Fedora :: Jbd2_log_wait_commit Showing Huge Latency In LatencyTOP?
Aug 4, 2011
My large ext4 / filesystem seems to cause huge latency problems when writing a large file. For example, if I use split to break up a 40GB file into DVD-sized chunks, my browser becomes unresponsive, and it can take several seconds for Gnome terminal to respond to a mouse click.
I installed LatencyTOP, and it shows jbd2_log_wait_commit as the big offender, with Chrome waiting on that function for over 31000ms (or 31 seconds). I tried remounting / with barrier=0, but that didn't help. My hard drive is a WD20EARS-00MVWB0 2TB SATA disk. I recently switched my BIOS from IDE emulation to AHCI mode, but that didn't help. I tried running split with ionice, and that does help, but the system still isn't responsive as it should be, and I'd hate to have to remember to ionice every large write. Here is some relevant stuff from dmesg:
Code:
[ 1.294068] ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 1.294096] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 1.294119] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[code]....
I'm running kernel version 2.6.38.8-35.fc15.x86_64.
View 3 Replies
ADVERTISEMENT
Aug 7, 2011
Having one issue with evolution not showing html websites showing up in email like verizon sending a promo. I have gone to edit, preferences, mail preferences, html messages and have always load images from the internet chosen. I have also added sender to contacts. Even if I right click message and tell it to dload images it doesn't.
View 1 Replies
View Related
May 13, 2011
I just finished installing Fedora 14 and the nVidia drivers, and after a reboot everything on the screen became huge, almost as if I am zoomed in. Text, icons, windows, everything is too big. How do I fix this?
View 3 Replies
View Related
Oct 10, 2009
I am a former KDE user and I am switching to gnome. I love amarok and quanta, so i installed them, but they seem to have a really big font, and because i am using my laptop and i have good eyesight I want to lessen the size of the fonts.
View 1 Replies
View Related
Feb 18, 2011
I've evaluated about 15 offline storage systems this week, and one of the best was spideroak, but there's a huge issue in their shared folder structure and procedure.When you make part of your data shareable you MUST share a folder from your original disk. This is a real pain. You cannot share specific files like you can on many others.To initiate sharing your establish your unique username for sharing (different preferably than your spideroak username) the share name, and the room key (password).While you might expect the share name to be part of the URL that guides you to the share which then accepts your password for access, thats not how it works. Instead spideroak gives you a URL that contains the PASSWORD and does not even mention the share name!!
Therefore anyone you give the URL to has direct access to the share you create (which is what you are trying to accomplish in general) but any browser THEY USE will remember the URL which contains the password, not the share name.THIS IS A HUGE SECURITY ISSUE since you have no control over how an authorized user is going to access your data and from where and most users are not sophisticated enough to guard against the default intrusion they are going to leave behind.
View 3 Replies
View Related
Dec 22, 2010
I am facing a strange problem in my server, One of my filesystem shows as 3.1G when I execute df -h command and the utilization shows as 83%, but when I cd to the directory /usr/local I could not find any huge files in that filesystem and I have searched for hidden files as well,
groupserver:~ # df -h
Filesystem Size Used Avail Use% Mounted on
/dev/sda9 3.1G 2.5G 532M 83% /usr/local
groupserver:/usr/local # du -sh *
0 bin
93M abinav
[Code]...
View 2 Replies
View Related
Nov 6, 2009
Recently upgraded to fc11. Have nvidia working ok. Using kernel 2.6.30.9-90.fc11.i586 (not the latest). When booting up I get to gui login and see the background change. It takes 20 seconds or more before I see the login dialog box. After selecting the user it takes another 20 seconds before I see the box change to enter the password. This only happens at boot. If I logout and log back in everything is fine.
View 2 Replies
View Related
Feb 4, 2011
I am currently waiting about 10min already for Fedora to finish downloading whatever-it-is-it-downloads after issuing a simple 'Query'. This is bearable when my BB-connection is performing. Unfortunately, like right now, it isn't - between 10-50kB/s - and the wait is excruciating!
So, why does Fedora seem to download the complete files database at least once every 24hrs if there's an update/query issued, and not just the 'differences'? And how do I prevent it from doing so? Ubuntu arguably has access to many more files but never pulls this stuff. Fedora would appear to be completely unusable without a broadband connection! And in the time it has taken me to type this, Fedora continues to download its update at a rate of 10-30kB/s...
View 13 Replies
View Related
Jun 26, 2010
I just installed Fedora 13 on my old compaq presario with a DLINK DWL-122 usb adapter. Both lights are on as if it were working, but network manager isn't auto connecting.
View 4 Replies
View Related
Aug 30, 2010
I've been running Fedora Core 3 on a P4 450 as a personal Samba server and domain controller. It's worked so well that I never gave any thought to upgrading. The other night, I noticed that Up To Date wasn't working, and that Firefox was acting strangely. I made the FC 13 installation disks, whereupon I found out that the system didn't have enough memory.
Rather than mess with the P3 450 any more, instead I swapped main boards and decided to do an upgrade. it even possible to do an "upgrade" from 3 to 13? Is it possible to maintain my existing partitions/settings. I've backed up everything that I'd be too unhappy to lose. It's a two drive system and the second is nothing but data, none of it catastrophic to lose, but at least disappointing. I'd like to keep the data and settings on the primary disk, but won't cry if I can't.
View 10 Replies
View Related
Sep 4, 2010
How do I find out the memory bandwidth/latency to RAM of the machine?
View 3 Replies
View Related
Jun 12, 2010
I'm getting close to ordering the components for a new machine based on the AMD Deneb quad core and had one last question.I'd like to try a little careful overclocking, not only for the performance increase but also to learn how. Nothing extreme, no gaming, just whatever I can get with good stability with the stock heatsink and fan.I was going to get 8GB on 2x4GB strips but they are all CAS latency 9. The MB has 4 slots for a total of 16GB capacity. Would I be better off going with 4x2GB strips and try to get a lower latency strip like maybe 7?
View 5 Replies
View Related
Feb 26, 2011
As I am trying to understand if there are any advantages using a kernel optimized to have low latency for the desktop, it would very helpful if anyone using one could give me his opinion. I read about the liquorix kernel and found a controversy and used google to find more information.
View 2 Replies
View Related
Jun 20, 2011
I tend to use commands like 'aptitude search $something' or 'dpkg -S /usr/bin/command' (some command/variable in both) or 'apt-file search $something' and all/or many of its brethen. I do run updatedb every now and then but that command is for the overall health of the system similar to tracker perhaps (but not running continously like tracker and the daemon).
What I'm looking for is, if there is a way to get the package list (installed and otherwise) updated aggressively so that whenever I use any combination of aptitude or dpkg I get better response from the system. From what little I understand, aptitude or dpkg or somewhere there would be some sort of index/database where the current state of package availability and system state would be recorded. If there is a way that this could be improved upon would be nice to know. If there is some experimental package or road which the debian folks are looking for in the future so this latency can come down.
View 5 Replies
View Related
Jun 28, 2011
is there a realtime or low-latency kernel in a repository somewhere for OpenSUSE 11.4? I know I can just compile a rt kernel, but that's a bit tedious and I'd like to avoid it if possible.
View 9 Replies
View Related
Jun 8, 2011
we are setuping high-performance web farm with 4 ubuntu servers (all 10.14 LTS 64bit, i5Core CPU, 16GB Ram). One server is "database" server with mysql installed, three servers are "webservers" with tomcat installed. All three webservers have public IP and are connected directly to internet by eth0 (onboard network card) and are connected to switch that is connected to database server by eth1 (pci network card). All servers has stardard instalation with no special modules/programes installed.
Web servers are already under load, but only on about 10 requests/minute. After several hours in production, strange thing happened - one of the web servers (each time another one, so it is happening to all of them but not at once) starts to have pings to database (that is connected directly on LAN) = 100ms (other two servers still has like 0,02ms). Pings stay high until we do /etc/init.d/networking restart, after that it is fixed and pins are again low again. Another strange think is, that when we let ping running for some time, it is slowly dropping from 100ms to 1 ms and then again jumps to 100ms (exactly to 100ms always) and again starts dropping - so it is cycling over and over again (one cycle takes about 2 minutes).
We were trying reconfigure network, play with switch (the same situation was happening even without switch when there was only one webserver and one database server directly connected), disable IPv6 but nothing helped. The only thing that we discovered is that it has to be caused by network configuration.Do you have any idea what can cause it? We went through systems logs but found nothing suspicious (at least according to our understanding).
View 3 Replies
View Related
May 15, 2010
It's an eMachines T2899 desktop, FIC AU31 motherboard, nForce2 chipset, AC97 sound (integrated), running Xubuntu 10.04 (wubi install), 2.6.32-22.I've got terrible sound latency (about one second between actions and sound) in some programs.Flash in both firefox and chrome (including ..... videos) and ZSNES (SNES emulator) are two offenders, as is Audacity.Videos played in the default "movie player" and VLC play with no delay, though.I've been told it could be an issue with the ALSA buffer size, or pulseaudio introducing latency... but I've no clue how to go about fixing it.Upon using the SNES9X emulator (which allows for choice of sound system)... Portaudio causes laggy emulation and bad sound latency. Open Sound System plays fine. SDL causes laggy emulation and bad sound latency. ALSA plays fine. Pulse Audio plays fine."sudo apt-get remove --purge pulseaudio" did nothing, so I reinstalled it just in case.
View 4 Replies
View Related
Feb 17, 2011
I have a four-cores machine (core1,core2, core3, core4 ). I want to test the communication or latency between two cores (for example, core1 and core2; core3 and core4). Does anyone know how to write a code to test it under linux operating system?
View 1 Replies
View Related
Apr 22, 2010
Program code as how to measure interrupt latency..
View 2 Replies
View Related
Feb 17, 2011
I'm looking for a program that can measure disk latency. I would prefer one that could do it on a raw device. Also reporting average and max latency would be a plus.
Anyone know a program that can do this?
View 1 Replies
View Related
Mar 7, 2010
I have a Macbook running Ubuntu Karmic and I have been asked to DJ (amateur to the MAX) a friend's wedding next weekend. I don't have the coin to spend on a Mixer so I can run my mic and laptop through my amp so I figure I'd just run the Mic into the mic input on my Macbook and let the laptop do the mixing for me.Well, I added the loopback module to Pulse and inserted a command to have it auto start:
Code:
pactl load-module module-loopback
Code:
[code]....
View 5 Replies
View Related
Aug 9, 2010
I'm looking for an open source/free network emulator tool that I could use on Mac OS X, to simulate a slow network connection, limited bandwidth and other network characteristics such as dropped packets etc for both UDP/TCP connections (or even on the physical layer).
I'm looking for the simplest solution that would allow me to run TCP/UDP servers and have a few clients connect to them on localhost emulating various network connections. I'm mainly wondering if I can use something like Linux's netem on Mac OS X (or even better cross-platform Windows/Linux/Mac). Perhaps I can run VirtualBox and a Linux kernel running netem, has anyone had luck with that?[URL]...
View 2 Replies
View Related
Sep 14, 2011
I'm hoping to find an existing Linux tool for measuring latency:
I'm trying to diagnose how much latency my OS and NIC card are adding to TCP latency in Linux. I looked at the following tools but all (at least at the surface level) measured bandwidth (Mbps/sec) rather than latency (nanoseconds for transmition of 1 packet of size x).
If I were to write a custom test, it would likely do the following:
Client:
Create a fake message of the specified length with some padding for an incrementing identifier. Open a TCP connection (with the right parameters like TCP_NODELAY, etc) Loop and send messages containing an incrementing identifier. Store the current system time (in nanos) associated with the identifier. Listen for responses, record the current time and record the latency of that identifier asynchronously Server Listen for a connection Echo back any message received
Assuming both boxes had the same setup (configs, cards, OS, CPU, etc), are relatively close to eachother in the network, and one knows roughly the network's latency contribution, one could get a rough estimate of the OS + NIC contribution and begin testing various configurations.
One could also get a more accurate picture of the latency by using a network sniffer and snooping on the lines between the two hosts, calculating the latency between the two sides for an ID, and then subtracting that from the internally measured latency.
View 3 Replies
View Related
Oct 12, 2010
I just installed Maverick Studio on a new hard drive, and am using an NVIDIA GeForce 7300 LE GPU. If I boot into the 2.6.35-22-generic kernel, everything runs fine, but if I try to boot into either the 2.6.35-20-Low Latency, or 2.6.33-29-Realtime kernels (installed from Synaptic), the computer boots straight to a command prompt instead of the desktop. Does anybody know what causes this? I need to be able to use one of these kernels for doing music production.
View 1 Replies
View Related
Dec 15, 2010
I'm experiencing massive latency/unreachable problems on my Linux machine. It's true for all network connections, here's an example of me trying to ping my router:
PING 192.168.0.1 (192.168.0.1) 56(84) bytes of data.
64 bytes from 192.168.0.1: icmp_req=1 ttl=64 time=15115 ms
64 bytes from 192.168.0.1: icmp_req=2 ttl=64 time=14107 ms
64 bytes from 192.168.0.1: icmp_req=3 ttl=64 time=13107 ms
64 bytes from 192.168.0.1: icmp_req=4 ttl=64 time=12107 ms
64 bytes from 192.168.0.1: icmp_req=5 ttl=64 time=11108 ms
[Code]...
I've tried now with both the maverick default kernel and 2.6.37-rc5 kernel (both 64 bit), same result. If I take the card up and down (ifup, ifdown) performance is restored for a little while, then it's back. I've tried changing cable, network card and router port but no luck.
View 4 Replies
View Related
Nov 30, 2010
i have installed ns 2.33 and added the patch mobiwan for supprting mobile ipv6. i ran some tcl scripts , and below is the trace file generated. calculate the handoff latency, and if someone has awk or perl script to do so, tcl file [URL] out.tr [URL]
View 1 Replies
View Related
Apr 20, 2011
I have a dedicated host on my lan to monitor other hosts/services using Nagios. I'm in the process of migrating to Zabbix on that host to perform the same purpose. Both Nagios and Zabbix monitor icmp ping latency (Nagios uses ping, Zabbix uses fping) and over time the latency to other hosts grows until threshold alarms are triggered. In one week, the average latency grows from sub-millisecond to over 100 milliseconds, and continues to grow until the Nagios host is rebooted. I have verified the latency numbers using ping/fping from the command line on the Nagios host.
The problem is that pings from the monitored hosts to the Nagios host show normal latency at the time the Nagios host is showing high latency from itself to the monitored hosts. The Nagios host and monitored hosts are all connected to the same Dell 24 port gigabit switch. I already posted this question on the Zabbix forums with a graph of the latency but there were no answers. [URL] why the icmp ping latency is growing over time and how I can fix it short of rebooting the host on a schedule.
[Code]...
View 5 Replies
View Related
Jan 8, 2011
I just put 10.10 on my D830 and I love it except for a delay when I'm using the internet. When I click on a link while surfing the web it takes about 13 seconds before it responds. After that it works just fine.
My Windows 7 PC and my Macbook Pro don't do that so I'm guessing it has something to do with Ubuntu.
View 5 Replies
View Related
May 11, 2010
What can be the cause of this error.
dmesg | grep -i time
ACPI: PM-Timer IO Port: 0x408
Calibrating delay using timer specific routine.. 4658.19 BogoMIPS (lpj=2329098)
Using local APIC timer interrupts.
[code]....
View 7 Replies
View Related
Feb 10, 2011
Recommend open source tools that can help in figuring out if we are experiencing a network latency due to the newly installed firewall on our server.
View 1 Replies
View Related