Re: [CentOS] scheduling differences between CentOS 4 and CentOS 5?
I would like to confirm Matt's claim. I too experienced larger latencies with Centos 5.x compared to 4.x. My application is very network sensitive and its easy to prove using lat_tcp. Russ, I am curious about identifying the problem. What tools do you recommend to find where the latency is coming from in the application? On Fri, May 20, 2011 at 2:46 PM, R P Herrold herr...@owlriver.com wrote: On Fri, 20 May 2011, Matt Garman wrote: We have several latency-sensitive pipeline-style programs that have a measurable performance degredation when run on CentOS 5.x versus CentOS 4.x. By pipeline program, I mean one that has multiple threads. The mutiple threads work on shared data. Between each thread, there is a queue. So thread A gets data, pushes into Qab, thread B pulls from Qab, does some processing, then pushes into Qbc, thread C pulls from Qbc, etc. The initial data is from the network (generated by a 3rd party). We basically measure the time from when the data is received to when the last thread performs its task. In our application, we see an increase of anywhere from 20 to 50 microseconds when moving from CentOS 4 to CentOS 5. Anyone have any experience with this? Perhaps some more areas to investigate? We do procesing similar to this with financials markets datastreams. You do not say, but I assume you are blocking on a select, rather than polling [polling is bad here]. Also you do not say if all threds are under a common process' ownership. If not, mod complexity of debugging threading, you may want to do so I say this, because in our testing (both with all housed in a single process, and when using co-processes fed through an anaoymous pipe), we will occasionally get hit with a context or process switch, which messes up the latencies something fierce. An 'at' or 'cron' job firing off can ruin the day as well Also, system calls are to be avoided, as the timing on when (and if, and in what order) one gets returned to, is not something controllable in userspace Average latencies are not so meaningful here ... collecton of all dispatch and return data and explaining the outliers is probably a good place to continue with afer addresing the foregoing. graphviz, and gnuplot are lovely for doing this kind of visualization -- Russ herrold ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] bizzare performance problem
I had a rather strange problem last week with one of our 8 core servers. The users complained the performance was slow so I checked the basic things, processes on top, vmstat for memory and context switching, i/o stats for internal disk I/O, netstat for any network issues and other things like network through put by copying a large file (1gb file across the network). It turned out I had an NMI related issue on the processor. I figured this out by checking the /var/log/messages but it was a real mystery for be at first. My question, is there a way to detect or benchmark a system and all of its processors to make sure I don't bypass this type of error again? I am not necessary looking for monitoring tools but more of techniques like, run a while loop on all processors/cores to make sure they all give a constant time? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Centos 6 - What are you looking forward to?
We are a data shop. nfs v4 support native XFS support ext4 Hopefully by 6.4 they will have native brtfs :-) On Sun, Mar 6, 2011 at 9:38 AM, Nico Kadel-Garcia nka...@gmail.com wrote: On Sun, Mar 6, 2011 at 8:50 AM, Pasi Kärkkäinen pa...@iki.fi wrote: On Fri, Mar 04, 2011 at 03:33:10PM -0500, Kwan Lowe wrote: On Fri, Mar 4, 2011 at 3:11 PM, John R Pierce pie...@hogranch.com wrote: IBM Power servers since the Power4+ CPU (they are up to Power7 now) have hardware partitioning support, commonly known as LPAR. LPAR can be divided in units of 1/10th of a CPU. The software to manage this is now called PowerVM (its been called other names in the past, not all polite). [informative text snipped] Yes, it is some nice stuff... In particular, having the hardware partitioning capability plays nice with Oracle licensing. Under KVM or Xen we still have to license the entire system. This probably won't change with the newer kvm, but one can hope. It's kind of funny since OracleVM *is* Xen, and it's counted as hardware partitioning :) -- Pasi On the Linux side I would like to see how KSM (kernel memory merge) stacks up against memory compression on the Power7 side. Not sure if this made it into RHEL6, but hope springs eternal... Storage management is always a big issue for me. AIX has some really great tools for managing disks. In Linux the LUN, block and fs layer are still relatively decoupled which gives an enormous amount of flexibility but certain types of changes require multiple commands on Linux. On the desktop side I've been running RHEL6 as my primary environment since release. Transition was easy. My old kickstart files needed tweaking, but so far it's been a breeze. What did you hve to tweak? I noticed the new use of the '%end' flag to mark the end of a section, and the new partitioning structure which names the LVM based volumes and groups things which contain the hostname. (This is a big deal if you have multiple virtual hosts on a machihe and want to compare their internal LVM's side by side from the virtualization server.) ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] measuring performance of glibc
I was wondering, how does one measure the performance of glibc? Are there any tools? I am planning to compile my own version of glibc for educational purposes and I was simply curious. TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] compiling a module
I am interested in fscache module. I know where to get the userland tools (http://people.redhat.com/dhowells/fscache/) but I am not sure where to obtain its module. Moreover, I am not sure once I get the source code how I can compile it for Centos 5.2. Has anyone compiled, fscache before? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] noatime effect
I know that with noatime attribute, http://tldp.org/LDP/solrhe/Securing-Optimizing-Linux-RH-Edition-v1.3/chap6sec73.html, it will have a performance gain. I want to know how I can figure out how much the kernel is waiting its time without noatime. Is the possible? ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] performance and interrupts
I am playing around with irqbalance to tune my 8 core system so I came across this page, http://kb.fusionio.com/KB/a65/irqbalance-avoid-overloading-cpu-0-with-interrupt-requests.aspx Now, lets say I disable irqbalance which will stop my autobalance and I pin all of my interrupts to core 0 and pin eth0 and eth1 to core 1. My application is network and CPU hungry. I am planning to dedicate cpu 3 to 8 for the application using taskset. Is there any draw back to this? ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] performance and interrupts
Thanks for the reply. I am just playing around to understand this. On Fri, Sep 24, 2010 at 9:43 AM, JohnS jse...@gmail.com wrote: On Fri, 2010-09-24 at 08:57 -0400, Mag Gam wrote: I am playing around with irqbalance to tune my 8 core system so I came across this page, http://kb.fusionio.com/KB/a65/irqbalance-avoid-overloading-cpu-0-with-interrupt-requests.aspx Now, lets say I disable irqbalance which will stop my autobalance and I pin all of my interrupts to core 0 and pin eth0 and eth1 to core 1. My application is network and CPU hungry. I am planning to dedicate cpu 3 to 8 for the application using taskset. Is there any draw back to this? --- NO but be aware of what your doing as to not starve out Kernel Threads. Whats the kernel? It want hurt to give them priority either. Gbit and higher nics I would give them there own cpu. It may take quit a while to come up with the optimal configuration though. Example: cpu0 app priority 60 - 99 no ionice is app dependent cpu1 app cpu2 eth0 cpu3 eth1 cpu4 fusionio cpu5 fusionio cpu6 kthreads cpu7 kthreads, misc John ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] measuring kernel speed
This is an interesting topic. So, how does one compare the kernel speed from RT and Stock kernel? Is there a benchmark I can use? For example (I know this is wrong): can I look at /proc/cpuinfo and look at the bogmips and compare and contrast? On Sat, May 8, 2010 at 7:38 PM, JohnS jse...@gmail.com wrote: On Sat, 2010-05-08 at 16:17 -0400, Ross Walker wrote: On May 8, 2010, at 8:35 AM, Mag Gam magaw...@gmail.com wrote: At our Physics research labs we do a lot with low latency networks. We have been using Centos for over 3 years now and its been great! We would like to tune and optimize our setup by removing unneeded packages -- kernel modules to be specific. I was wondering, how does one measure the speed of the kernel. Is that even possible? Use oprofile. -Ross --- Ross, never mind I just yummed it onto a machine there faq is inheritly wrong. John ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] measuring kernel speed
At our Physics research labs we do a lot with low latency networks. We have been using Centos for over 3 years now and its been great! We would like to tune and optimize our setup by removing unneeded packages -- kernel modules to be specific. I was wondering, how does one measure the speed of the kernel. Is that even possible? ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] autofs problems
We have about 800 CentOS 5.2 servers and our university. We use NFS being served from over 10 NetApp frames. We use autofs for to mount up our partitions. There have been times where we can't cd into the directory. It says the directory does not exist. On some servers it works but on others it does not. Typically we restart amd and autofs to resolve this issue. But sometimes it does not even work. A reboot fixes the problem. I am wondering if anyone knows any tricks to check if autofs is working properly on the system and also what I should do in a situation like this. TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] p800 and HP
I was wondering if anyone here has experience with HP MSA60 with P400 and P800 controller. How reliable are they for a 24x7 shop? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] p800 and HP
Well, I am poor and so is my school. We want to setup a cheap storage farm so I was asking what is people's opinions on the the controller and the disks :-) On Thu, Aug 20, 2009 at 10:33 PM, John R Piercepie...@hogranch.com wrote: Mag Gam wrote: I was wondering if anyone here has experience with HP MSA60 with P400 and P800 controller. How reliable are they for a 24x7 shop? well, its not 5-nines stuff, there's all kinda single points of failure. you want 0.9 kinda reliability, you need a fully redundant system with multipath, at every stage, like a fiberchannel SAN with dual HBA's on each system, dual switches, dual controllers on each storage array, etc, all components hotswappable, etc. of course, this all comes at siginficant expense, both in complexity and cost. ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] server is always getting hacked
WE have a centos 5.3 install, and our server is keep getting hacked. We see load averages of 500+ and see people from all over the world logging into our server (used last). Is there a good place to start to avoid these kinds of things? For example, here is what I already did. Open up sshd port only setup iptables to only accept port 80 and 22 No FTP No other ports are allowed according to IP Tables. I am not sure what else measures I can take. Can someone please assist? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] ypserv errors
You are right. Its not a major issue. Thanks again. On Sat, Jan 17, 2009 at 11:50 AM, James Pearson jame...@moving-picture.com wrote: Mag Gam wrote: In my syslog I get many of these types of errors: ypserv [4818]: refused connect from 127.0.0.1:57124 to procedure ypproc_match [domain.com,passwd.adjunct.byname;-1) Any idea what this error is? Something running on your ypserver is trying to match an entry in the passwd.adjunct map from the ypserver - which doesn't exist I believe the passwd.adjunct file is used for shadow passwords (on Solaris?). I doubt it is a major issue as whatever is requesting this map is probably just seeing if it exists - and probably falling back to using the passwd.byname map. James Pearson ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] ypserv errors
In my syslog I get many of these types of errors: ypserv [4818]: refused connect from 127.0.0.1:57124 to procedure ypproc_match [domain.com,passwd.adjunct.byname;-1) Any idea what this error is? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] ZFS on Linux
ext4 isn't going to help too much. Our biggest concerns are: compression, and unlimited inodes On Mon, Jan 5, 2009 at 8:36 AM, Matej Cepl mc...@redhat.com wrote: On 2008-12-30, 15:32 GMT, Tony Placilla wrote: The root answer is that if he wants to use ZFS (which is a *good* choice) he should use some flavor of Solaris I would just add that RHEL 5.3 (and thus CentOS 5.3) when it happens, will have ext4fs as a technology preview, which may fulfill OT needs as well. Matěj ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] ZFS on Linux
I am planning to use ZFS on my Centos 5.2 systems. The data I am storing is very large text files where each file can range from 10M to 20G. I am very interested on the compression feature of ZFS, and it seems no other native Linux FS supports it. My question are: Is ZFS stable? How does it scale for very large filesytems, ie, 2TB to 9TB? How is the performance of fuse? I plan to use it on my archive server first, so data reliability is very important Any thoughts or ideas? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] ZFS on Linux
thanks everyone for your fair and balanced opinions and experiences! On Sun, Dec 28, 2008 at 2:38 PM, Davide Cittaro davide.citt...@ifom-ieo-campus.it wrote: On Dec 28, 2008, at 7:16 PM, Mag Gam wrote: I am planning to use ZFS on my Centos 5.2 systems. The data I am storing is very large text files where each file can range from 10M to 20G. I am very interested on the compression feature of ZFS, and it seems no other native Linux FS supports it. Even if fuse implementation of ZFS looks rather stable, I won't suggest it in a production environment... We strongly wanted ZFS and we chose for Solaris 10 for our file server. My question are: Is ZFS stable? How does it scale for very large filesytems, ie, 2TB to 9TB? How is the performance of fuse? I plan to use it on my archive server first, so data reliability is very important ZFS really is great. We are now managing three 18Tb archives. It is not only reliable, it comes with zpool and zfs commands that really make it easy to manage! If you don't want Solaris, you can use FreeBSD 7 which supports native ZFS. d Davide Cittaro davide.citt...@ifom-ieo-campus.it ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] bonding theory question
So, I decided to go with mode 6 since my network admin says thats supported at my college. I have everything working perfectly however I still get an occasional packet drop which is not good. http://www.howtoforge.com/network_card_bonding_centos By reading the HOWTO and README.txt I am not sure if I am missing anything else. Has anyone else configured this before? TIA On Sat, Sep 6, 2008 at 2:22 PM, Filipe Brandenburger [EMAIL PROTECTED] wrote: On Sat, Sep 6, 2008 at 13:11, Mag Gam [EMAIL PROTECTED] wrote: Actually, would there be a big performance boost when using mode4? Not necessarily, since balance-rr already gives you load-balancing. They actually implement it differently. balance-rr can spread packets of the same TCP connection across the two links, so you may use your links more, but with the side effect of having your packets delivered out of order. In 802.3ad all packets of a single TCP connection will use the same link, this means your links will not be as balanced as what you get with balance-rr, but it will not require reordering on the other side of the connection. Check section 12.1.1 in /usr/share/doc/iputils-*/README.bonding . In any case, you should evaluate what your needs are and tune for that. Currently I am seeing 95% total throughput. If you have only a few clients doing huge transfers, 802.3ad will probably not be as good as balance-rr for that. Again, you should tune it for your needs. Which isn't that bad. I am peaking at 238MB/sec (each gig/e connections) I believe you mean 238MB/sec on both interfaces, since 1Gbps = 125MB/s. Also, mode0 does fault tolerance, meaning if a switch failure occurs we should still be good, but how would the packets then be transferred? I suppose rr would be disabled since it won't need to alternate, correct? Actually balance-rr is still there, it is only doing round-robin of one interface only. Remember, you could have a bonding of 3, 4 or more interfaces, in that case if you loose one you still have more than one to balance traffic through. Filipe ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] swap being used?
I have a machine with 64GB of memory in our lab. We have memory demanding processes and natually swap gets used. However when these processes are gone and the system is idle, we still see swap being used. Is this normal behavior? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] strict memory
ulimit is good for per process. What about for total usage? If a user has 5 processing -- each taking up 10G, will account for 50G. Is there a way to avoid this? Or have the VM be sensative, once its swapping we want to start killing the processing that take the most memory? TIA On Wed, Oct 22, 2008 at 1:58 AM, Amos Shapira [EMAIL PROTECTED] wrote: 2008/10/17 Mag Gam [EMAIL PROTECTED]: Hi John: Well, we run a lot of statistical analysis and our code loads a lot of data into a vector for fast calculations. I am not sure how else to do these calculations fast without loading it into memory. Thats why we have to do it this way. About 15 years ago I changed an application on SGI IRIX from using text files scanf(3)'ed into memory (with floating point numbers in them) to binary files mmap(2)'ed into memory. Processing time was cut down by over 95% and did much more in the 5% left (e.g. allow interactive real-time viewing of different frames of data). Using mmap'ed files means that the system will know that these pages are backed by blocks on the file system and therefore it won't take up so much buffer space which needs to be writen out into the swap partition whenever the memory buffer is needed for something else, only disk cache space which can be just freed if the buffer was only read. You can also benefit if multiple processes access same file - they'll share the buffer in memory too. It's not a silver bullet, there are still issues with too random access causing the system the thrash, but at least it won't take up so much swappable memory, it'll save lots of copying (file-kernel-user when reading and the other way around when writing), system calls etc. If you can process data in sequential order and possibly with help of madvise(2) you can probably squeeze out even more from this option. --Amos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] strict memory
Hello All: Running 5.2 at our university. We have several student's processes that take up too much memory. Our system have 64G of RAM and some processes take close to 32-48G of RAM. This is causing many problems for others. I was wondering if there is a way to restrict memory usage per process? If the process goes over 32G simply kill it. Any thoughts or ideas? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] strict memory
Yes. Thanks. I was thinking of that too. Any other suggestions? TIA On Thu, Oct 16, 2008 at 12:56 PM, Filipe Brandenburger [EMAIL PROTECTED] wrote: Hi, On Thu, Oct 16, 2008 at 12:48, Mag Gam [EMAIL PROTECTED] wrote: I was wondering if there is a way to restrict memory usage per process? If the process goes over 32G simply kill it. You can limit the amount of virtual memory of a process with ulimit -v. See help ulimit or man bash for more details. HTH, Filipe ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] strict memory
Hi John: Well, we run a lot of statistical analysis and our code loads a lot of data into a vector for fast calculations. I am not sure how else to do these calculations fast without loading it into memory. Thats why we have to do it this way. TIA On Thu, Oct 16, 2008 at 1:00 PM, John R Pierce [EMAIL PROTECTED] wrote: Mag Gam wrote: Hello All: Running 5.2 at our university. We have several student's processes that take up too much memory. Our system have 64G of RAM and some processes take close to 32-48G of RAM. This is causing many problems for others. I was wondering if there is a way to restrict memory usage per process? If the process goes over 32G simply kill it. Any thoughts or ideas? In /etc/profile, use ulimit -v (in kilobytes) to limit the max virtual of all processes spawned by that shell 32G per process on a 64G machine sounds like a bit much.wouldn't a limit more like 4GB per user session be more appropriate on a multiuser system? ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] need filesystem recommendation
Hi All, I have a backup site and I would like to rsync from production to backup site. However, I would like to have all backups be compressed so I can save space. Can anyone recommend a good way to do this? I am currently using tar and bzip2 to do this. TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] vmcore
I would like to analyze a kernel vmcore. Are there any docs you can recommend for me to read to understand the process? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] kernel and memory question
Currently at my university we are running many servers with Centos 4.6 and everything is okay, but when a user does a large operation such as 'cp' or 'tar' or 'rsync' all of the physical memory gets exhausted. Our lab servers have 32GB physical to 64GB of physical memory and when a user does a large copy which involves very small but over 10k files eventually we see a kswap process. I would like to control swapping so these files don't go into memory instead they get flushed out. These computers are used for fluid dynamics calculations and I would just like to have the memory do a FIFO and use the least swap as possible. I tried setting the swapiness to '10' or '0' but that really does not help. Also, has there been a major memory management advancement from 4.6 to 5.2? If so, where can I read about the changes? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] email and MS outlook
We use Microsoft Outlook heavy at school but our backed is CentOS. I use echo Foo | mail -s subject [EMAIL PROTECTED] a lot. Is it possible to change the priority to High so Outlook will understand it? The priority meaning the email will be sent to the normal email queue but on Outlook it would have the exclamation point. TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] HP Hardware
Looks like thats what I did. But what is the exact purpose of 'cmaidad'. Is it a replacement for SMART? I think it is...But just want to confirm On Sun, Sep 14, 2008 at 6:40 AM, Dermot [EMAIL PROTECTED] wrote: 2008/9/14 nate [EMAIL PROTECTED]: Mag Gam wrote: At my university we use HP hardware exclusively. When we build CentOS our Unix SA is running several HP utilities. I am wondering what some of these utilities are, such as cmaidad. Is it possible to to use these HP utilities to monitor for disk crashes (similar to smartd)? Is anyone using native HP utilities for this purpose? I just did a round of HP patches to my DL series servers. In doing so I went to the HP site and installed the Support Pack RPMs. This provide a load of tool including the Compaq RAID utility (cqpacuex). However these tools run as daemons so if you want a small footprint, this might not be the way for you. The tools do provide a web-based dignostics utility which also allows you to configure the host array or in my case, the fibre attached storage arrays. In the past I have had to change the name in the /etc/*release file to RedHat to install HP stuff. I can't remember if I had to do that this time! Dp. ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] HP Hardware
At my university we use HP hardware exclusively. When we build CentOS our Unix SA is running several HP utilities. I am wondering what some of these utilities are, such as cmaidad. Is it possible to to use these HP utilities to monitor for disk crashes (similar to smartd)? Is anyone using native HP utilities for this purpose? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Job Scheduling suggestions
Thankyou everyone. How does SGE compare? Is it easy to implement? What about its features compared to others? How is the code quality, stability, and documentation? TIA On Thu, Sep 11, 2008 at 4:15 AM, Bernhard Gschaider [EMAIL PROTECTED] wrote: On Wed, 10 Sep 2008 19:54:44 -0700 JRP == John R Pierce John wrote: JRP Mag Gam wrote: At my university we have 50 computers in the lab. We would like to use a scheduler to schedule our fluid models, and I was wondering what is a good suggestion? JRP you might look at using one of the scientific clustering JRP packages, like Oscar, which implements and manages an MPI JRP cluster. this of course assumes your fluid model software is JRP written to use MPI If you're going for cluster software you might consider http://www.rocksclusters.org/ It's even based on CentOS. Here at our place we have a dedicated cluster with Rocks. In addition I took the SGE-rpm from the distribution and installed it on our regular (CentOS) workstations so that jobs can be scheduled on these machines too ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Job Scheduling suggestions
At my university we have 50 computers in the lab. We would like to use a scheduler to schedule our fluid models, and I was wondering what is a good suggestion? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] bonding theory question
Hello All, I am currently using bonding with 2 NICs (using mode 0). Its been working well, but I am trying to understand how it works (I am a total newbie). mode=0 (balance-rr) Round-robin policy: Transmit packets in sequential order from the first available slave through the last. This mode provides load balancing and fault tolerance. So I have 2 NICs (1 NIC attached to switch A, 2nd NIC attached to switch B). I have 1 virtual interface. bon0. Suppose data is being pushed out, it will go with 1st NIC and when it gets overloaded it will use 2nd NIC. The bonding driver will be responsible for it. Similar to the push, the pull will be very similar. The data gets pulled and the bonding driver will assemble the packets together? Does this sound right? Sorry for a newbie question... TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] bonding theory question
Filipe: Thankyou! Your explanation helps a lot. Its makes more sense than reading mundane manuals :-) Actually, would there be a big performance boost when using mode4? Currently I am seeing 95% total throughput. Which isn't that bad. I am peaking at 238MB/sec (each gig/e connections) Also, mode0 does fault tolerance, meaning if a switch failure occurs we should still be good, but how would the packets then be transferred? I suppose rr would be disabled since it won't need to alternate, correct? On Sat, Sep 6, 2008 at 12:15 PM, Filipe Brandenburger [EMAIL PROTECTED] wrote: On Sat, Sep 6, 2008 at 11:57, Mag Gam [EMAIL PROTECTED] wrote: Suppose data is being pushed out, it will go with 1st NIC and when it gets overloaded it will use 2nd NIC. No. If you are using balance-rr, one packet will go through the 1st NIC, and the next packet will go through the 2nd one. That's what rr (round-robin) means. Similar to the push, the pull will be very similar. The data gets pulled and the bonding driver will assemble the packets together? Does this sound right? Actually this will not be determined by the bonding driver, it will be determined by the switch that is actually pushing the packets. The bonding driver will only make it look like the packets are coming from one (bonded) interface only. How the switch will behave depends on its configuration. It may be configured to send all the data through one of the interfaces only to balance through both of them using round-robin or something else. You should try to read this, it's very complete: /usr/share/doc/iputils-*/README.bonding Also, if your switch supports it, you should try to use the 802.3ad mode (mode=4) since that will probably give you the best results with bonding (in terms of load balancing and fault tolerance). HTH, Filipe ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] compiling libarchive
Thanks Ralph. Got libarchive compiled fine, now trying to compile archivemount I keep getting this error now: gcc -D_FILE_OFFSET_BITS=64 -O2 -DNDEBUG -Wall -W -MM archivemount.c dep gcc -larchive -lfuse -o archivemount archivemount.o archivemount.o(.text+0x1474): In function `save': : undefined reference to `archive_write_set_compression_gzip' archivemount.o(.text+0x147f): In function `save': : undefined reference to `archive_write_set_compression_bzip2' collect2: ld returned 1 exit status make: *** [archivemount] Error 1 On Fri, Sep 5, 2008 at 5:09 AM, Ralph Angenendt [EMAIL PROTECTED] wrote: Mag Gam wrote: Has anyone been able to compile libarchive and archivemount? I want to use this with fuse. The compile is very tough for libarchive, I keep getting tar/write.c:730: error: `EXT2_IOC_GETFLAGS' undeclared (first use in this function) e2fsprogs-devel is missing on your machine. Ralph ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] compiling libarchive
I got it to work. Thanks all! On Fri, Sep 5, 2008 at 10:26 AM, Peter Kjellstrom [EMAIL PROTECTED] wrote: On Friday 05 September 2008, Mag Gam wrote: Got libarchive compiled fine, now trying to compile archivemount I keep getting this error now: gcc -D_FILE_OFFSET_BITS=64 -O2 -DNDEBUG -Wall -W -MM archivemount.c dep gcc -larchive -lfuse -o archivemount archivemount.o Unless I'm mistaken, order is significant. put -larchive -lfuse after archivemount.o /Peter archivemount.o(.text+0x1474): In function `save': : undefined reference to `archive_write_set_compression_gzip' ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] compiling libarchive
Has anyone been able to compile libarchive and archivemount? I want to use this with fuse. The compile is very tough for libarchive, I keep getting c -o tar/bsdtar-util.o `test -f 'tar/util.c' || echo './'`tar/util.c mv -f tar/.deps/bsdtar-util.Tpo tar/.deps/bsdtar-util.Po gcc -DHAVE_CONFIG_H -I. -I./libarchive -I./libarchive -g -O2 -MT tar/bsdtar-write.o -MD -MP -MF tar/.deps/bsdtar-write.Tpo -c -o tar/bsdtar-write.o `test -f 'tar/write.c' || echo './'`tar/write.c tar/write.c: In function `write_hierarchy': tar/write.c:730: error: `EXT2_IOC_GETFLAGS' undeclared (first use in this function) tar/write.c:730: error: (Each undeclared identifier is reported only once tar/write.c:730: error: for each function it appears in.) tar/write.c:732: error: `EXT2_NODUMP_FL' undeclared (first use in this function) tar/write.c: In function `write_entry': tar/write.c:915: error: `EXT2_IOC_GETFLAGS' undeclared (first use in this function) make[1]: *** [tar/bsdtar-write.o] Error 1 make[1]: Leaving directory `/var/tmp/archivemount-0.5.3/libarchive-2.5.5' make: *** [all] Error 2 TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Re: CentOS 4.7 status
where can we get ISOs? I can test for VirtualBox atleast. If there is a problem I will submit a bug. On Tue, Sep 2, 2008 at 3:45 PM, Scott Silva [EMAIL PROTECTED] wrote: on 8-30-2008 6:37 PM Adrian Sevcenco spake the following: Hi, i was wondering what is the status of 4.7 Thank you, Best regards, Adrian 4.7 was delayed so the buildservers could get 5.2 ready. 4.7 is probably in the queue now, but it takes a while because CentOS doesn't have a million dollar hardware budget, and has to schedule things to best use the hardware available. When it is ready and synced to the mirrors, it will be announced. -- MailScanner is like deodorant... You hope everybody uses it, and you notice quickly if they don't ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] CentOS 4.7 status
+2 Seems Redhat already released 4.7 http://www.press.redhat.com/2008/07/24/red-hat-enterprise-linux-47-released-today/ On Mon, Sep 1, 2008 at 1:08 PM, Oliver Schulze L. [EMAIL PROTECTED] wrote: +1 Adrian Sevcenco wrote: Hi, i was wondering what is the status of 4.7 Thank you, Best regards, Adrian ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Changing swap resume signature location
Why not create a new swap partition and place it in /etc/fstab ? You don't have to worry about swap signatures and all... On Sat, Aug 30, 2008 at 8:05 AM, Patrice Guay [EMAIL PROTECTED] wrote: At boot time, the system is looking for a resume signature on the default SWAP partition that was defined during the OS installation. On several systems, I changed the location of the SWAP partition. How do I change the location where the system looks at boot time for the resume signature? Thanks, -- Patrice Guay [EMAIL PROTECTED] ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Changing swap resume signature location
1. Format the swap partition again: sudo mkswap /dev/XXX 2. Activate swap partition sudo swapon /dev/XXX 3. Replace UUID=XXX in /etc/initramfs-tools/conf.d/resume by resume=/dev/XXX 4. Regenerate the initrd: sudo mkinitramfs -o /boot/initrd.img-2.6.XX (same version as the kernel) On Mon, Sep 1, 2008 at 1:23 PM, Mag Gam [EMAIL PROTECTED] wrote: Why not create a new swap partition and place it in /etc/fstab ? You don't have to worry about swap signatures and all... On Sat, Aug 30, 2008 at 8:05 AM, Patrice Guay [EMAIL PROTECTED] wrote: At boot time, the system is looking for a resume signature on the default SWAP partition that was defined during the OS installation. On several systems, I changed the location of the SWAP partition. How do I change the location where the system looks at boot time for the resume signature? Thanks, -- Patrice Guay [EMAIL PROTECTED] ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Changing swap resume signature location
On Mon, Sep 1, 2008 at 2:42 PM, Patrice Guay [EMAIL PROTECTED] wrote: On Sat, Aug 30, 2008 at 8:05 AM, Patrice Guay [EMAIL PROTECTED] wrote: At boot time, the system is looking for a resume signature on the default SWAP partition that was defined during the OS installation. On several systems, I changed the location of the SWAP partition. How do I change the location where the system looks at boot time for the resume signature? 1. Format the swap partition again: sudo mkswap /dev/XXX 2. Activate swap partition sudo swapon /dev/XXX 3. Replace UUID=XXX in /etc/initramfs-tools/conf.d/resume by resume=/dev/XXX 4. Regenerate the initrd: sudo mkinitramfs -o /boot/initrd.img-2.6.XX (same version as the kernel) I cannot find the /etc/initramfs-tools directory on my system. Which package provides it under CentOS 5? Thanks, -- Patrice ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos This is a Debian specific command. I am certain something like this exists for CentOS too... ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] S.M.A.R.T
When I do a scan for 0 I get this, Device: HP P800 Version: 5.20 Terminate command early due to bad response to IEC mode page Very strange... Also, I am using smartctl -a -d cciss,1 -i /dev/cciss/c0d0 smartctl -a -d cciss,2 -i /dev/cciss/c0d0 smartctl -a -d cciss,3 -i /dev/cciss/c0d0 If I go above 3 I get the same type of error. I am not sure why this is occuring. Any ideas? TIA On 8/30/08, Mag Gam [EMAIL PROTECTED] wrote: But, how would the OS know about physical drives. I though it would only know about the logical drive On Sat, Aug 30, 2008 at 11:43 AM, Mogens Kjaer [EMAIL PROTECTED] wrote: Mag Gam wrote: Mogens, Correct thats what I am using. N=0 is the controller N=1 1 drive N=2 2 Drive N3 is not working for me. Strange I have 2 logical drives. /dev/cciss/c0d1 and /dev/cciss/c0d2 Each logical drive has 6 physical volumes totaling 12 physical volumes Are you experiencing the same thing? No. N refers to physical drives. N=0 is the first drive. Mogens -- Mogens Kjaer, Carlsberg A/S, Computer Department Gamle Carlsberg Vej 10, DK-2500 Valby, Denmark Phone: +45 33 27 53 25, Fax: +45 33 27 47 08 Email: [EMAIL PROTECTED] Homepage: http://www.crc.dk ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] S.M.A.R.T
At my physics lab we have 30 servers with 1TB disk packs. I am in need of monitoring for disk failures. I have been reading about SMART and it seems it can help. However, I am not sure what to look for if a drive is about to fail. Any thoughts about this? Is anyone using this method to predetermine disk failures? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] S.M.A.R.T
Rak, Thanks! The Google paper is intense. I was hoping to get some practical usage with command or scripts to better monitor my SMART environment. On Sat, Aug 30, 2008 at 4:57 AM, Richard Karhuse [EMAIL PROTECTED] wrote: On Sat, Aug 30, 2008 at 4:08 AM, Mag Gam [EMAIL PROTECTED] wrote: At my physics lab we have 30 servers with 1TB disk packs. I am in need of monitoring for disk failures. I have been reading about SMART and it seems it can help. However, I am not sure what to look for if a drive is about to fail. Any thoughts about this? Is anyone using this method to predetermine disk failures? Here are a few references from my archives w.r.t. SMART ... Hope they help ... -rak- http://hardware.slashdot.org/hardware/07/02/18/0420247.shtml Google Releases Paper on Disk Reliability The Google engineers just published a paper on Failure Trends in a Large Disk Drive Population. Based on a study of 100,000 disk drives over 5 years they find some interesting stuff. To quote from the abstract: 'Our analysis identifies several parameters from the drive's self monitoring facility (SMART) that correlate highly with failures. Despite this high correlation, we conclude that models based on SMART parameters alone are unlikely to be useful for predicting individual drive failures. Surprisingly, we found that temperature and activity levels were much less correlated with drive failures than previously reported.' http://hardware.slashdot.org/hardware/07/02/21/004233.shtml Everything You Know About Disks Is Wrong Google's wasn't the best storage paper at FAST '07. Another, more provocative paper looking at real-world results from 100,000 disk drives got the 'Best Paper' award. Bianca Schroeder, of CMU's Parallel Data Lab, submitted Disk failures in the real world: What does an MTTF of 1,000,000 hours mean to you? The paper crushes a number of (what we now know to be) myths about disks such as vendor MTBF validity, 'consumer' vs. 'enterprise' drive reliability (spoiler: no difference), and RAID 5 assumptions. StorageMojo has a good summary of the paper's key points. http://www.linuxjournal.com/article/6983?from=50comments_per_page=50 Monitoring Hard Disks with SMART By Bruce Allen on Thu, 2004-01-01 02:00. SysAdmin One of your hard disks might be trying to tell you it's not long for this world. Install software that lets you know when to replace it. It's a given that all disks eventually die, and it's easy to see why. The platters in a modern disk drive rotate more than a hundred times per second, maintaining submicron tolerances between the disk heads and the magnetic media that store data. Often they run 24/7 in dusty, overheated environments, thrashing on heavily loaded or poorly managed machines. So, it's not surprising that experienced users are all too familiar with the symptoms of a dying disk. Strange things start happening. Inscrutable kernel error messages cover the console and then the system becomes unstable and locks up. Often, entire days are lost repeating recent work, re-installing the OS and trying to recover data. Even if you have a recent backup, sudden disk failure is a minor catastrophe. http://smartmontools.sourceforge.net/ smartmontools Home Page Welcome! This is the home page for the smartmontools package. ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] S.M.A.R.T
Thankyou Anne. I just installed this and its seems to work. I am behind a RAID controller so hopefully anyone with cciss drivers can shed some light. I am able to see my logical devices but I have 6 drives per logical device. I would like to see all 12 drive status if possible. On Sat, Aug 30, 2008 at 6:11 AM, Anne Wilson [EMAIL PROTECTED] wrote: On Saturday 30 August 2008 09:57:10 Richard Karhuse wrote: http://smartmontools.sourceforge.net/ smartmontools Home Page Welcome! This is the home page for the smartmontools package. I use this, and it's worth noting that it can be run on windows boxes, too. Anne ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] S.M.A.R.T
Thankyou again. I suppose I can take a look at smartd to get log files and have them forward to syslog-ng, unless smartd has an email feature :-) What does your smartd config look like for HP P400/800 controller? I would be curious to look at that. TIA On Sat, Aug 30, 2008 at 10:15 AM, Mogens Kjaer [EMAIL PROTECTED] wrote: Mag Gam wrote: Thankyou Anne. I just installed this and its seems to work. I am behind a RAID controller so hopefully anyone with cciss drivers can shed some light. I am able to see my logical devices but I have 6 drives per logical device. I would like to see all 12 drive status if possible. The RAID controller watches the SMART status of the drives for you. You should watch the status of the RAID controller. It should give a warning if a drive is about to fail or has failed. I use array-info to get the status: http://sourceforge.net/projects/array-info/ # /usr/local/bin/array-info -d /dev/cciss/c0d0 Compaq Smart Array 5312 Firmware revision : 2.58 Rom revision : 2.58 1 logical drive configured. Logical drive 0 : Fault tolerance : RAID 5 Size: 957.10 GiB (2007181360 blocks of 512 bytes) Status : Logical drive is ok Mogens -- Mogens Kjaer, Carlsberg A/S, Computer Department Gamle Carlsberg Vej 10, DK-2500 Valby, Denmark Phone: +45 33 27 53 25, Fax: +45 33 27 47 08 Email: [EMAIL PROTECTED] Homepage: http://www.crc.dk ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] S.M.A.R.T
Mogens, Correct thats what I am using. N=0 is the controller N=1 1 drive N=2 2 Drive N3 is not working for me. Strange I have 2 logical drives. /dev/cciss/c0d1 and /dev/cciss/c0d2 Each logical drive has 6 physical volumes totaling 12 physical volumes Are you experiencing the same thing? On Sat, Aug 30, 2008 at 11:27 AM, Mogens Kjaer [EMAIL PROTECTED] wrote: Mag Gam wrote: Thankyou again. I suppose I can take a look at smartd to get log files and have them forward to syslog-ng, unless smartd has an email feature :-) What does your smartd config look like for HP P400/800 controller? I would be curious to look at that. I don't run smartd on the drives. I can get the SMART status like: smartctl -d cciss,N -a /dev/cciss/c0d0 where N is the drive number (from 0), but it will only return the status of 6 of the 8 drives. Mogens -- Mogens Kjaer, Carlsberg A/S, Computer Department Gamle Carlsberg Vej 10, DK-2500 Valby, Denmark Phone: +45 33 27 53 25, Fax: +45 33 27 47 08 Email: [EMAIL PROTECTED] Homepage: http://www.crc.dk ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] S.M.A.R.T
But, how would the OS know about physical drives. I though it would only know about the logical drive On Sat, Aug 30, 2008 at 11:43 AM, Mogens Kjaer [EMAIL PROTECTED] wrote: Mag Gam wrote: Mogens, Correct thats what I am using. N=0 is the controller N=1 1 drive N=2 2 Drive N3 is not working for me. Strange I have 2 logical drives. /dev/cciss/c0d1 and /dev/cciss/c0d2 Each logical drive has 6 physical volumes totaling 12 physical volumes Are you experiencing the same thing? No. N refers to physical drives. N=0 is the first drive. Mogens -- Mogens Kjaer, Carlsberg A/S, Computer Department Gamle Carlsberg Vej 10, DK-2500 Valby, Denmark Phone: +45 33 27 53 25, Fax: +45 33 27 47 08 Email: [EMAIL PROTECTED] Homepage: http://www.crc.dk ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] syslog-ng
Hello, I know centos does not use syslog-ng, but I have installed it at my university. My intention is if a particular string appears in my /var/log/messages I would like to get an email alert. For example, if i see a message foo in /var/log/kern I would like to email myself. Any idea how to do this? Has anyone done this before? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] syslog-ng
Oh, so syslog-ng probally isn't the right tool for the job? I can use these tools to monitor my /var/log/kern ? Also, thanks for all the responses! On Fri, Aug 29, 2008 at 7:36 AM, Jeremiah Heller [EMAIL PROTECTED] wrote: Have you heard of http://www.ossec.net/? It would do what you like and more. You configure which logs you want watched and who should be emailed/texted/paged according to various levels of criticality. I believe you can have it email you for custom log-events; although it will notice many common failure messages and other anomalies automatically - so many I haven't needed to modify much. I'm not sure if centos provides packages w/ similar functionality or not. Jeremiah On 29 Aug 2008, at 04:19, Mag Gam wrote: Hello, I know centos does not use syslog-ng, but I have installed it at my university. My intention is if a particular string appears in my /var/log/messages I would like to get an email alert. For example, if i see a message foo in /var/log/kern I would like to email myself. Any idea how to do this? Has anyone done this before? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] LVM not removing LV
Its impossible trying to find that deamon. lsof or fuser are no use :-( I just rebooted and was able to remove the LV without any problems. On Mon, Aug 25, 2008 at 8:40 AM, Toby Bluhm [EMAIL PROTECTED] wrote: Mag Gam wrote: There are too many mount points. Close to 120. I am fairly certain this volume is not mouted. I did a grep -i lvname /proc/mounts Maybe a daemon is still holding your lv device open? Somewhere, maybe this list, I remember a similar discussion where the culprit was a backup agent holding /dev/ open. The solution was to kill the daemon. -- Toby Bluhm Alltech Medical Systems America, Inc. ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] LVM not removing LV
I am using RHEL 5.1 with custom kernel. I have a LV I am trying to remove and its keep complaining its open. I have unmounted the filesystem, lsof shows nothing, fuser shows nothing. I am certain a reboot will fix it, but I don't know why this occurs. Can anyone shed some light on this? Are there some other LVM hacks I can use for this? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] LVM not removing LV
I can't even deactivate it. On Fri, Aug 22, 2008 at 10:33 AM, Toby Bluhm [EMAIL PROTECTED] wrote: Toby Bluhm wrote: nate wrote: . . . Verify that it's deactivated with the lvdisplay command Current versions of lvm/lvremove will do that automatically. . . . but verifying is still a good idea. -- Toby Bluhm Alltech Medical Systems America, Inc. ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] FSID and NFS
Thankyou. This helps a lot! On Sun, Aug 17, 2008 at 7:20 PM, Filipe Brandenburger [EMAIL PROTECTED] wrote: On Sat, Aug 16, 2008 at 11:30, Mag Gam [EMAIL PROTECTED] wrote: What is the purpose of FSIDs? I am exporting 30 volumes via NFS. Do I need a FSID option? FSID is needed in NFSv3 if the devices you are exporting may change minor numbers across reboots. For example, if you have a filesystem on /dev/sdc1 that you mount and export, if it is always /dev/sdc1 (and not sometimes /dev/sdd1 depending of having another disk attached during boot time) you don't need it. However, if you are exporting filesystems which are mounted on LVM volumes (which will change order on the next reboot if you create or destroy new logical volumes) you should set FSIDs explicitly to avoid them changing on the reboot. If you don't set the FSIDs explicitly, after a reboot of the NFS server, you may experience NFS clients that show the contents of a different filesystem where you formerly had a specific one mounted, or more frequently you will have your mounted filesystems with Stale NFS filehandle errors. You will have to unmount and remount the filesystems on all clients to fix these problems. HTH, Filipe ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] FSID and NFS
What is the purpose of FSIDs? I am exporting 30 volumes via NFS. Do I need a FSID option? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] slow NFS speed
I am using mode 0, which is an aggregate. I have 2 clients, which are bonded too. 70-80Mb/sec. MB, sorry :-) I was wondering if there were any tuning parameters I should look into. Would a tcp window help? Would increasing the number of server and client processes help (not sure how to do that BTW). Any others TIA On Wed, Jul 30, 2008 at 4:31 AM, Kai Schaetzl [EMAIL PROTECTED] wrote: Mag Gam wrote on Tue, 29 Jul 2008 23:20:10 -0400: 70-80Mb/sec. Mb or MB? Kai -- Kai Schätzl, Berlin, Germany Get your web at Conactive Internet Services: http://www.conactive.com ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] slow NFS speed
We upgraded from a 10/100Mbs to a 2 100/1000 bonding. We notice the speeds of NFS to be around 70-80Mb/sec. Which is slow, especially with bonding. I was wondering if we need to tune anything special with the Network and NFS. Does anyone have any experience with this? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Centos 5.1 NFS problems
Thankyou everyone. I updated the 5.2 kernel onto 5.1 and everything seems to work fine. Thanks for all of your help and wisdom. TIA On Fri, Jul 25, 2008 at 8:15 AM, Akemi Yagi [EMAIL PROTECTED] wrote: On Fri, Jul 25, 2008 at 4:22 AM, Mag Gam [EMAIL PROTECTED] wrote: Not an option at my university :-( Then you can try the patched kernel offered by Johnny Hughes: http://people.centos.org/~hughesjr/kernel/5/bz32/ Akemi ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Centos 5.1 NFS problems
I know this is a centos forum but I suppose it would be appropriate to ask a redhat question :-) Is anyone aware of a NFS client/server problem with Redhat 5.1 where the client/NFS do extra lookup() and getattr() calls? This is very similar to CentOS' problem, http://bugs.centos.org/view.php?id=2635 My question is, would upgrading the kernel help? or is this a userland issue? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Centos 5.1 NFS problems
Not an option at my university :-( On Fri, Jul 25, 2008 at 7:11 AM, Ralph Angenendt [EMAIL PROTECTED] wrote: Mag Gam wrote: I know this is a centos forum but I suppose it would be appropriate to ask a redhat question :-) Is anyone aware of a NFS client/server problem with Redhat 5.1 where the client/NFS do extra lookup() and getattr() calls? This is very similar to CentOS' problem, http://bugs.centos.org/view.php?id=2635 My question is, would upgrading the kernel help? or is this a userland issue? Update to 5.2 Ralph ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Disable hid debug
Just compiled a kernel. And I have hid-debug enabled. Whenever I move the mouse or type anything on the keyboard I get all action messages on the console. How can I disable this? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] make rpm for kernel
I am compiling a custom kernel. When I do a make oldconfig, and then make rpm, I get a kernel rpm. The problem is I am not getting the initrd image. Is this normal? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] make rpm for kernel
Thanks Actually, I am using Redhat distribution. I though CentOS would be very similar to Redhat's kernel build. TIA On Sat, Jul 12, 2008 at 8:42 AM, Akemi Yagi [EMAIL PROTECTED] wrote: On Sat, Jul 12, 2008 at 5:37 AM, Mag Gam [EMAIL PROTECTED] wrote: I am compiling a custom kernel. When I do a make oldconfig, and then make rpm, I get a kernel rpm. The problem is I am not getting the initrd image. Is this normal? Please try following this wiki: http://wiki.centos.org/HowTos/Custom_Kernel and do it CentOS way. :) Akemi ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] random file
Is it possible to create a file on a random inode on a file system? I am trying to simulate a random read and write for testing purposes. TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] random file
even seeking thru it requires a sequential scan, right? On Sun, Jun 22, 2008 at 1:57 PM, Frank Cox [EMAIL PROTECTED] wrote: On Sun, 22 Jun 2008 11:20:22 -0400 Mag Gam [EMAIL PROTECTED] wrote: Is it possible to create a file on a random inode on a file system? Wouldn't it be easier (and safer) to create a large file, then seek within it? -- MELVILLE THEATRE ~ Melville Sask ~ http://www.melvilletheatre.com ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] recommendations for copying large filesystems
I need to copy over 100TB of data from one server to another via network. What is the best option to do this? I am planning to use rsync but is there a better tool or better way of doing this? For example, I plan on doing rsync -azv /largefs /targetfs /targetfs is a NFS mounted filesystem. Any thoughts? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] recommendations for copying large filesystems
Network is a 10/100 1 million large files No SAN, JBOD On Sat, Jun 21, 2008 at 1:19 PM, Rainer Duffner [EMAIL PROTECTED] wrote: Am 21.06.2008 um 15:33 schrieb Mag Gam: I need to copy over 100TB of data from one server to another via network. What is the best option to do this? I am planning to use rsync but is there a better tool or better way of doing this? For example, I plan on doing rsync -azv /largefs /targetfs /targetfs is a NFS mounted filesystem. What network link is there between these hosts? Are these 1 or 2 million small files or bigger ones? Does the data change a lot? Is it a SAN or JBOD? cheers, Rainer -- Rainer Duffner CISSP, LPI, MCSE [EMAIL PROTECTED] ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] LVM and ext3 filesystem question
Can someone please explain what the purpose of stride is on ext3? I have been googling this for hours and wasn't really able to understand the underlying concepts. How does it fit with LVM, PV create's metablock size, and hardware RAID controller? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] GFS
Hello: I am planning to implement GFS for my university as a summer project. I have 10 servers each with SAN disks attached. I will be reading and writing many files for professor's research projects. Each file can be anywhere from 1k to 120GB (fluid dynamic research images). The 10 servers will be using NIC bonding (1GB/network). So, would GFS be ideal for this? I have been reading a lot about it and it seems like a perfect solution. Any thoughts? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Interface bonding?
Thanks Jim. Since, 802.3ad requires switch settings does it perform better than other modes? Does anyone have any benchmarks? TIA On Thu, May 22, 2008 at 7:19 AM, James Pearson [EMAIL PROTECTED] wrote: Mag Gam wrote: Just out of curiosity. If you wanted to bond do you have to ask your network admin to configure a special switch setting for MAC addresses? AFAIK, only with 802.3ad The other Linux bonding modes don't require any switch settings James Pearson ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Is tripwire still being developed?
___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Is tripwire still being developed?
sorry I didn't mean to break any rules on the mailing list. So, open source version of Tripwire isn't development anymore? I am hesitant to try new tools without any bells and whistles :-) On Sat, Mar 29, 2008 at 2:44 PM, Jim Perrin [EMAIL PROTECTED] wrote: On Sat, Mar 29, 2008 at 11:21 AM, Mag Gam [EMAIL PROTECTED] wrote absolutely nothing of use, however: For centos5, aide is built in, and does what tripwire did You can find a walkthrough here - http://www.bofh-hunter.com/2007/12/04/centos-5-and-aide/ -- During times of universal deceit, telling the truth becomes a revolutionary act. George Orwell ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] RHEL on The Pirate Bay, Mininova, etc
Why would you download an illegal version of RHEL? I see no point in that... On Fri, Mar 21, 2008 at 3:08 PM, Michael Semcheski [EMAIL PROTECTED] wrote: On Fri, Mar 21, 2008 at 2:17 PM, Simon Jolle sjolle [EMAIL PROTECTED] wrote: Hi Centos Users Its _really_ nonsense to release RHEL version on file sharing networks. The only reason why RHEL is so popular on torrent trackers is the lack of knowledge about Centos :-) Conclusion: we should do more marketing :-) If somebody's downloading an illegal version of RHEL, you have to ask yourself, do you really think they would've made a big contribution to CentOS if they knew about it? ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Apache2::Request on CentOS 5
Hi, Running mod_perl, and trying to get Apache2::Request installed. I can't seem to find an RPM for it. Has anyone got this working on CentOS 5? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] reading vmcore files
Ok. I have a 64bit vmcore file. I have a 32bit system I moved the 64bitvmcore to the 32bit system. What next? I would be happy to try that On 9/28/07, Tomasz 'Zen' Napierala [EMAIL PROTECTED] wrote: On Friday 28 September 2007 13:18:12 Mag Gam wrote: So is it possible? :-) In theory it should be. Why don't you try yourself and let us know? ;) Regards, -- Tomasz Napierala System Administrator Allegro Team http://www.allegro.pl/ ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] reading vmcore files
So, If I have a vmcore file from systemX (AMD 64), and I have a test box (Intel 32bit), can I still read the vmcore file on Intel32 bit box? Also, where can I find a guide to system crash handling (like, find the root cause of a problem), i guess backtrack... TIA On 9/19/07, Tomasz Napierała [EMAIL PROTECTED] wrote: On Wednesday 19 September 2007 02:35:59 Mag Gam wrote: I have several RHEL AS 4 systems, and when we get a vmcore, I would like to view them in my centos box.. How can I do that? Is that even possible? crash.x86_64 4.0-3.9installed Matched from: crash crash utility for live systems; netdump, diskdump, LKCD or mcore dumpfiles It's installed by default (CentOS pretty much follows RH policies) regards, -- Tomasz Napierala System Administrator Allegro Team http://www.allegro.pl/ ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] reading vmcore files
I have several RHEL AS 4 systems, and when we get a vmcore, I would like to view them in my centos box.. How can I do that? Is that even possible? Thanks! ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Linux User Auditing
Is it possible to audit the Linux User Shell? I am trying to gather what commands a user is running no our systems. Can auditd handle this? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Linux User Auditing
Bazy: Thanks. I hope in the future version of auditd, it will be much easier to monitor user's activities. On 9/3/07, Bazy [EMAIL PROTECTED] wrote: Mag Gam wrote: Is it possible to audit the Linux User Shell? I am trying to gather what commands a user is running no our systems. Can auditd handle this? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos Hi Mag Gam, I don't know if it can log what every user does... but it can watch a lot of things :) Here is an example of watching what happens in /tmp, the reads and writes (auditctl -w /tmp -p rw -k tmp-watch): [EMAIL PROTECTED] ~]# auditctl -l No rules [EMAIL PROTECTED] ~]# auditctl -w /tmp -p rw -k tmp-watch [EMAIL PROTECTED] ~]# auditctl -l LIST_RULES: exit,always watch=/tmp perm=rw key=tmp-watch [EMAIL PROTECTED] ~]# ausearch -k tmp-watch time-Mon Sep 3 18:22:36 2007 type=PATH msg=audit(1188832956.932:43): item=0 name=. inode=14207425 dev=08:01 mode=041777 ouid=0 ogid=0 rdev=00:00 type=CWD msg=audit(1188832956.932:43): cwd=/tmp type=SYSCALL msg=audit(1188832956.932:43): arch=4003 syscall=5 success=yes exit=3 a0=95c1e40 a1=18800 a2=0 a3=95c29d8 items=1 ppid=31137 pid=31213 auid=500 uid=500 gid=500 euid=500 suid=500 fsuid=500 egid=500 sgid=500 fsgid=500 tty=pts1 comm=ls exe=/bin/ls key=tmp-watch time-Mon Sep 3 18:25:02 2007 type=PATH msg=audit(1188833102.354:53): item=0 name=. inode=14207425 dev=08:01 mode=041777 ouid=0 ogid=0 rdev=00:00 type=CWD msg=audit(1188833102.354:53): cwd=/tmp type=SYSCALL msg=audit(1188833102.354:53): arch=4003 syscall=5 success=yes exit=3 a0=96e5010 a1=18800 a2=96e1458 a3=96e4ff8 items=1 ppid=31137 pid=31270 auid=500 uid=500 gid=500 euid=500 suid=500 fsuid=500 egid=500 sgid=500 fsgid=500 tty=pts1 comm=ls exe=/bin/ls key=tmp-watch time-Mon Sep 3 18:25:11 2007 type=PATH msg=audit(1188833111.401:54): item=1 name=testme.hack inode=14207429 dev=08:01 mode=0100664 ouid=500 ogid=500 rdev=00:00 type=PATH msg=audit(1188833111.401:54): item=0 name=/tmp inode=14207425 dev=08:01 mode=041777 ouid=0 ogid=0 rdev=00:00 type=CWD msg=audit(1188833111.401:54): cwd=/tmp type=SYSCALL msg=audit(1188833111.401:54): arch=4003 syscall=5 success=yes exit=0 a0=bfebec4e a1=8941 a2=1b6 a3=8941 items=2 ppid=31137 pid=31271 auid=500 uid=500 gid=500 euid=500 suid=500 fsuid=500 egid=500 sgid=500 fsgid=500 tty=pts1 comm=touch exe=/bin/touch key=tmp-watch What i did under uid 500 in the shell was: cd /tmp ls touch testme.hack Like this you can watch under /bin with -p rx for example, and see what your users execute from /bin. You get the ideea :) Your could add a watch on /etc/shadow with the arbitrary filterkey shadow-file that generates records for reads, writes, executes, and appends on shadow: auditctl -w /etc/shadow -k shadow-file -p rwxa Use man auditctl, and take a look at /etc/audit/audit.rules. BE CAREFUL!!! edit /etc/sysconfig/auditd and change the AUDITD_CLEAN_STOP to no, otherwise when you restart auditd all your rules will be wiped! ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] How do I know if I am using SAN?
How can I verify if I am using SAN for my Linux Server? Also, how do I find WWNs of HBAs? TIA ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] How do I know if I am using SAN?
No, not trolling Tom. I am faily new to Linux, and was wondering how can I verify if my Linux host is connected to a SAN? I want to know if my disks (sfdisk -l) are local or attached to external storage (ie, SAN). Also, how would I figure out parent and children relationships between devices, especially HBA and their disks. TIA On 8/22/07, Tom Brown [EMAIL PROTECTED] wrote: How can I verify if I am using SAN for my Linux Server? Also, how do I find WWNs of HBAs? errr what? Is that a serious question or trolling? If you have a SAN and you need to ask if you are using it i'd worry, or perhaps i just dont understand the wording of your question. ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Correlate i/o with a process
Very nice...thanks! On 8/19/07, Feizhou [EMAIL PROTECTED] wrote: Mag Gam wrote: Hello: I have a server with 2 HBAs, and the users keeps complaining about performance problems. My question is, how can I relate the process with high I/O wait? Also, is it possible to see how much data is being pushed thru by my 2 HBAs? atop http://oldwww.atconsultancy.nl/atop/ ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
[CentOS] Correlate i/o with a process
Hello: I have a server with 2 HBAs, and the users keeps complaining about performance problems. My question is, how can I relate the process with high I/O wait? Also, is it possible to see how much data is being pushed thru by my 2 HBAs? TIA! ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Correlate i/o with a process
Thanks John. Yes, this is a tricky question, but I face this a lotUnfortunately, I am not sure how to check the adapter throughput, and what process is causing the i/o wait. On 8/17/07, John R Pierce [EMAIL PROTECTED] wrote: Mag Gam wrote: Hello: I have a server with 2 HBAs, and the users keeps complaining about performance problems. My question is, how can I relate the process with high I/O wait? Also, is it possible to see how much data is being pushed thru by my 2 HBAs? iostat (part of the sysstat package) will answer your 2nd question. I dunno how to measure io wait time per process. maybe IBM's NMON can do that, not sure, I haven't used it for a while. http://www-941.haw.ibm.com/collaboration/wiki/display/WikiPtype/nmon ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos