Hi Elvin,<br>
<br>
The only way is for the oss/ofs to reply wait (say for a second or so). <br>
Then the client should retry after that. I suppose you can just alter the <br>
ofs but while esy its a bit messy to do exactly what you want without <br>
stalling (e.g. keep track of the files you replied &quot;wait&quot; and only do it <br>
once).<br>
<br>
Andy<br>
<br>
On Wed, 16 Sep 2015, Elvin Sindrilaru wrote:<br>
<br>
&gt;<br>
&gt; Happens quite often now in CASTOR for diskservers which are under heavy load. It has the following signature:<br>
&gt;<br>
&gt; 150916 17:43:22 21073 XrootdXeq: alicedaq.8138:441@aldaqtdsm03 pvt IPv4 login as alicedaq<br>
&gt; 150916 17:43:22 21073 alicedaq.8138:441@aldaqtdsm03 XrootdProtocol: endsess 14245:353.19908<br>
&gt; 150916 17:43:22 21073 alicedaq.8138:441@aldaqtdsm03 XrootdProtocol: endsess 14245:353.19908 rc=4 (Resource temporarily unavailable)<br>
&gt; 150916 17:43:22 time=1442418202.152684 func=open                     level=INFO  logid=a912d31c-5c89-11e5-bf06-001b21551dbc <a href="/cgi-bin/wa?LOGON=A3%3Dind1509%26L%3DXROOTD-DEV%26E%3D7bit%26P%3D217659%26B%3D----%253D%253D_mimepart_55f9e210267bc_17613ffd86e4b2b814872e%26T%3Dtext%252Fhtml%3B%2520charset%3DUTF-8%26pending%3D" target="_parent" >[log in to unmask]</a>:1094 tid=140534474995456 source=XrdxCastor2Ofs:448   tident=alicedaq.8138:441@aldaqtdsm03 path=/castor/cern.ch/alice/raw/technical/2015/09/16/16/15000236105030.1319.root, opaque=mode=644&amp;oss.asize=1865279545, isRW=1, open_mode=4002, file_ptr=0x7fd0d24ed010<br>
&gt; 150916 17:43:22 time=1442418202.152714 func=ExtractTransferInfo      level=ERROR logid=a912d31c-5c89-11e5-bf06-001b21551dbc <a href="/cgi-bin/wa?LOGON=A3%3Dind1509%26L%3DXROOTD-DEV%26E%3D7bit%26P%3D217659%26B%3D----%253D%253D_mimepart_55f9e210267bc_17613ffd86e4b2b814872e%26T%3Dtext%252Fhtml%3B%2520charset%3DUTF-8%26pending%3D" target="_parent" >[log in to unmask]</a>:1094 tid=140534474995456 source=XrdxCastor2Ofs:1000  tident=alicedaq.8138:441@aldaqtdsm03 no diskmanager opaque information i.e. castor.pfn2 missing<br>
&gt; 150916 17:43:22 17023 castor2ofs_open: alicedaq.8138:441@aldaqtdsm03 Unable to get diskmanager opaque info (pfn2) ; input/output error<br>
&gt;<br>
&gt; The opaque information should have contained the pfn2 info.<br>
&gt;<br>
&gt; Btw, @abh3  do you have any suggestion how I can easily get the server in a state where it triggers a retry on the client side for open?<br>
&gt;<br>
&gt; ---<br>
&gt; Reply to this email directly or view it on GitHub:<br>
&gt; https://github.com/xrootd/xrootd/issues/287<br>


<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/287#issuecomment-140902424">view it on GitHub</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AD7Yjpo2Q2mshVqVgeaxxHI4EZUzJ-uLks5oydmQgaJpZM4F-urC.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
  <link itemprop="url" href="https://github.com/xrootd/xrootd/issues/287#issuecomment-140902424"></link>
  <meta itemprop="name" content="View Issue"></meta>
</div>
<meta itemprop="description" content="View this Issue on GitHub"></meta>
</div>
<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>