[Tfug] Question tres: Overbuffering overkill

[John Gruenenfelder]

On Thu, Sep 04, 2014 at 02:36:17AM -0700, Zack Breckenridge wrote:
>First thought: did you check your dmesg output for write errors when you
>were copying your music to the SD card? It sounds to me like this card is
>faulty and you'll probably have to purchase a new one, unfortunately.
>
>You may also be able to go back and look through your /var/log/messages*
>(or other syslog records) for some of that info as well if you want. Also,
>you can try using the 'badblocks' utility to see how many sectors on the SD
>card are showing up corrupted. You can apparently use the output of this
>program (according to wikipedia) to create an ext2/3/4 filesystem that
>skips those sectors. I've never actually tried this, so I'd be interested
>in hearing your results if you do.

Hi Zack,

Yes, this was my immediate thought, too, considering that Android stopped
liking it.  And it was just some bad data, fine.  I tried to let Android
reformat the card and that failed to which lent even more credence to the
faulty hardware theory.

Solid state memory is unlike magnetic memory in that I don't think a bad
sector is likely to spread like a virus across the platter... at least, not as
quickly as it happeneds to HDDs.

So, I did in fact run the badblocks utility on the memory card.  I can't
remember if I actually let it run all the way to the end, but after a long
long time, there were no semblance of I/O issues.  Linux was perfectly happy
with the card and whatever I want to do with it/to it.

So, sorry, you'll need to wait a little longer to get a first hand account of
merging badblocks and mkfs.  :)

>As for your networking issue being related, that's a hard call. If you're
>using GNOME with dbus and hal, etc, I could imagine some weird condition
>where various utilities were trying to read from your SD card as you were
>writing to it, possibly causing some kind of deadlock (especially if
>there's bad sectors). And then also I'm sure corrupted disks and
>filesystems are a great source of potential kernel issues as well.

I can imagine that there could be some hypothetical nasty corner case
collision amongst these things.  However, nearly all of the system busses will
be communicating via named pipes, shared memory, or if they are using network
sockets then those connections are almost certainly travelling over the
loopback device.

And you're right that a bad disk and all the expensive delays, retrys,
failures, etc. can really bog down a system.  In this case, though, I think
the SD card was just fine.  I do not recall seeing anything out of the
ordinary in the dmesg output.

>But then again, I'm really not a huge fan of Network Manager. Sometimes its
>nice, but often I have to disable it completely and resort to manual/static
>network configuration, e.g. in /etc/network/interfaces (on Debian distros)
>or with a shell script even.

I'm not a particular fan either.  For all my non-wifi systems I just use
Debian's /etc/network/interface like you and be done with it.  It's simple and
easy to read and change.

Wifi WPA configuration, on the other hand, can be a royal pain, especially
when you take your laptop from its home base and need to ocnnect to other
random APs.  Here, Network Manager become very handy.  At the very least, it
keeps me from banging my head on the wall fighting with wpa-supplicant.



-- 
--John Gruenenfelder    Systems Manager, MKS Imaging Technology, LLC.
Try Weasel Reader for PalmOS  --  http://weaselreader.org
"This is the most fun I've had without being drenched in the blood
of my enemies!"
        --Sam of Sam & Max
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://tfug.org/pipermail/tfug_tfug.org/attachments/20140904/c1f2173a/attachment.asc>