Re: spin locks

Added to FAQ. Regards, David. > On 23 September 2013 at 22:52 John Miller iii <miller3@us.ibm.com> wrote: > > > The two mutex which are directly effected are sh_stamp and po_lock, but > the VP_MEMORY_CACHE_KB speeds up malloc()/free() functionality > which can have an indirect impact on many things. > > Setting this to a value of 1024 (i.e. 1MB) can have a great impact. If > you are not worried about > a few MB then setting this to 4096 would be my starting point. > > Two additional notes, > 1) The functionality of this has been improved so please look at the > setting > in new releases. > > 2) This feature is only available with the enterprises edition > > John F. Miller III > STSM, Lead Architect > miller3@us.ibm.com > > ids-bounces@iiug.org wrote on 09/23/2013 12:44:56 PM: > > > From: "david@smooth1.co.uk" <david@smooth1.co.uk> > > To: ids@iiug.org, > > Date: 09/23/2013 12:45 PM > > Subject: Re: spin locks [31483] > > Sent by: ids-bounces@iiug.org > > > > Can you go over what some of the other ones are and which ones are > > affected by > > VP_MEMORY_CACHE_KB? > > > > Also what values for VP_MEMORY_CACHE_KB do people use? > > > > David. > > > > On 23 September 2013 at 18:47 John Miller iii <miller3@us.ibm.com> wrote: > > > > The output of onstat -g spi is so low, it is really not even worth > > > worrying about. The po_pool lock > > > is the hottest mutex which has 118 latch waits in over 9 hours. This > means > > > you are averaging 1 wait > > > every 4.5 minutes and only spins 521 times before it acquires the > mutex. I > > > generally do not even look > > > at mutex with less than 1000 spins per acquisition. > > > > > > This is the lock on the global memory pool which often deals with > config, > > > gls, > > > network, and general overhead items which are not owned by a user. > > > > > > Hope it helps, > > > > > > John F. Miller III > > > STSM, Lead Architect > > > miller3@us.ibm.com > > > 503-747-1366 > > > IBM Informix Dynamic Server (IDS) > > > > > > ids-bounces@iiug.org wrote on 09/23/2013 09:04:07 AM: > > > > > > > From: "Art Kagel" <art.kagel@gmail.com> > > > > To: ids@iiug.org, > > > > Date: 09/23/2013 10:08 AM > > > > Subject: Re: spin locks [31481] > > > > Sent by: ids-bounces@iiug.org > > > > > > > > That's true. I missed the "IE" in the version string. > > > > > > > > Art > > > > > > > > Art S. Kagel, Principal Consultant > > > > > > > > Advanced DataTools (www.advancedatatools.com) > > > > Blog: http://informix-myview.blogspot.com/ > > > > > > > > Disclaimer: Please keep in mind that my own opinions are my own > opinions > > > > and do not reflect on my employer, Advanced DataTools, the IIUG, nor > any > > > > other organization with which I am associated either explicitly, > > > > implicitly, or by inference. Neither do those opinions reflect those > of > > > > other individuals affiliated with any entity with which I am > affiliated > > > nor > > > > those of the entities themselves. > > > > > > > > On Mon, Sep 23, 2013 at 3:02 AM, Hrvoje Zokovic > > > > <hzokovic.iiug@gmail.com>wrote: > > > > > > > > > According to 12.10.TC1IE i think this is innovator-C edition and > you > > > can > > > > > not use CPU VP memory > > > > > cache on this edition (it is Enterprise/Ultimate only feature) > > > > > HTH > > > > > Hrvoje > > > > > > > > > > On 22.9.2013. 3:20, Art Kagel wrote: > > > > > > IB that is the memory pool latch. You can probably reduce the > > > activity on > > > > > > it by enabling VP_MEMORY_CACHE_KB so that each CPU VP holds on to > > > > some of > > > > > > the memory from the central pool and so has to interact withthe > pool > > > > > > > > latch > > > > > > less frequently. > > > > > > > > > > > > Art > > > > > > > > > > > > Art S. Kagel, Principal Consultant > > > > > > > > > > > > Advanced DataTools (www.advancedatatools.com) > > > > > > Blog: http://informix-myview.blogspot.com/ > > > > > > > > > > > > Disclaimer: Please keep in mind that my own opinions are my own > > > opinions > > > > > > and do not reflect on my employer, Advanced DataTools, the IIUG, > nor > > > any > > > > > > other organization with which I am associated either explicitly, > > > > > > implicitly, or by inference. Neither do those opinions reflect > those > > > of > > > > > > other individuals affiliated with any entity with which I am > > > affiliated > > > > > nor > > > > > > those of the entities themselves. > > > > > > > > > > > > On Fri, Sep 20, 2013 at 4:56 PM, BillHatVerizon > > > > > <garage_dba@verizon.net>wrote: > > > > > > > > > > > >> This is the output of onstat g spi . > > > > > >> What is po_lock below? > > > > > >> Do the numbers look high or is it not possible to answer without > > > > more > > > > > info > > > > > >> ? > > > > > >> This is on Windows server 2008 R2 SP1. > > > > > >> > > > > > >> IBM Informix Dynamic Server Version 12.10.TC1IE -- On-Line -- Up > > > > > > 09:04:41 > > > > > >> --> > > > > >> 733952 Kbytes > > > > > >> > > > > > >> Spin locks with waits: > > > > > >> Num Waits Num Loops Avg Loop/Wait Name > > > > > >> 1 88 88.00 mutex lock, name = AIOreq > > > > > >> 2 31 15.50 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 121 121.00 mutex lock, name = AIOreq > > > > > >> 1 102 102.00 mutex lock, name = AIOreq > > > > > >> 1 38 38.00 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 110 110.00 mutex lock, name = AIOreq > > > > > >> 1 155 155.00 mutex lock, name = AIOreq > > > > > >> 1 203 203.00 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 28 28.00 mutex lock, name = AIOreq > > > > > >> 2 102 51.00 mutex lock, name = AIOreq > > > > > >> 1 14 14.00 mutex lock, name = AIOreq > > > > > >> 1 80 80.00 mutex lock, name = AIOreq > > > > > >> 2 63 31.50 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 68 68.00 mutex lock, name = AIOreq > > > > > >> 1 116 116.00 mutex lock, name = AIOreq > > > > > >> 1 19 19.00 mutex lock, name = AIOreq > > > > > >> 1 160 160.00 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 1 170 170.00 mutex lock, name = AIOreq > > > > > >> 1 48 48.00 mutex lock, name = AIOreq > > > > > >> 1 24 24.00 mutex lock, name = AIOreq > > > > > >> 1 68 68.00 mutex lock, name = AIOreq > > > > > >> 2 134 67.00 mutex lock, name = AIOreq > > > > > >> 2 183 91.50 mutex lock, name = AIOreq > > > > > >> 1 49 49.00 mutex lock, name = AIOreq > > > > > >> 3 284 94.67 mutex lock, name = AIOreq > > > > > >> 1 6 6.00 mutex lock, name = AIOreq > > > > > >> 1 58 58.00 mutex lock, name = AIOreq > > > > > >> 1 1 1.00 mutex lock, name = AIOreq > > > > > >> 2 135 67.50 mutex lock, name = AIOreq > > > > > >> 2 49 24.50 mutex lock, nam