Re: IDS 10 on RHEL4 Linux: I/O benchmark of RAW DEVICES vs BLOCK DEVICES vs COOKED FILES

Ben, thanx for the feedback. You are right. I did reset statistics and run the test again: all is cached in the buffers (see below). I need to either change the testing tool or reduce buffers. This means that the previously provided figures about test #2 are not very significant. I'll see if I manage to produce something more useful. Regards R. Ben Thompson wrote: > Test 2 works on a single table with one row initially. This is a small > amount of data and all the operations could easily take place inside > Informix's buffers with only occasional LRU writes or maybe a checkpoint > making any difference. 1000 operations may not be enough to cause a > checkpoint. You would need to tune your server to have a very small > bufferpool to force all the changes to be written to disc more quickly > to see any significant differences between filesystems in this test. For > this reason I would be interested to see your ONCONFIG and your cached > read and write rate from "onstat -p" after each test. I would also > bounce the server before every test (if you didn't do this before) to > clear out the bufferpool and reset the statistics ("onstat -z"). > > Ben. [orc@zeus:~/custom] onstat -p IBM Informix Dynamic Server Version 10.00.FC4 -- On-Line -- Up 23:36:44 --310052 Kbytes Profile dskreads pagreads bufreads %cached dskwrits pagwrits bufwrits %cached 0 0 6335194 100.00 166 2812 3046883 99.99 isamtot open start read write rewrite delete commit rollbk 9232557 22415 36912 3054060 14295 3005457 6375 927 0 gp_read gp_write gp_rewrt gp_del gp_alloc gp_free gp_curs 0 0 0 0 0 0 0 ovlock ovuserthread ovbuff usercpu syscpu numckpts flushes 0 0 0 26.09 0.68 0 0 bufwaits lokwaits lockreqs deadlks dltouts ckpwaits compress seqscans 2 0 15094199 0 0 0 1032 12354 ixda-RA idx-RA da-RA RA-pgsused lchwaits 0 0 0 0 96