[Gluster-devel] readahead: unexpected offset (131072 != 0) resetting

[Raghavendra G]

Hi Emmanuel,

Please find the inlined comments,


> I am still working on glusterfs on NetBSD (and I still have pending
> patches. Any taker?), and I see this debug message that may be caused
> by a bug in NetBSD FUSE interface:
>
> D [read-ahead.c:478:ra_readv] readahead: unexpected offset (131072 != 0)
> resetting
>

The log message means that the application is not doing sequential reads, it
has seeked to offset zero, after it had read till  offset 131072. When this
condition is hit, read-ahead senses that the application is no longer doing
sequential reads and flushes all the pages in its cache, since reading ahead
makes sense only for sequential reads but not for random reads. As far as
the correctness is concerned, there is nothing going wrong here.


> What does it mean? I notice that 131072 is 32 * PAGE_SIZE, which is the
> negociated max_read_ahead. Did I send too many requests at once?
>
> --
> Emmanuel Dreyfus
> manu at netbsd.org
>
> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at nongnu.org
> http://lists.nongnu.org/mailman/listinfo/gluster-devel
>



-- 
Raghavendra G
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-devel/attachments/20100923/a12304df/attachment-0003.html>