<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">Le 12/05/2015 20:27, Nathan Rutman a
écrit :<br>
</div>
<blockquote
cite="mid:CAB_j=MdgcH6_3Y0RopcL_YaX86iNrVjOo7Pp3dJD1kJvhVAcJQ@mail.gmail.com"
type="cite">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<div dir="ltr">Someone sent me a link to this:
<div><a moz-do-not-send="true"
href="http://arxiv.org/pdf/1505.02656v1.pdf">http://arxiv.org/pdf/1505.02656v1.pdf</a></div>
<div>Very cool. We'll need to start using that.</div>
<div><br>
</div>
<div>This reminded me to send my changelog/robinhood/HSM
concerns that I brought up at LUG to you guys for your
thoughts.</div>
<div><br>
</div>
<div>1. What should happen when the changelog on an MDS fills
up? Maybe LCAP helps with the processing rate, but
fundamentally the issue might still happen if nobody consumes
due to various software or comms errors. We should either stop
recording records and risk losing change tracking, or stop MDS
processing. (I believe at the moment this will just crash the
MDS.) We probably need a high water mark.</div>
<div><br>
</div>
<div>2. There should be some kind of rate limiting for HSM
requests (RH to MDS), so that the number of HSM requests
queued up in the coordinator doesn't grow without bound.
Probably we need a -EAGAIN return code to RH at some point.</div>
<div><br>
</div>
<div>3. It feels like there needs to be some feedback from the
backend HSM storage to RH, in particular to pass back a
"backend full" message. We can presumably pass a backend
ENOSPC from the copytool back to the Coordinator, but how can
that message get back to Robinhood? I guess coordinator could
start returning ENOSPC for subsequent archive requests from
RH, but then we have to clear that response if the backend
condition clears.</div>
<div><br clear="all">
<div>
<div class="gmail_signature">
<div dir="ltr">
<div>
<div dir="ltr"><b>--</b>
<div><font size="1"><b>Nathan Rutman · <font
color="#666666">Principal Systems Architect</font><br>
<font color="#0b5394">Seagate Technology</font></b><b> · </b>+1
503 877-9507<b> · </b>GMT-8</font></div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</blockquote>
<br>
Hello Nathan,<br>
<br>
1: when the changelog catalog is full (4B entries IIRC) lustre
should either automatically clear the catalog or turn the FS
read-only (tunable, indeed). I want to propose a patch for this but
don't have it yet.<br>
<br>
2: Right, there is no limitation at the moment. I think what is
needed there is rather a high watermark on the number of pending
requests than rate limiting. Note that on robinhood side your can
set limitations on the number of active requests.<br>
<br>
3: As you say, the copytools can propagate error messages back to
the coordinator, indicating whether they are retryable or not.
Non-retryable errors would cause the requests to fail. Lustre can
then either emit a changelog for failed requests (which is on the
edge of what changelogs are for, though...) or we can add some
mechanism into rbh to let it react when it detects that too many
requests have failed. That said, many failed requests is something
that probably has to be detected and handled by monitoring systems.
Avoiding too tight coupling between HSM components is desirable.<br>
<br>
<br>
Regards<br>
<br>
-- <br>
Henri<br>
</body>
</html>