Oninit cdi / Archive
Talk to an expert →

RE: Cook device vs Raw device

Posted in 1999

Topics: Performance & Tuning, SQL Development & Query Writing, Platform-Specific Issues

William Rice — — source: Informix-list mailing list archive (1991-1998)

This is a thread that has always interested me. I have been reading this group for awhile, and was concerned when I came to my current place of employment and discovered they were using filesystems to hold data. When we got the oppurtunity to do some limited testing on raw vs cooked we could only find at most a 1.5% difference between informix's performance to raw disk vs. cooked. We watched the following things: iostat, vmstat wall time We were running AIX 4.3.2 on a 520 Informix 7.31UC2 Only 2 disk drives, one of which was dedicated to informix data. Under 2 Gigabytes of data in the whole database These processes were simple queries(no more than three tables joined) and the loading of data into tables. The longest running process was somewhere around 15 minutes. The processes tested caused the system to be heavily io bound for some and CPU for others. From reading the newsgroup I got the impression that I could count on at least a 10% difference between cooked and raw, yet the tests I ran did not turn out that way. The data involved was literally identical. I was curious what factors might be causing the performance not to increase. Will ------------------------------------------------------------ This e-mail has been sent to you courtesy of OperaMail, a free web-based service from Opera Software, makers of the award-winning Web Browser - http://www.operasoftware.com ------------------------------------------------------------

↪ replying to William Rice
Steven Wilcoxon — — source: Informix-list mailing list archive (1991-1998)

One thing to remember is that the 10%-20% spead improvement is on the actual disk I/O. IDS systems with good cache hit rates will not notice much of an improvement based on clock time since it uses RAM mostly. S.W. William Rice <ricew@operamail.com> wrote in message news:7rouom$463$1@news.xmission.com... > > This is a thread that has always interested me. I have been reading this > group for awhile, and was concerned when I came to my current place of > employment > and discovered they were using filesystems to hold data. When we > got the oppurtunity to do some limited testing on raw vs cooked we > could only find at most a 1.5% difference between informix's performance > to raw disk vs. cooked. > We watched the following things: > iostat, > vmstat > wall time > > We were running AIX 4.3.2 on a 520 > Informix 7.31UC2 > > Only 2 disk drives, one of which was dedicated to informix data. > Under 2 Gigabytes of data in the whole database > > These processes were simple queries(no more than three tables joined) > and the loading of data into tables. > > The longest running process was somewhere around 15 minutes. > The processes tested caused the system to be heavily io bound for some > and CPU for others. > > From reading the newsgroup I got the impression that I could count on at least > a 10% difference between cooked and raw, yet the tests I ran did not turn out > that way. > > The data involved was literally identical. I was curious what factors might > be causing the performance not to increase. > > Will > > ------------------------------------------------------------ > This e-mail has been sent to you courtesy of OperaMail, a > free web-based service from Opera Software, makers of > the award-winning Web Browser - http://www.operasoftware.com > ------------------------------------------------------------

↪ replying to William Rice
Helmut Leininger — — source: Informix-list mailing list archive (1991-1998)

William Rice wrote: > This is a thread that has always interested me. I have been reading this > group for awhile, and was concerned when I came to my current place of > employment > and discovered they were using filesystems to hold data. When we > got the oppurtunity to do some limited testing on raw vs cooked we > could only find at most a 1.5% difference between informix's performance > to raw disk vs. cooked. > We watched the following things: > iostat, > vmstat > wall time > > We were running AIX 4.3.2 on a 520 > Informix 7.31UC2 > > Only 2 disk drives, one of which was dedicated to informix data. > Under 2 Gigabytes of data in the whole database > > These processes were simple queries(no more than three tables joined) > and the loading of data into tables. > > The longest running process was somewhere around 15 minutes. > The processes tested caused the system to be heavily io bound for some > and CPU for others. > > From reading the newsgroup I got the impression that I could count on at least > a 10% difference between cooked and raw, yet the tests I ran did not turn out > that way. > > The data involved was literally identical. I was curious what factors might > be causing the performance not to increase. > > Will > > ------------------------------------------------------------ > This e-mail has been sent to you courtesy of OperaMail, a > free web-based service from Opera Software, makers of > the award-winning Web Browser - http://www.operasoftware.com > ------------------------------------------------------------ Hi Will, Although I am a fan of using rwa devices for several reasons (among them speed, no accessability by "normal" Unix tools like cpio, rm, ...) I think your impression maybe right. AIX has a rather good caching mechanism for file systems (some people characterise it as "use all free memory for file system cache" or "the file system is just an extension of the memory") that will "hide" quite a lot of the performance difference between file systems and raw devices. Regards -- Helmut Leininger Bull AG / Vienna Open Systems Support Email: h.leininger@bull.at helmut.leininger@bull.net This opinion is mine and not necessarily that of my employer. No guarantees whatsoever.