Carlos Carvalho (carlos@xxxxxxxxxxxxxx) wrote on 15 April 2006 15:44: >Sorry, forgot to say this... > >Mark Hahn (hahn@xxxxxxxxxxxxxxxxxxx) wrote on 15 April 2006 13:06: > >> Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn > >> md0 14,46 57,17 104,96 18050544 33136016 > >> md2 71,53 145,46 519,37 45922192 163968648 > >> md1 0,05 0,19 0,19 60592 58688 > >> > >> md0 is /, md1 swap and md2 /home. > >> > >> What I find strange is that the Blk_read for md0 is not negligible > >> compared to md2; md0 only has bin, console, dev, etc, lib, proc, root, > >> sbin, sys and usr. These should be read mostly soon after boot and > > > >mounted with noatime? Well, I did what I should have done before bothering you... I remounted the partition with noatime and nodiratime, and IO dropped to almost zero. This shows that all that traffic is indeed inode updating! Thanks to Mark for pushing me to be less subjective. - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
