On 07/02/13 21:29, Carsten Aulbert wrote: > Hi > > On 02/07/2013 11:12 AM, Adam Goryachev wrote: >> Do you have any information on what your workload is, or how/why these >> values might help? > > Most of our data servers are exporting data read-only via NFS. It helped > well on these but more on download servers which allowed us to go from > 200k 4MB downloads per day to 1M/day while adding new files constantly. > >> >> You are changing values significantly from the default, and I am >> cautious that they may cause other issues. Also, someone else has >> advised to reduce nr_requests rather than increasing it? >> > > I know, but these larger queues really helped a lot in re-ordering > requests to better match the hardware underneath - but again, this was > for hard drives with physical arms and not SSDs OK, this makes a lot more sense then :) Definitely slowing things down/making the opportunity to re-order requests should help a lot for spinning disks... I don't see that helping much at all with SSD's though. Thanks, Adam -- Adam Goryachev Website Managers www.websitemanagers.com.au -- 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
