>>> On Wed, 20 Jan 2010 12:30:35 -0500, Doug Warner >>> <doug@xxxxxxxxx> said: doug> I'm trying to do an fsck on an ext3 partition but I'm doug> seeing abysmally slow disk throughput; monitoring with doug> "dstat" (like vmstat) shows ~1200-1500KB/s throughput to doug> the disks. That seems pretty good to me. Perhaps the impression of slowness is motivated by insufficient understanding of how 'fsck' works and the IOP limitations of small rotating mass storage arrays. doug> Even with 24hrs of fsck-ing I only get ~3% (still in doug> pass1). That's pretty good too. doug> The filesystem is ext3 running "e2fsck -C0 /dev/sda3" and doug> about 3.7TB on an x86_64-based system with 4GB RAM. doug> e2fsprogs is 1.41.9. There have been reports of a 1.5TB 'ext3' filesystem taking over a month: http://www.sabi.co.uk/blog/anno05-4th.html#051009 even if in optimal cases it can be better: http://www.sabi.co.uk/blog/0802feb.html#080210 doug> Just a rough extrapolation of the size of my filesystem doug> (3.4TB used; ~95%) makes it look like this will take ~28 doug> days to complete. I'm using approx 12M inodes out of my doug> 243M available. That sounds about right for lots of small files (~280KB average) in a very large number of directories (or in directories that are really very long), and which is 95% used. You have designed that filesystem that way, and it is performing as expected or better. People who use filesystems as databases deserve whatn they get. _______________________________________________ Ext3-users mailing list Ext3-users@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/ext3-users
