Exportfs and rpc.mountd optimalization
Subsystems (2)
I did some optimalization of exportfs and rpc.mountd (linked exportlist replaced by hash table). It has good results (I think) - computing of exportfs and mountd (after running exportfs) is quicker. Especially for long exportlists - about hundred thousand exports and more.
Can someone look on it?
thanks
Tomas Richter
I did some optimalization of exportfs and rpc.mountd (linked exportlist replaced by hash table). It has good results (I think) - computing of exportfs and mountd (after running exportfs) is quicker. Especially for long exportlists - about hundred thousand exports and more.
Can someone look on it?
thanks
Tomas Richter
m=C3=A5 den 20.06.2005 Klokka 19:34 (+0200) skreiv Tomas Richter:
Quoted 6 lines
I did some optimalization of exportfs and rpc.mountd (linked exportlist replaced by hash table). It has good results (I think) - computing of exportfs and mountd (after running exportfs) is quicker. Especially for long exportlists - about hundred thousand exports and more.
Can someone look on it?
If you would like to propose changes to the nfs-utils package, then please repost them in the form of a standard patch against the current nfs-utils CVS tree (see http://sourceforge.net/projects/nfs) so that they may be reviewed.
Cheers,
Trond
-------------------------------------------------------
SF.Net email is sponsored by: Discover Easy Linux Migration Strategies from IBM. Find simple to follow Roadmaps, straightforward articles, informative Webcasts and more! Get everything you need to get up to speed, fast. http://ads.osdn.com/?ad_id=7477&alloc_id=16492&op=click
_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs
Quoted 5 lines · Tomas Richter
I did some optimalization of exportfs and rpc.mountd (linked exportlist replaced by hash table). It has good results (I think) - computing of exportfs and mountd (after running exportfs) is quicker. Especially for long exportlists - about hundred thousand exports and more.
It'd be interesting to see whether you could reproduce (and improve on) Vincent Rouqueta's results:
http://nfsv4.bullopensource.org/tools/tests/page17.php
Quoted 1 line
Can someone look on it?
Could you send your changes in the form of patches? (See, e.g.,
http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt).
--b.
-------------------------------------------------------
SF.Net email is sponsored by: Discover Easy Linux Migration Strategies from IBM. Find simple to follow Roadmaps, straightforward articles, informative Webcasts and more! Get everything you need to get up to speed, fast. http://ads.osdn.com/?ad_id=7477&alloc_id=16492&op=click
_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs
Le lundi 20 Juin 2005 19:34, Tomas Richter a =E9crit=A0:
Quoted 6 lines
I did some optimalization of exportfs and rpc.mountd (linked exportlist replaced by hash table). It has good results (I think) - computing of exportfs and mountd (after running exportfs) is quicker. Especially for long exportlists - about hundred thousand exports and more.
Can someone look on it?
Yes! ;)
Vincent
-------------------------------------------------------
SF.Net email is sponsored by: Discover Easy Linux Migration Strategies from IBM. Find simple to follow Roadmaps, straightforward articles, informative Webcasts and more! Get everything you need to get up to speed, fast. http://ads.osdn.com/?ad_id=7477&alloc_id=16492&op=click
_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs