Toby Corkindale <[email protected]> wrote: > * set the 'discard' mount flag if you're using ext4, or 'ssd' on btrfs. > (This tells the SSD when you've deleted stuff to free up space, and > allows it to work a lot more efficiently) > * set 'relatime' mount flag as well; it helps performance on > everything, and in ssd cases, avoids a bunch of unnecessary writes. > * Align partitions and filesystems on multiples of the ssd erase > block.. or if you don't know what that is, just make sure it's a > multiple of a number like 16k or something.. just not the default of > 512. There are some tools around that'll benchmark different block sizes > to work out the appropriate value, too. However note that this issue > only seemed to be a *big* issue for earlier generation SSDs.. the > current ones seem to cope pretty well regardless.
That's a very helpful summary. Also, be sure that /tmp is a tmpfs file system rather than a directory on the ssd; this will reduce write activity. I think most distributions default to tmpfs already now. _______________________________________________ luv-main mailing list [email protected] http://lists.luv.asn.au/listinfo/luv-main
