but didn't try your script on that platform as I ...
    (comp.lang.perl.misc)