POHMELFS metadata benchmarks: tar and large dbench

Tagged:  

<a href="/projects/pohmelfs">POHMELFS</a> userspace server and the latest to date (pushed into the <a href="/cgi-bin/gitweb.cgi">git</a>) kernel client.
In-kernel async NFS server and client (2.6.28 tree).
Both client and server have 8Gb of RAM, 32bit CPUs.

The first bench: untarring the linux kernel sources (smaller is better):&#10;POHMELFS:   5 seconds&#10;     NFS:  44 seconds

Sync called after the untar takes less than a second, so it does not affect the test.

The second one: dbench with 30 threads. Servers exported <code>/dev/shm</code> to the clients.
<center><img src="/gallery/dbench_pohmelfs_vs_nfs_30.png"></center>

Updated POHMELFS version fixes fair number of bugs both from its move from own path to dentry cache and old cache coherency issues. There is a nasty issue in the code: object removal. It is not optimized at all, and, hmm, it does not work for directories :) It happens because unhashed direntry path lookup in the dcache returns not only path to the direntry, but also adds <code>(deleted)</code> string after it, so obviously object with such a pathname can not be removed.
I will work on this before pushing upstream (scheduled for tomorrow).

Stay tuned!

yuhuuuu upstream :)

Mmm... Dounuts! ;)

One-man very active upstream, you mean? Or... ah-ah, yeah, "please do/submit/go" upstream... Didn't you read "that e-mail"? :-P <a href="http://www.ioremap.net/node/72#comment-154" title="http://www.ioremap.net/node/72#comment-154">http://www.ioremap.net/node/72#comment-154</a> <a href="http://www.ioremap.net/node/120" title="http://www.ioremap.net/node/120">http://www.ioremap.net/node/120</a> Ehrm.. no %) , that one. <a href="http://www.ioremap.net/node/66" title="http://www.ioremap.net/node/66">http://www.ioremap.net/node/66</a>

2zbr: Good job making fun and $) publicity with the projects. Crazy idea, make an NFS-server front-end to the *FS, make it feature-bug-testcase(is there one?) compatible with and benchmark on the "same ground"? Then go upstream and replace %) the predecessor. World Domination is fun, can you see? :))))))