On 6/28/2012 2:03 PM, Jeffrey Altman wrote:
On 6/28/2012 2:37 PM, Douglas E. Engert wrote:
The OpenAFS Change log says:

     Since 1.7.1100 (1.7.11)
     * Treat all cached writes as write-through

This is write-through to the AFS cache from the Windows page cache;
not write-through to the file server.  In any case, it is a performance
hit but is a necessary one.Otherwise, it is possible for the page
cache to fill with data intended for AFS and it become impossible for
the pages to be cleared in a timely fashion to make room for non-AFS
data.

The best I can tell, Thunderbird for the local mail folders is doing
synchronous writes, which is another performance problem in itself,
although it looks like a Delete/Copy/Move has its own thread (or its using
the main thread which might be way it is not responding)  but as
a user, deleting messages (that get copied to the Trash folder)
it becomes single threaded waiting on the Trash folder and I have to wait
to do the next delete.

Note that by buffering I get about 60 times improvement in throughput,
so the performance hit is caused more by the number of writes, not on how
much data is written.

Could Windows be doing some throttling based on the number of writes?

I don't get this bad of performance using the Windows DFS as I do AFS.

CPU time, I/O and network I/O are NOT maxed out during one of these
Delete operations.


The page cache is quite often many multiples in size of the
AFS cache.

The change was made in 1.7.12 not 1.7.11.

I copied the above 2 lines from the Change Log, and it was not clear
if "since 1.7.1100" meant 1.7.1200 or not.


Jeffrey Altman


--

 Douglas E. Engert  <[email protected]>
 Argonne National Laboratory
 9700 South Cass Avenue
 Argonne, Illinois  60439
 (630) 252-5444


_______________________________________________
OpenAFS-devel mailing list
[email protected]
https://lists.openafs.org/mailman/listinfo/openafs-devel

Reply via email to