[OpenAFS] poor out of cache behavior on writing

Sven Oehme oehmes@de.ibm.com
Tue, 18 Feb 2003 14:25:57 +0100


This is a multipart message in MIME format.
--=_alternative 0049C793C1256CD1_=
Content-Type: text/plain; charset="US-ASCII"

hy , 

yes i know , under aix it is not a Problem , but under Linux (Redhat 8.0 
Kernel 2.4.18) 

Sven





Paul Blackburn <mpb@est.ibm.com>
Sent by: openafs-info-admin@openafs.org
02/18/2003 01:47 PM
 
        To:     Sven Oehme/Germany/IBM@IBMDE
        cc:     Edward Moy <emoy@apple.com>, openafs-info@openafs.org, 
openafs-info-admin@openafs.org
        Subject:        Re: [OpenAFS] poor out of cache behavior on 
writing

 

Sven,
I have seen that using a 256mb RAM cache on a machine with 1gb RAM
running AIX did not crash.
--
cheers
paul                       http://acm.org/~mpb

Sven Oehme wrote:

>
> hy ,
>
> i have seen increasing the memcache size >50 mb on a Linux Server with 
> 512 mb that afs is crashing .
>
> Sven
>
>
>
>
> *Paul Blackburn <mpb@est.ibm.com>*
> Sent by: openafs-info-admin@openafs.org
>
> 02/18/2003 10:06 AM
>
> 
>         To:        Edward Moy <emoy@apple.com>
>         cc:        openafs-info@openafs.org
>         Subject:        Re: [OpenAFS] poor out of cache behavior on 
> writing
>
> 
>
>
>
> Edward Moy wrote:
>
> >
> > Yes, it is true that fast read performance should be a higher
> > priority. But if I want to read a 1 GB file from AFS, I have to write
> > it there in the first place.
> >
> > Look at the times to read that same 1 GB file:
> >
> > nfs 0.050u 18.050s 2:25.59 12.4%
> > afs 0.5GB cache 0.030u 10.300s 2:29.26 6.9%
> > afs 2GB cache 0.030u 11.250s 2:32.67 7.3%
> >
> > Within the normal fluctuations in the network itself, AFS is very
> > close to raw NFA, for first-time reading. But also note that even when
> > the cache is smaller than the file, one does not see the poor behavior
> > exhibited in the write case.
>
> Hi Edward,
>
> I think you have succintly made the point that you need to size
> your AFS cache appropriately for your workload.
>
> If you plan on working with 1gb files often and writing 1gb files
> into /afs/@cell/$whatever/ then you better configure a big enough AFS 
> cache.
>
> I think that "cache thrashing" is similar to "page thrashing"
> in virtual memory operating systems. It is a situation that
> occurs when there is not enough resource allocated (eg cache too small)
> for the workload applied to it.
>
> Remember also that with AFS, you have a choice of disk cache
> or RAM cache. So if you have enough installed RAM, you
> will see faster access using AFS RAM cache (than using disk cache).
>
> >
> >
> > It takes 2 1/2 minutes to read the file, and 4 minutes to write it
> > when there is enough cache. But as a user, when that goes up to 10
> > minutes, and uses 80% of the processor, my first reaction would be
> > that something is wrong.
> >
> > From other comments I've seen, it appears that this is "expected"
> > (though hopefully not desirable) behavior. I just wanted to point out
> > that there is room for improvement in this area.
>
> You are absolutely right to point this out.
> If there is something "not working right" with AFS write function
> then this is a good place to discuss it and propose solutions.
> --
> cheers
> paul http://acm.org/~mpb
>
>
> _______________________________________________
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
>



_______________________________________________
OpenAFS-info mailing list
OpenAFS-info@openafs.org
https://lists.openafs.org/mailman/listinfo/openafs-info


--=_alternative 0049C793C1256CD1_=
Content-Type: text/html; charset="US-ASCII"


<br><font size=2 face="sans-serif">hy , </font>
<br>
<br><font size=2 face="sans-serif">yes i know , under aix it is not a Problem
, but under Linux (Redhat 8.0 Kernel 2.4.18) </font>
<br>
<br><font size=2 face="sans-serif">Sven</font>
<br>
<br>
<br>
<br>
<table width=100%>
<tr valign=top>
<td>
<td><font size=1 face="sans-serif"><b>Paul Blackburn &lt;mpb@est.ibm.com&gt;</b></font>
<br><font size=1 face="sans-serif">Sent by: openafs-info-admin@openafs.org</font>
<p><font size=1 face="sans-serif">02/18/2003 01:47 PM</font>
<td><font size=1 face="Arial">&nbsp; &nbsp; &nbsp; &nbsp; </font>
<br><font size=1 face="sans-serif">&nbsp; &nbsp; &nbsp; &nbsp; To:
&nbsp; &nbsp; &nbsp; &nbsp;Sven Oehme/Germany/IBM@IBMDE</font>
<br><font size=1 face="sans-serif">&nbsp; &nbsp; &nbsp; &nbsp; cc:
&nbsp; &nbsp; &nbsp; &nbsp;Edward Moy &lt;emoy@apple.com&gt;, openafs-info@openafs.org,
openafs-info-admin@openafs.org</font>
<br><font size=1 face="sans-serif">&nbsp; &nbsp; &nbsp; &nbsp; Subject:
&nbsp; &nbsp; &nbsp; &nbsp;Re: [OpenAFS] poor out of cache behavior
on writing</font>
<br>
<br><font size=1 face="Arial">&nbsp; &nbsp; &nbsp; &nbsp;</font></table>
<br>
<br><font size=2><tt>Sven,<br>
I have seen that using a 256mb RAM cache on a machine with 1gb RAM<br>
running AIX did not crash.<br>
--<br>
cheers<br>
paul &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;
&nbsp; http://acm.org/~mpb<br>
<br>
Sven Oehme wrote:<br>
<br>
&gt;<br>
&gt; hy ,<br>
&gt;<br>
&gt; i have seen increasing the memcache size &gt;50 mb on a Linux Server
with <br>
&gt; 512 mb that afs is crashing .<br>
&gt;<br>
&gt; Sven<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; *Paul Blackburn &lt;mpb@est.ibm.com&gt;*<br>
&gt; Sent by: openafs-info-admin@openafs.org<br>
&gt;<br>
&gt; 02/18/2003 10:06 AM<br>
&gt;<br>
&gt; &nbsp; &nbsp; &nbsp; &nbsp;<br>
&gt; &nbsp; &nbsp; &nbsp; &nbsp; To: &nbsp; &nbsp; &nbsp; &nbsp;Edward
Moy &lt;emoy@apple.com&gt;<br>
&gt; &nbsp; &nbsp; &nbsp; &nbsp; cc: &nbsp; &nbsp; &nbsp; &nbsp;openafs-info@openafs.org<br>
&gt; &nbsp; &nbsp; &nbsp; &nbsp; Subject: &nbsp; &nbsp; &nbsp; &nbsp;Re:
[OpenAFS] poor out of cache behavior on <br>
&gt; writing<br>
&gt;<br>
&gt; &nbsp; &nbsp; &nbsp; &nbsp;<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; Edward Moy wrote:<br>
&gt;<br>
&gt; &gt;<br>
&gt; &gt; Yes, it is true that fast read performance should be a higher<br>
&gt; &gt; priority. But if I want to read a 1 GB file from AFS, I have
to write<br>
&gt; &gt; it there in the first place.<br>
&gt; &gt;<br>
&gt; &gt; Look at the times to read that same 1 GB file:<br>
&gt; &gt;<br>
&gt; &gt; nfs 0.050u 18.050s 2:25.59 12.4%<br>
&gt; &gt; afs 0.5GB cache 0.030u 10.300s 2:29.26 6.9%<br>
&gt; &gt; afs 2GB cache 0.030u 11.250s 2:32.67 7.3%<br>
&gt; &gt;<br>
&gt; &gt; Within the normal fluctuations in the network itself, AFS is
very<br>
&gt; &gt; close to raw NFA, for first-time reading. But also note that
even when<br>
&gt; &gt; the cache is smaller than the file, one does not see the poor
behavior<br>
&gt; &gt; exhibited in the write case.<br>
&gt;<br>
&gt; Hi Edward,<br>
&gt;<br>
&gt; I think you have succintly made the point that you need to size<br>
&gt; your AFS cache appropriately for your workload.<br>
&gt;<br>
&gt; If you plan on working with 1gb files often and writing 1gb files<br>
&gt; into /afs/@cell/$whatever/ then you better configure a big enough
AFS <br>
&gt; cache.<br>
&gt;<br>
&gt; I think that &quot;cache thrashing&quot; is similar to &quot;page
thrashing&quot;<br>
&gt; in virtual memory operating systems. It is a situation that<br>
&gt; occurs when there is not enough resource allocated (eg cache too small)<br>
&gt; for the workload applied to it.<br>
&gt;<br>
&gt; Remember also that with AFS, you have a choice of disk cache<br>
&gt; or RAM cache. So if you have enough installed RAM, you<br>
&gt; will see faster access using AFS RAM cache (than using disk cache).<br>
&gt;<br>
&gt; &gt;<br>
&gt; &gt;<br>
&gt; &gt; It takes 2 1/2 minutes to read the file, and 4 minutes to write
it<br>
&gt; &gt; when there is enough cache. But as a user, when that goes up
to 10<br>
&gt; &gt; minutes, and uses 80% of the processor, my first reaction would
be<br>
&gt; &gt; that something is wrong.<br>
&gt; &gt;<br>
&gt; &gt; From other comments I've seen, it appears that this is &quot;expected&quot;<br>
&gt; &gt; (though hopefully not desirable) behavior. I just wanted to point
out<br>
&gt; &gt; that there is room for improvement in this area.<br>
&gt;<br>
&gt; You are absolutely right to point this out.<br>
&gt; If there is something &quot;not working right&quot; with AFS write
function<br>
&gt; then this is a good place to discuss it and propose solutions.<br>
&gt; --<br>
&gt; cheers<br>
&gt; paul http://acm.org/~mpb<br>
&gt;<br>
&gt;<br>
&gt; _______________________________________________<br>
&gt; OpenAFS-info mailing list<br>
&gt; OpenAFS-info@openafs.org<br>
&gt; https://lists.openafs.org/mailman/listinfo/openafs-info<br>
&gt;<br>
<br>
<br>
<br>
_______________________________________________<br>
OpenAFS-info mailing list<br>
OpenAFS-info@openafs.org<br>
https://lists.openafs.org/mailman/listinfo/openafs-info<br>
</tt></font>
<br>
--=_alternative 0049C793C1256CD1_=--