[neurosetta] positron experiences and questions

[Stan Seibert]

On Tue, 2003-07-01 at 11:21, Dan Berger wrote:
> Anyone having similar experiences?  Given the long startup-time for
> positron (while it scans the sync point), and only being able to sync
> in blocks of 30 - it'll take me days to get my 3000 odd tracks copied
> over.

Yes, all of the symptoms you describe have been observed by various
people, though there does not seem to be a clear fix.  Sometimes
changing the kernel version, or using a different computer has cleared
up the issue.  It is either a Neuros USB code issue or a Linux kernel
issue or both.  I'm not sure what to do about this.

> My first observation is that doing file reads off the neuros must be
> dog slow - as it's taking rsync forever to decide what files it
> doesn't need to update.
> 
> My second observation is that writes are pretty slow, too - as rsync
> reports about 500kB/s writing files.

Yes, this is a limitation of the USB 1.1 interface.  The USB 2.0
backpacks should bump this rate up by a factor of 10-20x.

> My fifth  and final (at least for now) observation is that during
> those times that rsync is getting poor throughput, my load average
> peaks around 4 - but once that file is written (and flushed, perhaps?)
> the load average drops and rsync continues.
> 
> My conclusion is that what seems to be going on is that positron is
> aggravating a kernel or usb-storage bug - and that rsync, for whatever
> reason, isn't doing the same.

This is interesting.  I'd be curious to know what the difference is. 
(For the record, since I couldn't find a "copy file" function in the os
module, I wrote my own that reads 1 MB from the source and writes 1 MB
to the destination alternately.  Would smaller chunks work better?)

> Can anyone out there corroborate these experiences?  Any comment from
> the positron folk(s)?

Other than saying, yes, random people have experiences some combination
of the problems you have seen, I'm not sure what else to do.  Something
is definitely wrong here, and I'm not enough of a kernel hacker to
figure out what it is.  :(


---
Stan Seibert

<p><p>--- >8 ----
List archives:  http://www.xiph.org/archives/
Neurosetta homepage: http://www.neurosetta.org/
To unsubscribe from this list, send a message to 'neurosetta-request at xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is needed.
Unsubscribe messages sent to the list will be ignored/filtered.