SLI Sync Limit effects on performance
Hello,
Can someone provide an accurate answer to what exactly is SLI sync limit as what can be seen in MSI Afterburner ?
I run a 3-way SLI setup, and most of the time, cards are under even load, but very rarely properly used. It's not unusual to see the load on each card to be within 30-40% range, with all three cards reporting SLI sync limit at 1.
What it means in many cases is that even if I removed one card out of the setup, FPS essentially does not change, but two cards are loaded at 50+ percent each. Again with sync limit at 1.
Disabling SLI altogether brings a marginal FPS drop, but a single card would be loaded at close to 100%. Which basically means that tripling the GPU horsepower brings very little performance gain over just one card...
So again, what exactly is SLI sync limit, and is there anything that can be done to mitigate issues related to it ?
PC Specs :
Asus Rampage V Extreme
3 x MSI 970 GTX OC 4GB
16GB DDR4
I should have provided more info. Sorry.
The scenario I was talking about is Witcher 3, but it occurs in many other games too (Skyrim etc). Resolution in question is 5760x1080, nv surround. With everything maxed out, three cards can produce 16-17 fps, with two cards I can see higher loads but still 16-17 fps, with single card it drops to 15 fps but loaded close to 100%.
Skyrim followed similar pattern, though with higher loads (50-55% per card in 3-way SLI, 40+ fps). However, once I added ENB to the mix, fps would drop to 20-ish. Card loads remained the same.
You are right about some engines being unable to use more GPU power anyway (UT3 also runs at approx 40% per card, but that is at ~240 FPS !!!). Since I have standard monitors, anything above 60 fps is irrelevant to me.
I know that GPU power does not scale in linear way, but theoretically, if cards were loaded to 100% in Witcher 3, I would be observing something in ~50 fps range, correct ? Which would be absolutely fine. So not sure if that is an issue with game code, or nvidia profiles, or ...
As for the settings : I never use VSync (input lag), always use highest details that still allow for smooth gameplay, and try to play with surround on (peripheral vision makes huge difference to me). At present though, playable frame rates are only possible with FHD (55 fps typically).
Similar Messages
-
Is there a way to speed up a Mac (similar to de-fragging on a PC)? Mine has gotten slower and slower over time.
When memory/disc comes close to full would that have an effect on performance? How should I determine what programs/software to remove and free space?Things You Can Do To Resolve Slow Downs
If your computer seems to be running slower here are some things you can do:
Start with visits to: OS X Maintenance - MacAttorney;
The X Lab: The X-FAQs;
The Safe Mac » Mac Performance Guide;
The Safe Mac » The myth of the dirty Mac;
Mac maintenance Quick Assist.
Boot into Safe Mode then repair your hard drive and permissions:
Repair the Hard Drive and Permissions Pre-Lion
Boot from your OS X Installer disc. After the installer loads select your language and click on the Continue button. When the menu bar appears select Disk Utility from the Utilities menu. After DU loads select your hard drive entry (mfgr.'s ID and drive size) from the the left side list. In the DU status area you will see an entry for the S.M.A.R.T. status of the hard drive. If it does not say "Verified" then the hard drive is failing or failed. (SMART status is not reported on external Firewire or USB drives.) If the drive is "Verified" then select your OS X volume from the list on the left (sub-entry below the drive entry,) click on the First Aid tab, then click on the Repair Disk button. If DU reports any errors that have been fixed, then re-run Repair Disk until no errors are reported. If no errors are reported click on the Repair Permissions button. Wait until the operation completes, then quit DU and return to the installer.
Repair the Hard Drive - Lion/Mountain Lion/Mavericks
Boot to the Recovery HD:
Restart the computer and after the chime press and hold down the COMMAND and R keys until the Utilites Menu screen appears. Alternatively, restart the computer and after the chime press and hold down the OPTION key until the boot manager screen appears. Select the Recovery HD disk icon and click on the arrow button below.
When the recovery menu appears select Disk Utility. After DU loads select your hard drive entry (mfgr.'s ID and drive size) from the the left side list. In the DU status area you will see an entry for the S.M.A.R.T. status of the hard drive. If it does not say "Verified" then the hard drive is failing or failed. (SMART status is not reported on external Firewire or USB drives.) If the drive is "Verified" then select your OS X volume from the list on the left (sub-entry below the drive entry,) click on the First Aid tab, then click on the Repair Disk button. If DU reports any errors that have been fixed, then re-run Repair Disk until no errors are reported. If no errors are reported, then click on the Repair Permissions button. Wait until the operation completes, then quit DU and return to the main menu. Select Restart from the Apple menu.
Restart your computer normally and see if this has helped any. Next do some maintenance:
For situations Disk Utility cannot handle the best third-party utility is Disk Warrior; DW only fixes problems with the disk directory, but most disk problems are caused by directory corruption; Disk Warrior 4.x is now Intel Mac compatible.
Note: Alsoft ships DW on a bootable DVD that will startup Macs running Snow Leopard or earlier. It cannot start Macs that came with Lion or later pre-installed, however, DW will work on those models.
Suggestions for OS X Maintenance
OS X performs certain maintenance functions that are scheduled to occur on a daily, weekly, or monthly period. The maintenance scripts run in the early AM only if the computer is turned on 24/7 (no sleep.) If this isn't the case, then an excellent solution is to download and install a shareware utility such as Macaroni, JAW PseudoAnacron, or Anacron that will automate the maintenance activity regardless of whether the computer is turned off or asleep. Dependence upon third-party utilities to run the periodic maintenance scripts was significantly reduced since Tiger. These utilities have limited or no functionality with Snow Leopard or later and should not be installed.
OS X automatically defragments files less than 20 MBs in size, so unless you have a disk full of very large files there's little need for defragmenting the hard drive.
Helpful Links Regarding Malware Protection
An excellent link to read is Tom Reed's Mac Malware Guide.
Also, visit The XLab FAQs and read Detecting and avoiding malware and spyware.
See these Apple articles:
Mac OS X Snow Leopard and malware detection
OS X Lion- Protect your Mac from malware
OS X Mountain Lion- Protect your Mac from malware
About file quarantine in OS X
If you require anti-virus protection I recommend using VirusBarrier Express 1.1.6 or Dr.Web Light both from the App Store. They're both free, and since they're from the App Store, they won't destabilize the system. (Thank you to Thomas Reed for these recommendations.)
Troubleshooting Applications
I recommend downloading a utility such as TinkerTool System, OnyX, Mavericks Cache Cleaner, or Cocktail that you can use for removing old log files and archives, clearing caches, etc. Corrupted cache, log, or temporary files can cause application or OS X crashes as well as kernel panics.
If you have Snow Leopard or Leopard, then for similar repairs install the freeware utility Applejack. If you cannot start up in OS X, you may be able to start in single-user mode from which you can run Applejack to do a whole set of repair and maintenance routines from the command line. Note that AppleJack 1.5 is required for Leopard. AppleJack 1.6 is compatible with Snow Leopard. Applejack does not work with Lion and later.
Basic Backup
For some people Time Machine will be more than adequate. Time Machine is part of OS X. There are two components:
1. A Time Machine preferences panel as part of System Preferences;
2. A Time Machine application located in the Applications folder. It is
used to manage backups and to restore backups. Time Machine
requires a backup drive that is at least twice the capacity of the
drive being backed up.
Alternatively, get an external drive at least equal in size to the internal hard drive and make (and maintain) a bootable clone/backup. You can make a bootable clone using the Restore option of Disk Utility. You can also make and maintain clones with good backup software. My personal recommendations are (order is not significant):
1. Carbon Copy Cloner
2. Get Backup
3. Deja Vu
4. SuperDuper!
5. Synk Pro
6. Tri-Backup
Visit The XLab FAQs and read the FAQ on backup and restore. Also read How to Back Up and Restore Your Files. For help with using Time Machine visit Pondini's Time Machine FAQ for help with all things Time Machine.
Referenced software can be found at MacUpdate.
Additional Hints
Be sure you have an adequate amount of RAM installed for the number of applications you run concurrently. Be sure you leave a minimum of 10% of the hard drive's capacity as free space.
Add more RAM. If your computer has less than 2 GBs of RAM and you are using OS X Leopard or later, then you can do with more RAM. Snow Leopard and Lion work much better with 4 GBs of RAM than their system minimums. The more concurrent applications you tend to use the more RAM you should have.
Always maintain at least 15 GBs or 10% of your hard drive's capacity as free space, whichever is greater. OS X is frequently accessing your hard drive, so providing adequate free space will keep things from slowing down.
Check for applications that may be hogging the CPU:
Pre-Mavericks
Open Activity Monitor in the Utilities folder. Select All Processes from the Processes dropdown menu. Click twice on the CPU% column header to display in descending order. If you find a process using a large amount of CPU time (>=70,) then select the process and click on the Quit icon in the toolbar. Click on the Force Quit button to kill the process. See if that helps. Be sure to note the name of the runaway process so you can track down the cause of the problem.
Mavericks and later
Open Activity Monitor in the Utilities folder. Select All Processes from the View menu. Click on the CPU tab in the toolbar. Click twice on the CPU% column header to display in descending order. If you find a process using a large amount of CPU time (>=70,) then select the process and click on the Quit icon in the toolbar. Click on the Force Quit button to kill the process. See if that helps. Be sure to note the name of the runaway process so you can track down the cause of the problem.
Often this problem occurs because of a corrupted cache or preferences file or an attempt to write to a corrupted log file. -
When I plug a LaCie external hard drive to work with Time Machine into my new Mac mini, [OS 10.9.1] it drastically effects the performance of the internet and email, turn off Time Machine, unplug the hard drive, internet and email go back to normal. Why?
Maybe:
http://www.macobserver.com/tmo/article/usb-3.0-hard-drives-can-cause-wi-fi-inter ference -
Is there a photo sync limit? It repeatedly says that there is not enough room, but I know for a fact that there is? I tried to sync multiple times with the same results. Last time I tried, I synced nothing but the pics. The same result happened. I have the 32GB 2nd gen. ipod touch. Any help would be appreciated. Thanks.
Did you find a solution to this? I have a folder of about 3.6Gb containing 2754 photos and have never had issues in the past synching. When I tried to synch last night, I got a message that "27 items could not be synched. See iTunes for more information." I looked all over itunes but could not find any error message. There was one specific picture I was looking for to upload which has not shown up and no matter how many syncs I tried it never did. To try to resolve this, I picked a new folder with only 6 pictures in it and re-synced. As expected, it eliminated my library of 2700+ pictures in favour of the 6 I have now told it to sync. I cleared the 'ipod photo cache folder' and then re-set itunes to sync this folder. It synced the folder again, however this time synced 1600 pictures and now I have a message '1154 items could not be synced. See iTunes for more information.' Again, iTunes has no more information.
I have an iPhone 3GS but this is the first time I've had sync problems. -
After Effects CS4 Performance (BRUTAL)
Despite the comments on this board (from Adobe themselves) claiming improved After Effects CS4 performance over its predecessor, my experience is the exact opposite. This version seems half baked to me.
AE CS4 isn't just SLOW, and by slow I really mean dreadfully unusable, It's unstable as well. Even running the same template files that came with CS3 and 4, there's a huge difference in render time, ram previews etc. When you can't even rotate a simple cube without crashing, there's some real problems, and this is just the beginning. The previous version had no show stopping issues, it performed like a trooper. This latest however, I can't see how I could use it day to day for anything..
There is no other software on this machine other than, CS4, Firefox, and Lightwave 9.5, which by the way, handles textured objects with hundreds of thousands of polys, not 6. I first get an error message that reads as followed;
After effect error: crash occurred while invoking effect plug-in "Live Photoshop 3D"
followed by, After Effects can't continue: sorry, After Effects has crashed. See... blah blah blah..
By the way this occurs with or without OpenGl enabled.
Systems specs
8GB Ram
Q6600
Hard Drive space 4TB, install drive, 156 GB free
Vista Business 64
Nvidia GeForce 8600 GTS (driver 178.13)
This is the same machine that ran CS3 very well, so there shouldn't be anything wrong with this rig..Fausto,
I have no problem importing or animating your PSD - no crashes, at least. The resolution is very high. I got better results by cutting the resolution of your PSD in half, which may or may not be an option for you. I improved responsiveness a little by setting the PS 3D layer to "Use Photoshop Transform" in AE.
But ultimately, the responsiveness of the 3D layer in AE is impossible to work with, except with Live Update disabled. It seems like a RAM issue to me. What size are the texture layers on each side of the cube? If they're all 3000x2000-ish like your document, and you're working at full res, consider that AE has to hold all six images in RAM, plus manipulate them in 3D.
My own sense is that the whole 3D layer thing simply isn't ready for that kind of resolution in AE yet. And probably wont be until true 64bit code allows the storage of all those textures in RAM more easily.
As a side note, don't know if it's my location or your server, but your 74Mb image took me almost 2 hours to download. -
Does the ETL workload effect the performance of reports?
Hello
There are several heavy ETL processes running on production. Do they effect the performance of the reports that user may execute during this time?
thanksDefinitely... Your server has a finite number of resources available to share with all those processes... Running a report is just one more process... Users can be (and are) impacted by other processes in the system...
-
About how many CDs can I put on my hard drive before it effects the performance of me iMac/
About how many CDs can I put on my hard drive before they effect the performance of my imac?
Well, it depends on how much content is on the CD. You should have, at a minimum 10 - 15 GB of empty hard drive space at all times - more is much better. I do a fair amount of video/graphics editing and in order to render and burn properly, I need at least as much empty hard drive space as I have files in my current project, which usually means at least 150 GB or more. So, to be safe, my goal is to have a minimum of 250 GB empty space at all times - the OS will thank you if it has more room to work with.
So, add up what you want to put there and keep watching your hard drive space diiminish - it's best to have space hogging files on an external hard drive to keep your internal working well. -
Does Row Wise Initialised block effects the performance of OBIEE 10.1.3.2.0
Hi,
I am trying to implement the security in my application using row wise initialisation block. Could any one help me with below mentioned doubts:
1) Does it effect the performance of the OBIEE server.
2) Cons with row wise initialisation block used for implementing security which uses Oracle customise function in it. this initialisation block is been created for implementing 2 level security.
Thanks
SavitaSavita,
Answers to your questions are as follows:
*1) Does it effect the performance of the OBIEE server.*
No. This is part of the Oracle BI Repository modeling process for Oracle BI 10g.
*2) Cons with row wise initialisation block used for implementing security which uses Oracle customise function in it. this initialisation block is been created for implementing 2 level security.*
There really aren't any cons. To get the security you are seeking row-wise security in Oracle BI 10g is the route you must take. In addition, this process is used widely in Oracle BI 10g for numbers of consecutive users and total users/groups in an LDAP or security group table ranging from hundreds to tens of thousands with nothing but success. So, don't worry about implementing this as your implementation will be sound by configuring row-wise security. -
Does Coloring Of Rows and Column in Query effect the Performance of Query
Hi to all,
Does Coloring of Rows and Column in Query via WAD or Report designer , will effect the performance of query.
If yes, then how.
What are the key factor should we consider while design of query in regards of Query performance.
I shall ne thankful to you for this.
Regards
Pavneet RanaThere will not be any significance perofrmance issue for Colouring the rows or columns...
But there are various performance parameters which should be looked into while designing a query...
Hope this PPT helps you.
http://www.comeritinc.com/UserFiles/file/tips%20tricks%20to%20speed%20%20NW%20BI%20%202009.ppt
rgds, Ghuru -
Hi, I'm unable to see if I have any music/videos/photos on my ipad and itunes advise that I have 23gb of 'other' material therefore the sync is unable to perform when transfering music/videos to the ipad. I was forced to perform a restore earlier and now cant see the videos/music so want to replace. Pls assist, thanks
23 GB of other indicates a corrupt file(s). A restore should resolve.
-
Does having too many project effect FCPX performance?
I have 100 - 150 projects
Selecting a project takes about 5 - 10 seconds
Dragging into folder takes a similar time
Does having that number of projects effect the performance?
When loading up, it reads all project names and checks links (I think)
So I'm guessing there HAS to be some sort of performance hit?
Thanks
Omarjames, thanks for the reply
currently i'm working off the hard drive on my macbook pro
the 'events' what are these? are they simply pointers to where the media is stored?
similar with 'projects' - assuming there are a few more parameters stored for specific settings?
apart from rendering files, these files all should be light weight?
i read that link u gave. i'm now going to move events and project folders as mentioned
Event Manager X: is it worth getting?
i read the reviews. it doesnt say whether or not u can specify where the files are hidden to - lets say you want to keep on the current drive - or maybe move to an external drive
some reviews have complained about the lack of response from buyers - doesnt sound too good
EDIT: i've moved events and projects. i closed fcpx and then started again. the event and project names are still there
what am i doing wrong?
EDIT: lets say i move events called abc. let's say i have a projects folder called xyz which used media in abc. i move xyz this as well
12 months, i need abc and xyz - but i've forgetton how they are connected and i have 100's of project files and events i have taken offline
what happens then?
thanks -
Periods of 2010 are opend , can it effect on perform ance?
Hi,
We are facing performance issues with EBS r12.0.6.
Our periods of Jan-2010 to dec-2010 are still opened, my functional team aks me that if u close the open periods then
u can have batter performance for retriving data or overall performance.
So, can open periods effect on performance????
Thanks,
Fayaz AhmedYou are having performance problem ...where?
Are there specific requests that are running slow? Specific screens?
If the problem is everywhere, then your problem lies somewhere else.
Having open periods may affect a small number of screens but that won't cause any application wide performance issues.
Sandeep Gandhi -
780 SLI - "Voltage Limit" and "Utilization Limit" Flags
Hello,
I'm trying to pinpoint an issue I'm having with my video cards, and wanted additional advice before I make purchases. My questions will be: is there anything else I should try? Is there anything I can do to pinpoint the problem?
My setup:
Core i7-950 - OC'd to 3.84 ghz
ASUS P6X58D-E - mobo
2x MSI n780 TF in SLI
Corsair 850AX Power Supply
Also drawing power: 5x Hard Drives; Typically only 2 are running at one time (OS RAID), the other 2 are a backup RAID I only use to archive stuff, and the last is a Linux drive that Windows doesn't even see
Issue:
Most games run without issue; but Metro Last Light is unstable. I run at 1920x1080, Advanced Physx, 2x AA, Very High quality and Very High Tessalation. There are times when I get 60 FPS (V-Sync); however, there are times that the performance drops to 6 or 14 FPS. When it is at 14 FPS it is still playable, but 6 FPS is terrible. I use Afterburner's OSD to monitor GPU Usage, Temp, and FPS. When it is at 6 FPS, it is only using 12% of either GPU at most.
While investigating, I noticed a few things in Afterburner that stand out when this occurs.
1) The Core Clock drops down (throttling?)
2) The "Voltage Limit" and "Utilization Limit" flags are both set on both GPUs.
My thoughts:
I'm thinking that my Power Supply isn't quite big enough. I thought this may become an issue when I first bought the two cards (I was previously running 2 460's on SLI, then upgraded to 780s).
My question is if the video cards are pulling the power supply's limit - will this trip the two flags? I would have thought the Voltage Limit would indicate the voltage going too high; but power supply being strained should drop voltage.
I have not changed any of the voltage settings to the card - they are whatever MSI has them set to for the stock OC.
If I buy another PSU, I don't like to go cheap - so it will definitely be beefy. Before I drop a few hundred on it, I want to be sure the Power Supply is the issue. Is there anything else you guys/gals can think of that may be an issue? Any tests I can do to confirm?
The new Thief seems to run fine; also Kombustor runs without issue (but only runs on one GPU - does not SLI). I have no other stability issues - the PC doesn't randomly shut down or reboot. It just seems to be Metro Last Light - but Metro is also the most demanding game that I own.
Any assistance or feedback will be greatly appreciated!
Edit - Update:
I tried disabling SLI to see if the issue would improve by only loading 1 GPU. No difference at all - no better or worse. Same flag (just only on the one GPU), same exact FPS 6.4.
I installed GPU-Z to be able to monitor core voltage. It normally runs at about 1.1 volts. However, once the issue occurs it is as low as 0.875 volts. Seems to confirm the PSU may be an issue. Any feedback or additional confirmation is still greatly appreciated!Apologize for the bump - I could not see a way to edit the original post. However, I wanted to make sure this information is available in case others had similar issues.
I found an even better solution. NVIDIA has an updated "Physx" driver - you have to download it from the NVIDIA site (i.e. Other NVIDIA drivers, not GeForce). Look for Physx version 9.13.1220 or later. 9.13.1220 was release on 1/27/2014 - but an older version is included in the most recent GeForce drivers for some reason.
The patch notes from Physx 9.13.1220 specifically state:
*Changes & fixed issues in this release
**Fixes a bug that caused the Metro Last Light to not be GPU accelerated on some systems.
With this software update I can enable Advanced Physx and max settings in Last Light and still run at 60 FPS. -
Number of columns and effect on performance
We are trying to improve the performance of our system and have noticed that the number of columns in our select statements has a dramatic, non-linear effect on the performance we see. For a particular query (with a single record returned) retrieving 10 columns from the table takes about 120 milliseconds, but if we reduce the request to 6 columns the time shrinks to about 18 milliseconds. It doesn't seem to matter which columns we pick, just how many of them are chosen.
We have even been able to retrieve a large number of columns from a table using multiple requests of 5 columns each and see a 2X performance improvement over a single request for all of the columns. Use of prepared statements and setting column types seems to have negligible effect.
Any ideas what we are seeing here and how we might improve the performance without cluttering our code up with these wierd multiple requests? This is happening in the middle of a large system, with a number of other database requests happening other than the ones we have currently instrumented for performance measurements. Don't know if this is some kind of interaction with a cache or what. We are using Oracle 8i Enterprise Edition version 8.1.6.3.0.Hi,
1) This forum provides a search option, you should use it Doing so you will find this post
2) Did you solve your earlier questions? If yes, you should mark the answers that helped you find a solution. -
Log file sync top event during performance test -av 36ms
Hi,
During the performance test for our product before deployment into product i see "log file sync" on top with Avg wait (ms) being 36 which i feel is too high.
Avg
wait % DB
Event Waits Time(s) (ms) time Wait Class
log file sync 208,327 7,406 36 46.6 Commit
direct path write 646,833 3,604 6 22.7 User I/O
DB CPU 1,599 10.1
direct path read temp 1,321,596 619 0 3.9 User I/O
log buffer space 4,161 558 134 3.5 ConfiguratAlthough testers are not complaining about the performance of the appplication , we ,DBAs, are expected to be proactive about the any bad signals from DB.
I am not able to figure out why "log file sync" is having such slow response.
Below is the snapshot from the load profile.
Snap Id Snap Time Sessions Curs/Sess
Begin Snap: 108127 16-May-13 20:15:22 105 6.5
End Snap: 108140 16-May-13 23:30:29 156 8.9
Elapsed: 195.11 (mins)
DB Time: 265.09 (mins)
Cache Sizes Begin End
~~~~~~~~~~~ ---------- ----------
Buffer Cache: 1,168M 1,136M Std Block Size: 8K
Shared Pool Size: 1,120M 1,168M Log Buffer: 16,640K
Load Profile Per Second Per Transaction Per Exec Per Call
~~~~~~~~~~~~ --------------- --------------- ---------- ----------
DB Time(s): 1.4 0.1 0.02 0.01
DB CPU(s): 0.1 0.0 0.00 0.00
Redo size: 607,512.1 33,092.1
Logical reads: 3,900.4 212.5
Block changes: 1,381.4 75.3
Physical reads: 134.5 7.3
Physical writes: 134.0 7.3
User calls: 145.5 7.9
Parses: 24.6 1.3
Hard parses: 7.9 0.4
W/A MB processed: 915,418.7 49,864.2
Logons: 0.1 0.0
Executes: 85.2 4.6
Rollbacks: 0.0 0.0
Transactions: 18.4Some of the top background wait events:
^LBackground Wait Events DB/Inst: Snaps: 108127-108140
-> ordered by wait time desc, waits desc (idle events last)
-> Only events with Total Wait Time (s) >= .001 are shown
-> %Timeouts: value of 0 indicates value was < .5%. Value of null is truly 0
Avg
%Time Total Wait wait Waits % bg
Event Waits -outs Time (s) (ms) /txn time
log file parallel write 208,563 0 2,528 12 1.0 66.4
db file parallel write 4,264 0 785 184 0.0 20.6
Backup: sbtbackup 1 0 516 516177 0.0 13.6
control file parallel writ 4,436 0 97 22 0.0 2.6
log file sequential read 6,922 0 95 14 0.0 2.5
Log archive I/O 6,820 0 48 7 0.0 1.3
os thread startup 432 0 26 60 0.0 .7
Backup: sbtclose2 1 0 10 10094 0.0 .3
db file sequential read 2,585 0 8 3 0.0 .2
db file single write 560 0 3 6 0.0 .1
log file sync 28 0 1 53 0.0 .0
control file sequential re 36,326 0 1 0 0.2 .0
log file switch completion 4 0 1 207 0.0 .0
buffer busy waits 5 0 1 116 0.0 .0
LGWR wait for redo copy 924 0 1 1 0.0 .0
log file single write 56 0 1 9 0.0 .0
Backup: sbtinfo2 1 0 1 500 0.0 .0During a previous perf test , things didnt look this bad for "log file sync. Few sections from the comparision report(awrddprt.sql)
{code}
Workload Comparison
~~~~~~~~~~~~~~~~~~~ 1st Per Sec 2nd Per Sec %Diff 1st Per Txn 2nd Per Txn %Diff
DB time: 0.78 1.36 74.36 0.02 0.07 250.00
CPU time: 0.18 0.14 -22.22 0.00 0.01 100.00
Redo size: 573,678.11 607,512.05 5.90 15,101.84 33,092.08 119.13
Logical reads: 4,374.04 3,900.38 -10.83 115.14 212.46 84.52
Block changes: 1,593.38 1,381.41 -13.30 41.95 75.25 79.38
Physical reads: 76.44 134.54 76.01 2.01 7.33 264.68
Physical writes: 110.43 134.00 21.34 2.91 7.30 150.86
User calls: 197.62 145.46 -26.39 5.20 7.92 52.31
Parses: 7.28 24.55 237.23 0.19 1.34 605.26
Hard parses: 0.00 7.88 100.00 0.00 0.43 100.00
Sorts: 3.88 4.90 26.29 0.10 0.27 170.00
Logons: 0.09 0.08 -11.11 0.00 0.00 0.00
Executes: 126.69 85.19 -32.76 3.34 4.64 38.92
Transactions: 37.99 18.36 -51.67
First Second Diff
1st 2nd
Event Wait Class Waits Time(s) Avg Time(ms) %DB time Event Wait Class Waits Time(s) Avg Time
(ms) %DB time
SQL*Net more data from client Network 2,133,486 1,270.7 0.6 61.24 log file sync Commit 208,355 7,407.6
35.6 46.57
CPU time N/A 487.1 N/A 23.48 direct path write User I/O 646,849 3,604.7
5.6 22.66
log file sync Commit 99,459 129.5 1.3 6.24 log file parallel write System I/O 208,564 2,528.4
12.1 15.90
log file parallel write System I/O 100,732 126.6 1.3 6.10 CPU time N/A 1,599.3
N/A 10.06
SQL*Net more data to client Network 451,810 103.1 0.2 4.97 db file parallel write System I/O 4,264 784.7 1
84.0 4.93
-direct path write User I/O 121,044 52.5 0.4 2.53 -SQL*Net more data from client Network 7,407,435 279.7
0.0 1.76
-db file parallel write System I/O 986 22.8 23.1 1.10 -SQL*Net more data to client Network 2,714,916 64.6
0.0 0.41
{code}
*To sum it sup:
1. Why is the IO response getting such an hit during the new perf test? Please suggest*
2. Does the number of DB writer impact "log file sync" wait event? We have only one DB writer as the number of cpu on the host is only 4
{code}
select *from v$version;
BANNER
Oracle Database 11g Enterprise Edition Release 11.1.0.7.0 - 64bit Production
PL/SQL Release 11.1.0.7.0 - Production
CORE 11.1.0.7.0 Production
TNS for HPUX: Version 11.1.0.7.0 - Production
NLSRTL Version 11.1.0.7.0 - Production
{code}
Please let me know if you would like to see any other stats.
Edited by: Kunwar on May 18, 2013 2:20 PM1. A snapshot interval of 3 hours always generates meaningless results
Below are some details from the 1 hour interval AWR report.
Platform CPUs Cores Sockets Memory(GB)
HP-UX IA (64-bit) 4 4 3 31.95
Snap Id Snap Time Sessions Curs/Sess
Begin Snap: 108129 16-May-13 20:45:32 140 8.0
End Snap: 108133 16-May-13 21:45:53 150 8.8
Elapsed: 60.35 (mins)
DB Time: 140.49 (mins)
Cache Sizes Begin End
~~~~~~~~~~~ ---------- ----------
Buffer Cache: 1,168M 1,168M Std Block Size: 8K
Shared Pool Size: 1,120M 1,120M Log Buffer: 16,640K
Load Profile Per Second Per Transaction Per Exec Per Call
~~~~~~~~~~~~ --------------- --------------- ---------- ----------
DB Time(s): 2.3 0.1 0.03 0.01
DB CPU(s): 0.1 0.0 0.00 0.00
Redo size: 719,553.5 34,374.6
Logical reads: 4,017.4 191.9
Block changes: 1,521.1 72.7
Physical reads: 136.9 6.5
Physical writes: 158.3 7.6
User calls: 167.0 8.0
Parses: 25.8 1.2
Hard parses: 8.9 0.4
W/A MB processed: 406,220.0 19,406.0
Logons: 0.1 0.0
Executes: 88.4 4.2
Rollbacks: 0.0 0.0
Transactions: 20.9
Top 5 Timed Foreground Events
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Avg
wait % DB
Event Waits Time(s) (ms) time Wait Class
log file sync 73,761 6,740 91 80.0 Commit
log buffer space 3,581 541 151 6.4 Configurat
DB CPU 348 4.1
direct path write 238,962 241 1 2.9 User I/O
direct path read temp 487,874 174 0 2.1 User I/O
Background Wait Events DB/Inst: Snaps: 108129-108133
-> ordered by wait time desc, waits desc (idle events last)
-> Only events with Total Wait Time (s) >= .001 are shown
-> %Timeouts: value of 0 indicates value was < .5%. Value of null is truly 0
Avg
%Time Total Wait wait Waits % bg
Event Waits -outs Time (s) (ms) /txn time
log file parallel write 61,049 0 1,891 31 0.8 87.8
db file parallel write 1,590 0 251 158 0.0 11.6
control file parallel writ 1,372 0 56 41 0.0 2.6
log file sequential read 2,473 0 50 20 0.0 2.3
Log archive I/O 2,436 0 20 8 0.0 .9
os thread startup 135 0 8 60 0.0 .4
db file sequential read 668 0 4 6 0.0 .2
db file single write 200 0 2 9 0.0 .1
log file sync 8 0 1 152 0.0 .1
log file single write 20 0 0 21 0.0 .0
control file sequential re 11,218 0 0 0 0.1 .0
buffer busy waits 2 0 0 161 0.0 .0
direct path write 6 0 0 37 0.0 .0
LGWR wait for redo copy 380 0 0 0 0.0 .0
log buffer space 1 0 0 89 0.0 .0
latch: cache buffers lru c 3 0 0 1 0.0 .0 2 The log file sync is a result of commit --> you are committing too often, maybe even every individual record.
Thanks for explanation. +Actually my question is WHY is it so slow (avg wait of 91ms)+3 Your IO subsystem hosting the online redo log files can be a limiting factor.
We don't know anything about your online redo log configuration
Below is my redo log configuration.
GROUP# STATUS TYPE MEMBER IS_
1 ONLINE /oradata/fs01/PERFDB1/redo_1a.log NO
1 ONLINE /oradata/fs02/PERFDB1/redo_1b.log NO
2 ONLINE /oradata/fs01/PERFDB1/redo_2a.log NO
2 ONLINE /oradata/fs02/PERFDB1/redo_2b.log NO
3 ONLINE /oradata/fs01/PERFDB1/redo_3a.log NO
3 ONLINE /oradata/fs02/PERFDB1/redo_3b.log NO
6 rows selected.
04:13:14 perf_monitor@PERFDB1> col FIRST_CHANGE# for 999999999999999999
04:13:26 perf_monitor@PERFDB1> select *from v$log;
GROUP# THREAD# SEQUENCE# BYTES MEMBERS ARC STATUS FIRST_CHANGE# FIRST_TIME
1 1 40689 524288000 2 YES INACTIVE 13026185905545 18-MAY-13 01:00
2 1 40690 524288000 2 YES INACTIVE 13026185931010 18-MAY-13 03:32
3 1 40691 524288000 2 NO CURRENT 13026185933550 18-MAY-13 04:00Edited by: Kunwar on May 18, 2013 2:46 PM
Maybe you are looking for
-
Collaboration : Share Application not working
Hi, I have configured for Collaboration. After click on Collaboration, select the userA now from context menu, select the "Share Application". Now the pop-up comes having the tab as "<b>Select an application to share</b>" with the <b>Cross Sign</b
-
How can i get files that were downloaded to my phone deleted?
I downloaded picture/information to my iphone and when doing this, I accidentally transferred files from my computer to my iphone. How can I delete them?
-
Form6 package doc & unix question
Hi, I starting to work using Forms6. Can someone give me some links about Form6 doc about built-in packages (TEXT_IO ...) and other doc . I found PDF file on this site but I cant download them (problem with my navigator i suppose). I searching a func
-
Enable Navigation to WebClient View from Inbox of IC
Hi All, I am using CRM 2007. In the IC, when you click on a particular transaction in the Quick Create group we have it enabled to navigate to the Web Client view for that particular transaction within the IC. This is working fine which is great. How
-
How do I get iphoto to import images
Since I installed Yosemite if I attempt to import more than a few images at a time they all are black! I am a professional photographer and have used iphoto as the gateway to my computer forever. This is a real PITA apple.