Search Results

Search found 10951 results on 439 pages for 'high definition'.

Page 2/439 | < Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >

  • High server load - [jbd2/md1-8] using 99.99% IO

    - by Alex
    I've been having spike in load over the last week. This usually occurs once or twice a day. I've managed to identify from iotop that [jbd2/md1-8] is using 99.99 % IO. During the high load times there is no high traffic to the server. Server specs are: AMD Opteron 8 core 16 GB RAM 2x2.000 GB 7.200 RPM HDD Software Raid 1 Cloudlinux + Cpanel Mysql is properly tuned Apart from the spikes, the load usually is around 0.80 at most. I've searched around but can't find what [jbd2/md1-8] does exactly. Has anyone had this problem or does anyone know a possible solution? Thank you. UPDATE: TIME TID PRIO USER DISK READ DISK WRITE SWAPIN IO COMMAND 16:05:36 399 be/3 root 0.00 B/s 38.76 K/s 0.00 % 99.99 % [jbd2/md1-8]

    Read the article

  • Cheapest High Available Web Server [closed]

    - by xyz
    I would like to create a high-available setup (e.g. a small cluster) for a webserver, i.e. it will run Apache, PHP and MySQL. There will be between 2-8 small websites running with only very little traffic and workload. High availability is however very important. I don't want to be dependent on 1 datacenter, so there must be a minimum of 2 servers placed in different datacenters, and if one server goes down, the user must experience no or only a minimum of downtime - and no data loss. I have considered Amazon AWS using their Elastic Load Balancing, since it is possible to buy 2 EC2 instances in 2 availability zones and set up load balancing and RDS (Multi-AZ). However this seems rather expensive. Using the AWS price calculator http://calculator.s3.amazonaws.com/calc5.html it totals to 185$/month the first year (including the free tier). Are my calculations incorrect or is there a cheaper way to make this HA setup? Best regards

    Read the article

  • How to setup Wordpress High Availability

    - by Ketam
    I have installed Galera Cluster on 3 cluster + 1 management. I wanted to make it like this, Server1: Home (www.domain.com) Server2: For BBpress/Forum (Forum Tab Menu will forward to forum.domain.com) Server3: BuddyPress Activity (Social Tab Menu will forward to social.domain.com) The purpose I am doing this is to distribute my resource and load balancing each other at same time. However, I have difficulty to setup Apache Load-Balancing/mod_proxy/clustering or any suitable to have high availability WordPress. Any best suggestion/solution to make high availability WordPress? Or how to? And another question is I tried to copy whole WordPress files & folders to Server2 connecting to local database (same data inside since it is already on Galera Cluster) but the page blank. Any advice? OS: Centos 6.2 Thanks in advanced.

    Read the article

  • Error 'duplicate definition' when compiling 2 c files that reference 1 header file

    - by super newbie
    I have two C files and one header that are as follows: Header file header.h: char c = 0; file1.c: #include "header.h" file2.c: #include "header.h" I was warned about 'duplicate definition' when compiling. I understand the cause as the variable c is defined twice in both file1.c and file2.c; however, I do need to reference the header.h in both c files. How should I overcome this issue?

    Read the article

  • No clue for high load average on top

    - by Oz.
    We have several machines on Amazon (ec2) of the type c1.xlarge with 16 cpus, running the Amazon AMI. Details on the machine: 7 GB of memory 20 EC2 Compute Units (8 virtual cores with 2.5 EC2 Compute Units each) 1690 GB of instance storage 64-bit platform I/O Performance: High API name: c1.xlarge One out of the several machines is showing a high load average, since we have run the last yum upgrade a couple of weeks a go. We did not yet update the other machines, and everything looks normal on them. The strange thing is that the top command not showing any hint for the cause of the load. CPUs are 4.8%us, 1.1%sy, 0.0%ni, 94.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st(see below). Mem is about 1.5GB free. Any idea what could it be, or where else can we check? Many thanks for the help. # # top # top - 07:57:42 up 4:18, 1 user, load average: 1.36, 1.45, 1.47 Tasks: 131 total, 1 running, 130 sleeping, 0 stopped, 0 zombie Cpu(s): 4.8%us, 1.1%sy, 0.0%ni, 94.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 7120092k total, 5644920k used, 1475172k free, 532888k buffers Swap: 0k total, 0k used, 0k free, 3463936k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 1557 mysql 20 0 1829m 374m 6448 S 14.3 5.4 11:15.09 mysqld 6655 apache 20 0 416m 49m 3744 S 9.3 0.7 0:04.85 httpd 27683 apache 20 0 421m 54m 3708 S 9.0 0.8 0:00.99 httpd 6682 apache 20 0 424m 57m 3788 S 8.3 0.8 0:03.81 httpd 16816 apache 20 0 419m 51m 3760 S 4.3 0.7 0:04.09 httpd 22182 apache 20 0 417m 50m 3756 S 1.7 0.7 0:06.34 httpd 219 root 20 0 0 0 0 S 0.3 0.0 0:00.34 kworker/7:1 699 root 20 0 0 0 0 S 0.3 0.0 0:00.40 kworker/3:1 1 root 20 0 19376 1508 1212 S 0.0 0.0 0:00.29 init 2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd 3 root 20 0 0 0 0 S 0.0 0.0 0:00.71 ksoftirqd/0

    Read the article

  • Specific 'boot file' definition

    - by Jazz
    Hey, I have been given a general explanation of how a computer boots up. However a very loose definition to the term 'boot file' was given. Could someone explain 'boot file' to me in a very simple but concise manner? I have read about the POST, the clearing of registers, BIOS in the CMOS, etc. What I understand is that the boot file is different to the boot program. the boot program gets the system ready to accept an OS while the boot file contains some of the parameters by which the system will operate. The boot program is stored on ROM and the boot file isnt? cheers, jazz

    Read the article

  • C++ multiple definition error

    - by user231536
    Starting with sth's answer to this question: http://stackoverflow.com/questions/3023760/c-template-specialization I was wondering how to resolve multiple definition errors if the following code is put in a header file included multiple times by different .cc files and linked together: template <typename T> class C { static const int K; static ostream& print(ostream& os, const T& t) { return os << t;} }; // general case template <typename T> const int C<T>::K = 1; // specialization template <> const int C<int>::K = 2;

    Read the article

  • High CPU from httpd process

    - by KHWeb
    I am currently getting high CPU on a server that is just running a couple of sites with very low traffic. One of the sites is in still development going live soon. However, this site is very very slow...When browsing through its pages I can see that the CPU goes from 30% to 100% for httpd (see top output below). I have tuned httpd & MySQL, Apache Solr, Tomcat for high performance, and I am using APC. Not sure what to do from here or how to find the culprit as I have a bunch of messages on the httpd log and have been chasing dead ends for some time...any help is greatly appreciated. Server: AuthenticAMD, Quad-Core AMD Opteron(tm) Processor 2352, RAM 16GB Linux 2.6.27 64-bit, Centos 5.5 Plesk 9.5.4, MySQL 5.1.48, PHP 5.2.17 Apache/2.2.3 (CentOS) DAV/2 mod_jk/1.2.15 mod_ssl/2.2.3 OpenSSL/0.9.8e-fips-rhel5 PHP/5.2.17 mod_perl/2.0.4 Perl/v5.8.8 Tomcat6-6.0.29-1.jpp5, Tomcat-native-1.1.20-1.el5, Apache Solr top 17595 apache 20 0 1825m 507m 10m R 100.4 3.2 0:17.50 httpd 17596 apache 20 0 1565m 247m 9936 R 83.1 1.5 0:10.86 httpd 17598 apache 20 0 1430m 110m 6472 S 54.5 0.7 0:08.66 httpd 17599 apache 20 0 1438m 124m 12m S 37.2 0.8 0:11.20 httpd 16197 mysql 20 0 13.0g 2.0g 5440 S 9.6 12.6 297:12.79 mysqld 17617 root 20 0 12748 1172 812 R 0.7 0.0 0:00.88 top 8169 tomcat 20 0 4613m 268m 6056 S 0.3 1.7 6:40.56 java httpd error_log [debug] prefork.c(991): AcceptMutex: sysvsem (default: sysvsem) [info] mod_fcgid: Process manager 17593 started [debug] proxy_util.c(1854): proxy: grabbed scoreboard slot 0 in child 17594 for worker proxy:reverse [debug] proxy_util.c(1967): proxy: initialized single connection worker 0 in child 17594 for (*) [debug] proxy_util.c(1854): proxy: grabbed scoreboard slot 0 in child 17595 for worker proxy:reverse [debug] proxy_util.c(1873): proxy: worker proxy:reverse already initialized [notice] child pid 22782 exit signal Segmentation fault (11) [error] (43)Identifier removed: apr_global_mutex_lock(jk_log_lock) failed [debug] util_ldap.c(2021): LDAP merging Shared Cache conf: shm=0x7fd29a5478c0 rmm=0x7fd29a547918 for VHOST: example.com [info] APR LDAP: Built with OpenLDAP LDAP SDK [info] LDAP: SSL support available [info] Init: Seeding PRNG with 256 bytes of entropy [info] Init: Generating temporary RSA private keys (512/1024 bits) [info] Init: Generating temporary DH parameters (512/1024 bits) [debug] ssl_scache_shmcb.c(374): shmcb_init allocated 512000 bytes of shared memory [debug] ssl_scache_shmcb.c(554): entered shmcb_init_memory() [debug] ssl_scache_shmcb.c(576): for 512000 bytes, recommending 4265 indexes [debug] ssl_scache_shmcb.c(619): shmcb_init_memory choices follow [debug] ssl_scache_shmcb.c(621): division_mask = 0x1F [debug] ssl_scache_shmcb.c(623): division_offset = 96 [debug] ssl_scache_shmcb.c(625): division_size = 15997 [debug] ssl_scache_shmcb.c(627): queue_size = 2136 [debug] ssl_scache_shmcb.c(629): index_num = 133 [debug] ssl_scache_shmcb.c(631): index_offset = 8 [debug] ssl_scache_shmcb.c(633): index_size = 16 [debug] ssl_scache_shmcb.c(635): cache_data_offset = 8 [debug] ssl_scache_shmcb.c(637): cache_data_size = 13853 [debug] ssl_scache_shmcb.c(650): leaving shmcb_init_memory()

    Read the article

  • High Availability with 2 servers?

    - by Tom R
    Is it possible to have a high availability setup with 2 servers? Running Windows Web Server 2008 and MSSQL Web Edition (as I know Express isn't supported)? Getting to the point where our one dedicated server needs scaled out and going to a second server already more than doubles the cost as need to use Web Edition rather than Express (db is only 500MB).

    Read the article

  • high resolution on small screen size

    - by vishesh
    I have recently got an intel ultrabook,but its screen size is 13.3' and the native resolution is 1600X900.So the problem is that the letters that appear on screen are very small.Reducing resolution blurs the display and making everything bigger also doesn't feel very good.is there a way to get around this problem without changing hardware. I am even ok with this high resolution but I am concerned about the harmful effects it might have on my eyes in long term. Any advice will be very useful.Please help

    Read the article

  • Why not have a High Level Language based OS? Are Low Level Languages more efficient?

    - by rtindru
    Without being presumptuous, I would like you to consider the possibility of this. Most OS today are based on pretty low level languages (mainly C/C++) Even the new ones such as Android uses JNI & underlying implementation is in C In fact, (this is a personal observation) many programs written in C run a lot faster than their high level counterparts (eg: Transmission (a bittorrent client on Ubuntu) is a whole lot faster than Vuze(Java) or Deluge(Python)). Even python compilers are written in C, although PyPy is an exception. So is there a particular reason for this? Why is it that all our so called "High Level Languages" with the great "OOP" concepts can't be used in making a solid OS? So I have 2 questions basically. Why are applications written in low level languages more efficient than their HLL counterparts? Do low level languages perform better for the simple reason that they are low level and are translated to machine code easier? Why do we not have a full fledged OS based entirely on a High Level Language?

    Read the article

  • Creating a Build Definition using the TFS 2010 API

    - by Jakob Ehn
    In this post I will show how to create a new build definition in TFS 2010 using the TFS API. When creating a build definition manually, using Team Explorer, the necessary steps are lined out in the New Build Definition Wizard:     So, lets see how the code looks like, using the same order. To start off, we need to connect to TFS and get a reference to the IBuildServer object: TfsTeamProjectCollection server = newTfsTeamProjectCollection(newUri("http://<tfs>:<port>/tfs")); server.EnsureAuthenticated(); IBuildServer buildServer = (IBuildServer) server.GetService(typeof (IBuildServer)); General First we create a IBuildDefinition object for the team project and set a name and description for it: var buildDefinition = buildServer.CreateBuildDefinition(teamProject); buildDefinition.Name = "TestBuild"; buildDefinition.Description = "description here..."; Trigger Next up, we set the trigger type. For this one, we set it to individual which corresponds to the Continuous Integration - Build each check-in trigger option buildDefinition.ContinuousIntegrationType = ContinuousIntegrationType.Individual; Workspace For the workspace mappings, we create two mappings here, where one is a cloak. Note the user of $(SourceDir) variable, which is expanded by Team Build into the sources directory when running the build. buildDefinition.Workspace.AddMapping("$/Path/project.sln", "$(SourceDir)", WorkspaceMappingType.Map); buildDefinition.Workspace.AddMapping("$/OtherPath/", "", WorkspaceMappingType.Cloak); Build Defaults In the build defaults, we set the build controller and the drop location. To get a build controller, we can (for example) use the GetBuildController method to get an existing build controller by name: buildDefinition.BuildController = buildServer.GetBuildController(buildController); buildDefinition.DefaultDropLocation = @\\SERVER\Drop\TestBuild; Process So far, this wasy easy. Now we get to the tricky part. TFS 2010 Build is based on Windows Workflow 4.0. The build process is defined in a separate .XAML file called a Build Process Template. By default, every new team team project containtwo build process templates called DefaultTemplate and UpgradeTemplate. In this sample, we want to create a build definition using the default template. We use te QueryProcessTemplates method to get a reference to the default for the current team project   //Get default template var defaultTemplate = buildServer.QueryProcessTemplates(teamProject).Where(p => p.TemplateType == ProcessTemplateType.Default).First(); buildDefinition.Process = defaultTemplate;   There are several build process templates that can be set for the default build process template. Only one of these are required, the ProjectsToBuild parameters which contains the solution(s) and configuration(s) that should be built. To set this info, we use the ProcessParameters property of thhe IBuildDefinition interface. The format of this property is actually just a serialized dictionary (IDictionary<string, object>) that maps a key (parameter name) to a value which can be any kind of object. This is rather messy, but fortunately, there is a helper class called WorkflowHelpers inthe Microsoft.TeamFoundation.Build.Workflow namespace, that simplifies working with this persistence format a bit. The following code shows how to set the BuildSettings information for a build definition: //Set process parameters varprocess = WorkflowHelpers.DeserializeProcessParameters(buildDefinition.ProcessParameters); //Set BuildSettings properties BuildSettings settings = newBuildSettings(); settings.ProjectsToBuild = newStringList("$/pathToProject/project.sln"); settings.PlatformConfigurations = newPlatformConfigurationList(); settings.PlatformConfigurations.Add(newPlatformConfiguration("Any CPU", "Debug")); process.Add("BuildSettings", settings); buildDefinition.ProcessParameters = WorkflowHelpers.SerializeProcessParameters(process); The other build process parameters of a build definition can be set using the same approach   Retention  Policy This one is easy, we just clear the default settings and set our own: buildDefinition.RetentionPolicyList.Clear(); buildDefinition.AddRetentionPolicy(BuildReason.Triggered, BuildStatus.Succeeded, 10, DeleteOptions.All); buildDefinition.AddRetentionPolicy(BuildReason.Triggered, BuildStatus.Failed, 10, DeleteOptions.All); buildDefinition.AddRetentionPolicy(BuildReason.Triggered, BuildStatus.Stopped, 1, DeleteOptions.All); buildDefinition.AddRetentionPolicy(BuildReason.Triggered, BuildStatus.PartiallySucceeded, 10, DeleteOptions.All); Save It! And we’re done, lets save the build definition: buildDefinition.Save(); That’s it!

    Read the article

  • An XEvent a Day (4 of 31) – Querying the Session Definition and Active Session DMV’s

    - by Jonathan Kehayias
    Yesterdays post, Managing Event Sessions , showed how to manage Event Sessions in Extended Events Sessions inside the Extended Events framework in SQL Server. In today's post, we’ll take a look at how to find information about the defined Event Sessions that already exist inside a SQL Server using the Session Definition DMV’s and how to find information about the Active Event Sessions that exist using the Active Session DMV’s. Session Definition DMV’s The Session Definition DMV’s provide information...(read more)

    Read the article

  • Pseudocode: a clear definition?

    - by Cian E
    The following code is an example of what I think would qualify as pseudocode, since it does not execute in any language but the logic is correct. string checkRubric(gpa, major) bool brake = false num lastRange num rangeCounter string assignment = "unassigned" array bus['business']= array('person a'=>array(0, 2.9), 'person b'=>array(3, 4)) array cis['computer science']= array('person c'=>array(0, 2.9), 'person d'=>array(3, 4)) array lib['english']= array('person e'=>array(0, 4)) array rubric = array(bus, cis, lib) foreach (rubric as fieldAr) foreach (fieldAr as field => advisorAr) if (major == field) foreach (advisorAr as advisor => gpaRangeAr) rangeCounter = 0 foreach (gpaRangeAr as gpaValue) if (rangeCounter < 1) lastRange = gpaValue else if (gpa >= lastRange && gpa <= gpaValue) assignment = advisor brake = true break endif rangeCounter++ endforeach if (brake == true) break endif endforeach if (brake == true) break endif endif endforeach if (brake == true) break endif endforeach return assignment For the past couple of weeks I've been trying to create a clear definition of what pseudocode actually is. Is it relative to the programmer or is there an actual clearcut syntax? I say pseudocode is any code that does not execute, how about you? Thanks (links to this subject welcome)

    Read the article

  • spring - constructor injection and overriding parent definition of nested bean

    - by mdma
    I've read the Spring 3 reference on inheriting bean definitions, but I'm confused about what is possible and not possible. For example, a bean that takes a collaborator bean, configured with the value 12 <bean name="beanService12" class="SomeSevice"> <constructor-arg index="0"> <bean name="beanBaseNested" class="SomeCollaborator"> <constructor-arg index="0" value="12"/> </bean> </constructor-arg> </bean> I'd then like to be able to create similar beans, with slightly different configured collaborators. Can I do something like <bean name="beanService13" parent="beanService12"> <constructor-arg index="0"> <bean> <constructor-arg index="0" value="13"/> </bean> </constructor> </bean> I'm not sure this is possible and, if it were, it feels a bit clunky. Is there a nicer way to override small parts of a large nested bean definition? It seems the child bean has to know quite a lot about the parent, e.g. constructor index. I'd prefer not to change the structure - the parent beans use collaborators to perform their function, but I can add properties and use property injection if that helps. This is a repeated pattern, would creating a custom schema help? Thanks for any advice!

    Read the article

  • GlusterFs - high load 90-107% CPU

    - by Sara
    I try and try and try to performance and fix problem with gluster, i try all. I served on gluster webpages, php files, images etc. I have problem after update from 3.3.0 to 3.3.1. I try 3.4 when i think maybe fix it but still the same problem. I temporarily have 1 brick, but before upgrade will be fine. Config: Volume Name: ... Type: Replicate Volume ID: ... Status: Started Number of Bricks: 0 x 2 = 1 Transport-type: tcp Bricks: Brick1: ...:/... Options Reconfigured: cluster.stripe-block-size: 128KB performance.cache-max-file-size: 100MB performance.flush-behind: on performance.io-thread-count: 16 performance.cache-size: 256MB auth.allow: ... performance.cache-refresh-timeout: 5 performance.write-behind-window-size: 1024MB I use fuse, hmm "Maybe the high load is due to the unavailable brick" i think about it, but i cant find information on how to safely change type of volume. Maybe u know how?

    Read the article

  • Providing high availability and failover using MySQL on EC2

    - by crb
    I would like to have a highly-available MySQL system, with automatic failover, running on Amazon EC2 instances. The standard approach to solving this is problem Heartbeat + DRBD, but I've found a lot of posts suggesting DRBD doesn't work on EC2, though none saying exactly why. Obviously, a serial heartbeat or distinct network is out of the question in the virtualised environment. It would also be good to have the different servers be in different availability zones, but we're getting into a much harder problem there. What are peoples' opinion on having a high uptime solution in "the cloud"?

    Read the article

  • Most suitable high availability solution

    - by Alex Bagnolini
    My company is hosting a website in a server with IIS, SQL Server and a 3rd party windows service (written in C#, source code available for amendments). We bought a new identical server, composed by: 1x Quad Core, 12GB RAM, 4x160GB SATA Raid 5, Windows Server 2008 R2 Datacenter, Public IP. We aim to put all webpages and the 3rd party windows service in an high-availability state. After some lab-testing on how to configure Failover Clustering and Hyper-V, we have deep doubts on what the "best" solution would be, by "best" meaning maintainable and able to correctly handle a physical server failure. Any suggestion on how we should configure the two servers? We don't need all the configuration's step, just an hint on the right direction to follow.

    Read the article

  • Unable to watch a high resolution and high frame rate video

    - by Abhijith Madhav
    I have a video of a tennis match whose Resolution = 1280 * 720 Codec = H264 Frame rate = 50fps (Copy paste from info given by totem media player) My laptop is not powerful enough to play this video smoothly. How can I reduce the frame-rate of this video so that my laptop can play it? I have observed that my laptop can play videos with 25fps without an issue. I use ubuntu. I wouldn't mind using windows to edit/re-encode this video.

    Read the article

  • VMware Virtual vCenter and High Availability

    - by rufo
    To continue with this question: Should be Vmware vCenter server high available? According to the response there even if vCenter is down HA will continue to work. So, if my vCenter is a VM, using the express sql edition in the same VM, and that VM is hosted in the same cluster it manages (and the cluster is setup for HA): Am I correct to assume that if the host that hosts the vCenter goes down HA will vmotion the vCenter VM to another host and it will continue to function? BTW: my environment is small, two ESXi 5.0 hosts, with about 50 VMs, using iSCSI shared storaged for everything.

    Read the article

  • High availability for Windows Service under Windows Server 2003

    - by empi
    Hi. I have a following situation: I need to deploy a windows service that listens for incoming request on tcp port (basically WCF service). I have a High Availability requirement - the service must be deployed on two servers and if the service stops (only the service, not the whole server) on one server, all the requests must be redirected to the second one. For me it looks like a basic failover scenario. How can I achieve this on Windows Server 2003? Should I use Microsoft Cluster Service or Network Load Balancing? The important part is that the process of swapping the servers should not concern the clients (the client must see only single address / single host or domain name). Thanks in advance for help.

    Read the article

  • Very fast Laptop Heating due to very high CPU usage by dwm.exe

    - by Sushan Shrestha
    My laptop gets heated very fast and when I check the task manager, I find dwm.exe consuming very high CPU (mostly 100%). In the beginning I found the message "The graphic adapter has been stopped and recovered".Also I am getting one error message "Cidaemon.exe has stopped working" very frequently. During this period also, cpu usage is 100% which is consumed by dwm.exe. I have run ccleaner and Kingsoft PC doctor monitor to fix the register problem but the problem has not been solved. My display adaptor is : NVIDIA NVS 5200M. After the driver update, I am not getting "The graphic adapter has been stopped and recovered" but dwm.exe is still consuming 100% CPU one time in about 5 mins. Multiple restarts has not helped. Laptop Model: Dell Latitude E6430. Thanks in advance.

    Read the article

  • Providing high availability and failover using MySQL on EC2

    - by crb
    I would like to have a highly-available MySQL system, with automatic failover, running on Amazon EC2 instances. The standard approach to solving this is problem Heartbeat + DRBD, but I've found a lot of posts suggesting DRBD doesn't work on EC2, though none saying exactly why. Obviously, a serial heartbeat or distinct network is out of the question in the virtualised environment. It would also be good to have the different servers be in different availability zones, but we're getting into a much harder problem there. What are peoples' opinion on having a high uptime solution in "the cloud"? Note: This question was asked before RDS with multi-AZ was announced, which is the nice automatic answer for today's modern IT professional. :)

    Read the article

  • Linux Tuning for High Traffic JBoss Server with LDAP Binds

    - by Levi Stanley
    I'm configuring a high traffic Linux server (RedHat) and running into a limit I haven't been able to track down. I need to be able to handle sustained 300 requests per second throughput using Nginx and JBoss. The point of this server is to run checks on a user's account when that user signs in. Each request goes through Nginx to JBoss (specifically Torquebox with JBoss A7 with a Sinatra app) and then makes an LDAP request to bind that user and retrieve several attributes. It is during the bind that these errors occur. I'm able to reproduce this going directly to JBoss, so that rules out Nginx at least. I get a variety of error messages, though oddly JBoss stopped writing to the log file recently. It used to report errors about creating native threads. Now I just see "java.net.SocketException: Connection reset" and "org.apache.http.conn.HttpHostConnectException: Connection to http://my.awesome.server:8080 refused" as responses in jmeter. To the best of my knowledge, I have plenty of available file handles, processes, sockets, and ports, yet the issue persists. Unfortunately, I have very little experience tuning servers. I've found a couple useful documents - Ipsysctl tutorial 1.0.4 and Linux Tuning - but those documents are a bit over my head (and just entering the the configuration described in Linux Tuning doesn't fix my issue. Here are the configuration changes I've tried (webproxy is the user that runs Nginx and JBoss): /etc/security/limits.conf webproxy soft nofile 65536 webproxy hard nofile 65536 webproxy soft nproc 65536 webproxy hard nproc 65536 root soft nofile 65536 root hard nofile 65536 root soft nproc 65536 root hard nofile 65536 First attempt /etc/sysctl.conf sysctl net.core.somaxconn = 8192 sysctl net.ipv4.ip_local_port_range = 32768 65535 sysctl net.ipv4.tcp_fin_timeout = 15 sysctl net.ipv4.tcp_keepalive_time = 1800 sysctl net.ipv4.tcp_keepalive_intvl = 35 sysctl net.ipv4.tcp_tw_recycle = 1 sysctl net.ipv4.tcp_tw_reuse = 1 Second attempt /etc/sysctl.conf net.core.rmem_max = 16777216 net.core.wmem_max = 16777216 net.ipv4.tcp_rmem = 4096 87380 16777216 net.ipv4.tcp_wmem = 4096 65536 16777216 net.core.netdev_max_backlog = 30000 net.ipv4.tcp_congestion_control=htcp net.ipv4.tcp_mtu_probing=1 Any ideas what might be happening here? Or better yet, are there some good documentation resources designed for beginners?

    Read the article

  • Large, high performance object or key/value store for HTTP serving on Linux

    - by Tommy
    I have a service that serves images to end users at a very high rate using plain HTTP. The images vary between 4 and 64kbytes, and there are 1.300.000.000 of them in total. The dataset is about 30TiB in size and changes (new objects, updates, deletes) make out less than 1% of the requests. The number of requests pr. second vary from 240 to 9000 and is dispersed pretty much all over, with few objects being especially "hot". As of now, these images are files on a ext3 filesystem distributed read only across a large amount of mid range servers. This poses several problems: Using a fileysystem is very inefficient since the metadata size is large, the inode/dentry cache is volatile on linux and some daemons tend to stat()/readdir() it's way through the directory structure, which in my case becomes very expensive. Updating the dataset is very time consuming and requires remounting between set A and B. The only reasonable handling is operating on the block device for backup, copying, etc. What I would like is a deamon that: speaks HTTP (get, put, delete and perhaps update) stores data it in an efficient structure. The index should remain in memory, and considering the amount of objects, the overhead must be small. The software should be able to handle massive connections with slow (if any) time needed to ramp up. Index should be read in memory at startup. Statistics would be nice, but not mandatory. I have experimented a bit with riak, redis, mongodb, kyoto and varnish with persistent storage, but I haven't had the chance to dig in really deep yet.

    Read the article

< Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >