Search Results

Search found 14282 results on 572 pages for 'performance counter'.

Page 17/572 | < Previous Page | 13 14 15 16 17 18 19 20 21 22 23 24  | Next Page >

• Performance of file operations on thousands of files on NTFS vs HFS, ext3, others

  - by peterjmag

  [Crossposted from my Ask HN post. Feel free to close it if the question's too broad for superuser.] This is something I've been curious about for years, but I've never found any good discussions on the topic. Of course, my Google-fu might just be failing me... I often deal with projects involving thousands of relatively small files. This means that I'm frequently performing operations on all of those files or a large subset of them—copying the project folder elsewhere, deleting a bunch of temporary files, etc. Of all the machines I've worked on over the years, I've noticed that NTFS handles these tasks consistently slower than HFS on a Mac or ext3/ext4 on a Linux box. However, as far as I can tell, the raw throughput isn't actually slower on NTFS (at least not significantly), but the delay between each individual file is just a tiny bit longer. That little delay really adds up for thousands of files. (Side note: From what I've read, this is one of the reasons git is such a pain on Windows, since it relies so heavily on the file system for its object database.) Granted, my evidence is merely anecdotal—I don't currently have any real performance numbers, but it's something that I'd love to test further (perhaps with a Mac dual-booting into Windows). Still, my geekiness insists that someone out there already has. Can anyone explain this, or perhaps point me in the right direction to research it further myself?

  Read the article

• Outbound HTTP performance tuning recommendations

  - by Richard Gadsden

  I'll detail my exact setup below, but general recommendations for a better web-browsing experience will be useful. A nice checklist of things to try would be great! I have 600 users on a single site with an 8MB leased line. I get a lot of moans about the performance of "the internet" (ie web-browsing). What recommendations do the community have for speeding things up without just throwing more bandwidth at it? I expect I will end up buying some more, but good management tips are always valuable. My setup is this: Cisco PIX (515E) firewall on the edge of the network. It's just doing some basic NAT, and opening up a handful of ports to various bastion hosts (aka DMZ servers). The DMZ is just a switch that the servers are plugged into. ISA 2006 Enterprise array (two servers) connecting DMZ to the internal LAN, with WebSense Web Security filtering HTTP traffic so users can't look at porn or waste bandwidth on YouTube during working hours. I've done a few things - I've just switched my internal DNS over to use root hints, which halved DNS query latency from 500ms to 250ms. Well worth doing. I'm trying to cache more aggressively, but so much more of the internet is AJAXy and doesn't cache very well as compared to five years ago. Plus the 70GB of cache which felt like a lot a few years ago really isn't any more. I'm getting about 45% cache hits by number of requests, but only about 22% by size, ie larger objects are less likely to be cached. Latency seems to be part of the problem. Is that attributable to the bandwidth problem, or are there things I can look at to try to reduce latency even on heavily-loaded bandwidth?

  Read the article

• SAN performance issues storing SQL Server tempdb on a SAN that's being backed up

  - by user42724

  I'm afraid I don't know much about SAN's so please forgive my lack of detail or technical terms. As a developer I've just completed and put on an existing production system a new application but it would appear to have tipped the scales regarding the performance of the backups being taken from the SAN. As I understand it there's a mirror of the SAN being taken usually constantly at the block-level. However, there seem to be so many new writes to the disk that the SAN mirroring/backup process can no longer keep up. I believe I've narrowed this down to SQL Servers tempdb which exists on a drive that contributes the largest portion of the problem! In fact I think tempdb has be contributing the largest portion of the issues all along regardless of my application! My question therefore is whether the tempdb should ever be mirrored or backed on the SAN and whether anyone else has gone through this sort of pain already? I'm wondering whether it's a best practise to make sure that tempdb is never mirrored on a SAN simply because any writes to it don't need to be saved. This also raises a slightly connected question - is it better to rely on SQL Servers built-in database backups tools (DB in full-recovery mode with full/differential and transaction log backups) or, as is the case with our application, SQL server is in simple recovery mode and never backed up since the SAN is mirrored and backed up? Many thanks

  Read the article

• Strange performance differences in read/write from/to USB flash drive

  - by Mario De Schaepmeester

  When copying files from my 8GB USB 2.0 flash drive with Windows 7 to a traditional hard drive, the average speed is between 25 and 30 MB/s. When doing the reverse, copying to the USB drive, the speed is 5MB/s average. I have tested this with about 4.5GB of files, a mixture of smaller and larger ones. The observations were the same on both FAT32 and exFAT file systems on the USB drive, NTFS on the internal hard disk. I don't think I can be mistaken in saying that flash memory has a lot higher performance than a spinning hard drive in both terms of reading and writing. For both memory types, reading should be faster than writing too. Now I wonder, how can it be that copying files from a fast read memory to a faster write memory is actually slower than copying files from a fast read memory to a slow write memory? I think that the files are stored in RAM before being copied over too, and there's caching as well, but I don't see how even that could tip the balance. It can only be in the advantage of writing to the USB drive, since it is "closer" to the SATA system than the USB port and it will receive data from the internal SATA HDD faster. Perhaps my way of thinking is all wrong or it just depends on the manufacturer of the USB pen. But I am curious.

  Read the article

• Poor gaming performance with hyper-v installed in windows 8

  - by SnowCrash

  I am getting very poor gaming performance on my Windows 8 host OS with Hyper-V installed but no guest machines running. For example World of Tanks reports 60-70 FPS without Hyper-V installed and 4-14 FPS with it installed. A similar, dramatic, hit is observed in several other games so the issue is not WoT specific. To make the point clear, I am not trying to run games in a virtual machine. I don't even have a VM running while observing this effect. I simply have the Hyper-V feature installed. My system specs: AMD Phenom II 965 (3.4 GHz) AMD Radeon 6950 2GB (XFX Double D HD-695X-CDFC) 16GB DDR3 1333 AMD 790GX chipset Mainboard (Gigabyte GA-MA790GPT-UD3H) I have tried every AMD driver from 12.8 to the current 12.11beta8, virtualization is enabled in the BIOS settings, the onboard 3300HD video device is disabled in BIOS and I have read the MSDN blog entry here regarding a similar issue in Server 2008 that was resolved in 2008 R2 (and hopefully not regressed in Win 8). I'd like to be able to use Hyper-V for development and testing at home (I am a sysadmin/software developer professionally). If, however, I can't also use my home system for entertainment I'll have to scrap those plans.

  Read the article

• SSD, AHCI and write performance

  - by Dan

  We've started to deploy SSD drives to our developers workstations. At this moment we're having the unpleasant surprise that the systems using the new SSDs often freeze, with the HDD activity led blinking or being continuously on. Benchmarks shows read speeds around 180 MB/s, but write speeds around 5 MB/s. All developers are using Windows 7 Enterprise, 64 bit, SP1. One of our developers suggested (based on his experience) the following sequence: backup the workstation use a tool to completely erase the SSD make sure AHCI is enabled in BIOS install Windows restore from backup So far, this procedure seems to work (we're still testing, but write speed seems to be 120 MB/s). There are some questions in this context: why do we have to completely reinstall Windows? Is it possible to clean the SSD without reinstalling Windows? Is there a reliable tool? If AHCI was disabled when Windows was installed and we enable it, shouldn't this be enough to correct the write performance issue? If we have to completely erase the SSDs, does this mean the SSDs we've received were used before (SH)? I'm wondering this because the package I've got was open (I didn't think about it at that time, as I considered one of my coworkers simply took a peek inside the package). Has anyone seen a similar problem before?

  Read the article

• Poor Write Performance in VM inside Proxmox PVE 2.0

  - by sorsenne

  I am running a PVE 2.0 on a decent Hardware (2 SATA HDDs as RAID1, 12GB RAM, i7 CPU) but the I/O Performance is very poor inside the VM (Ubuntu 11.10 Server). The very same VM was copied to another Server running simply Ubuntu Server with KVM and had better I/O Perf. this is how the HDD is shown in the Guest: ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300) ata1.00: ATA-8: ST3000DM001-9YN166, CC49, max UDMA/133 ata1.00: 5860533168 sectors, multi 16: LBA48 NCQ (depth 31/32), AA ata1.00: configured for UDMA/133 scsi 0:0:0:0: Direct-Access ATA ST3000DM001-9YN1 CC49 PQ: 0 ANSI: 5 sd 0:0:0:0: [sda] 5860533168 512-byte logical blocks: (3.00 TB/2.72 TiB) sd 0:0:0:0: [sda] 4096-byte physical blocks sd 0:0:0:0: [sda] Write Protect is off sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA I tested with DD: $ dd bs=1M count=128 if=/dev/zero of=test conv=fdatasync 128+0 records in 128+0 records out 134217728 bytes (134 MB) copied, 19.2222 s, 7.0 MB/s on the Host, this same Test will result with 156 MB/s in average. PS: I am using VirtIO and see no error in dmesg.

  Read the article

• Very poor SCSI hd performance on IBM x336 with LSI 1030 RAID1

  - by David Tschoepe

  I'm experiencing very poor performance on an IBM x336 server with dual 73GB 15k hard drives on a U320 controller, LSI 1030. We're getting maybe 3.5MB/sec max (per HD Tune utility). It should be over 100MB/sec at least, I would think (another x335 box is running 70-80MB/sec). The server was recently setup and didn't really notice the problem, but may have been there from the beginning, so not sure. I have installed the IBM ServerRAID Windows utility. The server is running Windows 2008 R2 Web edition (if that matters). I thought maybe one of the drives was bad, so far I have removed one of the drives out of the array and tested again, but still the same results. I'm waiting for the RAID1 to resync and I will try pulling the other drive next. I've also used the ServerRAID utility but haven't noticed anything in there that might indicate a problem. Not sure if I'm on the right path here. So looking for some advice to track this down.

  Read the article

• performance wise htaccess

  - by purpler

  hese's the my htaccess template, i wonder if anything could be added to increase website performance.. # Defaults AddDefaultCharset UTF-8 DefaultLanguage en-US ServerSignature Off FileETag None Header unset ETag Options -MultiViews #Options All -Indexes # Force the latest IE version or ChromeFrame <IfModule mod_setenvif.c> <IfModule mod_headers.c> BrowserMatch MSIE ie Header set X-UA-Compatible "IE=Edge,chrome=1" env=ie </IfModule> </IfModule> # Proxy X-UA Setup <IfModule mod_headers.c> Header append Vary User-Agent </IfModule> #Rewrites Options +FollowSymlinks RewriteEngine On RewriteBase / # Redirect to non-WWW RewriteCond %{HTTPS} !=on RewriteCond %{HTTP_HOST} ^www\.(.+)$ [NC] RewriteRule ^(.*)$ http://%1/$1 [R=301,L] # Redirect to WWW RewriteCond %{HTTP_HOST} ^domain.com RewriteRule (.*) http://www.domain.com/$1 [R=301,L] # Redirect index to root RewriteRule ^(.*)index\.(php|html)$ /$1 [R=301,L] # Caching ExpiresActive On ExpiresDefault A0 Header set Cache-Control "public" # 1 Year Long Cache <FilesMatch "\.(flv|fla|ico|pdf|avi|mov|ppt|doc|mp3|wmv|wav|png|jpg|jpeg|gif|swf|js|css|ttf|eot|woff|svg|svgz)$"> ExpiresDefault A31622400 </FilesMatch> # Proxy Caching <FilesMatch "\.(css|js|png)$"> ExpiresDefault A31622400 Header set Cache-Control "private" </FilesMatch> # Protect against DOS attacks by limiting file upload size LimitRequestBody 10240000 # Proper SVG serving AddType image/svg+xml svg svgz AddEncoding gzip svgz # GZip Compression <IfModule mod_deflate.c> <FilesMatch "\.(php|html|css|js|xml|txt|ttf|otf|eot|svg)$" > SetOutputFilter DEFLATE </FilesMatch> </IfModule> # Error page ErrorDocument 404 /404.html # Deny access to sensitive files <FilesMatch "\.(htaccess|ini|log|psd)$"> Order Allow,Deny Deny from all </FilesMatch>

  Read the article

• Slow performance of MySQL database on one server and fast on another one, with similar configurations

  - by Alon_A

  We have a web application that run on two servers of GoDaddy. We experince slow preformance on our production server, although it has stronger hardware then the testing one, and it is dedicated. I'll start with the configurations. Testing: CentOS Linux 5.8, Linux 2.6.18-028stab101.1 on i686 Intel(R) Xeon(R) CPU L5609 @ 1.87GHz, 8 cores 60 GB total, 6.03 GB used Apache/2.2.3 (CentOS) MySQL 5.5.21-log PHP Version 5.3.15 Production: CentOS Linux 6.2, Linux 2.6.18-028stab101.1 on x86_64 Intel(R) Xeon(R) CPU L5410 @ 2.33GHz, 8 cores 120 GB total, 2.12 GB used Apache/2.2.15 (CentOS) MySQL 5.5.27-log - MySQL Community Server (GPL) by Remi PHP Version 5.3.15 We are running the same code on both servers. The Problem We have some function that executes ~30000 PDO-exec commands. On our testing server it takes about 1.5-2 minutes to complete and our production server it can take more then 15 minutes to complete. As you can see here, from qcachegrind: Researching the problem, we've checked the live graphs on phpMyAdmin and discovered that the MySQL server on our testing server was preforming at steady level of 1000 execution statements per 2 seconds, while the slow production MySQL server was only 250 executions statements per 2 seconds and not steady at all, jumping from 0 to 250 every seconds. You can clearly see it in the graphs: Testing server: Production server: You can see here the comparison between both of the configuration of the MySQL servers.Left is the fast testing and right is the slow production. The differences are highlighted, but I cant find anything that can cause such a behavior difference, as the configs are mostly the same. Maybe you can see something that I cant see. Note that our tables are all InnoDB, so the MyISAM difference is (probably) not relevant. Maybe it is the MySQL Community Server (GPL) that is installed on the production server that can cause the slow performance? Or maybe it needs to be configured differently for 64bit ? I'm currently out of ideas...

  Read the article

• Disk usage on IIS, PHP5, performance problems.

  - by Jacob84

  Hi everybody, I'm quite worried with a performance problem that I'm facing in one of our production servers. I'm working for a hosting company, so you can imagine how heterogeneous the applications runnning here are. All started with a call of a client complaining about the speed loading a Joomla. The setup is IIS6 (Windows 2003) with PHP5 and FAST CGI wich normally works pretty well. I've tested the loading time and indeed, he was right. 7 or 8 seconds to load, when usually this can be accomplished in 2. Seeing this results, I started to check first CPU and RAM. Everithing normal, 2GB of RAM free, 3%-8% of CPU activity. That's what I call a relaxed server ;). Unfortunately, digging a little deeper I've found the 'PhysicalDisk' counters quite high (above 10), specially the read queues. I've used Process Explorer to see wich of those processes has the higher deltas, but everything seemed normal. As the problem is specially related to PHP pages, I've checked specific IIS counters, as Actual connections, Number of CGI requeriments and Number of ISAPI requeriments. CGI -> 3 to 7 ISAPI -> 5 to 9 Connections-> 90 to 120 (wich appears at the top of the graph) More than a solution (I know this is hard to find), I would like to know if you have an specifical methodology to face this kind of problems. Thanks a lot, as always.

  Read the article

• Photoshop CS5 performance over network drive (cifs)

  - by grub

  Hello Everyone I did install a QNAP NAS TS410 for a customer (professional photographer) with 3 Hitachi Deskstar 7200rpm 2TB disk configured as RAID5. The NAS and the workstations are connected over a Gigabit network. He and his co-worker are accessing the photos (about 1TB of photos) over a mapped network drive from their windows machines (Windows XP - 32bit and Windows 7 Ultimate - 32bit). Both are using Photoshop CS5 to edit the photos. The problem is that to save a edited photo takes a really long time, it takes about 3 times as long to save a photo as to open it. After some tests I can exclude the network, the NAS and the windows machines as source of the issue. I think the problem is the Photoshop software and its handling of the network drives. Officially network drives are not supported by Adobe. I do not have any experience with the Adobe products, especially with Adobe Photoshop CS5. What are your recommendation to solve the performance issue? Should my customer copy the photos to the local drive, edit them and upload them again to the network drive or is Adobe Drive or Adobe Version Cue the answer? One requirement is that the photos need to be accessible / editable from both computers even when one of them is offline. Adobe Version Cue needs a dedicated service running to be usable, so this solution is not possible as far as I understand the Cue software. Thank you for your input to this issue and have a nice day :-) Greetings grub

  Read the article

• Performance decrease in every game and application

  - by Márk Vincze

  When I start a game, initially it runs smoothly, but after a couple of minutes, the performance gradually decreases to the point of being unplayable (1-2 FPS). The sound also starts to lag at this point. This does not happen every time I start my PC, usually exiting the game, rebooting, then starting the game again solves the problem, and I can play with perfect FPS for as long as I want. I could not find any deterministic reason when this happens and when doesn't. It happens in every game I tried (SWTOR, Diablo 3, Skyrim), and not even games, but simple applications like a browser or the Control Panel can get unusably slow. This is a brand new PC I bought three months ago, and this problem occurs since the first day I've been using it. Could you provide any advice how to further diagnose the problem? I tried to reinstall Windows, and tried different video card drivers, but it did not help. It would be important to know whether this is a hardware or software problem, because I can use the warranty if it is a hardware issue. (I did not want to return the PC yet, because I can't reproduce the issue deterministically.) Spec of the pc: Motherboard: ASROCK H61M-HVS CPU: INTEL Core i3-2120 3.30GHz 1155 BOX Memory: KINGMAX 4096MB DDR3 1333MHz KIT Video card: GIGABYTE GV-R685OC-1GD HD6850 1GB GDDR5 PCIE HDD: SEAGATE 500GB Barracuda 7200rpm 16MB SATA3 ST500DM002 I am using Windows 7 64 bit. Thanks a lot in advance!

  Read the article

• file read performance degrades as number of files increases

  - by bfallik-bamboom

  We're observing poor file read IO results that we'd like to better understand. We can use fio to write 100 files with a sustained aggregate throughput of ~700MB/s. When we switch the test to read instead of write, the aggregate throughput is only ~55MB/s. The drop seems related to the number of files since the throughput for read and write are comparable for a single file then diverge proportionally as we increase the number of files. The test server has 24 CPU cores, 48GB of memory, and is running CentOS 6.0. The disk hardware is a RAID 6 array with 12 disks and a Dell H800 controller. This device is partitioned with ext4 using the default settings. Increasing the readahead (using blockdev) improves the read throughput significantly but it still doesn't match write speed. For instance, increasing the readahead from 128KB to 1M improved the read throughput to ~145MB/s. Is this a known performance issue in our OS/disk/filesystem configuration? If so, how can we tell? If not, what tools or tests can we use to further isolate the issue? Thanks.

  Read the article

• SQL SERVER – 3 Online SQL Courses at Pluralsight and Free Learning Resources

  - by pinaldave

  Usain Bolt is an inspiration for all. He broke his own record multiple times because he wanted to do better! Read more about him on wikipedia. He is great and indeed fastest man on the planet. Usain Bolt – World’s Fastest Man “Can you teach me SQL Server Performance Tuning?” This is one of the most popular questions which I receive all the time. The answer is YES. I would love to do performance tuning training for anyone, anywhere.  It is my favorite thing to do, and it is my favorite thing to train others in.  If possible, I would love to do training 24 hours a day, 7 days a week, 365 days a year.  To me, it doesn’t feel like a job. Of course, as much as I would love to do performance tuning 24/7/365, obviously I am just one human being and can only be in one place t one time.  It is also very difficult to train more than one person at a time, and it is difficult to train two or more people at a time, especially when the two people are at different levels.  I am also limited by geography.  I live in India, and adjust to my own time zone.  Trying to teach a live course from India to someone whose time zone is 12 or more hours off of mine is very difficult.  If I am trying to teach at 2 am, I am sure I am not at my best! There was only one solution to scale – Online Trainings. I have built 3 different courses on SQL Server Performance Tuning with Pluralsight. Now I have no problem – I am 100% scalable and available 24/7 and 365. You can make me say the same things again and again till you find it right. I am in your mobile, PC as well as on XBOX. This is why I am such a big fan of online courses.  I have recorded many performance tuning classes and you can easily access them online, at your own time.  And don’t think that just because these aren’t live classes you won’t be able to get any feedback from me.  I encourage all my viewers to go ahead and ask me questions by e-mail, Twitter, Facebook, or whatever way you can get a hold of me. Here are details of three of my courses with Pluralsight. I suggest you go over the description of the course. As an author of the course, I have few FREE codes for watching the free courses. Please leave a comment with your valid email address, I will send a few of them to random winners. SQL Server Performance: Introduction to Query Tuning  SQL Server performance tuning is an art to master – for developers and DBAs alike. This course takes a systematic approach to planning, analyzing, debugging and troubleshooting common query-related performance problems. This includes an introduction to understanding execution plans inside SQL Server. In this almost four hour course we cover following important concepts. Introduction 10:22 Execution Plan Basics 45:59 Essential Indexing Techniques 20:19 Query Design for Performance 50:16 Performance Tuning Tools 01:15:14 Tips and Tricks 25:53 Checklist: Performance Tuning 07:13 The duration of each module is mentioned besides the name of the module. SQL Server Performance: Indexing Basics This course teaches you how to master the art of performance tuning SQL Server by better understanding indexes. In this almost two hour course we cover following important concepts. Introduction 02:03 Fundamentals of Indexing 22:21 Practical Indexing Implementation Techniques 37:25 Index Maintenance 16:33 Introduction to ColumnstoreIndex 08:06 Indexing Practical Performance Tips and Tricks 24:56 Checklist : Index and Performance 07:29 The duration of each module is mentioned besides the name of the module. SQL Server Questions and Answers This course is designed to help you better understand how to use SQL Server effectively. The course presents many of the common misconceptions about SQL Server, and then carefully debunks those misconceptions with clear explanations and short but compelling demos, showing you how SQL Server really works. In this almost 2 hours and 15 minutes course we cover following important concepts. Introduction 00:54 Retrieving IDENTITY value using @@IDENTITY 08:38 Concepts Related to Identity Values 04:15 Difference between WHERE and HAVING 05:52 Order in WHERE clause 07:29 Concepts Around Temporary Tables and Table Variables 09:03 Are stored procedures pre-compiled? 05:09 UNIQUE INDEX and NULLs problem 06:40 DELETE VS TRUNCATE 06:07 Locks and Duration of Transactions 15:11 Nested Transaction and Rollback 09:16 Understanding Date/Time Datatypes 07:40 Differences between VARCHAR and NVARCHAR datatypes 06:38 Precedence of DENY and GRANT security permissions 05:29 Identify Blocking Process 06:37 NULLS usage with Dynamic SQL 08:03 Appendix Tips and Tricks with Tools 20:44 The duration of each module is mentioned besides the name of the module. SQL in Sixty Seconds You will have to login and to get subscribed to the courses to view them. Here are my free video learning resources SQL in Sixty Seconds. These are 60 second video which I have built on various subjects related to SQL Server. Do let me know what you think about them? Here are three of my latest videos: Identify Most Resource Intensive Queries – SQL in Sixty Seconds #028 Copy Column Headers from Resultset – SQL in Sixty Seconds #027 Effect of Collation on Resultset – SQL in Sixty Seconds #026 You can watch and learn at your own pace.  Then you can easily ask me any questions you have.  E-mail is easiest, but for really tough questions I’m willing to talk on Skype, Gtalk, or even Facebook chat.  Please do watch and then talk with me, I am always available on the internet! Here is the video of the world’s fastest man.Usain St. Leo Bolt inspires us that we all do better than best. We can go the next level of our own record. We all can improve if we have a will and dedication.  Watch the video from 5:00 mark. Reference: Pinal Dave (http://blog.sqlauthority.com) Filed under: PostADay, SQL, SQL Authority, SQL in Sixty Seconds, SQL Performance, SQL Query, SQL Server, SQL Tips and Tricks, SQL Training, SQLServer, T SQL, Technology, Video

  Read the article

• VMWare Esxi Looking for Bottlenecks

  - by nextgenneo

  I have a VMWare ESxi box, 22GB ram, Dual Quad Core Xeon, 2 Sas drives + Write caching raid controller etc. Anyways, have about 30 small XP VM's running on it and starting to get some very slow boot times and other performance issues. I THINK its I/O but looking at the graphs not too sure what to look for. Any ideas on what to look for would be appreciated. Here is the data I've got so far: (I feel like my IO is high but not sure what to bench it against)

  Read the article

• Is it OK to run perfmon on production servers? And why?

  - by Bill Paetzke

  Or should perfmon be limited to a Dev/QA server with load tests that simulate production activity? I'd like to run perfmon for a two days (like Sql Server master Brent Ozar suggests) to get an overall feel of my web app's database performance.

  Read the article

• Baseline / Benchmark Physical and virtual server performance

  - by EyeonTech

  I am setting up a new server and there are some options. I want to perform some benchmarks and I need your help in determining the best tools and if possible run pre-configured benchmarks designed for SQL servers on Windows Server 2008/2012. Step 1. Run a performance monitor on the current Live SQL server (Windows Server 2008 Virtual machine running on ESXi. New server Hardware rundown: Intel® Server System R1304BTLSHBN - 1U Rack, LGA1155 http://ark.intel.com/products/53559/Intel-Server-System-R1304BTLSHBN Intel Xeon E3-1270V2 2x Intel SSD 330 Series 240GB 2.5in SATA 6Gb/s 25nm 1x WD 2TB WD2002FAEX 2TB 64M SATA3 CAVIAR BLACK 4x 8GB 1333MHz DDR3 ECC CL9 DIMM There are several options for configurations and I want to benchmark some of them and share the results. Option 1. Configure 2x SSDs at RAID 0. Install Windows Server 2008 directly to the 2TB WD Caviar HDD. Store Database files on the RAID 0 Volume. Benchmark the OS direct on the hardware as an SQL Server. Store SQL Backup databases on the 2TB WD Caviar HDD. Option 2. Configure 2x SSDs at RAID 0. Install Windows Server 2012 directly to the 2TB WD Caviar HDD. Install Hyper-V. Install the SQL Server (Server 2008) as a virtual machine. Store the Virtual Hard Disks on the SSDs. Option 3. Configure 2x SSDs at RAID 0. Install VMWare ESXi on a partition of the 2TB WD Caviar HDD. Install the SQL Server (Server 2008) as a virtual machine. Store the Virtual Hard Disks on the SSDs. I have a few tools in mind from http://technet.microsoft.com/en-us/library/cc768530(v=bts.10).aspx. Any tools with pre-configured test would be fantastic. Specifically if there are pre-configured perfmon sets avaliable. Any opinions on the setup to gain the best results is welcome. Thanks in advance.

  Read the article

• MySQL performance over a (local) network much slower than I would expect

  - by user15241

  MySQL queries in my production environment are taking much longer than I would expect them too. The site in question is a fairly large Drupal site, with many modules installed. The webserver (Nginx) and database server (mysql) are hosted on separated machines, connected by a 100mbps LAN connection (hosted by Rackspace). I have the exact same site running on my laptop for development. Obviously, on my laptop, the webserver and database server are on the same box. Here are the results of my database query times: Production: Executed 291 queries in 320.33 milliseconds. (homepage) Executed 517 queries in 999.81 milliseconds. (content page) Development: Executed 316 queries in 46.28 milliseconds. (homepage) Executed 586 queries in 79.09 milliseconds. (content page) As can clearly be seen from these results, the time involved with querying the MySQL database is much shorter on my laptop, where the MySQL server is running on the same database as the web server. Why is this?! One factor must be the network latency. On average, a round trip from from the webserver to the database server takes 0.16ms (shown by ping). That must be added to every singe MySQL query. So, taking the content page example above, where there are 517 queries executed. Network latency alone will add 82ms to the total query time. However, that doesn't account for the difference I am seeing (79ms on my laptop vs 999ms on the production boxes). What other factors should I be looking at? I had thought about upgrading the NIC to a gigabit connection, but clearly there is something else involved. I have run the MySQL performance tuning script from http://www.day32.com/MySQL/ and it tells me that my database server is configured well (better than my laptop apparently). The only problem reported is "Of 4394 temp tables, 48% were created on disk". This is true in both environments and in the production environment I have even tried increasing max_heap_table_size and Current tmp_table_size to 1GB, with no change (I think this is because I have some BLOB and TEXT columns).

  Read the article

• PHP OOP class Sensative To Counter field name !

  - by Mac Taylor

  hey guys recently i managed to write a class for my stories , and everything is fine , unless counter field that stores page's hits here is my class : class nk_posts { var $data = array(); public function _data() { global $db; $result = $db->sql_query(" SELECT bt_stories.*, bt_tags.*, bt_topics.*, group_concat(DISTINCT bt_tags.tag ) as mytags, group_concat(DISTINCT bt_topics.topicname ) as mytopics FROM bt_stories,bt_tags,bt_topics WHERE CONCAT( ' ', bt_stories.tags, ' ' ) LIKE CONCAT( '%', bt_tags.tid, '%' ) AND CONCAT( ' ', bt_stories.associated, ' ' ) LIKE CONCAT( '%', bt_topics.topicid, '%' ) AND time<=now() AND section='news' AND approved='1' GROUP BY bt_stories.sid ORDER BY bt_stories.sid DESC "); while ($this->data = $db->sql_fetchrow($result)) { $this->sid = $this->data['sid']; $this->title = $this->data['title']; $this->counter = $this->data['counter']; //------Rest of Fields ------ $this->_output(); } } public function _output() { themeindex( $this->sid, $this->title, $this->counter, //------Rest of Fields ------ ); } } problem this class can't show counter filed value , but if i change counter field name to other thing like hit , .. everything goes fine im sure its okay if i write it in normal php mysql way , but i need this to be in OOP way any comment why it's sensitive to counter field name ?!

  Read the article

• Performance Tuning a High-Load Apache Server

  - by futureal

  I am looking to understand some server performance problems I am seeing with a (for us) heavily loaded web server. The environment is as follows: Debian Lenny (all stable packages + patched to security updates) Apache 2.2.9 PHP 5.2.6 Amazon EC2 large instance The behavior we're seeing is that the web typically feels responsive, but with a slight delay to begin handling a request -- sometimes a fraction of a second, sometimes 2-3 seconds in our peak usage times. The actual load on the server is being reported as very high -- often 10.xx or 20.xx as reported by top. Further, running other things on the server during these times (even vi) is very slow, so the load is definitely up there. Oddly enough Apache remains very responsive, other than that initial delay. We have Apache configured as follows, using prefork: StartServers 5 MinSpareServers 5 MaxSpareServers 10 MaxClients 150 MaxRequestsPerChild 0 And KeepAlive as: KeepAlive On MaxKeepAliveRequests 100 KeepAliveTimeout 5 Looking at the server-status page, even at these times of heavy load we are rarely hitting the client cap, usually serving between 80-100 requests and many of those in the keepalive state. That tells me to rule out the initial request slowness as "waiting for a handler" but I may be wrong. Amazon's CloudWatch monitoring tells me that even when our OS is reporting a load of 15, our instance CPU utilization is between 75-80%. Example output from top: top - 15:47:06 up 31 days, 1:38, 8 users, load average: 11.46, 7.10, 6.56 Tasks: 221 total, 28 running, 193 sleeping, 0 stopped, 0 zombie Cpu(s): 66.9%us, 22.1%sy, 0.0%ni, 2.6%id, 3.1%wa, 0.0%hi, 0.7%si, 4.5%st Mem: 7871900k total, 7850624k used, 21276k free, 68728k buffers Swap: 0k total, 0k used, 0k free, 3750664k cached The majority of the processes look like: 24720 www-data 15 0 202m 26m 4412 S 9 0.3 0:02.97 apache2 24530 www-data 15 0 212m 35m 4544 S 7 0.5 0:03.05 apache2 24846 www-data 15 0 209m 33m 4420 S 7 0.4 0:01.03 apache2 24083 www-data 15 0 211m 35m 4484 S 7 0.5 0:07.14 apache2 24615 www-data 15 0 212m 35m 4404 S 7 0.5 0:02.89 apache2 Example output from vmstat at the same time as the above: procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 8 0 0 215084 68908 3774864 0 0 154 228 5 7 32 12 42 9 6 21 0 198948 68936 3775740 0 0 676 2363 4022 1047 56 16 9 15 23 0 0 169460 68936 3776356 0 0 432 1372 3762 835 76 21 0 0 23 1 0 140412 68936 3776648 0 0 280 0 3157 827 70 25 0 0 20 1 0 115892 68936 3776792 0 0 188 8 2802 532 68 24 0 0 6 1 0 133368 68936 3777780 0 0 752 71 3501 878 67 29 0 1 0 1 0 146656 68944 3778064 0 0 308 2052 3312 850 38 17 19 24 2 0 0 202104 68952 3778140 0 0 28 90 2617 700 44 13 33 5 9 0 0 188960 68956 3778200 0 0 8 0 2226 475 59 17 6 2 3 0 0 166364 68956 3778252 0 0 0 21 2288 386 65 19 1 0 And finally, output from Apache's server-status: Server uptime: 31 days 2 hours 18 minutes 31 seconds Total accesses: 60102946 - Total Traffic: 974.5 GB CPU Usage: u209.62 s75.19 cu0 cs0 - .0106% CPU load 22.4 requests/sec - 380.3 kB/second - 17.0 kB/request 107 requests currently being processed, 6 idle workers C.KKKW..KWWKKWKW.KKKCKK..KKK.KKKK.KK._WK.K.K.KKKKK.K.R.KK..C.C.K K.C.K..WK_K..KKW_CK.WK..W.KKKWKCKCKW.W_KKKKK.KKWKKKW._KKK.CKK... KK_KWKKKWKCKCWKK.KKKCK.......................................... ................................................................ From my limited experience I draw the following conclusions/questions: We may be allowing far too many KeepAlive requests I do see some time spent waiting for IO in the vmstat although not consistently and not a lot (I think?) so I am not sure this is a big concern or not, I am less experienced with vmstat Also in vmstat, I see in some iterations a number of processes waiting to be served, which is what I am attributing the initial page load delay on our web server to, possibly erroneously We serve a mixture of static content (75% or higher) and script content, and the script content is often fairly processor intensive, so finding the right balance between the two is important; long term we want to move statics elsewhere to optimize both servers but our software is not ready for that today I am happy to provide additional information if anybody has any ideas, the other note is that this is a high-availability production installation so I am wary of making tweak after tweak, and is why I haven't played with things like the KeepAlive value myself yet.

  Read the article

• Understanding RedHats recommended tuned profiles

  - by espenfjo

  We are going to roll out tuned (and numad) on ~1000 servers, the majority of them being VMware servers either on NetApp or 3Par storage. According to RedHats documentation we should choose the virtual-guestprofile. What it is doing can be seen here: tuned.conf We are changing the IO scheduler to NOOP as both VMware and the NetApp/3Par should do sufficient scheduling for us. However, after investigating a bit I am not sure why they are increasing vm.dirty_ratio and kernel.sched_min_granularity_ns. As far as I have understood increasing increasing vm.dirty_ratio to 40% will mean that for a server with 20GB ram, 8GB can be dirty at any given time unless vm.dirty_writeback_centisecsis hit first. And while flushing these 8GB all IO for the application will be blocked until the dirty pages are freed. Increasing the dirty_ratio would probably mean higher write performance at peaks as we now have a larger cache, but then again when the cache fills IO will be blocked for a considerably longer time (Several seconds). The other is why they are increasing the sched_min_granularity_ns. If I understand it correctly increasing this value will decrease the number of time slices per epoch(sched_latency_ns) meaning that running tasks will get more time to finish their work. I can understand this being a very good thing for applications with very few threads, but for eg. apache or other processes with a lot of threads would this not be counter-productive?

  Read the article

• What is recommended minimum object size for gzip performance benefits?

  - by utt73

  I'm working on improving page speed display times, and one of the methods is to gzip content from the webserver. Google recommends: Note that gzipping is only beneficial for larger resources. Due to the overhead and latency of compression and decompression, you should only gzip files above a certain size threshold; we recommend a minimum range between 150 and 1000 bytes. Gzipping files below 150 bytes can actually make them larger. We serve our content through Akamai, using their network for a proxy and CDN. What they've told me: Following up on your question regarding what is the minimum size Akamai will compress the requested object when sending it to the end user: The minimum size is 860 bytes. My reply: What is the reason(s) for why Akamai's minimum size is 860 bytes? And why, for example, is this not the case for files Akamai serves for facebook? (see below) Google recommends to gzip more agressively. And that seems appropriate on our site where the most frequent hits, by far, are AJAX calls that are <860 bytes. Akamai's response: The reasons 860 bytes is the minimum size for compression is twofold: (1) The overhead of compressing an object under 860 bytes outweighs performance gain. (2) Objects under 860 bytes can be transmitted via a single packet anyway, so there isn't a compelling reason to compress them. So I'm here for some fact checking. Is the 860 byte limit due to packet size the end of this reasoning? Why would high traffic sites push this down to the 150 byte limit... just to save on bandwidth costs (since CDNs base their charges on bandwith offloaded from origin), or is there a performance gain in doing so?

  Read the article

• How do I measure performance of a virtual server?

  - by Sergey

  I've got a VPS running Ubuntu. Being a virtual server, I understand that it shares resources with unknown number of other servers, and I'm noticing that it's considerably slower than my desktop machine. Is there some tool to measure the performance of the virtual machine? I'd be curious to see some approximate measure similar to bogomips, possibly for CPU (operations/sec), memory and disk read/write speed. I'd like to be able to compare those numbers to my desktop machine. I'm not interested in the specs of the actual physical machine my VPS is running on - by doing cat /proc/cpuinfo I can see that it's a nice quad-core Xeon machine, but it doesn't matter to me. I'm basically interested in how fast a program would run in my VPS - how many CPU operations it can make in a second, how many bytes to write to RAM or to disk. I only have ssh access to the machine so the tool need to be command-line. I could write a script which, say, does some calculations in a loop for a second and counts how many loops it was able to do, or something similar to measure disk and RAM performance. But I'm sure something like this already exists.

  Read the article

• Performing client-side OAuth authorized Twitter API calls versus server side, how much of a difference is there in terms of performance?

  - by Terence Ponce

  I'm working on a Twitter application in Ruby on Rails. One of the biggest arguments that I have with other people on the project is the method of calling the Twitter API. Before, everything was done on the server: OAuth login, updating the user's Twitter data, and retrieving tweets. Retrieving tweets was the heaviest thing to do since we don't store the tweets in our database, so viewing the tweets means that we have to call the API every time. One of the people in the project suggested that we call the tweets through Javascript instead to lessen the load on the server. We used GET search, which, correct me if I'm wrong, will be removed when v1.0 becomes completely deprecated, but that really isn't a concern now. When the Twitter API has migrated completely to v1.1 (again, correct me if I'm wrong), every calls to the API must be authenticated, so we have to authenticate our Javascript requests to the API. As said here: We don't support or recommend performing OAuth directly through Javascript -- it's insecure and puts your application at risk. The only acceptable way to perform it is if you kept all keys and secrets server-side, computed the OAuth signatures and parameters server side, then issued the request client-side from the server-generated OAuth values. If we do exactly what Twitter suggests, the only difference between this and doing everything server-side is that our server won't have to contact the Twitter API anymore every time the user wants to view tweets. Here's how I would picture what's happening every time the user makes a request: If we do it through Javascript, it would be harder on my part because I would have to create the signatures manually for every request, but I will gladly do it if the boost in performance is worth all the trouble. Doing it through Ruby on Rails would be very easy since the Twitter gem does most of the grunt work already, so I'm really encouraging the other people in the project to agree with me. Is the difference in performance trivial or is it significant enough to switch to Javascript?

  Read the article

< Previous Page | 13 14 15 16 17 18 19 20 21 22 23 24  | Next Page >