optimizari surpriza de ext3 pentru nfs
Tocmai a aparut pe slashdot un articol despre filesystemele next-generation din kernelul Linux. Articolul in sine e simpatic, dar interesant e ca in commenturi apare in mai multe randuri Theodore Ts'o (cu nickul "tytso") cu o serie de comentarii mult mai interesante decat articolul 
Cel care mi-a atras atentia a fost un reply pentru cineva care se plangea de performanta scazuta pe care o poate avea ext3 cu fisiere foarte multe cand e folosit prin NFS:
NFS semantics require that the data be stably written on disk before it can be client's RPC request can be acknowledged. This can cause some very nasty performance problems. One of the things that can help is to use a second hard drive to store an external journal. Since the journal is only written during normal operation (you need it when you recover after an system crash), and the writes are contiguous on disk, this eliminates nearly all of the seek delays associated with the journal. If you use data journalling, so that data blocks are written to the journal, the fact that no writes are required means that the data can be written onto stable storage very quickly, and thus will accelerate your NFS clients. If you want things to go _really_ fast, use a battery-backed NVRAM for your external journal device.
Asta tocmai mi-a aprins o gramada de beculete, dat fiind ca citisem mai de mult despre faptul ca poti tine jurnalul pe alt device, dar nu m-am gandit pana acum la implicatii. Sper sa-mi aduc aminte de asta data viitoare cand o sa am probleme de performanta, dar daca are cineva success/horror stories cu scamatorii cu jurnalul, please share.