Search Results

Search found 13341 results on 534 pages for 'obiee performance tuning'.

Page 91/534 | < Previous Page | 87 88 89 90 91 92 93 94 95 96 97 98  | Next Page >

  • SAN with iSCSI-Target Performance Horrendous

    - by Justin
    We have a poor man's SAN setup in a 1U Ubuntu server running iSCSI-Target with two 300GB drives in RAID-0. We then are using it for block level storage for virtual machines. The hypervisor is connected to the SAN via gigabit on a dedicated VLAN and interfaces. We only have a single virtual machine setup and doing some benchmarks. If we run hdparm -t /dev/sda1 from the virtual machine, we get 'ok' performance of 75MB/s from the virtual machine to the SAN. Then we basically compile a package with ./configure and make. Things start ok, but then all the sudden the load average on the SAN grows to 7+ and things slow down to a crawl. When we SSH into the SAN and run top, sure the load is 7+, but the CPU usage is basically nothing, also the server has 1.5GB of memory available. When we kill the compile on the virtual machine, slowly the LOAD on the SAN goes back to sub 1 figures. What in the world is causing this? How can we diagnosis this further? Here are two screenshot from the SAN during high load. 1> Output of iotop on the SAN: 2> Output of top on the SAN:

    Read the article

  • X11 performance problem after upgrading from Centos3 to Centos5 with an ATI Rage XL

    - by Marcelo Santos
    After upgrading a computer from Centos3 to Centos5 an application that does a lot of scrolling took a very high performance hit. top tells me that X is using a lot of CPU and that was not happening before. The machine has an ATI Rage XL with 8MB and X is using the ati driver as there is no proprietary ATI driver for this board on linux. The xorg.conf: Section "Device" Identifier "Videocard0" Driver "ati" EndSection Section "Screen" Identifier "Screen0" Device "Videocard0" DefaultDepth 24 SubSection "Display" Viewport 0 0 Depth 24 Modes "1024x768" "800x600" "640x480" EndSubSection EndSection Section "DRI" Group 0 Mode 0666 EndSection A similar machine that still has Centos3 installed is able to start DRI on the X server while this one is not, this is the Xorg.0.log for the Centos5 machine: drmOpenDevice: node name is /dev/dri/card0 drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: Open failed drmOpenDevice: node name is /dev/dri/card0 drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: Open failed [drm] failed to load kernel module "mach64" (II) ATI(0): [drm] drmOpen failed (EE) ATI(0): [dri] DRIScreenInit Failed (II) ATI(0): Largest offscreen areas (with overlaps): (II) ATI(0): 1024 x 1279 rectangle at 0,768 (II) ATI(0): 768 x 1280 rectangle at 0,768 (II) ATI(0): Using XFree86 Acceleration Architecture (XAA) Screen to screen bit blits Solid filled rectangles 8x8 mono pattern filled rectangles Indirect CPU to Screen color expansion Solid Lines Offscreen Pixmaps Setting up tile and stipple cache: 32 128x128 slots 10 256x256 slots (==) ATI(0): Backing store disabled (==) ATI(0): Silken mouse enabled (II) ATI(0): Direct rendering disabled (==) RandR enabled I also tried using EXA instead of XAA and setting: Option "AccelMethod" "XAA" Option "XAANoOffscreenPixmaps" "true" uname -a Linux sir5.erg.inpe.br 2.6.18-128.7.1.el5 #1 SMP Mon Aug 24 08:20:55 EDT 2009 i686 i686 i386 GNU/Linux rpm -qa | grep xorg-x11-server xorg-x11-server-utils-7.1-4.fc6 xorg-x11-server-sdk-1.1.1-48.52.el5 xorg-x11-server-Xvfb-1.1.1-48.52.el5 xorg-x11-server-Xnest-1.1.1-48.52.el5 xorg-x11-server-Xorg-1.1.1-48.52.el5 The drmOpenDevice error continues when using the suggested Option "AIGLX" "true".

    Read the article

  • Bad Performance when SQL Server hits 99% Memory Usage

    - by user15863
    I've got a server that reports 8 GB of ram used up at 99%. When restart Sql Server, it drops down to about 5% usage, but gradually builds back up to 99% over about 2 hours. When I look at the sqlserver process, its reported as only using 100k ram, and generally never goes up or below that number by very much. In fact, if I add up all the processes in my TaskManager, it's barely scratching the surface of my total available (yet TaskManager still shows 99% memory usage with "All processes shown"). It appears that Sql Server has a huge memory leak going on but it's not reporting it. The server has ran fine for nearly two years, with this only starting to manifest itself in the last 3-4 weeks. Anyone seen this or have any insight into the problem? EDIT When the server hits 99%, performance goes down hill. All queries to the server, apps, etc. come to a crawl. Restarting the service makes things zippy again, until 2 hours has passed and the server hits 99% once again.

    Read the article

  • Performance of Virtual machines on very low end machines

    - by TheLQ
    I am managing a few cheap servers as my user base isn't large enough to get much more powerful servers. I also don't have the money lying around to invest in a server to prepare for the larger user base. So I'm stuck with the old hardware I have. I am toying with the idea of virtualizing all the current OS's with most likely VMware vSphere Hypervisor (AKA ESXi) Xen (ESXi has too strict of an HCL, and my hardware is too old). Big reasons for doing so: Ability to upgrade and scale hardware rapidly - This is most likely what I'll be doing as I distribute services, get a bigger server, centralize (electricity bills are horrible), distribute, get a bigger server, etc... Manually doing this by reinstalling the entire OS would be a big pain Safety from me - I've made many rookie mistakes, like doing lots of risky work on a vital production server. With a VM I can just backup the state, work on my machine, test, and revert if necessary. No worries, and no OS reinstallation Safety from other factors - As I scale servers might go down, and a backup VM can instantly be started. Various other reasons. However the limiting factor here is hardware. And I mean very depressing hardware. The current server's run off of a Pentium 3 and 4, and have 512 MB and 768 MB RAM respectively (RAM can be upgraded soon however). Is the Virtualization layer small enough to run itself and a Linux OS effectively? Will performance be acceptable (50% CPU overhead for every operation isn't acceptable)? Does it leave enough RAM for the Linux OS? Is this even feasible?

    Read the article

  • Hints on diagnosing performance issue in OpenBSD firewall

    - by Tom
    My OpenBSD 4.6 pf firewall has started having really bad performance in the past few weeks. I've isolated the firewall (as opposed to the WAN connection, switch, cable, etc.) as the problem, but need a hint on how to further diagnose or fix the problem. The facts: Normal setup is: DSL Modem - FW Ext. NIC - FW Int. NIC - Switch - Laptop Normal setup described above gives only 25 Kbps! Plugging the laptop straight from the DSL modem gives a 1 MBps connection (full speed, as advertised). Therefore, the DSL connection seems to be OK. Plugging the laptop directly into the firewall's internal NIC (bypassing the switch) also gives only 25 Kbps. Therefore, the switch does not seem to be a problem. I've replaced the ethernet cables, but it didn't help. Here's the weird thing. Reloading the ruleset (/sbin/pfctl -Fa -f /etc/pf.conf) causes the laptop's connection to go up to 1 Mbps (i.e. full speed) for a few minutes before it gradually degrades back down to 25Kbps again. Any ideas on what's wrong or how I could further diagnose the problem?

    Read the article

  • Nginx + uWSGI + Django performance stuck on 100rq/s

    - by dancio
    I have configured Nginx with uWSGI and Django on CentOS 6 x64 (3.06GHz i3 540, 4GB), which should easily handle 2500 rq/s but when I run ab test ( ab -n 1000 -c 100 ) performance stops at 92 - 100 rq/s. Nginx: user nginx; worker_processes 2; events { worker_connections 2048; use epoll; } uWSGI: Emperor /usr/sbin/uwsgi --master --no-orphans --pythonpath /var/python --emperor /var/python/*/uwsgi.ini [uwsgi] socket = 127.0.0.2:3031 master = true processes = 5 env = DJANGO_SETTINGS_MODULE=x.settings env = HTTPS=on module = django.core.handlers.wsgi:WSGIHandler() disable-logging = true catch-exceptions = false post-buffering = 8192 harakiri = 30 harakiri-verbose = true vacuum = true listen = 500 optimize = 2 sysclt changes: # Increase TCP max buffer size setable using setsockopt() net.ipv4.tcp_rmem = 4096 87380 8388608 net.ipv4.tcp_wmem = 4096 87380 8388608 net.core.rmem_max = 8388608 net.core.wmem_max = 8388608 net.core.netdev_max_backlog = 5000 net.ipv4.tcp_max_syn_backlog = 5000 net.ipv4.tcp_window_scaling = 1 net.core.somaxconn = 2048 # Avoid a smurf attack net.ipv4.icmp_echo_ignore_broadcasts = 1 # Optimization for port usefor LBs # Increase system file descriptor limit fs.file-max = 65535 I did sysctl -p to enable changes. Idle server info: top - 13:34:58 up 102 days, 18:35, 1 user, load average: 0.00, 0.00, 0.00 Tasks: 118 total, 1 running, 117 sleeping, 0 stopped, 0 zombie Cpu(s): 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 3983068k total, 2125088k used, 1857980k free, 262528k buffers Swap: 2104504k total, 0k used, 2104504k free, 606996k cached free -m total used free shared buffers cached Mem: 3889 2075 1814 0 256 592 -/+ buffers/cache: 1226 2663 Swap: 2055 0 2055 **During the test:** top - 13:45:21 up 102 days, 18:46, 1 user, load average: 3.73, 1.51, 0.58 Tasks: 122 total, 8 running, 114 sleeping, 0 stopped, 0 zombie Cpu(s): 93.5%us, 5.2%sy, 0.0%ni, 0.2%id, 0.0%wa, 0.1%hi, 1.1%si, 0.0%st Mem: 3983068k total, 2127564k used, 1855504k free, 262580k buffers Swap: 2104504k total, 0k used, 2104504k free, 608760k cached free -m total used free shared buffers cached Mem: 3889 2125 1763 0 256 595 -/+ buffers/cache: 1274 2615 Swap: 2055 0 2055 iotop 30141 be/4 nginx 0.00 B/s 7.78 K/s 0.00 % 0.00 % nginx: wo~er process Where is the bottleneck ? Or what am I doing wrong ?

    Read the article

  • X11 performance problem after upgrading from Centos3 to Centos5 with an ATI Rage XL

    - by Marcelo Santos
    After upgrading a computer from Centos3 to Centos5 an application that does a lot of scrolling took a very high performance hit. top tells me that X is using a lot of CPU and that was not happening before. The machine has an ATI Rage XL with 8MB and X is using the ati driver as there is no proprietary ATI driver for this board on linux. The xorg.conf: Section "Device" Identifier "Videocard0" Driver "ati" EndSection Section "Screen" Identifier "Screen0" Device "Videocard0" DefaultDepth 24 SubSection "Display" Viewport 0 0 Depth 24 Modes "1024x768" "800x600" "640x480" EndSubSection EndSection Section "DRI" Group 0 Mode 0666 EndSection A similar machine that still has Centos3 installed is able to start DRI on the X server while this one is not, this is the Xorg.0.log for the Centos5 machine: drmOpenDevice: node name is /dev/dri/card0 drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: Open failed drmOpenDevice: node name is /dev/dri/card0 drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: open result is -1, (No such device or address) drmOpenDevice: Open failed [drm] failed to load kernel module "mach64" (II) ATI(0): [drm] drmOpen failed (EE) ATI(0): [dri] DRIScreenInit Failed (II) ATI(0): Largest offscreen areas (with overlaps): (II) ATI(0): 1024 x 1279 rectangle at 0,768 (II) ATI(0): 768 x 1280 rectangle at 0,768 (II) ATI(0): Using XFree86 Acceleration Architecture (XAA) Screen to screen bit blits Solid filled rectangles 8x8 mono pattern filled rectangles Indirect CPU to Screen color expansion Solid Lines Offscreen Pixmaps Setting up tile and stipple cache: 32 128x128 slots 10 256x256 slots (==) ATI(0): Backing store disabled (==) ATI(0): Silken mouse enabled (II) ATI(0): Direct rendering disabled (==) RandR enabled I also tried using EXA instead of XAA and setting: Option "AccelMethod" "XAA" Option "XAANoOffscreenPixmaps" "true" uname -a Linux sir5.erg.inpe.br 2.6.18-128.7.1.el5 #1 SMP Mon Aug 24 08:20:55 EDT 2009 i686 i686 i386 GNU/Linux rpm -qa | grep xorg-x11-server xorg-x11-server-utils-7.1-4.fc6 xorg-x11-server-sdk-1.1.1-48.52.el5 xorg-x11-server-Xvfb-1.1.1-48.52.el5 xorg-x11-server-Xnest-1.1.1-48.52.el5 xorg-x11-server-Xorg-1.1.1-48.52.el5 The drmOpenDevice error continues when using the suggested Option "AIGLX" "true".

    Read the article

  • apache performance timing out

    - by Mike
    Im running a webserver where I'm hosting about 6-7 websites. Most of these websites get their content from MySQL which is hosted on the same server. Traffic average per day is about 500-600 unique visitors, about 150K hits per week. But for some reason sometimes websites send a timeout, OR sometimes websites dont load all images. I know that I should perhaps separate static content from dynamic content, but for now I think that's not a possibility. I would appreciate any suggestions on how could I improve the performance of apache, so it doesn't keep timing out. Server is running on Sempron LE 1300; 2.3GHz,512K Cache 2GB RAM 10Mbps/1Mbps Services: MySQL, ProFTPD, Apache. Private + Shared = RAM used Program ---------------------------------------------------- 1.2 MiB + 54.0 KiB = 1.2 MiB proftpd 4.1 MiB + 23.0 KiB = 4.1 MiB munin-node 20.8 MiB + 120.5 KiB = 20.9 MiB mysqld 47.3 MiB + 9.9 MiB = 57.3 MiB apache2 (22) top: Mem: 2075356k total, 1826196k used, 249160k free, Timeout 35 KeepAlive On MaxKeepAliveRequests 300 KeepAliveTimeout 5 <IfModule mpm_prefork_module> StartServers 10 MinSpareServers 20 MaxSpareServers 20 MaxClients 60 MaxRequestsPerChild 1000 </IfModule> <IfModule mpm_worker_module> StartServers 2 MaxClients 150 MinSpareThreads 25 MaxSpareThreads 75 ThreadsPerChild 25 MaxRequestsPerChild 0 </IfModule>

    Read the article

  • VMWare converter performance

    - by bellocarico
    Hello, I have a question about my test lab. It's more to understand the concept more than apply this into production: I have an ESXi with few VMs linux/windows configured and I'd like to use VMWare converter to create backups. To speedup the process I decided to create a Windows VM on the same ESXi host where I've installed Windows 7 and VMWare Converter. The Host has a gigabit card but it's currently connected to a 100Mb FD port. Windows 7 sees a 1gb card connected. When I do the backup using VMWare converter I specify the host IP as source and destination, so I thought the copy could be faster then use my laptop across the network. Well, to cut a long sotry short: I get dreadful performance (4Mb/sec). I'm a buit confused on this because despite the fact that the host is running 100Mb communication between VMs and hosts shouldn't (correct me if I'm wrong) have any limitation instead. I did tweak windows 7 to optimise network performane but I got just a little improvement. i still need 4 hours to back up a 50Gb (thin) VM. Additionally I wanted to ask: Would jumbo frame help in this? I know that jumbo frame have to be supported end to end, and the network switch where the host is currently connected doesn't support this, but I was wondering: 1) Does ESXi host support jumbo frames at all? 2) Can I enable it somehow? 3) If I do so, I guess bulk transfert between VMs and host would improve, but would this affect the communication going through the real switch as this doesn't do jumbo? Thanks for reading

    Read the article

  • Setting up MongoDB in High Performance Computing LSF linux cluster

    - by Dnaiel
    I am trying to run mongo in a LSF cluster computing environment where I have no admin control. Our sysadmin installed mongodb, but it is not running. Any ideas on what should I ask the server admin to do for it to run? Or if I could run it locally? [node1382]allelix> mongod --dbpath /users/dnaiel/ma/mongodb/ Tue Oct 2 21:33:48 [initandlisten] MongoDB starting : pid=22436 port=27017 dbpath=/seq/epigenome01/allelix/ma/mongodb/ 64-bit host=node1382 Tue Oct 2 21:33:48 [initandlisten] Tue Oct 2 21:33:48 [initandlisten] ** WARNING: You are running on a NUMA machine. Tue Oct 2 21:33:48 [initandlisten] ** We suggest launching mongod like this to avoid performance problems: Tue Oct 2 21:33:48 [initandlisten] ** numactl --interleave=all mongod [other options] Tue Oct 2 21:33:48 [initandlisten] Tue Oct 2 21:33:48 [initandlisten] db version v2.2.0, pdfile version 4.5 Tue Oct 2 21:33:48 [initandlisten] git version: f5e83eae9cfbec7fb7a071321928f00d1b0c5207 Tue Oct 2 21:33:48 [initandlisten] build info: Linux ip-10-2-29-40 2.6.21.7-2.ec2.v1.2.fc8xen #1 SMP Fri Nov 20 17:48:28 EST 2009 x86_64 BOOST_LIB_VERSION=1_49 Tue Oct 2 21:33:48 [initandlisten] options: { dbpath: "/users/dnaiel/ma/mongodb/" } Tue Oct 2 21:33:48 [initandlisten] journal dir=users/dnaiel/ma/mongodb/journal Tue Oct 2 21:33:48 [initandlisten] recover begin Tue Oct 2 21:33:48 [initandlisten] info no lsn file in journal/ directory Tue Oct 2 21:33:48 [initandlisten] recover lsn: 0 Tue Oct 2 21:33:48 [initandlisten] recover /seq/epigenome01/allelix/ma/mongodb/journal/j._0 Tue Oct 2 21:33:48 [initandlisten] recover cleaning up Tue Oct 2 21:33:48 [initandlisten] removeJournalFiles Tue Oct 2 21:33:48 [initandlisten] recover done Tue Oct 2 21:33:48 [websvr] admin web console waiting for connections on port 28017 Tue Oct 2 21:33:48 [initandlisten] waiting for connections on port 27017 It basically waits forever and cannot start mongodb. These servers are not webservers but they do have network access, it's a cloud computing LSF environment system. Any advice would be welcome, thanks in advance.

    Read the article

  • iSCSI performance questions

    - by RyanLambert
    Hi everyone, apologies for the long-winded post in advance... Attempting to troubleshoot some iSCSI sluggishness on a brand new vSphere deployment (still in test). Layout is as such: 3 VSphere hosts, each with 2x 10GB NICs plugged into a pair of Nexus 5020s with a 10gig back-to-back between them. NICs are port-channeled in an active/active redundant fashion (using vPC-mac pinning for those of you familiar with N1KV) Both NICs carry service console, vmotion, iSCSI, and guest traffic. iSCSI is on a single subnet/single VLAN that is not routed through our IP network (strictly layer2) Had this been a 1gig deployment, we probably would have split the iSCSI traffic off onto separate NICs, but the price/port gets rather ridiculous when you start throwing 4+ NICs to a server in a 10gigabit infrastructure, and I'm not really convinced it's necessary. Open to dialogue/tech facts re: this, though. At this point even a single VM guest will boot slowly to iSCSI storage (EMC CX4 on the same Nexus 5020 10gig switches), and restores of VMs from iSCSI take about twice as long as we'd expect them to. Our server folks mentioned that if we split the iSCSI off onto its own NIC, performance seems significantly better. From a network perspective, I've run through the variables I can think of (port configuration errors, MTU problems, congestion etc.) and I'm coming up dry. There really is no other traffic on these hosts other than the very specific test being performed at the time. Important thing to note is that guest traffic works just fine... it seems storage is the only thing affected by whatever gremlin exists. Concluding that we're not 'overutilizing' the network infrastructure since we're doing hardly anything, I'm just looking for some helpful tips/ideas we can use to resolve this... preferably without hurling extra 10gig NICs that are going to sit around 10% utilization while we've got 70+% left on our others.

    Read the article

  • Bad Mumble control channel performance in KVM guest

    - by aef
    I'm running a Mumble server (Murmur) on a Debian Wheezy Beta 4 KVM guest which runs on a Debian Wheezy Beta 4 KVM hypervisor. The guest machines are attached to a bridge device on the hypervisor system through Virtio network interfaces. The Hypervisor is attached to a 100Mbit/s uplink and does IP-routing between the guest machines and the remaining Internet. In this setup we're experiencing a clearly recognizable lag between double-clicking a channel in the client and the channel joining action happening. This happens with a lot of different clients between 1.2.3 and 1.2.4 on Linux and Windows systems. Voice quality and latency seems to be completely unaffected by this. Most of the times the client's information dialog states a 16ms latency for both the voice and control channel. The deviation for the control channels mostly is a lot higher than the one of the voice channels. In some situations the control channel is displayed with a 100ms ping and about 1000 deviation. It seems the TCP performance is a problem here. We had no problems on an earlier setup which was in principle quite like the new one. We used Debian Lenny based Xen hypervisor and a soft-virtualised guest machine instead and an earlier version of the Mumble 1.2.3 series. The current murmurd --version says: 1.2.3-349-g315b5f5-2.1

    Read the article

  • Improving performance by using an additional static file server

    - by Max
    Hello there, I´m planning for a large website that includes many static assets (js, css, images and thumbnails) in the generated pages. That website will use TYPO3 as CMS (is is a customer requirement). I guess I could seriously improve performance / page load times by using a two server setup. One server where the main application (PHP) runs and another one where the static files sit being served by a trimmed down version of apache or something like lighthttpd. Including e. g. js or css files from the file server is of course no big deal. Just use an absolute url http://static.example.com/js/main.js and be done with it. But: that website will have pages with MANY thumbnails of e. g. product images on it. So I see two problems when the main application tries to create a thumbnail of some image: the original image like products/some.jpg is uploaded on the static file server and therefore not on the same server as the PHP application which tries to create the thumbnail. TYPO3 writes created thumbnails to a temp directory which is expected to be on the same server. Therefore, hundreds of thumbnails will be written and served from that temp directory which is on the same server as the main application - the static file server is in that case basically useless, all thumbnails will be requested from the server of the main application. So, my question is: how to overcome this shortcomings? Is it possible to "symlink" some directories to another server? So, for example, if PHP tries to open the original products image for thumbnail creation with imagecreate("products/some.jpg") the products folder actually "points" to the products folder on the static image server? I know something like this can be done with .htaccess but is it possible on file system level?

    Read the article

  • Poor write performance on Debian server running NFS with 22TB exported JFS filesystem

    - by user143546
    I am currently running a debian server that is exporting a large JFS filesystem (22TB) over NFS (nfs-kernel-server.) When attempting to write to the NFS share, the performance is very poor. The 22TB disk is sitting on a NAS mounted using iSCSI. It will bust for a moment near expected line speed, and then sit idle for several seconds. Very little traffic measured in the low kb/sec. The wait peeks on write. When reading from the NFS mount, the system operates at expected speeds (11MB/sec). The issue does not occur when using SFTP, rsync, or local coping (non-nfs). The issue persists between stable and testing releases. On the same machine I have a 14TB ext4 filesystem using the exact same export configuration that does not share the issue. This share is not in regular use and thus not consuming resources. NFS Server: cat /etc/exports /data2 10.1.20.86(rw,no_subtree_check,async,all_squash) cat /sys/block/sdb/queue/scheduler noop [deadline] cfq cat /etc/default/nfs-kernel-server RPCNFSDCOUNT=8 RPCNFSDPRIORITY=0 RPCMOUNTDOPTS=--manage-gids NEED_SVCGSSD= RPCSVCGSSDOPTS= NFS Client: cat /etc/fstab 10.1.20.100:/data2 /root/incoming nfs rw,noatime,soft,intr,noacl 0 2 cat /sys/block/sdb/queue/scheduler noop [deadline] cfq cat /proc/mounts 10.1.20.100:/data2/ /root/incoming nfs4 rw,noatime,vers=4,rsize=262144,wsize=262144,namlen=255,soft,proto=tcp,port=0,timeo=600,retrans=2,sec=sys,clientaddr=10.1.20.86,minorversion=0,addr=10.1.20.100 0 0 This problem has me pretty stumped. Any help would be greatly welcomed. Thanks.

    Read the article

  • Incredble low disk performance on HP DL385 G7

    - by 3molo
    Hi, As a test of the Opteron processor family, I bought a HP DL385 G7 6128 with HP Smart Array P410i Controller - no memory. The machine has 20GB ram 2x146GB 15k rpm SAS + 2x250GB SATA2, both in Raid 1 configurations. I run Vmware ESXi 4.1. Problem: Even with one virtual machine only, tried Linux 2.6/Windows server 2008/Windows 7, the VMs' feel really sluggish. With windows 7, the vmware converter installation even timed out. Tried both SATA and SAS disks and SATA disks are nearly unsusable, while SAS disks feels extremely slow.I can't see a lot of disk activity in the infrastructure client, but I haven't been looking for causes or even tried diagnostics because I have a feeling that it's either because of the cheap raid controller - or simply because of the lack of memory for it. Despite the problems, I continued and installed a virtual machine that serves a key function, so it's not easy to take it down and run diagnostics. Would very much like to know what you guys have to say of it, is it more likely to be a problem with the controller/disks or is it low performance because of budget components? Thanks in advance,

    Read the article

  • "What happens?" server performance monitor

    - by AlexAtNet
    Hello! After reviewing some thread about server monitoring software I end up with a simple question: Which of the server monitoring tools should I use for automatic detection of "abnormal" situations with recommendations on how to fix them? I look for software that checks the system performance after installation and calculate some average load values (memory, CPU, etc). And when something happens (CPU load is increased to 20%) then it tries to detect a reason for this. If it is apache, it should check for access logs. If mysql, it should check mysql logs and tell me what happens. It this is because some user decodes a lot of images, I'd like to know which command is executed, when and user name. The same for disk usage, memory, number of processes, threads and so on. Ideally, this software should periodically checks the system and report problems: errors in PHP error log, outdated packages, security vulnerabilities. In other word I'm looking a software that will keep my simple Debian/Apache/PHP/MySQL server without forcing me to monitor the charts every day. I hope that such program exists. Thanks, Alex

    Read the article

  • High-performance Academic Server [closed]

    - by PHPsmith
    Suppose I want to build a server for the university's academic interests. The server is dedicated only to a site, where users (students and lecturers) just view and fill the academic data. But at a time (e.g. once a semester), about 12,000 students will access the site simultaneously. Due to limitation of resources, I have to build the server using free software (except for the operating system Windows 7, the university has been prepared). The hardware is also limited to the usual 4-core computers (eg, Ivy Bridge Intel Core i7-3770) with approximately 16GB of memory (DDR3 1600 MHz), equipped with an RJ-45 port (Intel 82 579 Gigabit Ethernet). With all these limitations, I have to choose the software (web server, database, etc) are appropriate for this purpose is achieved. I decided to create a site in PHP. Please help me by answering the following questions based on your expertise. (my prime candidate software to consider after googling) Web server which is faster & stable & secure, when implemented and optimized for PHP? And why? (nginx) PHP accelerator which is faster & stable & compatible with the selected web server? And why? (APC with Zend Optimizer+) Database which is faster & stable & secure, when implemented and optimized for selected web server and selected PHP accelerator? (MySQL) Are there any errors that have been or will be happening from my condition is? If there is, please enlighten me? Is there anything else I need to know in order to achieve this goal? If there is, please enlighten me? I understand that the performance also depends on the implementation of source-code program, so I assume it will create a site with the best efficiency (e.g. using AJAX).

    Read the article

  • Software raid 0 with six disks performance

    - by user134880
    I have some problems with disk performance. I have 6 x WD 500Gb RE4 disks. Each disk gives 135Mb/sec throughput. All measurements are made with hdparm with options "-tT" (I know that it is just synthetic test, but I need some start point to make measurements). I have controller with Sil3124 x 4 ports PCI Express 1x So... RAID0 on controller with 2 disks gives 200Mb/s - ok, pcie limit. RAID0 on motherboard with 2 disks gives 270Mb/s - niceeee :) RAID0 on contorller with 4 disks gives 200Mb/s - ok, pcie limit. RAID0 on controller with 4 disks + 1 disks on motherboard = 340Mb/s ... :( RAID0 on controller with 4 disks + 2 disks on motherboard = 300Mb/s .... why? Any ideas? Maybe need more cpu power? Now there is Pentium D Dual core 2.8Ghz, 4Gb RAM. It is dedicated box for storage.. no other activity.

    Read the article

  • Optimize Apache performance

    - by Phliplip
    I'm looking for ways to optimize our current web server hosted in-house. I'm trying to supply as much relevant information below. Please let me know if you would require additional information in order to assist. Server is running 1 single website, which is an online pizza ordering platform built on Zend Framework (ver1). On traffic stats from the last month aprox 6.000 pageloads per day, concentrated mainly around dinnertime. Around 1500 loads/hour peaks in that period. We recently upgraded from a 2/2mbit aDSL-line to 100/100mbit fiber, and we still have performance issues at dinner time. We assumed the 2mbit was the issue. Website is pretty snappy in low-load periods. Hardware CPU: Intel(R) Xeon(R) CPU 5160 @ 3.00GHz (3000.13-MHz K8-class CPU) Mem: 328M Active, 4427M Inact, 891M Wired, 244M Cache, 623M Buf, 33M Free Swap: 16G Total, 468K Used, 16G Free (6GB physical, 16GB swap) Filesystem Type Size Used Avail Capacity Mounted on /dev/ad7s1a ufs 4.8G 768M 3.7G 17% / devfs devfs 1.0K 1.0K 0B 100% /dev /dev/ad7s1g ufs 176G 5.2G 157G 3% /home /dev/ad7s1e ufs 4.8G 2.8M 4.5G 0% /tmp /dev/ad7s1f ufs 19G 3.5G 14G 19% /usr /dev/ad7s1d ufs 4.8G 550M 3.9G 12% /var Server OS FreeBSD 8.2-RELEASE Software apache-2.2.17 php5-5.3.8 mysql-server-5.5 Apache footprint (example, taken from # top) 31140 www 1 45 0 377M 41588K lockf 2 0:00 0.00% httpd 31122 www 1 44 0 375M 35416K lockf 2 0:00 0.00% httpd 31109 www 1 44 0 375M 38188K lockf 2 0:00 0.00% httpd 31113 www 1 44 0 375M 35188K lockf 2 0:00 0.00% httpd Apache is using the prefork MPM, APC (Alternative PHP Cache). SSL module is loaded, but not utilized (as in don't really work, thus not used). There is a file containing settings for MPM modules, but as i see it's not included in the httpd.conf file, the include line is commented out. Thus i would guess that the prefork MPM is working of default values too. Here are some other Apache conf values that i found - which are included in https.conf Timeout 300 KeepAlive On MaxKeepAliveRequests 100 KeepAliveTimeout 5 UseCanonicalName Off HostnameLookups Off

    Read the article

  • Performance of external USB disk with ESXi5

    - by PeterMmm
    I have a new HP DL120 G7 server with ESXi5. One VM is a Win2003 instalation and I have an external USB2.0 drive attached by USB Controller and USB Device. I copy a 4GB file from external USB to server disk. In the VM that takes up to 10 minutes. On a native Win2003 that takes aprox. 3 minutes. I have no explaination for that diference: In any case the bottleneck is the USB connection, much slower than the disks (SAS, RAID1). If the USB connection on the VM would be USB1.1 and not USB2.0 it would take much more time. (The disk performance between server partitions on the VM is correct. - see update) Could be that my native box is extremely fast and the VM is the normal case. ??? Update I try with passtrough and a first run copy the same data in aprox. 7 minutes. Still 2 times slower than the native connection. I also did another messure and the copy between partitions on the same VM takes 3 minutes.

    Read the article

  • c# WinForms ReportViewer Performance issue using RefreshReport() and ServerReport.SetParameters()

    - by mdk
    Hi All, Currently I am writing a c# client application that uses the WinForms ReportViewer Control to display reports from a remote server. I am having performance troubles with the ReportViewer Control, to be specific with the 2 methods reportViewer.ServerReport.SetParameters() and reportViewer.RefreshReport() – they both take a really long time to complete and not just on the very first call, but on each subsequent call as well. SetParameters() takes 20 to 40 seconds (they vary greatly in time, some execute event okay fast) and RefreshReport() is a bit faster but still takes ages. I don’t think the server is the culprit, as the same report viewed using the browser renders pretty fast, about a second tops. The report in question doesn't matter as well. When I break into the process and take a look at the call stack, I see a call to Socket.DoConnect. So I thought that’s a good reason to start using fiddler and I installed it, disabled caching and fired up the app again to see which call takes that long to connect, but the performance issue was gone. By using a proxy I am having the same performance as the webbrowser. FYI: I am using NTLM authentication in the following way: reportViewer.ServerReport.ReportServerCredentials.NetworkCredentials = new NetworkCredentials() { Username = ... } I don’t have a strong webbackground, so I guess my question is: What should this tell me / What should I be looking into? (Btw: Adding fiddler to my installation package is not the solution I am looking for :)) I am grateful for any pointers. Take care, -Martin

    Read the article

  • emacs tramp performance

    - by Oleg Pavliv
    Is there a way to improve emacs tramp performance? For me it's faster to open an external ftp client (filezilla), transfer files to the local disk and open them in an external editor (notepad) than open them with emacs. I use emacs23.1 under windows xp. I tried different tramp-default-method (telnet, pscp, ftp), all of them have the same performance. Profiling results with elp-instrument-package are the following (I opened 3 remote files of 1.5 MB each one) tramp-file-name-handler 1461 350.41599999 0.2398466803 tramp-sh-file-name-handler 1461 350.02699999 0.2395804243 tramp-send-command 227 179.63400000 0.7913392070 tramp-send-command-and-check 205 177.77600000 0.8672000000 tramp-wait-for-regexp 227 176.47800000 0.7774361233 tramp-wait-for-output 226 176.40000000 0.7805309734 tramp-barf-unless-okay 18 133.46699999 7.4148333333 tramp-handle-insert-file-contents 3 132.046 44.015333333 tramp-handle-file-local-copy 3 131.281 43.760333333 tramp-accept-process-output 2375 112.95100000 0.0475583157 So, actual file transfer takes 132 sec, about 1/3 of total time. Why does it spend so much time in tramp-sh-file-name-handler? I tried to advice a function tramp-sh-file-name-handler to store and return cached results but it does not work, probably this function has some side effects. Any ideas how to improve tramp performance? (I use emacs 23.1 under WindowsXP)

    Read the article

  • Difference in performance between Stax and DOM parsing

    - by Fazal
    I have been using DOM for a long time and as such DOM parsing performance wise has been pretty good. Even when dealing with XML of about 4-7 MB the parsing has been fast. The issue we face with DOM is the memory footprint which become huge as soon as we start dealing with large XMLs. Lately I tried moving to Stax (Streaming parsers for XML) which are supposed top be second generation parsers (reading about Stax it said its the fastest parser now). When I tried stax parser for large XML for about 4MB memory footprint definitely reduced drastically but time take to parse entire XML and create java object out of it increased almost by 5 times over DOM. I used sjsxp.jar implementation of Stax. I can deuce to some extent logically that performance may not be extremely good due to streaming nature of the parser but a reduction of 5 time (e.g. DOM takes about 8 seconds to build object for this XML, whereas Stax parsing took about 40 seconds on average) is definitely not going to be acceptable. Am I missing some point here completely as I am not able to come to terms with these performance numbers

    Read the article

  • Writing to a log4net FileAppender with multiple threads performance problems

    - by Wayne
    TickZoom is a very high performance app which uses it's own parallelization library and multiple O/S threads for smooth utilization of multi-core computers. The app hits a bottleneck where users need to write information to a LogAppender from separate O/S threads. The FileAppender uses the MinimalLock feature so that each thread can lock and write to the file and then release it for the next thread to write. If MinimalLock gets disabled, log4net reports errors about the file being already locked by another process (thread). A better way for log4net to do this would be to have a single thread that takes care of writing to the FileAppender and any other threads simply add their messages to a queue. In that way, MinimalLock could be disabled to greatly improve performance of logging. Additionally, the application does a lot of CPU intensive work so it will also improve performance to use a separate thread for writing to the file so the CPU never waits on the I/O to complete. So the question is, does log4net already offer this feature? If so, how do you do enable threaded writing to a file? Is there another, more advanced appender, perhaps? If not, then since log4net is already wrapped in the platform, that makes it possible to implement a separate thread and queue for this purpose in the TickZoom code. Sincerely, Wayne

    Read the article

  • Performance degrades for more than 2 threads on Xeon X5355

    - by zoolii
    Hi All, I am writing an application using boost threads and using boost barriers to synchronize the threads. I have two machines to test the application. Machine 1 is a core2 duo (T8300) cpu machine (windows XP professional - 4GB RAM) where I am getting following performance figures : Number of threads :1 , TPS :21 Number of threads :2 , TPS :35 (66 % improvement) further increase in number of threads decreases the TPS but that is understandable as the machine has only two cores. Machine 2 is a 2 quad core ( Xeon X5355) cpu machine (windows 2003 server with 4GB RAM) and has 8 effective cores. Number of threads :1 , TPS :21 Number of threads :2 , TPS :27 (28 % improvement) Number of threads :4 , TPS :25 Number of threads :8 , TPS :24 As you can see, performance is degrading after 2 threads (though it has 8 cores). If the program has some bottle neck , then for 2 thread also it should have degraded. Any idea? , Explanations ? , Does the OS has some role in performance ? - It seems like the Core2duo (2.4GHz) scales better than Xeon X5355 (2.66GHz) though it has better clock speed. Thank you -Zoolii

    Read the article

< Previous Page | 87 88 89 90 91 92 93 94 95 96 97 98  | Next Page >