<div dir="ltr">Whether flush-behind is enabled or not, close() will guarantee all previous write()s on that fd have been acknowledged by server. It is just the post processing of close() itself which is performed in background when flush-behind is enabled. The word "flush" here is probably confusing as it is specific to FUSE terminology where an app triggered close() appears as a flush fop.<div>
<br></div><div>Thanks</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Jul 28, 2014 at 9:58 AM, Richard van der Hoff <span dir="ltr"><<a href="mailto:richard@swiftserve.com" target="_blank">richard@swiftserve.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Would anyone be able to help out with this question?<br>
<br>
Thanks<span class="HOEnZb"><font color="#888888"><br>
<br>
Richard</font></span><div class="HOEnZb"><div class="h5"><br>
<br>
<br>
On 11/07/14 00:08, Pranith Kumar Karampuri wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
CC write-behind Dev<br>
On 07/10/2014 11:59 PM, Richard van der Hoff wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi folks,<br>
<br>
Just wondering if anyone could clear up a question about expected<br>
behavior for the performance/writebehind translator.<br>
<br>
I'm using Gluster 3.3, with a single volume which is distributed to<br>
two bricks on a pair of servers. I have performance.flush-behind=off;<br>
the documentation [1] leads me to expect (but doesn't say explicitly)<br>
that this will make close() block until the write has been flushed -<br>
but that isn't consistent with the behaviour I'm seeing:<br>
<br>
$ dd if=/dev/zero of=/shared/vod/zero bs=1024 count=1000; wc -c<br>
/shared/vod/zero<br>
1000+0 records in<br>
1000+0 records out<br>
1024000 bytes (1.0 MB) copied, 0.133975 s, 7.6 MB/s<br>
1016832 /shared/vod/zero<br>
<br>
As you can see, the wc doesn't see all of the data which has been<br>
written by dd.<br>
<br>
If anyone could clear up whether or not this is expected, I'd be<br>
grateful.<br>
<br>
Thanks<br>
<br>
Richard<br>
<br>
[1]<br>
<a href="http://gluster.org/community/documentation/index.php/Translators/performance/writebehind" target="_blank">http://gluster.org/community/<u></u>documentation/index.php/<u></u>Translators/performance/<u></u>writebehind</a><br>
<br>
______________________________<u></u>_________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="http://supercolony.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://supercolony.gluster.<u></u>org/mailman/listinfo/gluster-<u></u>users</a><br>
</blockquote>
<br>
</blockquote>
<br>
<br>
______________________________<u></u>_________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="http://supercolony.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://supercolony.gluster.<u></u>org/mailman/listinfo/gluster-<u></u>users</a><br>
</div></div></blockquote></div><br></div>