Search Results

Search found 13151 results on 527 pages for 'performance counters'.

Page 7/527 | < Previous Page | 3 4 5 6 7 8 9 10 11 12 13 14  | Next Page >

• What causes bad performance in consumer apps?

  - by Crashworks

  My Comcast DVR takes at least three seconds to respond to every remote control keypress, making the simple task of watching television into a frustrating button-mashing experience. My iPhone takes at least fifteen seconds to display text messages and crashes ¼ of the times I try to bring up the iPad app; simply receiving and reading an email often takes well over a minute. Even the navcom in my car has mushy and unresponsive controls, often swallowing successive inputs if I make them less than a few seconds apart. These are all fixed-hardware end-consumer appliances for which usability should be paramount, and yet they all fail at basic responsiveness and latency. Their software is just too slow. What's behind this? Is it a technical problem, or a social one? Who or what is responsible? Is it because these were all written in managed, garbage-collected languages rather than native code? Is it the individual programmers who wrote the software for these devices? In all of these cases the app developers knew exactly what hardware platform they were targeting and what its capabilities were; did they not take it into account? Is it the guy who goes around repeating "optimization is the root of all evil," did he lead them astray? Was it a mentality of "oh it's just an additional 100ms" each time until all those milliseconds add up to minutes? Is it my fault, for having bought these products in the first place? This is a subjective question, with no single answer, but I'm often frustrated to see so many answers here saying "oh, don't worry about code speed, performance doesn't matter" when clearly at some point it does matter for the end-user who gets stuck with a slow, unresponsive, awful experience. So, at what point did things go wrong for these products? What can we as programmers do to avoid inflicting this pain on our own customers?

  Read the article

• Do or can robots cause considerable performance issues?

  - by Anicho

  So the question in the title is exactly what I am trying to find out. My case is: At work we are in a discussion with team members who seem to think bots will cause us problems relating to performance when running on our services website. Out setup: Lets say I have site www.mysite.co.uk this is a shop window to our online services which sit on www.mysiteonline.co.uk. When people search in google for mysite they see mysiteonline.co.uk as well as mysite.co.uk. Cases against stopping bots crawling: We don't store gb's of data publicly available on the web Most friendly bots, if they were to cause issues would have done so already In our instance the bots can't crawl the site because it requires username & password Stopping bots with robot .txt causes an issue with seo (ref.1) If it was a malicious bot, it would ignore robot.txt or meta tags anyway Ref 1. If we were to block mysiteonline.co.uk from having robots crawl this will affect seo rankings and make it inconvenient for users who actively search for mysite to find mysiteonline. Which we can prove is the case for a good portion of our users.

  Read the article

• android game performance regarding timers

  - by iQue

  Im new to the game-dev world and I have a tendancy to over-simplify my code, and sometimes this costs me alot fo memory. Im using a custom TimerTask that looks like this: public class Task extends TimerTask { private MainGamePanel panel; public Task(MainGamePanel panel) { this.panel=panel; } /** * When the timer executes, this code is run. */ public void run() { panel.createEnemies(); } } this task calls this method from my view: public void createEnemies() { Bitmap bmp = BitmapFactory.decodeResource(getResources(), R.drawable.female); if(enemyCounter < 24){ enemies.add(new Enemy(bmp, this)); } enemyCounter++; } Since I call this in the onCreate-method instead of in my views contructor (because My enemies need to get width and height of view). Im wondering if this will work when I have multiple levels in game (start a new intent). And if this kind of timer really is the best way to add a delay between the spawning-time of my enemies performance-wise. adding code for my timer if any1 came here cus they dont understand timers: private Timer timer1 = new Timer(); private long delay1 = 5*1000; // 5 sec delay public void surfaceCreated(SurfaceHolder holder) { timer1.schedule(new Task(this), 0, delay1); //I call my timer and add the delay thread.setRunning(true); thread.start(); }

  Read the article

• 12.10 visual performance using nvidia driver

  - by user100485

  My fresh ubuntu 12.10 install is slow, not something extreme but dragging windows, switching workspaces and things like that are just slow and look horrible. it feels like the fps is dropping in a game. Doing some photoshop work in windows was even a relief! This effect gets worse if I connect my external monitor. My system is an intel pentium dual core T4500 with 4gb memory and a GeForce 8200M G/integrated/SSE2 graphics chip. Nothing fancy but should be able to run ok. My "experience" in ubuntu is set to standard. (MSI cr500 laptop) I've installed the nvidia drivers, tried current and experimental and the experimental drivers seem to perform a bit better but overall bad anyway. I set the mode to adaptive in the nvidia-settings tool and it goes to maximum setting directly and doesn't come back. Using htop I found out that compiz or the X server always use a few percent of my cpu, more than I think it should and the time consumed is 5:18 for compiz, 4:33 for /usr/bin/X and 2:41 for google chrome(about 30 tabs open so not too strange I think.) What can I do to increase the visual performance cause this makes me not want to use ubuntu in public!

  Read the article

• Count a row VS Save the Row count after each update

  - by SAFAD

  I want to know whether saving row count in a table is better than counting it each time of the proccess. Quick Example : A visitor goes to Group Clan, the page displays clan information and Members who have joined the group,Should the page look for all the users who joined the clan and count them, or just display the number of members already saved in table ? I think the first one is not possible to get manipulated with but IT MIGHT cost performance Your Ideas ?

  Read the article

• SQL SERVER – What is Incremental Statistics? – Performance improvements in SQL Server 2014 – Part 1

  - by Pinal Dave

  This is the first part of the series Incremental Statistics. Here is the index of the complete series. What is Incremental Statistics? – Performance improvements in SQL Server 2014 – Part 1 Simple Example of Incremental Statistics – Performance improvements in SQL Server 2014 – Part 2 DMV to Identify Incremental Statistics – Performance improvements in SQL Server 2014 – Part 3 Statistics are considered one of the most important aspects of SQL Server Performance Tuning. You might have often heard the phrase, with related to performance tuning. “Update Statistics before you take any other steps to tune performance”. Honestly, I have said above statement many times and many times, I have personally updated statistics before I start to do any performance tuning exercise. You may agree or disagree to the point, but there is no denial that Statistics play an extremely vital role in the performance tuning. SQL Server 2014 has a new feature called Incremental Statistics. I have been playing with this feature for quite a while and I find that very interesting. After spending some time with this feature, I decided to write about this subject over here. New in SQL Server 2014 – Incremental Statistics Well, it seems like lots of people wants to start using SQL Server 2014′s new feature of Incremetnal Statistics. However, let us understand what actually this feature does and how it can help. I will try to simplify this feature first before I start working on the demo code. Code for all versions of SQL Server Here is the code which you can execute on all versions of SQL Server and it will update the statistics of your table. The keyword which you should pay attention is WITH FULLSCAN. It will scan the entire table and build brand new statistics for you which your SQL Server Performance Tuning engine can use for better estimation of your execution plan. UPDATE STATISTICS TableName(StatisticsName) WITH FULLSCAN Who should learn about this? Why? If you are using partitions in your database, you should consider about implementing this feature. Otherwise, this feature is pretty much not applicable to you. Well, if you are using single partition and your table data is in a single place, you still have to update your statistics the same way you have been doing. If you are using multiple partitions, this may be a very useful feature for you. In most cases, users have multiple partitions because they have lots of data in their table. Each partition will have data which belongs to itself. Now it is very common that each partition are populated separately in SQL Server. Real World Example For example, if your table contains data which is related to sales, you will have plenty of entries in your table. It will be a good idea to divide the partition into multiple filegroups for example, you can divide this table into 3 semesters or 4 quarters or even 12 months. Let us assume that we have divided our table into 12 different partitions. Now for the month of January, our first partition will be populated and for the month of February our second partition will be populated. Now assume, that you have plenty of the data in your first and second partition. Now the month of March has just started and your third partition has started to populate. Due to some reason, if you want to update your statistics, what will you do? In SQL Server 2012 and earlier version You will just use the code of WITH FULLSCAN and update the entire table. That means even though you have only data in third partition you will still update the entire table. This will be VERY resource intensive process as you will be updating the statistics of the partition 1 and 2 where data has not changed at all. In SQL Server 2014 You will just update the partition of Partition 3. There is a special syntax where you can now specify which partition you want to update now. The impact of this is that it is smartly merging the new data with old statistics and update the entire statistics without doing FULLSCAN of your entire table. This has a huge impact on performance. Remember that the new feature in SQL Server 2014 does not change anything besides the capability to update a single partition. However, there is one feature which is indeed attractive. Previously, when table data were changed 20% at that time, statistics update were triggered. However, now the same threshold is applicable to a single partition. That means if your partition faces 20% data, change it will also trigger partition level statistics update which, when merged to your final statistics will give you better performance. In summary If you are not using a partition, this feature is not applicable to you. If you are using a partition, this feature can be very helpful to you. Tomorrow: We will see working code of SQL Server 2014 Incremental Statistics. Reference: Pinal Dave (http://blog.sqlauthority.com)Filed under: PostADay, SQL, SQL Authority, SQL Performance, SQL Query, SQL Server, SQL Tips and Tricks, T SQL Tagged: SQL Statistics, Statistics

  Read the article

• Increase application performance

  - by Prayos

  I'm writing a program for a company that will generate a daily report for them. All of the data that they use for this report is stored in a local SQLite database. For this report, the utilize pretty much every bit of the information in the database. So currently, when I query the datbase, I retrieve everything, and store the information in lists. Here's what I've got: using (var dataReader = _connection.Select(query)) { if (dataReader.HasRows) { while (dataReader.Read()) { _date.Add(Convert.ToDateTime(dataReader["date"])); _measured.Add(Convert.ToDouble(dataReader["measured_dist"])); _bit.Add(Convert.ToDouble(dataReader["bit_loc"])); _psi.Add(Convert.ToDouble(dataReader["pump_press"])); _time.Add(Convert.ToDateTime(dataReader["timestamp"])); _fob.Add(Convert.ToDouble(dataReader["force_on_bit"])); _torque.Add(Convert.ToDouble(dataReader["torque"])); _rpm.Add(Convert.ToDouble(dataReader["rpm"])); _pumpOneSpm.Add(Convert.ToDouble(dataReader["pump_1_strokes_pm"])); _pumpTwoSpm.Add(Convert.ToDouble(dataReader["pump_2_strokes_pm"])); _pullForce.Add(Convert.ToDouble(dataReader["pull_force"])); _gpm.Add(Convert.ToDouble(dataReader["flow"])); } } } I then utilize these lists for the calculations. Obviously, the more information that is in this database, the longer the initial query will take. I'm curious if there is a way to increase the performance of the query at all? Thanks for any and all help. EDIT One of the report rows is called Daily Drilling Hours. For this calculation, I use this method: // Retrieves the timestamps where measured depth == bit depth and PSI >= 50 public double CalculateDailyProjectDrillingHours(DateTime date) { var dailyTimeStamps = _time.Where((t, i) => _date[i].Equals(date) && _measured[i].Equals(_bit[i]) && _psi[i] >= 50).ToList(); return _dailyDrillingHours = Convert.ToDouble(Math.Round(TimeCalculations(dailyTimeStamps).TotalHours, 2, MidpointRounding.AwayFromZero)); } // Checks that the interval is less than 10, then adds the interval to the total time private static TimeSpan TimeCalculations(IList<DateTime> timeStamps) { var interval = new TimeSpan(0, 0, 10); var totalTime = new TimeSpan(); TimeSpan timeDifference; for (var j = 0; j < timeStamps.Count - 1; j++) { if (timeStamps[j + 1].Subtract(timeStamps[j]) <= interval) { timeDifference = timeStamps[j + 1].Subtract(timeStamps[j]); totalTime = totalTime.Add(timeDifference); } } return totalTime; }

  Read the article

• How to use caching to increase render performance?

  - by Christian Ivicevic

  First of all I am going to cover the basic design of my 2d tile-based engine written with SDL in C++, then I will point out what I am up to and where I need some hints. Concept of my engine My engine uses the concept of GameScreens which are stored on a stack in the main game class. The main methods of a screen are usually LoadContent, Render, Update and InitMultithreading. (I use the last one because I am using v8 as a JavaScript bridge to the engine. The main game loop then renders the top screen on the stack (if there is one; otherwise, it exits the game) - actually it calls the render methods, but stores all items to be rendered in a list. After gathering all this information the methods like SDL_BlitSurface are called by my GameUIRenderer which draws the enqueued content and then draws some overlay. The code looks like this: while(Game is running) { Handle input if(Screens on stack == 0) exit Update timer etc. Clear the screen Peek the screen on the stack and collect information on what to render Actually render the enqueue screen stuff and some overlay etc. Flip the screen } The GameUIRenderer uses as hinted a std::vector<std::shared_ptr<ImageToRender>> to hold all necessary information described by this class: class ImageToRender { private: SDL_Surface* image; int x, y, w, h, xOffset, yOffset; }; This bunch of attributes is usually needed if I have a texture atlas with all tiles in one SDL_Surface and then the engine should crop one specific area and draw this to the screen. The GameUIRenderer::Render() method then just iterates over all elements and renders them something like this: std::for_each( this->m_vImageVector.begin(), this->m_vImageVector.end(), [this](std::shared_ptr<ImageToRender> pCurrentImage) { SDL_Rect rc = { pCurrentImage->x, pCurrentImage->y, 0, 0 }; // For the sake of simplicity ignore offsets... SDL_Rect srcRect = { 0, 0, pCurrentImage->w, pCurrentImage->h }; SDL_BlitSurface(pCurrentImage->pImage, &srcRect, g_pFramework->GetScreen(), &rc); } ); this->m_vImageVector.clear(); Current ideas which need to be reviewed The specified approach works really good and IMHO it is really has a good structure, however the performance could be definitely increased. I would like to know what do you suggest, how to implement efficient caching of surfaces etc so that there is no need to redraw the same scene over and over again? The map itself would be almost static, only when the player moves, we would need to move the map. Furthermore animated entities would either require updates of the whole map or updates of only the specific areas the entities are currently moving in. My first approaches were to include a flag IsTainted which should be used by the GameUIRenderer to decide whether to redraw everything or use cached version (or to not render anything so that we do not have to Clear the screen and let the last frame persist). However this seems to be quite messy if I have to manually handle in my Render method of the screen class if something has changed or not.

  Read the article

• HPCM 11.1.2.x - Outline Optimisation for Calculation Performance

  - by Jane Story

  When an HPCM application is first created, it is likely that you will want to carry out some optimisation on the HPCM application’s Essbase outline in order to improve calculation execution times. There are several things that you may wish to consider. Because at least one dense dimension for an application is required to deploy from HPCM to Essbase, “Measures” and “AllocationType”, as the only required dimensions in an HPCM application, are created dense by default. However, for optimisation reasons, you may wish to consider changing this default dense/sparse configuration. In general, calculation scripts in HPCM execute best when they are targeting destinations with one or more dense dimensions. Therefore, consider your largest target stage i.e. the stage with the most assignment destinations and choose that as a dense dimension. When optimising an outline in this way, it is not possible to have a dense dimension in every target stage and so testing with the dense/sparse settings in every stage is the key to finding the best configuration for each individual application. It is not possible to change the dense/sparse setting of individual cloned dimensions from EPMA. When a dimension that is to be repeated in multiple stages, and therefore cloned, is defined in EPMA, every instance of that dimension has the same storage setting. However, such manual changes may not be preserved in all cases. Please see below for full explanation. However, once the application has been deployed from EPMA to HPCM and from HPCM to Essbase, it is possible to make the dense/sparse changes to a cloned dimension directly in Essbase. This can be done by editing the properties of the outline in Essbase Administration Services (EAS) and manually changing the dense/sparse settings of individual dimensions. There are two methods of deployment from HPCM to Essbase from 11.1.2.1. There is a “replace” deploy method and an “update” deploy method: “Replace” will delete the Essbase application and replace it. If this method is chosen, then any changes made directly on the Essbase outline will be lost. If you use the update deploy method (with or without archiving and reloading data), then the Essbase outline, including any manual changes you have made (i.e. changes to dense/sparse settings of the cloned dimensions), will be preserved. Notes If you are using the calculation optimisation technique mentioned in a previous blog to calculate multiple POVs (https://blogs.oracle.com/pa/entry/hpcm_11_1_2_optimising) and you are calculating all members of that POV dimension (e.g. all months in the Period dimension) then you could consider making that dimension dense. Always review Block sizes after all changes! The maximum block size recommended in the Essbase Database Administrator’s Guide is 100k for 32 bit Essbase and 200k for 64 bit Essbase. However, calculations may perform better with a larger than recommended block size provided that sufficient memory is available on the Essbase server. Test different configurations to determine the most optimal solution for your HPCM application. Please note that this blog article covers HPCM outline optimisation only. Additional performance tuning can be achieved by methodically testing database settings i.e data cache, index cache and/or commit block settings. For more information on Essbase tuning best practices, please review these items in the Essbase Database Administrators Guide. For additional information on the commit block setting, please see the previous PA blog article https://blogs.oracle.com/pa/entry/essbase_11_1_2_commit

  Read the article

• graph performance monitor windows and linux

  - by Patrik

  We are using Munin to get graphs of our servers. (such as CPU load, I/O, available disk space, etc. ) Munin gives us last 24h, last 7 days, last month and last year. The good thing with Munin is that it supports all kinds of clients, such as Windows, Linux and switches because it can monitor over SNMP. However, we have a problem with the Munin client for Windows. Since we upgraded to Windows Server 2008 R2 it won't show graphs for some performance counters. What options are there out there? Both free and commercial.

  Read the article

• New Whitepaper: Oracle E-Business Suite on Exadata

  - by Steven Chan

  Our Maximum Availability Architecture (MAA) team has quietly been amassing a formidable set of whitepapers about the Oracle Exadata Database Machine.  They're available here:MAA Best Practices - Exadata Database MachineIf you're one of the lucky ones with access to this hardware platform, you'll be pleased to hear that the MAA team has just published a new whitepaper with best practices for EBS environments:Oracle E-Business Suite on ExadataThis whitepaper covers the following topics:Getting to Exadata -- a high level overview of fresh installation on, and migration to, Exadata Database Machine with pointers to more detailed documentation High Availability and Disaster Recovery -- an overview of our MAA best practices with pointers to our detailed MAA Best Practices documentation Performance and Scalability -- best practices for running Oracle E-Business Suite on Exadata Database Machine based on our internal testing

  Read the article

• theoretical and practical matrix multiplication FLOP

  - by mjr

  I wrote traditional matrix multiplication in c++ and tried to measure and compare its theoretical and practical FLOP. As I know inner loop of MM has 2 operation therefore simple MM theoretical Flops is 2*n*n*n (2n^3) but in practice I get something like 4n^3 + number of operation which is 2 i.e. 6n^3 also if I just try to add up only one array a[i][j]++ practical flops then calculate like 3n^3 and not n^3 as you see again it is 2n^3 +1 operation and not 1 operation * n^3 . This is in case if I use 1D array in three nested loops as Matrix multiplication and compare flop, practical flop is the same (near) the theoretical flop and depend exactly as the number of operation in inner loop.I could not find the reason for this behaviour. what is the reason in both case? I know that theoretical flop is not the same as practical one because of some operations like load etc. system specification: Intel core2duo E4500 3700g memory L2 cache 2M x64 fedora 17 sample results: Matrix matrix multiplication 512*512 Real_time: 1.718368 Proc_time: 1.227672 Total flpops: 807,107,072 MFLOPS: 657.429016 Real_time: 3.608078 Proc_time: 3.042272 Total flpops: 807,024,448 MFLOPS: 265.270355 theoretical flop: 2*512*512*512=268,435,456 Practical flops= 6*512^3 =807,107,072 Using 1 dimensional array float d[size][size]:512 or any size for (int j = 0; j < size; ++j) { for (int k = 0; k < size; ++k) { d[k]=d[k]+e[k]+f[k]+g[k]+r; } } Real_time: 0.002288 Proc_time: 0.002260 Total flpops: 1,048,578 MFLOPS: 464.027161 theroretical flop: *4n^2=4*512^2=1,048,576* practical flop : 4n^2+overhead (other operation?)=1,048,578 3 loop version: Real_time: 1.282257 Proc_time: 1.155990 Total flpops: 536,872,000 MFLOPS: 464.426117 theoretical flop:4n^3 = 536,870,912 practical flop: *4n^3=4*512^3+overheads(other operation?)=536,872,000* thank you

  Read the article

• Strategy to find bottleneck in a network

  - by Simone

  Our enterprise is having some problem when the number of incoming request goes beyond a certain amount. To make things simpler, we have N websites that uses, amongst other, a local web service. This service is hosted by IIS, and it's a .NET 4.0 (C#) application executed in a farm. It's REST-oriented, built around OpenRasta. As already mentioned, by stress testing it with JMeter, we've found that beyond a certain amount of request the service's performance drop. Anyway, this service is, amongst other, a client itself of other 3 distinct web services and also a client for a DB server, so it's not very clear what really is the culprit of this abrupt decay. In turn, these 3 other web services are installed in our farm too, and client of other DB servers (and services, possibly, that are out of my team control). What strategy do you suggest to try to locate where the bottleneck(s) are? Do you have any high-level suggestions?

  Read the article

• Should I group all of my .js files into one large bundle?

  - by Scottie

  One of the difficulties I'm running into with my current project is that the previous developer spaghetti'd the javascript code in lots of different files. We have modal dialogs that are reused in different places and I find that the same .js file is often loaded twice. My thinking is that I'd like to just load all of the .js files in _Layout.cshtml, and that way I know it's loaded once and only once. Also, the client should only have to download this file once as well. It should be cached and therefore shouldn't really be a performance hit, except for the first page load. I should probably note that I am using ASP.Net bundling as well and loading most of the jQuery/bootstrap/etc from CDN's. Is there anything else that I'm not thinking of that would cause problems here? Should I bundle everything into a single file?

  Read the article

• What's the largest (most complex) PHP algorithm ever implemented in a single monolithic PHP script?

  - by Alex R

  I'm working on a tool which converts PHP code to Scala. As one of the finishing touches, I'm in need of a really good (er, somewhat biased) benchmark. By dumb luck my first benchmark attempt was with some code which uses bcmath extensively, which unfortunately is 1000x slower in Java, making the Scala code 22x slower overall than the original PHP. So I'm looking for some meaningful PHP benchmark with the following characteristics: The source needs to be in a single file. I need it to be simple to setup - no databases, hard-to-find input files, etc. Simple text input and output preferred. It should not use features that are slow in Java (BigInteger, trigonometric functions, etc). It should not use exoteric or dynamic PHP functions (e.g. no "eval" or "variable vars"). It should not over-rely on built-in libraries, e.g. MD5, crypt, etc. It should not be I/O bound. A CPU-bound memory-hungry algorithm is preferred. Basically, intensive OO operations, integer and string manipulation, recursion, etc would be great. Thanks

  Read the article

• Is there a PHP benchmark that meets these specific criteria? [closed]

  - by Alex R

  I'm working on a tool which converts PHP code to Scala. As one of the finishing touches, I'm in need of a really good (er, somewhat biased) benchmark. By dumb luck my first benchmark attempt was with some code which uses bcmath extensively, which unfortunately is 1000x slower in Java, making the Scala code 22x slower overall than the original PHP. So I'm looking for some meaningful PHP benchmark with the following characteristics: The PHP source needs to be in a single file. It should solve a real-world problem. No silly looping over empty methods etc. I need it to be simple to setup - no databases, hard-to-find input files, etc. Simple text input and output preferred. It should not use features that are slow in Java (BigInteger, trigonometric functions, etc). It should not use exoteric or dynamic PHP functions (e.g. no "eval" or "variable vars"). It should not over-rely on built-in libraries, e.g. MD5, crypt, etc. It should not be I/O bound. A CPU-bound memory-hungry algorithm is preferred. Basically, intensive OO operations, integer and string manipulation, recursion, etc would be great. Thanks

  Read the article

• Exchange 2010 - resolving Calendar Attendant\Requests Failed

  - by marcwenger

  On my mailbox server, I am receiving the alert: MSExchange Calendar Attendant\Requests Failed Or in Solarwinds Requests Failed (Calendar Attendant) for Exchange 2010 Mailbox Role Counters (Advanced) on *servername* All I know is this figure should be 0 at all times. Currently I am at 2 and this is the only alert on the Exchange servers. No where I can find how to resolve this. How can I fix this? thank you

  Read the article

• FreeBSD performance tuning. Sysctls, loader.conf, kernel.

  - by SaveTheRbtz

  I wanted to share knowledge of tuning FreeBSD via sysctls, so i'm posting them with comments. Based on Igor Sysoev (author of nginx) presentation about FreeBSD tuning up to 100,000-200,000 active connections. Sysctls are for 7.x FreeBSD. Since 7.2 amd64 some of them are tuned well by default. Prior 7.0 some of them are boot only (set via /boot/loader.conf) or does not exist at all. Highload web server sysctls: # Max. backlog size kern.ipc.somaxconn=4096 # Shared memory // 7.2+ can use shared memory > 2Gb kern.ipc.shmmax=2147483648 # Sockets kern.ipc.maxsockets=204800 # Do not use lager sockbufs on 8.0 # ( http://old.nabble.com/Significant-performance-regression-for-increased-maxsockbuf-on-8.0-RELEASE-tt26745981.html#a26745981 ) kern.ipc.maxsockbuf=262144 # Recive clusters (on amd64 7.2+ 65k is default) # For such high value vm.kmem_size must be increased to 3G #kern.ipc.nmbclusters=229376 # Jumbo pagesize(4k/8k) clusters # Used as general packet storage for jumbo frames # can be monitored via `netstat -m` #kern.ipc.nmbjumbop=192000 # Jumbo 9k/16k clusters # If you are using them #kern.ipc.nmbjumbo9=24000 #kern.ipc.nmbjumbo16=10240 # Every socket is a file, so increase them kern.maxfiles=204800 kern.maxfilesperproc=200000 kern.maxvnodes=200000 # Turn off receive autotuning #net.inet.tcp.recvbuf_auto=0 # Small receive space, only usable on http-server, on file server this # should be increased to 65535 or even more #net.inet.tcp.recvspace=8192 # Small send space is useful for http servers that serve small files # Autotuned since 7.x net.inet.tcp.sendspace=16384 # This should be enabled if you going to use big spaces (>64k) #net.inet.tcp.rfc1323=1 # Turn this off on highspeed, lossless connections (LAN 1Gbit+) #net.inet.tcp.delayed_ack=0 # This feature is useful if you are serving data over modems, Gigabit Ethernet, # or even high speed WAN links (or any other link with a high bandwidth delay product), # especially if you are also using window scaling or have configured a large send window. # You can try setting it to 0 on fileserver with 1GBit+ interfaces # Automatically disables on small RTT ( http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/netinet/tcp_subr.c?#rev1.237 ) #net.inet.tcp.inflight.enable=0 # Disable randomizing of ports to avoid false RST # Before usage check SA here www.bsdcan.org/2006/papers/ImprovingTCPIP.pdf # (it's also says that port randomization auto-disables at some conn.rates, but I didn't tested it thou) #net.inet.ip.portrange.randomized=0 # Increase portrange # For outgoing connections only. Good for seed-boxes and ftp servers. net.inet.ip.portrange.first=1024 net.inet.ip.portrange.last=65535 # Security net.inet.ip.redirect=0 net.inet.ip.sourceroute=0 net.inet.ip.accept_sourceroute=0 net.inet.icmp.maskrepl=0 net.inet.icmp.log_redirect=0 net.inet.icmp.drop_redirect=1 net.inet.tcp.drop_synfin=1 # Security net.inet.udp.blackhole=1 net.inet.tcp.blackhole=2 # Increases default TTL, sometimes useful # Default is 64 net.inet.ip.ttl=128 # Lessen max segment life to conserve resources # ACK waiting time in miliseconds (default: 30000 from RFC) net.inet.tcp.msl=5000 # Max bumber of timewait sockets net.inet.tcp.maxtcptw=40960 # Don't use tw on local connections # As of 15 Apr 2009. Igor Sysoev says that nolocaltimewait has some buggy realization. # So disable it or now till get fixed #net.inet.tcp.nolocaltimewait=1 # FIN_WAIT_2 state fast recycle net.inet.tcp.fast_finwait2_recycle=1 # Time before tcp keepalive probe is sent # default is 2 hours (7200000) #net.inet.tcp.keepidle=60000 # Should be increased until net.inet.ip.intr_queue_drops is zero net.inet.ip.intr_queue_maxlen=4096 # Interrupt handling via multiple CPU, but with context switch. # You can play with it. Default is 1; #net.isr.direct=0 # This is for routers only #net.inet.ip.forwarding=1 #net.inet.ip.fastforwarding=1 # This speed ups dummynet when channel isn't saturated net.inet.ip.dummynet.io_fast=1 # Increase dummynet(4) hash #net.inet.ip.dummynet.hash_size=2048 #net.inet.ip.dummynet.max_chain_len # Should be increased when you have A LOT of files on server # (Increase until vfs.ufs.dirhash_mem becames lower) vfs.ufs.dirhash_maxmem=67108864 # Explicit Congestion Notification (see http://en.wikipedia.org/wiki/Explicit_Congestion_Notification) net.inet.tcp.ecn.enable=1 # Flowtable - flow caching mechanism # Useful for routers #net.inet.flowtable.enable=1 #net.inet.flowtable.nmbflows=65535 # Extreme polling tuning #kern.polling.burst_max=1000 #kern.polling.each_burst=1000 #kern.polling.reg_frac=100 #kern.polling.user_frac=1 #kern.polling.idle_poll=0 # IPFW dynamic rules and timeouts tuning # Increase dyn_buckets till net.inet.ip.fw.curr_dyn_buckets is lower net.inet.ip.fw.dyn_buckets=65536 net.inet.ip.fw.dyn_max=65536 net.inet.ip.fw.dyn_ack_lifetime=120 net.inet.ip.fw.dyn_syn_lifetime=10 net.inet.ip.fw.dyn_fin_lifetime=2 net.inet.ip.fw.dyn_short_lifetime=10 # Make packets pass firewall only once when using dummynet # i.e. packets going thru pipe are passing out from firewall with accept #net.inet.ip.fw.one_pass=1 # shm_use_phys Wires all shared pages, making them unswappable # Use this to lessen Virtual Memory Manager's work when using Shared Mem. # Useful for databases #kern.ipc.shm_use_phys=1 /boot/loader.conf: # Accept filters for data, http and DNS requests # Usefull when your software uses select() instead of kevent/kqueue or when you under DDoS # DNS accf available on 8.0+ accf_data_load="YES" accf_http_load="YES" accf_dns_load="YES" # Async IO system calls aio_load="YES" # Adds NCQ support in FreeBSD # WARNING! all ad[0-9]+ devices will be renamed to ada[0-9]+ # 8.0+ only #ahci_load= #siis_load= # Increase kernel memory size to 3G. # # Use ONLY if you have KVA_PAGES in kernel configuration, and you have more than 3G RAM # Otherwise panic will happen on next reboot! # # It's required for high buffer sizes: kern.ipc.nmbjumbop, kern.ipc.nmbclusters, etc # Useful on highload stateful firewalls, proxies or ZFS fileservers # (FreeBSD 7.2+ amd64 users: Check that current value is lower!) #vm.kmem_size="3G" # Older versions of FreeBSD can't tune maxfiles on the fly #kern.maxfiles="200000" # Useful for databases # Sets maximum data size to 1G # (FreeBSD 7.2+ amd64 users: Check that current value is lower!) #kern.maxdsiz="1G" # Maximum buffer size(vfs.maxbufspace) # You can check current one via vfs.bufspace # Should be lowered/upped depending on server's load-type # Usually decreased to preserve kmem # (default is 200M) #kern.maxbcache="512M" # Sendfile buffers # For i386 only #kern.ipc.nsfbufs=10240 # syncache Hash table tuning net.inet.tcp.syncache.hashsize=1024 net.inet.tcp.syncache.bucketlimit=100 # Incresed hostcache net.inet.tcp.hostcache.hashsize="16384" net.inet.tcp.hostcache.bucketlimit="100" # TCP control-block Hash table tuning net.inet.tcp.tcbhashsize=4096 # Enable superpages, for 7.2+ only # Also read http://lists.freebsd.org/pipermail/freebsd-hackers/2009-November/030094.html vm.pmap.pg_ps_enabled=1 # Usefull if you are using Intel-Gigabit NIC #hw.em.rxd=4096 #hw.em.txd=4096 #hw.em.rx_process_limit="-1" # Also if you have ALOT interrupts on NIC - play with following parameters # NOTE: You should set them for every NIC #dev.em.0.rx_int_delay: 250 #dev.em.0.tx_int_delay: 250 #dev.em.0.rx_abs_int_delay: 250 #dev.em.0.tx_abs_int_delay: 250 # There is also multithreaded version of em drivers can be found here: # http://people.yandex-team.ru/~wawa/ # # for additional em monitoring and statistics use # `sysctl dev.em.0.stats=1 ; dmesg` # #Same tunings for igb #hw.igb.rxd=4096 #hw.igb.txd=4096 #hw.igb.rx_process_limit=100 # Some useful netisr tunables. See sysctl net.isr #net.isr.defaultqlimit=4096 #net.isr.maxqlimit: 10240 # Bind netisr threads to CPUs #net.isr.bindthreads=1 # Nicer boot logo =) loader_logo="beastie" And finally here is my additions to GENERIC kernel # Just some of them, see also # cat /sys/{i386,amd64,}/conf/NOTES # This one useful only on i386 #options KVA_PAGES=512 # You can play with HZ in environments with high interrupt rate (default is 1000) # 100 is for my notebook to prolong it's battery life #options HZ=100 # Polling is goot on network loads with high packet rates and low-end NICs # NB! Do not enable it if you want more than one netisr thread #options DEVICE_POLLING # Eliminate datacopy on socket read-write # To take advantage with zero copy sockets you should have an MTU of 8K(amd64) # (4k for i386). This req. is only for receiving data. # Read more in man zero_copy_sockets #options ZERO_COPY_SOCKETS # Support TCP sign. Used for IPSec options TCP_SIGNATURE options IPSEC # This ones can be loaded as modules. They described in loader.conf section #options ACCEPT_FILTER_DATA #options ACCEPT_FILTER_HTTP # Adding ipfw, also can be loaded as modules options IPFIREWALL options IPFIREWALL_VERBOSE options IPFIREWALL_VERBOSE_LIMIT=10 options IPFIREWALL_DEFAULT_TO_ACCEPT options IPFIREWALL_FORWARD # Adding kernel NAT options IPFIREWALL_NAT options LIBALIAS # Traffic shaping options DUMMYNET # Divert, i.e. for userspace NAT options IPDIVERT # This is for OpenBSD's pf firewall device pf device pflog # pf's QoS - ALTQ options ALTQ options ALTQ_CBQ # Class Bases Queuing (CBQ) options ALTQ_RED # Random Early Detection (RED) options ALTQ_RIO # RED In/Out options ALTQ_HFSC # Hierarchical Packet Scheduler (HFSC) options ALTQ_PRIQ # Priority Queuing (PRIQ) options ALTQ_NOPCC # Required for SMP build # Pretty console # Manual can be found here http://forums.freebsd.org/showthread.php?t=6134 #options VESA #options SC_PIXEL_MODE # Disable reboot on Ctrl Alt Del #options SC_DISABLE_REBOOT # Change normal|kernel messages color options SC_NORM_ATTR=(FG_GREEN|BG_BLACK) options SC_KERNEL_CONS_ATTR=(FG_YELLOW|BG_BLACK) # More scroll space options SC_HISTORY_SIZE=8192 # Adding hardware crypto device device crypto device cryptodev # Useful network interfaces device vlan device tap #Virtual Ethernet driver device gre #IP over IP tunneling device if_bridge #Bridge interface device pfsync #synchronization interface for PF device carp #Common Address Redundancy Protocol device enc #IPsec interface device lagg #Link aggregation interface device stf #IPv4-IPv6 port # Also for my notebook, but may be used with Opteron #device amdtemp # Support for ECMP. More than one route for destination # Works even with default route so one can use it as LB for two ISP # For now code is unstable and panics (panic: rtfree 2) on route deletions. #options RADIX_MPATH # Multicast routing #options MROUTING #options PIM # DTrace options KDTRACE_HOOKS # all architectures - enable general DTrace hooks options DDB_CTF # all architectures - kernel ELF linker loads CTF data #options KDTRACE_FRAME # amd64-only # Adaptive spining in lockmgr (8.x+) # See http://www.mail-archive.com/[email protected]/msg10782.html options ADAPTIVE_LOCKMGRS # UTF-8 in console (9.x+) #options TEKEN_UTF8 #options TEKEN_XTERM # NCQ support # WARNING! all ad[0-9]+ devices will be renamed to ada[0-9]+ #options ATA_CAM # FreeBSD 9+ # Deadlock resolver thread # For additional information see http://www.mail-archive.com/[email protected]/msg18124.html #options DEADLKRES PS. Also most of FreeBSD's limits can be monitored by # vmstat -z and # limits PPS. variety of network counters can be monitored via # netstat -s In FreeBSD-9 netstat's -Q option appeared, try following command to display netisr stats # netstat -Q PPPS. also see # man 7 tuning PPPPS. I wanted to thank FreeBSD community, especially author of nginx - Igor Sysoev, nginx-ru@ and FreeBSD-performance@ mailing lists for providing useful information about FreeBSD tuning. So here is the question: What tunings are you using on yours FreeBSD servers? You can also post your /etc/sysctl.conf, /boot/loader.conf, kernel options, etc with description of its' meaning (do not copy-paste from sysctl -d). Don't forget to specify server type (web, smb, gateway, etc) Let's share experience!

  Read the article

• SQL Server v.Next (Denali) : Changes to performance counters

  - by AaronBertrand

  In a previous post about changed system objects in Denali , I talked about the changes to memory-related DMVs due to underlying changes in the memory manager. The SQLOS team has posted a great introduction to these changes , and they plan to post more details in future posts. In the meantime, and due to a question yesterday from Tom LaRock ( blog | twitter ): ...I thought I would tell you about some performance counters that have changed between SQL Server 2008 R2 and Denali - most of which involve...(read more)

  Read the article

• Get Something For Nothing - Benefit From Free Web Page Counters

  Offers for free web page counters are everywhere. A free web page counter provides beneficial information. Get one, at least one.

  Read the article

• Why VM snapshots are affecting performance?

  - by Samselvaprabu

  I read in one of the VMware KB article says that snapshots will directly proportional to VM performance. But my team keep asking me how snapshots can affect performance. I would like to give them solid reason behind the statement that snapshots are performance killers. Can any one explain a little bit theory behind why actually snapshots are affecting the performance? Is it just because Disk I/O rate of hard disk would be slow?

  Read the article

• Performance monitoring on Linux/Unix

  - by ervingsb

  I run a few Windows servers and (Debian and Ubuntu) Linux and AIX servers. I would like to continously monitor performance on these systems in order to easily identify bottlenecks as well as to have an overview of the general activity on the servers. On Windows, I use Windows Performance Monitor (perfmon) for this. I set up these counters: For bottlenecks: Processor utilization : System\Processor Queue Length Memory utilization : Memory\Pages Input/Sec Disk Utilization : PhysicalDisk\Current Disk Queue Length\driveletter Network problems: Network Interface\Output Queue Length\nic name For general activity: Processor utilization : Processor\% Processor Time_Total Memory utilization : Process\Working Set_Total (or per specific process) Memory utilization : Memory\Available MBytes Disk Utilization : PhysicalDisk\Bytes/sec_Total (or per process) Network Utilization : Network Interface\Bytes Total/Sec\nic name (More information on the choice of these counters on: http://itcookbook.net/blog/windows-perfmon-top-ten-counters ) This works really well. It allows me to look in one place and identify most common bottlenecks. So my question is, how can I do something equivalent (or just very similar) on Linux servers? I have looked a bit on nmon (http://www.ibm.com/developerworks/aix/library/au-analyze_aix/) which is a free performance monitoring tool developed for AIX but also availble for Linux. However, I am not sure if nmon allows me to set up the above counters. Maybe it is because Linux and AIX does not allow monitoring these exact same measures. Is so, which ones should I choose and why? If nmon is not the tool to use for this, then what do you recommend?

  Read the article

• Low graphics performance with Intel HD graphics

  - by neil

  hey, my laptop should be capable of running some games fine but doesn't. Examples are egoboo and tome. http://www.ebuyer.com/product/237739 this is my laptop. I tried the gears test and i only get 60 FPS, on IRC they said thats a big issue and should try the forums. I am using Ubuntu 11.04 and was told I should have the newest drivers. neil@neil-K52F:~$ /usr/lib/nux/unity_support_test --print OpenGL vendor string: Tungsten Graphics, Inc OpenGL renderer string: Mesa DRI Intel(R) Ironlake Mobile GEM 20100330 DEVELOPMENT OpenGL version string: 2.1 Mesa 7.10.2 Not software rendered: yes Not blacklisted: yes GLX fbconfig: yes GLX texture from pixmap: yes GL npot or rect textures: yes GL vertex program: yes GL fragment program: yes GL vertex buffer object: yes GL framebuffer object: yes GL version is 1.4+: yes Unity supported: yes

  Read the article

• SQLAuthority News – SQL Server Technical Article – The Data Loading Performance Guide

  - by pinaldave

  The white paper describes load strategies for achieving high-speed data modifications of a Microsoft SQL Server database. “Bulk Load Methods” and “Other Minimally Logged and Metadata Operations” provide an overview of two key and interrelated concepts for high-speed data loading: bulk loading and metadata operations. After this background knowledge, white paper describe how these methods can be [...]

  Read the article

• SQLAuthority News – Hyderabad Techies February Fever Feb 11, 2010 – Indexing for Performance

  - by pinaldave

  I recently presented in Hyderabad User Group on the subject of The Other Side of SQL Server Index: Advanced Solutions to Ancient Problem , you can read more about this event here SQLAuthority News – MUGH – Microsoft User Group Hyderabad – Feb 2, 2010 Session Review. I really had great time talking about Index [...]

  Read the article

< Previous Page | 3 4 5 6 7 8 9 10 11 12 13 14  | Next Page >