[OpenAFS] Connection timed out - problem with cache manager?

[Staffan Hämälä]

Some users at our site reports problems with downloading files directly to AFS (and this problem has existed for years).

The AFS cache is set to:
> cat /etc/openafs/cacheinfo
/afs:/cache/openafs:5000000


What happens is this:


HTTP request sent, awaiting response... 200 OK
Length: 1983588866 (1,8G) [application/zip]
Saving to: `nx-9.0.3.zip.1'



utime(nx-9.0.3.zip.1): Connection timed out




If I look at the resulting file, I see that it's corrupt.



Does anyone recognize this problem?

/Staffan

I'm now working to try to find the cause. Just to eliminate the server, we have moved the user's volume to our YFS server, but we experience exactly the same problem. I can't seem to reproduce it on my own machine (Ubuntu 14.04.1 LTS with openafs client 1.6.7-1ubuntu1.1). However, the machine where I have managed to reproduce the problem is a terminal server (with lots of users). It's a Ubuntu 12.04.5 LTS with openafs version 1.6.1-1+ubuntu0.7. I run a wget (from siemens in this case, but probably not important). The wget either aborts at 70% or so, with a "Connection timed out", or, as happened for me just now: 100%[====================================>] 1 983 588 866 17,7M/s in 1m 50s 2016-11-30 11:33:39 (17,3 MB/s) - `nx-9.0.3.zip.1' saved [1983588866/1983588866] So, the file downloaded 100% (to the AFS cache). Then there was a delay for some time before the error popped up (while flushing the cache, I would guess). Downloading to local disk first, and then copy to AFS seems to work every time.

smime.p7s
Description: S/MIME Cryptographic Signature