<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">Le 13 avr. 2014 à 00:13, Ben RUBSON <<a href="mailto:ben.rubson@gmail.com">ben.rubson@gmail.com</a>> a écrit :<br><div><blockquote type="cite"><div dir="ltr"><div><div><div><div>I'm wondering about "WRITE SAME" which has been introduced in 3.10.<br></div>Quite the same issue here :<br><a href="http://www.redhat.com/archives/dm-devel/2013-September/msg00093.html">http://www.redhat.com/archives/dm-devel/2013-September/msg00093.html</a><br>
</div>I'll try to disable it.<br></div>However, any known workaround, patch… ?</div></div></blockquote><br></div><div>OK, after further tests, "WRITE SAME" (which fails) seems to be the root cause.</div><div>Here is a workaround, to launch at boot time :</div><div>find /sys/devices/ -name max_write_same_blocks -exec sh -c 'echo 0 > {}’ \;</div><div><br></div><div>So, kernel should be improved to detect "WRITE SAME" compliance more friendly.</div><div>Or DRBD should include a patch to ignore such errors.</div><div>But sounds like that work should be done at kernel side.</div><div><br></div><div>Ben</div></body></html>