RE: TUNING:aio parameters on AIX
This message is in MIME format. Since your mail reader does not understand this format, some or all of this message may not be legible. ------_=_NextPart_001_01BDE27C.E95DF374 Content-Type: text/plain; charset="iso-8859-1" I always read but never post to this forum, however this affects me as well and there is some confusion. The article Mr. Stock quotes is simply verbatim from the AIX documentation, not Informix. I have followed the IBM recommendation and have noticed no performance improvement on my RS/6000 at 4.2.1. I feel that given the fact our DB is small (< 2Gig) and spread across multiple SSA disks, I should have better performance. I would also like to know if perhaps anyone has found that Informix AIO is faster than AIX kaio, as has been claimed by some with regards to kaio on the HP platform. I think part of it is wanting something to tweak with kaio like you can with VP's just to satisfy our curiosity. Thanks Mr. Kagel, even though your response was a little off on this one I still learned something from it as I a always do. Given the expertise in this forum I would think that someone might shed light on Informix interaction with AIX kaio and wether there is something tunable we can try in order to "Make it go faster". Can someone try again to answer Mr. Thacker's question? > ---------- > From: Mark D. Stock[SMTP:mdstock@informix.com] > Reply To: mdstock@informix.com > Sent: Thursday, September 17, 1998 6:45 AM > To: kagel@bloomberg.net > Cc: informix-list@iiug.org; Dave Thacker > Subject: Re: TUNING:aio parameters on AIX > > Art S. Kagel wrote: > > > > Dave Thacker wrote: > > > > > > Platform: IBM Rs/6000 J30 AIX V4.1.5 > > > Engine Online DSA 7.23 > > > > > > From much reading of vmstat, iostat, and xmperf we appear to be I/0 > bound > > > on our production machine. > > > While investigating the problem I came across a configuration for aio > > > servers. We are currently set to the default and IBM docs recommend > that > > > we increase them to MAX= (10* count of disks using aio) and > > > MIN = (MAX * .5). I believe that OL 7.23 does use the aio libraries. > Has > > > someone else in an AIX shop changed this configuration? Did it help? > > > > WHOA HORSEY! Informix's recommendations for 7.10 was 2-3 AIO VPs per > > WHOA YOURSELF! I think the question was about the recommended kernel > parameter settings. I saw a related question elsewhere recently, and > this is what someone @ Informix had to say: > > ------------------------------------------------------------------------ > Asynchronous Disk I/O > > Applications can use the aio_read and aio_write subroutines to perform > asynchronous disk I/O. Control returns to the application from the > subroutine as soon as the request has been queued. The application can > then continue processing while the disk operation is being performed. > > Although the application can continue processing, a kernel process > (kproc) called a server is in charge of each request from the time it is > taken off the queue until it completes. The number of servers limits the > number of asynchronous disk I/O operations that can be in progress in > the system simultaneously. The number of servers can be set with smit > (smit->Devices->Asynchronous I/O->Change/Show Characteristics of > Asynchronous I/O->{MINIMUM|MAXIMUM} number of servers or smit aio) or > with chdev. The minimum number of servers is the number to be started at > system boot. The maximum limits the number that can be started in > response to large numbers of simultaneous requests. > > The default values are minservers=1 and maxservers=10. In systems that > seldom run applications that use asynchronous I/O, this is usually > adequate. For environments with many disk drives and key applications > that use asynchronous I/O, the default is far too low. The result of a > deficiency of servers is that disk I/O seems much slower than it should > be. Not only do requests spend inordinate lengths of time in the queue, > the low ratio of servers to disk drives means that the seek-optimization > algorithms have too few requests to work with for each drive. > > For environments in which the performance of asynchronous disk I/O is > critical and the volume of requests is high, we recommend that: > > maxservers should be set to at least 10*(number of disks accessed > asynchronously) minservers should be set to maxservers/2. > > This could be achieved for a system with 3 asynchronously accessed disks > with: > > # chdev -l aio0 -a minservers='15' -a maxservers='30' > ------------------------------------------------------------------------ > > Hope that helps, > -- > Mark. > > +----------------------------------------------------------+-----------+ > |Mark D. Stock - Informix SA http://www.informix.com |//////// /| > |mailto:mdstock@informix.com http://www.informix.com/idn |///// / //| > |http://www.iiug.org +-----------------------------------+//// / ///| > | Tel: +27 11 807 0313 |If it's slow, the users complain. |/// / ////| > | Fax: +27 11 807 2594 |If it's fast, the users keep quiet.|// / /////| > |Cell: +27 83 250 2325 |Therefore, "No news: travels fast"!|/ ////////| > +----------------------+-----------------------------------+-----------+ > ------_=_NextPart_001_01BDE27C.E95DF374 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN"> <HTML> <HEAD> <META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; = charset=3Dus-ascii"> <META NAME=3D"Generator" CONTENT=3D"MS Exchange Server version = 5.5.2232.0"> <TITLE>RE: TUNING:aio parameters on AIX</TITLE> </HEAD> <BODY> <P> <FONT COLOR=3D"#0000FF" = SIZE=3D2 FACE=3D"Arial">I always read but never post to this forum, = however this affects me as well and there is some confusion. The = article Mr. Stock quotes is simply verbatim from the AIX documentation, = not Informix. I have followed the IBM recommendation and have noticed = no performance improvement on my RS/6000 at 4.2.1. I feel that given = the fact our DB is small (< 2Gig) and spread across multiple SSA = disks, I should have better performance. </FONT></P> <P> <FONT COLOR=3D"#0000FF" = SIZE=3D2 FACE=3D"Arial">I would also like to know if perhaps anyone has = found that Informix AIO is faster than AIX kaio, as has been claimed by = some with regards to kaio on the HP platform. I think part of it is = wanting something to tweak with kaio like you can with VP's just to = satisfy our curiosity. Thanks Mr. Kagel, even though your response was = a little off on this one I still learned something from it as I a = always do. Given the expertise in this forum I would think that someone = might shed light on Informix interaction with AIX kaio and wether there = is something tunable we can try in order to "Make it go = faster". Can someone try again to answer Mr. Thacker's = question?</FONT></P> <UL>