Search Results

Search found 13249 results on 530 pages for 'virtualized performance'.

facebook twitter digg google delicious technorati stumbleupon myspace wordpress linkedin gmail igoogle windows live tumblr viadeo yahoo buzz yahoo mail yahoo bookmarks favorites email print

Page 18/530 | < Previous Page | 14 15 16 17 18 19 20 21 22 23 24 25  | Next Page >

  • Basic multicast network performance problems

    - by davedavedave
    I've been using mpong from 29west's mtools package to get some basic idea of multicast latency across various Cisco switches: 1Gb 2960G, 10Gb 4900M and 10Gb Nexus N5548P. The 1Gb is just for comparison. I have the following results for ~400 runs of mpong on each switch (sending 65536 "ping"-like messages to a receiver which then sends back -- all over multicast). Numbers are latencies measured in microseconds. Switch Average StdDev Min Max 2960 (1Gb) 109.68463 0.092816 109.4328 109.9464 4900M (10Gb) 705.52359 1.607976 703.7693 722.1514 NX 5548(10Gb) 58.563774 0.328242 57.77603 59.32207 The result for 4900M is very surprising. I've tried unicast ping and I see the 4900 has ~10us higher latency than the N5548P (average 73us vs 64us). Iperf (with no attempt to tune it) shows both 10Gb switches give me 9.4Gbps line speed. The two machines are connected to the same switch and we're not doing any multicast routing. OS is RHEL 6. 10Gb NICs are HP 10GbE PCI-E G2 Dual-port NICs (I believe they are rebranded Mellanox cards). The 4900 switch is used in a project with tight access control so I'm waiting for approval before I can access it and check the config. The other two I have full access to configure. I've looked at the Cisco document[2] detailing differences between NX-OS and IOS w.r.t multicast so I've got some ideas to try out but this isn't an area where I have much expertise. Does anyone have any idea what I should be looking at once I get access to the switch? [1] http://docwiki.cisco.com/wiki/Cisco_NX-OS/IOS_Multicast_Comparison

    Read the article

  • Performance difference between compiled and binary linux distributions/packages

    - by jozko
    I was searching a lot on the internet and couldn't find an exact answer. There are distros like Gentoo (or FreeBSD) which does not come with binaries but only with source code for packages (ports). The majority of distros uses binary backages (debian, etc.). First question: How much speed increase can I expect from compiled package? How much speed increase can I get from real world packages like apache or mysql? i.e. queries per second? Second question: Does binary package means it does not use any CPU instructions that was introduced after first AMD 64bit CPU? With the 32bit packages does it mean that the package will run on 386 and basically does not use most of the modern CPU instructions? Additional info: - I am not talking about desktop, but server environment. - I dont care about compile time - I have more servers, so speed increase more than 15% is worth for using source code packages - Please no flamewars. Thank you very much

    Read the article

  • SQL Server 2005 standard filegroups / files for performance on SAN

    - by Blootac
    Ok so I've just been on a SQL Server course and we discussed the usage scenarios of multiple filegroups and files when in use over local RAID and local disks but we didn't touch SAN scenarios so my question is as follows; I currently have a 250 gig database running on SQL Server 2005 where some tables have a huge number of writes and others are fairly static. The database and all objects reside in a single file group with a single data file. The log file is also on the same volume. My interpretation is that separate data files should be used across different disks to lessen disk contention and that file groups should be used for partitioning of data. However, with a SAN you obviously don't really have the same issue of disk contention that you do with a small RAID setup (or at least we don't at the moment), and standard edition doesn't support partitioning. So in order to improve parallelism what should I do? My understanding of various Microsoft publications is that if I increase the number of data files, separate threads can act across each file separately. Which leads me to the question how many files should I have. One per core? Should I be putting tables and indexes with high levels of activity in separate file groups, each with the same number of data files as we have cores? Thank you

    Read the article

  • apache and ajp performance

    - by user12145
    I have an apache sitting in front of two tomcat app servers(one on the same physical server, the other on a different one) that does time consuming work(0.5 sec to 10sec per request). The apache http server is getting killed by an average of 1 to 2 concurrent requests per second. both Server spec is about 2GB of RAM. Is there a way to optimize apache to handle the load? any advise is welcome. BalancerMember ajp://localhost:8009/whoisserver BalancerMember ajp://XXX.XX.XXX.XX:8009/whoisserver I keep getting the following in apache2.2 log: [Mon Dec 28 00:31:02 2009] [error] ajp_read_header: ajp_ilink_receive failed [Mon Dec 28 00:31:02 2009] [error] (120006)APR does not understand this error code: proxy: read response failed from 127.0.0.1:8009 (localhost)

    Read the article

  • Improve performance of bind9 service restart

    - by Jakob
    Hi, I'm setting up a name server hosting DNS for a large number of domains, 50,000 - 100,000 domains. I will be using Bind9 and the service will need to be restarted several times a day. I have made some tests and it seems that restart of the Bind9 service scales very poorly with the number of domains. #domains | restart time ----------------------- 10,000 | 3.1 sec 25,000 | 8.9 sec 50,000 | 50 sec 100,000 | 7:50 min Is there some way to speedup the restart of the service? I have noticed that restart only utilizes one core, is there some way for it to use more cores? The Bind9 version is 9.7.1-P2 with default configuration. The server running Bind9 is a Intel Core 2 Due 2.93 GHz with 4 GB memory and Ubuntu Server 10.10. Any help will be appreciated. Jakob

    Read the article

  • PostgreSQL: performance descrease due to index bloatper

    - by Henry-Nicolas Tourneur
    I'm running a PgSQL 8.1 on a CentOS 4.4 system (not upgradable unfortunately). There's a Java app running on top of the PgSQL daemon and we got to reindex the database every 2 months or so. Also important: the database isn't growing. It looks like the bloat is now coming faster than before and this tends to increase. My config is available here, autovacuum daemon is enabled and running quite often: pastebin.com/RytNj7dK You can also find the output of this query wiki.postgresql.org/wiki/Show_database_bloat 3 hours after running reindex: http://pastebin.com/raw.php?i=75fybKyd 72 hours after running reindex: http://pastebin.com/raw.php?i=89VKd7PC Does anyone have any idea what should I tweak to get rid of that growing bloat? Thanks for your help PS: due to antispam prevention system, I had to remove the first 2 http:// prefixes for my two first links.

    Read the article

  • Finegrain Performance Reporting on svchost.exe

    - by Randolpho
    This is something that's always bothered me, so I'll ask the serverfault community. I love me some Process Explorer for keeping track of more than just the high-level tasks you get in the Task Manager. But I constantly want to know which of those dozen services hosted in a single process under svchost is making my processor spike. So... is there any non-intrusive way to find this information out?

    Read the article

  • Identifying Hard Drive as performance bottleneck for desktop machines

    - by Programming Hero
    I'm working in a development team where we all use laptops so we can work in multiple locations. These laptops are proving notoriously slow for development work, but at a glance they all look to have the specification for a much faster experience: CPU - Intel Core 2 Duo T7500 Memory - 2GB of RAM We all experience the biggest delays when the hard-drives are being accessed, particularly when swap-files are being thrashed. After doing a little bit of profile, a colleague discovered that our HDDs are seeing Read/Write speeds of about 10MB/sec. This seems abnormally low and we believe it the cause of the problem. Sensibly (though somewhat annoyingly) our business wont blow money on faster drives just to see if it fixes the problem; we need to illustrate this is definitely the problem and that buying some solid-state drives will make it go away. I need some way of showing how 90% of the system resources aren't being used over the course of a day, and that whenever there is utilization, it's all in HDD reads or writes. Are there any tools I could use to provide this information? Does it seem likely the problem is going to be fixed by a faster drive? Should I be looking for alternatives?

    Read the article

  • FreeBSD: Samba performance over GBit-Ethernet

    - by Axel Gneiting
    I'm using a FreeBSD NAS with RAID-Z. I can read ~300MB/s from the ZFS disks to /dev/null on the box, but only get about 50MB/s over GBit-Ethernet with SMB to Windows 7 (Samba 3.5.6). Both systems have Intel-PCIe-NICs and are connected directly. Samba is configured to use AIO and I already tried to tune TCP/IP: kern.ipc.maxsockbuf=16777216 net.inet.tcp.sendspace=1048576 net.inet.tcp.recvspace=1048576 net.inet.tcp.sendbuf_max=8388608 net.inet.tcp.recvbuf_max=8388608 net.inet.tcp.delayed_ack=0 Any ideas what's causing the bottleneck? I think the link should handle 100 MB/s easily.

    Read the article

  • monitoring TCP/IP performance on Solaris

    - by Andy Faibishenko
    I am trying to tune a high message traffic system running on Solaris. The architecture is a large number (600) of clients which connect via TCP to a big Solaris server and then send/receive relatively small messages (.5 to 1K payload) at high rates. The goal is to minimize the latency of each message processed. I suspect that the TCP stack of the server is getting overwhelmed by all the traffic. What are some commands/metrics that I can use to confirm this, and in case this is true, what is the best way to alleviate this bottleneck?

    Read the article

  • How to calculate RAM value on performance per dollar spent

    - by Stucko
    Hi, I'm trying to make decisions on buying a new PC. I have most specifications (processor/graphic card/hard disk) pin-downed except for RAM. I am wondering what is the best RAM configuration for the amount of money I'm spending. As the question of best is subjective, I'd like to know how would I calculate the value of RAM sticks sold. 1.(sample)The value of amount of memory: 1) CORSAIR PC1333 D3 2GB = costs $80 2) CORSAIR PC1333 D3 4GB = costs $190 would it be better to buy 2 of item 1) instead of 1 of item 2) ?? Although I would normally choose to have 1 of 2) as the difference is only (190-(80*2)) = 30 as I would save 1 DIMM slot, What I need is the value per amount: 1) 80/ 2 = $40 per 1GB 2) 190/ 4 = $47.5 per 1GB 2. The value of frequency: 1) CORSAIR PC1333 4GB = costs 190 2) CORSAIR PC1600C7 4GB = costs 325 Im not even sure of the denominator ... $ per 1 ghz speed? 3. The value of latency: 1) CORSAIR CMP1600C8 8-8-8-24 2GBx3 (triple channel) = costs 589 2) CORSAIR CMP1600C7D 7-7-7-20 2GBx3 (triple channel) = costs 880 Im not even sure of the denominator ... $ per 1 ghz speed? Just for your information i'd like to get the best out of the money im going to spend to put on a 6 DIMM slot i7core motherboard.

    Read the article

  • NAS Performance issues

    - by Markus
    I bought a NAS from Conceptronic CH3MNAS and built in two Western Digital 1,5TB Green Drives. I only get a write speed of 6mb/s in LAN The configuration of the drives is as follows: - Raid 0 - EXT2 Is that a normal speed?

    Read the article

  • Vista startup performance

    - by PeterMmm
    After 2 years my Vista (32-bit) machine now boots quite slowly. The event viewer tells me two programs comming up slow: explorer.exe and svchost.exe. Fine. But what can i do that these programs comes up as quickly as before ?

    Read the article

  • Webserver: Performance impact when storing session files on /dev/shm

    - by GetFree
    I have a website runing on a typical setup: Linux, Apache, PHP, MySQL. However, what's not typical about it, is that it's getting tons of traffic (400,000+ visits a day) and so, efficiency is becoming more and more important to me. I'm constantly looking for things I could optimize and, right now, my attention is focused on PHP's session files. There's a hell lot of session files constantly being read and created on the /tmp directory. So my question is: Is it a good idea to store the session files in /dev/shm (tmpfs) in order to speed things up a little bit??

    Read the article

  • Hard Drive Fundamentals And Verifying Disk Performance

    - by Agnel Kurian
    Over the past few months, my Windows XP machine has slowed down to a crawl. It takes about 10-15 minutes to go from power-up to reaching a responsive state. I have reasons to believe that this is a result of the hard disk slowing down. Questions: Do hard disks slow down as a result of mechanical wear and tear ...or age? How do I check if my disk has slowed down? Conversely, how can I verify that my disk is indeed running at the speed it's designed to run at? Could drivers be at fault here? Do hard disks come with drivers or does Windows use a generic driver?

    Read the article

  • Methodologies for performance-testing a WAN link

    - by Chopper3
    We have a pair of new diversely-routed 1Gbps Ethernet links between locations about 200 miles apart. The 'client' is a new reasonably-powerful machine (HP DL380 G6, dual E56xx Xeons, 48GB DDR3, R1 pair of 300GB 10krpm SAS disks, W2K8R2-x64) and the 'server' is a decent enough machine too (HP BL460c G6, dual E55xx Xeons, 72GB, R1 pair of 146GB 10krpm SAS disks, dual-port Emulex 4Gbps FC HBA linked to dual Cisco MDS9509s then onto dedicated HP EVA 8400 with 128 x 450GB 15krpm FC disks, RHEL 5.3-x64). Using SFTP from the client we're only seeing about 40Kbps of throughput using large (2GB) files. We've performed server to 'other local server' tests and see around 500Mbps through the local switches (Cat 6509s), we're going to do the same on the client side but that's a day or so away. What other testing methods would you use to prove to the link providers that the problem is theirs?

    Read the article

  • Solaris TCP/IP performance tuning

    - by Andy Faibishenko
    I am trying to tune a high message traffic system running on Solaris. The architecture is a large number (600) of clients which connect via TCP to a big Solaris server and then send/receive relatively small messages (.5 to 1K payload) at high rates. The goal is to minimize the latency of each message processed. I suspect that the TCP stack of the server is getting overwhelmed by all the traffic. What are some commands/metrics that I can use to confirm this, and in case this is true, what is the best way to alleviate this bottleneck? PS I posted this on StackOverflow originally. One person suggested snoop and dtrace. dtrace seems pretty general - are there any additional pointers on how to use it to diagnose TCP issues?

    Read the article

  • Google bots are severely affecting site performance

    - by Lynn
    I have an aggregate site on a linux server that pulls in feeds from a universe of about 2,000 blogs. It's in Wordpress 3.4.2 and I have a cron job that is staggered to run five times an hour on another server to pull in the stories and then publish them to the front page of this site. This is so I didn't put too much pressure all on one server. However, the Google bots, which visit a few times every hour bring the server to its knees in the morning and evenings when there is an increase in traffic on the site. The bots have something like 30,000 links to follow at this point. How do I throttle the bots to simply grab the new stories off the front page and stop there? EDIT- Details of my server configuration: The way we have this set up is the server that handles all the publishing is an unmanaged instance via AWS. It mounts the NFS server and connects to the RDS to update content, etc. You get to this publishing instance via a plugin that detects the wp-admin link and then redirects you into there. The front end app server also mounts the NFS and requests data from the RDS. It is the only one that has the WP Super Cache on it.... The OS is Ubuntu on the App server and the NFS runs CentOs. The front end is Nginx and the publishing server is Apache.

    Read the article

  • apache and ajp performance

    - by user12145
    I have an apache sitting in front of two tomcat app servers(one on the same physical server, the other on a different one) that does time consuming work(0.5 sec to 10sec per request). The apache http server is getting killed by an average of 1 to 2 concurrent requests per second. both Server spec is about 2GB of RAM. Is there a way to optimize apache to handle the load? any advise is welcome. BalancerMember ajp://localhost:8009/xxxxxx BalancerMember ajp://XXX.XX.XXX.XX:8009/xxxxxx I keep getting the following in apache2.2 log: [Mon Dec 28 00:31:02 2009] [error] ajp_read_header: ajp_ilink_receive failed [Mon Dec 28 00:31:02 2009] [error] (120006)APR does not understand this error code: proxy: read response failed from 127.0.0.1:8009 (localhost)

    Read the article

  • SamFS performance problem on file creation

    - by Gregor Longariva
    I have two samfs filesystems (samfs1 and samfs2), both on the same 6130, both with the same config/watermarks/timeouts etc. creating a file on samfs2 works as it should, on samfs1 not. A little simple script shows up, that every while and then the file creation needs between 11 and 28 seconds: stan 12:32 [scratch]# while ( 1 ) while? echo - while? time echo test file while? time mv file file2 while? echo + while? sleep 1 while? end 0.00u 0.00s 0:00.01 0.0% 0.00u 0.00s 0:00.00 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.03 0.0% + 0.00u 0.00s 0:23.71 0.0% 0.00u 0.00s 0:00.14 0.0% + 0.00u 0.00s 0:00.18 0.0% 0.00u 0.00s 0:00.13 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.05 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.06 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.05 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.05 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.05 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.04 0.0% + 0.00u 0.00s 0:00.04 0.0% 0.00u 0.00s 0:00.05 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.01 0.0% + 0.00u 0.00s 0:26.05 0.0% 0.00u 0.00s 0:00.50 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.06 0.0% + 0.00u 0.00s 0:00.00 0.0% 0.00u 0.00s 0:00.12 0.0% + Any idea where the problem could be?

    Read the article

  • poor performance when deleteing many files

    - by choppy
    I've got two machines: The first is IBM Blade with 24 cores 96GB RAM and single local hard drive with 278GB divided to 4 partitions: 1. c: - 40GB; 3GB free 2. d: - 40GB; 37GB free 3. e: - 198322GB; 198.1 free 4. 100MB (EFI system Partition) Formatted with GPT The other is pizza server with 4 cores 8GB RAM and single local hard drive with 273GB divided to 3 partitions: 1. c: - 136.81; 20GB free 2. d: - 88.74GB; 87.91 free 3. e: - 47.85GB; 46.91 free Formatted with MBR I have two scripts, the first creates 20,000 files in one directory, each file size is 192KB, the second delete the folder (recursive) and prints how much time it toke to delete all files. The problem is on the first server (blade) it takes about 2 minutes to delete all 20,000 files while on the second (pizza) it takes about 4 seconds!? Both servers have clean windows server 2008R2 with no special application running on background. Any ideas what is going on?

    Read the article

facebook twitter digg google delicious technorati stumbleupon myspace wordpress linkedin gmail igoogle windows live tumblr viadeo yahoo buzz yahoo mail yahoo bookmarks favorites email print

< Previous Page | 14 15 16 17 18 19 20 21 22 23 24 25  | Next Page >