IDS 10.0 performance on RedHat

Having now got IDS 10.0FC5 to work on RHEL I thought I'd share a few findings. These are based on multipe runs of a dbimport, and of populating a single large-ish table then building a couple of indexes thereon, utilising PDQ, thereafter. The server is an IBM x3850 with 4 dual-core cpus (these boxes are *seriously* fast, kids), writing to an EMC Clariion CX300 RAID 1+0. (All supplied by Ardenta, the UK's premier system integrator ;-) ) The baseline time for the dbimport with kaio disabled was 90 mins. With kaio enabled and 3 cpu vps about 100 mins. With 8 or12 cpu vps down to about 65 mins, with neither consistently faster than the other. 16 cpu vps no better than 12. Similarly scalable results with the load and index build, with the index builds increasing appreciably in speed up to the limit of 12. Interestingly to me, - although unsurprisngly as my colleague Andy Watson, inter alia, has previously posted this observation - the kaio speeds are not affected at all by the use of character over block devices. Not a thorough benchmark by any means, but I offer it up in case anyone is interested. regards -- Neil Truby t:01932 724027 Director m:07798 811708 Ardenta Limited e:neil.truby@ardenta.com

Neil Truby wrote: > Having now got IDS 10.0FC5 to work on RHEL I thought I'd share a few > findings. > > > Not a thorough benchmark by any means, but I offer it up in case anyone is > interested. > Thanks Neil. We are skipping UC5 and looking at UC6 next. Do you find UC5 faster than UC4 with all the Performance Improvement stuff mentioned in the Chat with the Labs session? Have you tried the FASTPOLL feature? Does it work on RHEL? David. > regards > -- > Neil Truby t:01932 724027 > Director m:07798 811708 > Ardenta Limited e:neil.truby@ardenta.com

<david@smooth1.co.uk> wrote in message news:1153345490.761273.226670@i42g2000cwa.googlegroups.com... > > Neil Truby wrote: >> Having now got IDS 10.0FC5 to work on RHEL I thought I'd share a few >> findings. >> >> >> Not a thorough benchmark by any means, but I offer it up in case anyone >> is >> interested. >> > > Thanks Neil. We are skipping UC5 and looking at UC6 next. > > Do you find UC5 faster than UC4 with all the Performance Improvement > stuff mentioned in the Chat with the Labs session? Due to a bug - RedHat, according to IBM, not IDS - you cannot use kaio on UCx on a 64-bit server. Possibly your point is: was it quicker than FC4? This is a new installation (yes, there are new customers buying Informix!!), so I didn't do a comparison. With kaio disabled I found the performance identical between the two releases. I missed the session anyway - is the presentation available.

> These are based on multipe runs of a dbimport, and of populating a single > large-ish table then building a couple of indexes thereon, utilising PDQ, > thereafter. how many table fragments? why use dbimport and not HPL or similar to load the table? With dbimport you are likely to only use 1 of your many CPUs How would the results look then?