Re: KAIO vps, and bufwaits

In article <6bmtcu$jmi@drn.zippo.com>, Neil Truby <?@?.?> writes >In article <Z0$3mTASWg30EwR4@smooth1.demon.co.uk>, David says... >> >> That could be from when Online is booting and loading its cache >> with data. Try doing an onstat -z 1 hour after the server has >> booted then look at the stats at the end of the day, >> >Yes, I'd already done this at frequent intervals. The maxlength still zips back >up to 16 fairly quickly, therefore I would stand by my assessement that the >system is I/O bound. Can't decide what to do about it 'though! > >Neil What does onstat -d onstat -D onstat -g iof give and how do chunks pathnames map to physical disks and controllers? Sounds like I/O is not balanced across disks. Also check try select partnum, pf_rqlock, pf_wtlock, pf_deadlk, pf_lktouts, pf_dskreads, pf_isread, pf_dskwrites, pf_iswrite, pf_isrwrite, pf_isdelete, pf_bfcread, pf_bfcwrite, pf_seqscans, from systmaster:sysptntab compare this against select tabname,hex(partnum) from systables order by 2 run against each database and see which tables are getting most i/o. Check onstat -u for any users doing a lot of i/o as well. I normally say >1000 reads or writes needs more investigation. -- David Williams Maintainer of the Informix FAQ Primary site (Beta Version) http://www.smooth1.demon.co.uk Official site http://www.iiug.org/techinfo/faq/faq_top.html I see you standin', Standin' on your own, It's such a lonely place for you, For you to be If you need a shoulder, Or if you need a friend, I'll be here standing, Until the bitter end... So don't chastise me Or think I, I mean you harm... All I ever wanted Was for you To know that I care