Hi Dirk,
<br>

<br>
Sad to say it took me 7 months, but I think I have the issue fixed!  In the end, it wasn&#39;t a mysterious threading or memory management issue - a simple logic mistake exists in the new client when reading ReadV requests.
<br>

<br>
Any user of the new client sufficiently unlucky should be able to trigger it - all that needs to be done is perform ReadV (no threading necessary!).  In our tests (which &quot;encourage&quot; the race condition because things are read over the wide area), about 10% of jobs die due to it.
<br>

<br>
IMHO, this definitely needs to be backported to the stable series.
<br>

<br>
Brian
<br>

<br>
On Apr 24, 2014, at 2:54 AM, xrootd-dev &lt;<a href="/cgi-bin/wa?LOGON=A3%3Dind1404%26L%3DXROOTD-DEV%26E%3Dquoted-printable%26P%3D202177%26B%3D----%253D%253D_mimepart_5359285bb2dde_39e43f9985a732a4741555%26T%3Dtext%252Fhtml%3B%2520charset%3DUTF-8%26pending%3D" target="_parent" >[log in to unmask]</a>&gt; wrote:
<br>

<br>
&gt; Hi Brian, 
<br>
&gt; 
<br>
&gt; Lukasz is probably still traveling - let me know if we need someone to look at this before he is back on May 5th. 
<br>
&gt; 
<br>
&gt; 
<br>
&gt; Cheers, Dirk 
<br>
&gt; 
<br>
&gt; On 24 Apr 2014, at 05:42, Brian Bockelman &lt;<a href="/cgi-bin/wa?LOGON=A3%3Dind1404%26L%3DXROOTD-DEV%26E%3Dquoted-printable%26P%3D202177%26B%3D----%253D%253D_mimepart_5359285bb2dde_39e43f9985a732a4741555%26T%3Dtext%252Fhtml%3B%2520charset%3DUTF-8%26pending%3D" target="_parent" >[log in to unmask]</a>&gt; wrote: 
<br>
&gt; 
<br>
&gt; &gt; Hi @ljanyst - 
<br>
&gt; &gt; 
<br>
&gt; &gt; Any further thoughts on this one? I&#39;m still stumped and large-scale testing hasn&#39;t really revealed any more clues. 
<br>
&gt; &gt; 
<br>
&gt; &gt; Currently, this is the last thing standing in the way from using the new client in CMS. 
<br>
&gt; &gt; 
<br>
&gt; &gt; Brian 
<br>
&gt; &gt; 
<br>
&gt; &gt; — 
<br>
&gt; &gt; Reply to this email directly or view it on GitHub. 
<br>
&gt; &gt; 
<br>
&gt; &gt; 
<br>
&gt; &gt; Use REPLY-ALL to reply to list 
<br>
&gt; &gt; 
<br>
&gt; &gt; To unsubscribe from the XROOTD-DEV list, click the following link: 
<br>
&gt; &gt; https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-DEV&amp;A=1 
<br>
&gt; &gt;
<br>
&gt; —
<br>
&gt; Reply to this email directly or view it on GitHub.
<br>
&gt; 

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br>Reply to this email directly or <a href='https://github.com/xrootd/xrootd/issues/45#issuecomment-41290997'>view it on GitHub</a>.<img src='https://github.com/notifications/beacon/4118670__eyJzY29wZSI6Ik5ld3NpZXM6QmVhY29uIiwiZXhwaXJlcyI6MTcxMzk3MTE2MywiZGF0YSI6eyJpZCI6MTY3OTk5ODR9fQ==--538186896c3eff768d368afc2397d374fdea42ac.gif' height='1' width='1'></p><br>
<hr>
<p align="left">
Use REPLY-ALL to reply to list</p>
<p align="center">To unsubscribe from the XROOTD-DEV list, click the following link:<br>
<a href="https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-DEV&A=1" target="_blank">https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-DEV&A=1</a>
</p>