Search Results

Search found 4946 results on 198 pages for 'proper benchmarking'.

Page 45/198 | < Previous Page | 41 42 43 44 45 46 47 48 49 50 51 52  | Next Page >

  • Performance: Nginx SSL slowness or just SSL slowness in general?

    - by Mauvis Ledford
    I have an Amazon Web Services setup with an Apache instance behind Nginx with Nginx handling SSL and serving everything but the .php pages. In my ApacheBench tests I'm seeing this for my most expensive API call (which cache via Memcached): 100 concurrent calls to API call (http): 115ms (median) 260ms (max) 100 concurrent calls to API call (https): 6.1s (median) 11.9s (max) I've done a bit of research, disabled the most expensive SSL ciphers and enabled SSL caching (I know it doesn't help in this particular test.) Can you tell me why my SSL is taking so long? I've set up a massive EC2 server with 8CPUs and even applying consistent load to it only brings it up to 50% total CPU. I have 8 Nginx workers set and a bunch of Apache. Currently this whole setup is on one EC2 box but I plan to split it up and load balance it. There have been a few questions on this topic but none of those answers (disable expensive ciphers, cache ssl, seem to do anything.) Sample results below: $ ab -k -n 100 -c 100 https://URL This is ApacheBench, Version 2.3 <$Revision: 655654 $> Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/ Licensed to The Apache Software Foundation, http://www.apache.org/ Benchmarking URL.com (be patient).....done Server Software: nginx/1.0.15 Server Hostname: URL.com Server Port: 443 SSL/TLS Protocol: TLSv1/SSLv3,AES256-SHA,2048,256 Document Path: /PATH Document Length: 73142 bytes Concurrency Level: 100 Time taken for tests: 12.204 seconds Complete requests: 100 Failed requests: 0 Write errors: 0 Keep-Alive requests: 0 Total transferred: 7351097 bytes HTML transferred: 7314200 bytes Requests per second: 8.19 [#/sec] (mean) Time per request: 12203.589 [ms] (mean) Time per request: 122.036 [ms] (mean, across all concurrent requests) Transfer rate: 588.25 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 65 168 64.1 162 268 Processing: 385 6096 3438.6 6199 11928 Waiting: 379 6091 3438.5 6194 11923 Total: 449 6264 3476.4 6323 12196 Percentage of the requests served within a certain time (ms) 50% 6323 66% 8244 75% 9321 80% 9919 90% 11119 95% 11720 98% 12076 99% 12196 100% 12196 (longest request)

    Read the article

  • Website has become slower on a VPS, was much fast on a shared host. What's wrong?

    - by Arpit Tambi
    My shared host suspended my website stating system overload, so I moved my website to a VPS which has 4GB RAM. But for some reason the website has become very slow. This is the vmstat output - procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------ r b swpd free buff cache si so bi bo in cs us sy id wa st 1 0 0 3050500 0 0 0 0 0 1 0 0 0 0 100 0 0 Here's the Apache Benchmark output for a STATIC html page I ran on the server itself - Benchmarking www.ask-oracle.com (be patient)...apr_poll: The timeout specified has expired (70007) Total of 20 requests completed Update: Server Config: List item Centos 5.6 4 cores cpu 4 GB RAM LAMP stack with APC Wordpress Only one website It takes almost double time to load now, same website was much fast on shared hosting. I know I need to tweak some settings but have no clue where to start from? I have already tried to optimize apache, mysql etc. Update 2: CPU usage is low, see uptime output: 11:09:02 up 7 days, 21:26, 1 user, load average: 0.09, 0.11, 0.09 Update 3: When I load any webpage, browser shows "Waiting" for a long time and then page loads quickly. So I suspect server can accept only limited connections and holds extra connections in a waiting state. How to check this? Update 4: Following is the output on executing netperf TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to localhost.localdomain (127.0.0.1) port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 9615.40 [root@ip-118-139-177-244 j3ngn5ri6r01t3]# Here are the Apache MPM settings from httpd.conf, do they look okay? <IfModule worker.c> StartServers 5 MaxClients 100 MinSpareThreads 50 MaxSpareThreads 250 ThreadsPerChild 125 MaxRequestsPerChild 10000 ServerLimit 100 </IfModule>

    Read the article

  • Why is writing to my external hard drive slow, while benchmarks show fast writing?

    - by matix2267
    I have an iOmega eGo 320GB portable drive connected through USB2.0 to my laptop running Windows Vista. It's been working fine for quite some time until recently it became very slow when writing e.g. when copying ~300MB movie over to the drive at first it is extremely fast but it actually doesn't write it only puts in cache and then hangs on last 10-20MBs for about a minute. When copying larger files it's the same story: starts fast but then slows down to ~5MB/s (sometimes even slower down to 2MB/s). Strange thing is that I have always had caching disabled for this drive (it was disabled by default and I never bothered changing it). At first I thought that the disk is dying so I checked S.M.A.R.T. values and everything is fine there. I also run chkdsk and it seemed to fix the problem - it worked fast for a few minutes but then it slowed down again. I also tried plugging it into another USB port - no difference. Additionally I noticed that reading under certain circumstances is sometimes slower e.g. loading times for some games are ~10 times longer, whereas simple copying files from this drive to my internal HDD is fast. I ran a speed benchmark using CrystalDiskMark with a 5x100MB run and strangely got these results: read write (MB/s) Seq 33.05 28.25 512k 17.30 15.27 4k 0.267 0.372 4kQD32 0.510 0.260 This is different from what most other people have (I've found many threads about slow disk write while googling but all of them were slow on benchmarks too) which is why I decided to post this problem here. BTW most of the time when writing (or sometimes reading) the activity led is mostly idle (blinks a while and then stops for longer, sometimes has slower blinks ~1 sek, sometimes goes off for a few seconds - extremely long blink :) ) but when benchmarking, defragmenting or just reading (copying from this drive, installing apps from installers there, watching HD videos) it is blinking really fast (like it should) and there are no slowdowns. It shouldn't be driver issue unless stock Windows drivers have some issues I'm not aware of.

    Read the article

  • IBM BladeCenter S: Disk Configuration

    - by gravyface
    Have just the one storage bay right now (SAS 15K 600GB x 6) and have configured one storage pool in RAID 10 with 4 disks (and two global spares). For each blade, I've created a volume and mapped accordingly: Blade #1 400 GB Blade #2 200 GB Blade #3 100 GB Blade #4 100 GB When I boot up Blade 1 and enter into the UEFI Setup (F1) followed by the Adapters and UEFI Drivers LSI Logic Fusion MPT SAS Driver Utility, I see 4 disks: two are the on-board 73GB drives, the other two are 200GB each and assume I'm being presented with two logical disks from the volume I created and mapped to this blade. I was a bit surprised by this: I figured I would've been presented with one logical drive per volume, not two. I'm assuming I can just configure whatever RAID level I wish that supports two disks, but not really sure what the benefits/trade-offs here. Should I go with RAID 10 on top of RAID 10? RAID 0? Software RAID 0/1/10? Does it even matter? If this is "normal" to see two disks, then I'm going to likely just do some benchmarking and see if it makes a difference changing the RAID levels (my guess is no); if this is not normal, well, please let me know. :)

    Read the article

  • Tuning Linux + HAProxy

    - by react
    I'm currently rolling out HAProxy on Centos 6 which will send requests to some Apache HTTPD servers and I'm having issues with performance. I've spent the last couple of days googling and still can't seem to get past 10k/sec connections consistently when benchmarking (sometimes I do get 30k/sec though). I've pinned the IRQ's of the TX/RX queues for both the internal and external NICS to separate CPU cores and made sure HAProxy is pinned to it's own core. I've also made the following adjustments to sysctl.conf: # Max open file descriptors fs.file-max = 331287 # TCP Tuning net.ipv4.tcp_tw_reuse = 1 net.ipv4.ip_local_port_range = 1024 65023 net.ipv4.tcp_max_syn_backlog = 10240 net.ipv4.tcp_max_tw_buckets = 400000 net.ipv4.tcp_max_orphans = 60000 net.ipv4.tcp_synack_retries = 3 net.core.somaxconn = 40000 net.ipv4.tcp_rmem = 4096 8192 16384 net.ipv4.tcp_wmem = 4096 8192 16384 net.ipv4.tcp_mem = 65536 98304 131072 net.core.netdev_max_backlog = 40000 net.ipv4.tcp_tw_reuse = 1 If I use AB to hit the a webserver directly I easily get 30k/s connections. If I stop the webservers and use AB to hit HAProxy then I get 30k/s connections but obviously it's useless. I've also disabled iptables for now since I read that nf_conntrack can slow everything down, no change. I've also disabled the irqbalance service. The fact that I can hit each individual device with 30k/s makes me believe the tuning of the servers is OK and that it must be some HAProxy config? Here's the config which I've built from reading tuning articles, etc http://pastebin.com/zsCyAtgU The server is a dual Xeon CPU E5-2620 (6 cores) with 32GB of RAM. Running Centos 6.2 x64. The private and public interfaces are on separate NICS. Anyone have any ideas? Thanks.

    Read the article

  • When using software RAID and LVM on Linux, which IO scheduler and readahead settings are honored?

    - by andrew311
    In the case of multiple layers (physical drives - md - dm - lvm), how do the schedulers, readahead settings, and other disk settings interact? Imagine you have several disks (/dev/sda - /dev/sdd) all part of a software RAID device (/dev/md0) created with mdadm. Each device (including physical disks and /dev/md0) has its own setting for IO scheduler (changed like so) and readahead (changed using blockdev). When you throw in things like dm (crypto) and LVM you add even more layers with their own settings. For example, if the physical device has a read ahead of 128 blocks and the RAID has a readahead of 64 blocks, which is honored when I do a read from /dev/md0? Does the md driver attempt a 64 block read which the physical device driver then translates to a read of 128 blocks? Or does the RAID readahead "pass-through" to the underlying device, resulting in a 64 block read? The same kind of question holds for schedulers? Do I have to worry about multiple layers of IO schedulers and how they interact, or does the /dev/md0 effectively override underlying schedulers? In my attempts to answer this question, I've dug up some interesting data on schedulers and tools which might help figure this out: Linux Disk Scheduler Benchmarking from Google blktrace - generate traces of the i/o traffic on block devices Relevant Linux kernel mailing list thread

    Read the article

  • amazon ec2-medium apache requests per second terrible

    - by TheDayIsDone
    EDITED -- test running from localhost now to rule out network... i have a c1.medium using EBS. when i do an apache benchmark and i'm just printing a "hello" for the test from localhost - no database hits, it's very slow. i can repeat this test many times with the same results. any thoughts? thanks in advance. ab -n 1000 -c 100 http://localhost/home/test/ Benchmarking localhost (be patient) Completed 100 requests Completed 200 requests Completed 300 requests Completed 400 requests Completed 500 requests Completed 600 requests Completed 700 requests Completed 800 requests Completed 900 requests Completed 1000 requests Finished 1000 requests Server Software: Apache/2.2.23 Server Hostname: localhost Server Port: 80 Document Path: /home/test/ Document Length: 5 bytes Concurrency Level: 100 Time taken for tests: 25.300 seconds Complete requests: 1000 Failed requests: 0 Write errors: 0 Total transferred: 816000 bytes HTML transferred: 5000 bytes Requests per second: 39.53 [#/sec] (mean) Time per request: 2530.037 [ms] (mean) Time per request: 25.300 [ms] (mean, across all concurrent requests) Transfer rate: 31.50 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 7 21.0 0 73 Processing: 81 2489 665.7 2500 4057 Waiting: 80 2443 654.0 2445 4057 Total: 85 2496 653.5 2500 4057 Percentage of the requests served within a certain time (ms) 50% 2500 66% 2651 75% 2842 80% 2932 90% 3301 95% 3506 98% 3762 99% 3838 100% 4057 (longest request)

    Read the article

  • VHD Boot failure in Hyper-V (Win7 boot from vhd)

    - by stuck_again
    I've have a virtual machine with a VHD image that I've copied from Windows 7 to the Hyper-V server. This image was created on Windows 7 (Windows 7 64-bit), and I'm using it on Windows 7 as boot image. Starting this virtual machine with the Hyper-V Manager gives this error: "Boot failure. Reboot and Select proper Boot device or Insert Boot Media in selected Boot device." What do I need to do to boot from this vhd in Hyper-V?

    Read the article

  • using own mail server with external domain and dns. Now have internal dns. dkim test not working

    - by mojotaker
    I am not very knowledgeable in this area, but have been able to make great head way. Now i am stuck I setup my own mail server, e.g mailbox.example.com. I had the domain dns point to my mail server in my office. i was able to set up everything working fine. such as dkim and spf records. Recently i decided to setup an internal dns server in the office so as to resolve some addresses for some development servers internally. Ok the problem now is my mail server is sitting on the internal dns server (the mail server is on the same box as the dns server) its still able to send and receive emails but not sure if dkim is working properly. when i try to do a dkim test "amavisd test keys" i get "invalid (public key: not available)" and i know that that means i have a dns issue. so what should i do? I am currently looking at my internal dns zonefile and i dont know what to do (i am using bind dns server on an ubuntu-server box). do i configure a dkim txt record on the local dns ? or is there a way to forward dkim "request" to the external dns ? or do i have this whole thing done wrong ? To be clear Basically my internal domain name is the same as my external domain name (i.e example.com) i have a mail server within my internal domain mailbox.example.com, that uses my external domain dns (external dns has been setup to point to my emailserver (which of course is now sitting behind my internal dns)) dkim (i dont think its working because it fails the dkim test") Need help in determing the proper setup What is the proper way to set this up ? thank you Update: Here is my local dns zone file ; ; BIND data file for local loopback interface ; $TTL 604800 @ IN SOA webserver.example.com. root.example.com. ( //dns and webserver on the same box 2012030809 ; Serial 604800 ; Refresh 86400 ; Retry 2419200 ; Expire 604800 ) ; Negative Cache TTL ; @ IN NS webserver.example.com. @ IN A 192.168.1.117 @ IN AAAA ::1 ns IN A 192.168.1.117 www IN A xx.xx.xx.xxx // ip of external domain box (bluehost) work around to let local clients access website newsletter IN A xx.xx.xxx.117 // external ip address of local network mailbox.example.com. IN A 192.168.1.111 // internal ip of mailbox (mailserver webserver.example.com. IN A 192.168.1.117 //internal ip of a webserver

    Read the article

  • How to use sudo with rcp command to copy files from linux host to HP-UX host?

    - by Justin
    I'm having this issue where when I try to use sudo to rcp some files from a Linux host to an HP-UX host (note that the destination directory requires root access to write to), I get the following error from HP-UX's side: remshd: Login incorrect. I should note that the passwords for the Linux host and the HP-UX host are different. The command doesn't seem to give me a chance to enter the proper HP-UX password and automatically defaults to this error.

    Read the article

  • Linux LiveCD (or LiveUSB) with custom xorg.conf

    - by Jakub Narebski
    Is there some Live Linux distribution (on CD, DVD or USB), which allow one to use specific xorg.conf file, i.e. specific X11 configuration? The problem I am trying to solve is to find Linux Live distribution for web browsing which would work well with NEC LCD 22WV monitor. It is supposedly DDCCCI capable, but X.Org X Window System autoconfiguration fails to detect proper modeline, and uses fallback 800x600 screen resolution, instead of preferred screen resolution of 1680x1050.

    Read the article

  • GRUB 2 freezing at OS selection screen, what could be the cause?

    - by Michael Kjörling
    Mains power is somewhat unreliable where I live, so every now and then, the computer gets rebooted when the PSU can't maintain proper voltage during a brown-out or momentary black-out. It's happened a few times recently that when power is restored, the BIOS POST completes successfully, GRUB starts to load and then freezes. I've seen this at the Welcome to GRUB! message, but it seems to happen more often just past the switch to the graphical OS list. At this point, the computer will not respond to anything (arrow keys, control commands, Ctrl+Alt+Del, ...) - it simply sits there displaying this image, seemingly doing nothing more. At that point, turning the computer off using the power button and letting it sit for a while (cooling down?) has allowed it to boot successfully. Turning the computer off and immediately back on seems to give the same result (successful POST then freeze in GRUB). This behavior began recently, although does not seem to be directly correlated with my hard disk woes (although it may be relevant that GRUB resides on that physical disk, I don't know). Once the computer has booted, it runs without a hitch. I know that a "proper" solution would be to invest in a UPS, but what might be causing behavior like this? I was thinking in terms of perhaps the CPU shutting down as a thermal control measure, but if that was the cause then wouldn't I see similar freezes during use (which I do not)? What else could cause freezes apparently closely but not perfectly related to the BIOS handover from POST to OS bootloader? The BIOS settings are to reset to previous power status after a power loss. Since the PC in question is almost always turned on, this means restore to full power status. I have no expansion cards installed that make any BIOS extensions known by screen output during the boot process, at least, but I do have a few expansion cards installed. Haven't made any changes in that regard in a long time, now. I haven't touched GRUB itself for a long time, whether configuration or binaries, so I don't think that's the problem. Also, it doesn't really make sense that a bug in GRUB would manifest itself only once in a blue moon but significantly more often after a power failure.

    Read the article

  • Do I have to prepare Active Directory prior to installing an Exchange service pack?

    - by music2myear
    I'm having trouble determining the proper procedure for installing Exchange 2007 sp3 on a Server 2008 R2 box running Exchange 2007 sp1. It is not clear on websites I have consulted (Microsoft TechNet and others) whether preparing Active Directory is only required on a NEW install of Exchange 2007 sp3, or if it is required when upgrading an existing Exchange 2007 install to sp3. Could someone who has experience with this please set me straight?

    Read the article

  • Dell XPS 15z/ L511Z merging partitions

    - by Alvin M
    i have a situation here, i bought a new dell xps 15z and was successful in making drive partitions through the help of this site (http://superuser.com/questions/313082/dell-xps-15-l502x-hard-drive-partition) now i have drive C with 100.55gb and a new volume with 578.45gb im planning to use EaseUS again to undo this and resize my drive C but im scared i might cause damage to my drive, is there a proper way to undo this and transfer the remaining 78.45gb from the new volume back to my drive C again? please help

    Read the article

  • Create a sub domain for each user

    - by Avinash
    I am working on one site, in which i need to create a sub domain for each user. For e.g, my xite: www.demo.com And user name is :: Mark then sub domain for that user will be as below, mark.demo.com I need to know that what is the proper way to do like the above. I am running on PHP. Thanks, Avinash

    Read the article

  • What are your favourite free fonts?

    - by Rich Bradshaw
    As super users, using nicer fonts is often an important issue. Now that many sites are using @font-face to embed fonts in the page, having the same fonts installed locally means less downloading, and producing documents with custom fonts often look nicer. What are your favourite fonts? Ideally fonts that have unicode support and that have proper ligatures and kerning. Please add pictures if possible!

    Read the article

  • Nvidia driver for Dell xps M1330 in XP

    - by Recursion
    I need to run xp, and cannot find a driver that works for this laptop in windows xp. I have tried quite a few of them, from my google searches, but none work, they all come up and say no proper driver can be found for your hardware. I have tried to replace the inf files on driver installs but I still get nothing, same error. Any ideas will be appreciated, thank you.

    Read the article

  • How do I do an exact whois search?

    - by brianegge
    When I execute the following whois command on my Ubuntu server, I get all sorts of other domains which contain google.com in the name, but clearly aren't owned by google. As this appears to be some sort of spam, I won't paste the output here. I'd like to check for exactly the name I typed in. I thought the following would work, but it doesn't. What is the proper way to do an exact match? whois -Hx google.com

    Read the article

  • Printing to a Windows 7 incompatible printer shared on supported Windows XP machine

    - by MGSoto
    I have an HP Laserjet 1500 that is supported by Windows XP, but not supported by Windows-7. I want to print from my 7 machine(s) to my XP machine on this printer. Is there some sort of way to send a generic job (like sending raw postscript or something) to the XP machine, which will then print it with the proper drivers? Is there a virtual printer that has drivers for both XP and 7 that will just re-print it on the XP machine using the real printer?

    Read the article

  • SVN Backup using rsync command

    - by user37143
    Hi, I setup a cron for taking backup of my SVN repo( 8 GB) to another server. But some times I get errors and I feel that this is not the proper way to back an svn to a remote server. I used the command rsync -avz myrepo. Please suggest me a good way to do svn backup to a remote server. I cannot zip the files and transfer it daily since it's 7 GB. Thanks

    Read the article

  • How to restore a dd overwritten disk partition?

    - by DairyKnight
    First of all, I admit I'm stupid and I didn't run proper backup of my data, but you know crap happens... So, I've used dd to overwrite the first 2GB of my 750GB NTFS partition with a FAT32 partition. I've run Photorec and EasyRecovery but all I can restore is the 2GB FAT32 partition and the files on that. Is there a way to "roll back" to the NTFS paritition, and recover - at least - some part of the 750GB data? Thanks.

    Read the article

  • Redhat | ftp configuration

    - by MMRUSer
    I'm looking for a way to configure the ftp setting in my Redhat EL 5.4 (64bit) server in order to transfer some files from my client machine. I have search all over the net but couldn't find any good resources. I'm really new to Redhat and requesting a proper guidance. Thanks.

    Read the article

  • Qmail Toaster and Squirrelmail SSL config location.

    - by BlaineM
    I've been racking my brain and Google to try and find where the location of the SSL config is located for my Qmail / Squirrelmail install. I've installed SSL certs for Apache before, where I specify inside of the proper virtualhost section where the SSL cert is located, but am unable to find it for the services above. Inside of the httpd.conf, there are two include file additions which are for Qmail Toaster and Squirrelmail, but when I edit the files, they don't specify locations for the SSL cert they're using. thanks for the help!

    Read the article

< Previous Page | 41 42 43 44 45 46 47 48 49 50 51 52  | Next Page >