gluster-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

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


From: Raghavendra G
Subject: Re: [Gluster-devel] readahead: unexpected offset (131072 != 0) resetting
Date: Thu, 23 Sep 2010 22:34:06 +0400

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 tillĀ  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
address@hidden

_______________________________________________
Gluster-devel mailing list
address@hidden
http://lists.nongnu.org/mailman/listinfo/gluster-devel



--
Raghavendra G


reply via email to

[Prev in Thread] Current Thread [Next in Thread]