Search Results

Search found 5919 results on 237 pages for 'io priority'.

Page 3/237 | < Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >

  • sqlserver how to set job priority

    - by Buzz
    Is there any way to set one job priority higher then other, In my case there are two jobs those are working on same set of tables,first JOB-A which is running every 12 hr and other JOB-B is every 10 minutes , i think at some time when they run simultaneously JOB-B is getting in to deadlock and get failed, i google the topic and found sqlgoverner is helpful in such cases does anyone know how to resolve?

    Read the article

  • PHP Priority Queue Implementation

    - by Zahymaka
    I just finished coding a complex job assignment application where a lot of the work was done using priority queues. When I deployed, however, I discovered the web server ran PHP 5.2. Has there been an implementation for PHP<5.3 that can server as a drop-in replacement for SPLPriorityQueue?

    Read the article

  • Socket.io v.9 with Actionscript

    - by funseiki
    I'm attempting to develop an online multiplayer game using Node.js for the server and Flash to display the client. I've been reading up a bit and have found quite a few recommendations for the socket.io library. I've also found a github project which exposes code to help facilitate communication between an Actionscript 3.0 client and a server using socket.io. The project I mentioned is a bit dated and doesn't seem to have support for the latest version of socket.io, so I was wondering if leveraging this framework (socket.io, that is) would be the most ideal way to go. I have found a simple project that uses the standard 'net' module for node.js, but because there a few options available, I'm a little lost as to which one to go with. I'm currently leaning towards just using the regular 'net' module as it is already familiar to me. Since much of the client is already coded up, I'd really like to not switch over to using the HTML5 canvas just yet (but using socket.io would make a transition in the future more friendly, I think?). Any advice/direction on this matter would be much appreciated, though I do realize that there may be no one right answer. Edit: To be more specific, are there any client-side socket.io frameworks available that allow for communication between an Actionscript 3.0 client and a socket.io server and are robust enough to support current/future versions of socket.io? If not, what are the alternatives?

    Read the article

  • Go - Using a container/heap to implement a priority queue

    - by Seth Hoenig
    In the big picture, I'm trying to implement Dijkstra's algorithm using a priority queue. According to members of golang-nuts, the idiomatic way to do this in Go is to use the heap interface with a custom underlying data structure. So I have created Node.go and PQueue.go like so: //Node.go package pqueue type Node struct { row int col int myVal int sumVal int } func (n *Node) Init(r, c, mv, sv int) { n.row = r n.col = c n.myVal = mv n.sumVal = sv } func (n *Node) Equals(o *Node) bool { return n.row == o.row && n.col == o.col } And PQueue.go: // PQueue.go package pqueue import "container/vector" import "container/heap" type PQueue struct { data vector.Vector size int } func (pq *PQueue) Init() { heap.Init(pq) } func (pq *PQueue) IsEmpty() bool { return pq.size == 0 } func (pq *PQueue) Push(i interface{}) { heap.Push(pq, i) pq.size++ } func (pq *PQueue) Pop() interface{} { pq.size-- return heap.Pop(pq) } func (pq *PQueue) Len() int { return pq.size } func (pq *PQueue) Less(i, j int) bool { I := pq.data.At(i).(Node) J := pq.data.At(j).(Node) return (I.sumVal + I.myVal) < (J.sumVal + J.myVal) } func (pq *PQueue) Swap(i, j int) { temp := pq.data.At(i).(Node) pq.data.Set(i, pq.data.At(j).(Node)) pq.data.Set(j, temp) } And main.go: (the action is in SolveMatrix) // Euler 81 package main import "fmt" import "io/ioutil" import "strings" import "strconv" import "./pqueue" const MATSIZE = 5 const MATNAME = "matrix_small.txt" func main() { var matrix [MATSIZE][MATSIZE]int contents, err := ioutil.ReadFile(MATNAME) if err != nil { panic("FILE IO ERROR!") } inFileStr := string(contents) byrows := strings.Split(inFileStr, "\n", -1) for row := 0; row < MATSIZE; row++ { byrows[row] = (byrows[row])[0 : len(byrows[row])-1] bycols := strings.Split(byrows[row], ",", -1) for col := 0; col < MATSIZE; col++ { matrix[row][col], _ = strconv.Atoi(bycols[col]) } } PrintMatrix(matrix) sum, len := SolveMatrix(matrix) fmt.Printf("len: %d, sum: %d\n", len, sum) } func PrintMatrix(mat [MATSIZE][MATSIZE]int) { for r := 0; r < MATSIZE; r++ { for c := 0; c < MATSIZE; c++ { fmt.Printf("%d ", mat[r][c]) } fmt.Print("\n") } } func SolveMatrix(mat [MATSIZE][MATSIZE]int) (int, int) { var PQ pqueue.PQueue var firstNode pqueue.Node var endNode pqueue.Node msm1 := MATSIZE - 1 firstNode.Init(0, 0, mat[0][0], 0) endNode.Init(msm1, msm1, mat[msm1][msm1], 0) if PQ.IsEmpty() { // make compiler stfu about unused variable fmt.Print("empty") } PQ.Push(firstNode) // problem return 0, 0 } The problem is, upon compiling i get the error message: [~/Code/Euler/81] $ make 6g -o pqueue.6 Node.go PQueue.go 6g main.go main.go:58: implicit assignment of unexported field 'row' of pqueue.Node in function argument make: *** [all] Error 1 And commenting out the line PQ.Push(firstNode) does satisfy the compiler. But I don't understand why I'm getting the error message in the first place. Push doesn't modify the argument in any way.

    Read the article

  • Dell PE2950 - slow IO rates for writing and reading locally

    - by OrenM
    I'm having a serious issue with dell server PE2950. The server has really slow IO rates, so slow that I'm not able to use it anymore I tried few things to solve this: changing disks to new disks (configured them as raid1) changing perc card + perc cables reinstalling the OS of course, had to cause of changing of disks, centos 5.5 x64bit firmware update to everything virtual disks policy: No Read Ahead,Write Back, disk cache policy disabled. openmanage doesn't alert about anything, also i ran dell's diag tests, everything passed, also dell didn't see anything in deset log. dell offered to reseat everything, including the cpu, we did that as well, still io rates are slow I have several PE2950 servers, and I never had such a thing with any of those. All have similar or exact hardware as this one, all configured the same, with the same os centos 5.5 x64, same disks, same raid, same policy. Just for comparison: the problematic PE2950 server: [root@bad ~]# time sh -c "dd if=/dev/zero of=/tmp/ddfile bs=8k count=200000 && sync" 200000+0 records in 200000+0 records out 1638400000 bytes (1.6 GB) copied, 27.7946 seconds, 58.9 MB/s real 0m33.968s user 0m0.531s sys 0m26.000s good PE2950 server (with the exact same hardware): [root@good ~]# time sh -c "dd if=/dev/zero of=/tmp/ddfile bs=8k count=200000 && sync" 200000+0 records in 200000+0 records out 1638400000 bytes (1.6 GB) copied, 3.19999 seconds, 512 MB/s real 0m7.694s user 0m0.053s sys 0m4.057s Hopefully you will have an idea what can cause the problem.

    Read the article

  • C++: A variation of priority queue

    - by Helltone
    I need some kind of priority queue to store pairs <key, value>. Values are unique, but keys aren't. I will be performing the following operations (most common first): random insertion; retrieving (and removing) all elements with the least key. random removal (by value); I can't use std::priority_queue because it only supports removing the head. For now, I'm using an unsorted std::list. Insertion is performed by just pushing new elements to the back (O(1)). Operation 2 sorts the list with std::sort (O(N*logN)), before performing the actual retrieval. Removal, however, is O(n), which is a bit expensive. Any idea of a better data structure?

    Read the article

  • Multiset of shared_ptrs as a dynamic priority queue: Concept and practice

    - by Sarah
    I was using a vector-based priority queue typedef std::priority_queue< Event, vector< Event >, std::greater< Event > > EventPQ; to manage my Event objects. Now my simulation has to be able to find and delete certain Event objects not at the top of the queue. I'd like to know if my planned work-around can do what I need it to, and if I have the syntax right. I'd also like to know if dramatically better solutions exist. My plan is to make EventPQ a multiset of smart pointers to Event objects: typedef std::multi_set< boost::shared_ptr< Event > > EventPQ; I'm borrowing functions of the Event class from a related post on a multimap priority queue. // Event.h #include <cstdlib> using namespace std; #include <set> #include <boost/shared_ptr.hpp> class Event; typedef std::multi_set< boost::shared_ptr< Event > > EventPQ; class Event { public: Event( double t, int eid, int hid ); ~Event(); void add( EventPQ& q ); void remove(); bool operator < ( const Event & rhs ) const { return ( time < rhs.time ); } bool operator > ( const Event & rhs ) const { return ( time > rhs.time ); } double time; int eventID; int hostID; EventPQ* mq; EventPQ::iterator mIt; }; // Event.cpp Event::Event( double t, int eid, int hid ) { time = t; eventID = eid; hostID = hid; } Event::~Event() {} void Event::add( EventPQ& q ) { mq = &q; mIt = q.insert( boost::shared_ptr<Event>(this) ); } void Event::remove() { mq.erase( mIt ); mq = 0; mIt = EventPQ::iterator(); } I was hoping that by making EventPQ a container of pointers, I could avoid wasting time copying Events into the container and avoid accidentally editing the wrong copy. Would it be dramatically easier to store the Events themselves in EventPQ instead? Does it make more sense to remove the time keys from Event objects and use them instead as keys in a multimap? Assuming the current implementation seems okay, my questions are: Do I need to specify how to sort on the pointers, rather than the objects, or does the multiset automatically know to sort on the objects pointed to? If I have a shared_ptr ptr1 to an Event that also has a pointer in the EventPQ container, how do I find and delete the corresponding pointer in EventPQ? Is it enough to .find( ptr1 ), or do I instead have to find by the key (time)? Is the Event::remove() sufficient for removing the pointer in the EventPQ container? There's a small chance multiple events could be created with the same time (obviously implied in the use of multiset). If the find() works on event times, to avoid accidentally deleting the wrong event, I was planning to throw in a further check on eventID and hostID. Does this seem reasonable? (Dumb syntax question) In Event.h, is the declaration of dummy class Event;, then the EventPQ typedef, and then the real class Event declaration appropriate? I'm obviously an inexperienced programmer with very spotty background--this isn't for homework. Would love suggestions and explanations. Please let me know if any part of this is confusing. Thanks.

    Read the article

  • scipy.io typeerror:buffer too small for requested array

    - by kartiku
    I have a problem in python. I'm using scipy, where i use scipy.io to load a .mat file. The .mat file was created using MATLAB. listOfFiles = os.listdir(loadpathTrain) for f in listOfFiles: fullPath = loadpathTrain + '/' + f mat_contents = sio.loadmat(fullPath) print fullPath Here's the error: Traceback (most recent call last): File "tryRankNet.py", line 1112, in demo() File "tryRankNet.py", line 645, in demo mat_contents = sio.loadmat(fullPath) File "/usr/lib/python2.6/dist-packages/scipy/io/matlab/mio.py", line 111, in loadmat matfile_dict = MR.get_variables() File "/usr/lib/python2.6/dist-packages/scipy/io/matlab/miobase.py", line 356, in get_variables getter = self.matrix_getter_factory() File "/usr/lib/python2.6/dist-packages/scipy/io/matlab/mio5.py", line 602, in matrix_getter_factory return self._array_reader.matrix_getter_factory() File "/usr/lib/python2.6/dist-packages/scipy/io/matlab/mio5.py", line 274, in matrix_getter_factory tag = self.read_dtype(self.dtypes['tag_full']) File "/usr/lib/python2.6/dist-packages/scipy/io/matlab/miobase.py", line 171, in read_dtype order='F') TypeError: buffer is too small for requested array The whole thing is in a loop, and I checked the size of the file where it gives the error by loading it interactively in IDLE. The size is (9,521), which is not at all huge. I tried to find if I'm supposed to clear the buffer after each iteration of the loop, but I could not find anything. Any help would be appreciated. Thanks.

    Read the article

  • error on connecting to the server : socket io is not defined

    - by max
    i know there's been couple of question about the same problem , i've already check them . i have very simple node.js chat app i have a server running on 8000 port and it works fine my client pages are html , they are running on apache and i'm using socket.io to connect them to the server and it works fine on the local host but when i upload the app on the server i keep on getting this error in the firebug io is not defined var socket = io.connect('http://atenak.com:8000/'); or sometimes it doesn't show that but when i try to broadcast message from cliend i get this error : socket is undefined socket.emit('msg', { data: msg , user:'max' }); the only difference is i've changed the localhost with atenak.com ! here is my html code var socket = io.connect('http://atenak.com:8000/'); var user = 'jack'; socket.on('newmsg', function (data) { if(data.user == user ) { $('#container').html(data.data); } }); function brodcast(){ var msg = $('#fild').val(); socket.emit('msg', { data: msg , user:'max' }); } </script> </head> <body> <div id="container"> </div> <input id="fild" type="text"> <input name="" type="button" onClick="brodcast();"> </body> i have included the sockt.io.js and server is running ok which means socket.io is installed on the server here is the live page http://atenak.com/client.html

    Read the article

  • How can I automatically change the priority of Javaw.exe when loading Minecraft?

    - by Arch Angel
    I launch Minecraft.exe which invokes Javaw.exe. I wish for Javaw.exe to be running in High priority because Minecraft lags if not. I tried invoking Minecraft.exe with a high priority by doing this: Start "Minecraft" /high "C:\Users\Barrie\Documents\Program Files\Minecraft\Minecraft.exe" This would work if it wasn't for Minecraft loading Javaw.exe. I would love a simple solution - perhaps a command I can put into the batch script - which will change the priority of Javaw.exe after it loads. Edit: I'd like to thank everyone for their response to my issue. I fixed this by executing Minecraft.exe with a batch script then calling an AHK script to change the priority of Javaw.exe.

    Read the article

  • Debugging IO limitation

    - by Martin F
    I have a Fedora box with some severe IO limitations which I have no idea how to debug. The server has a Areca Technology Corp. ARC-1130 12-Port PCI-X to SATA RAID Controller with 12 7200 RPM 1.5 TB disks and a Marvell Technology Group Ltd. 88E8050 PCI-E ASF Gigabit Ethernet Controller. uname -a output: 2.6.32.11-99.fc12.x86_64 #1 SMP Mon Apr 5 19:59:38 UTC 2010 x86_64 x86_64 x86_64 GNU/Linux The server is a file server running Nginx with the stub status module enabled, so I can see the current amount of connections. The problem present itself when I have a high number of simultaneous connections in a writing state. Usually around 350, at this very moment it's at 590 and the server is almost unusable and stuck at 230mbit/s. If I run stop and hit 1 to see CPU core usages I have all 4 cores with around 99% io wait, if I run iotop the nginx workers are the only processes producing any read load, currently at around 25MB/s. I have each of the workers bound to their own core. Initially I figured it was just the disks being bugged. But I've run fscheck and smartmontools checks and found no errors. I also ran an iozone test which you can see the result of here: http://www.pastie.org/951667.txt?key=fimcvljulnuqy2dcdxa Additionally, when the amount of connections are low I have no problem getting a good speed. If I wget over the local network it easily hits 60MB/sec. Right now I just tried putting a file in /dev/shm, then I symlinked a file from the public dir to it and used wget over the local network and only got 50KB/s. Also, if I try to cp /dev/shm/test /root/test it quickly copies around 740MB and then slows down HEAVILY. Again with iotop reporting 99% iowait. I'm not really sure how to go about figuring out what the problems are. It could be a natural disk limitation but then the file from /dev/shm ought to transfer so it seems there's a network limit, but that's fine when there's not many connections. Perhaps it's a TCP stack problem but I really have no idea how to check that. Any suggestions on how to proceed with debugging would be very welcome. If additional information is required then let me know and I'll try to get it. Thanks.

    Read the article

  • Pancake.io Is a Dead Simple Way to Host a Web Site from Your Dropbox Account

    - by Jason Fitzpatrick
    Pancake.io is a web-based app that makes it dead simple to use your Dropbox account as as simple web host. Signup for an account and Pancake.io creates a folder in your Dropbox. You can modify the page in one of two ways: you can simply put files into the folder and use the simple template provided by Pancake.io to share them or you can edit the template (located in the Pancake.io folder) to customize the page. Hit up the link below to read more about Pancake.io and take it for a test drive. Pancake.io [via ReadWriteWeb] HTG Explains: How Hackers Take Over Web Sites with SQL Injection / DDoS Use Your Android Phone to Comparison Shop: 4 Scanner Apps Reviewed How to Run Android Apps on Your Desktop the Easy Way

    Read the article

  • Filtering serial port io

    - by mr odus
    I am currently working on a project where I communicate with hardware via a com port on its respective pc(win xp or 7) It is a fairly large project and sifting through the log file can be a bit of pain. This is my current setup. I use putty to do the actual serial communication, and write it to a log file. Then using MinGW Msys I filter it using tail -f "puttyLog" | grep -i "search term" Is there a better way to do this? I mean specifically filtering the input in realtime. Not that mine is terrible, but it still involves having to read from a log and sometimes there have been hangups where it will be delayed for a minute or 2. I have used software in the past with a main io window and then internal filter panels, but can no longer remember or find it.

    Read the article

  • Changing the priority of Gnome Shell

    - by user32655
    I want to give Gnome-Shell the highest priority, but I couldn't change the priority on the System Monitor, an error messeage says: Can't change priority's process with pid 2841 to -5. Access denied I tried the following commands: gksu gnome-system-monitor But I can't find Gnome-Shell on the processes list, so I tried "renice command", like this: sudo renice -15 2841 And finally got this problem, the Gnome-Shell's PID always changes, it's not the same PID numbers, so I have to change the priority every time I start up my system. Can anyone help me? Thanks.

    Read the article

  • Possible disk IO issue

    - by Tim Meers
    I've been trying to really figure out what my IOPS are on my DB server array and see if it's just too much. The array is four 72.6gb 15k rpm drives in RAID 5. To calculate IOPS for RAID 5 the following formula is used: (reads + (4 * Writes)) / Number of disks = total IOPS. The formula is from MSDN. I also want to calculate the Avg Queue Length but I'm not sure where they are getting the formula from, but i think it reads on that page as avg que length/number of disks = actual queue. To populate that formula I used the perfmon to gather the needed information. I came up with this, under normal production load: (873.982 + (4 * 28.999)) / 4 = 247.495. Also the disk queue lengh of 14.454/4 = 3.614. So to the question, am I wrong in thinking this array has a very high disk IO? Edit I got the chance to review it again this morning under normal/high load. This time with even bigger numbers and IOPS in excess of 600 for about 5 minutes then it died down again. But I also took a look at the Avg sec/Transfer, %Disk Time, and %Idle Time. These number were taken when the reads/writes per sec were only 332.997/17.999 respectively. %Disk Time: 219.436 %Idle Time: 0.300 Avg Disk Queue Length: 2.194 Avg Disk sec/Transfer: 0.006 Pages/sec: 2927.802 % Processor Time: 21.877 Edit (again) Looks like I have that issue solved. Thanks for the help. Also for a pretty slick parser I found this: http://pal.codeplex.com/ It works pretty well for breaking down the data into something usable.

    Read the article

  • io operations in compilers

    - by Aastha
    How are constructs of io operations handled by a compiler? Like the RTL mapping for memory related operations which is done in a compiler at the time of target code generation, where and how exactly is the same done for io operations? How are the appeoaches different for processors supporting MMIO and I/O mapped I/O? Are there any optimizations done for the io operations in compilers?

    Read the article

  • Multi Player game using Nodejs and Socket IO

    - by Kishorevarma
    I am trying out multi player racing game using Node and Socket IO ,express . So I have tried simple example to see the latency between node server and the clients. I have a draggable image in client . when I move the image ienter code heren one client ,it has to move in all clients. so basically when I am moving the image I am sending the image position to the node server in a json format , then from there I am broadcasting to all clients. there is a ~approx 300ms latency from the time. following are the results. Client 1 sending data to server at : 286136 (timestamp) Server received at : 286271 Client2 received data at : 286470 Client3 received data at : 286479 Client4 received data at : 286487 Client5 received data at : 286520 the latency between move from client1 to client5 is 384ms. its too hight for a racing game .. here is my server code. var app = require('express').createServer(); var io = require('socket.io'); var http = require('http'); var http_server = http.createServer(); var server = http.createServer(app); server.listen(3000); var socket = io.listen(server,{ log: false }); socket.sockets.on('connection', function (client) { client.on('message', function (data){ console.log("data arrived to server",new Date().getTime()); // Below both statements are giving same latency between the client 1 and client 5 client.broadcast.emit('message',data); //socket.sockets.emit('message',data); }); }); 1) Is there any way to optimize the server code to reduce the latency? 2) is this expected latency using node and websockets ? 3) is socket io can't broadcast the data asynchronously (I mean at a same time) ? Thanks Kishorevarma

    Read the article

  • WPF Animation / Processing priority

    - by Matt B
    Hi all, I have a button which has an animation (in xaml) on it's click event. Cool so far. Problem is that I also have processing occurring on the click event (so I can do stuff) - and this occurs first. How do I prioritise or re-order so that the animation takes place before any custom processing... Thanks.

    Read the article

  • .NET Form_load priority

    - by mtranda
    So, the problem is such as this: I have a method that does stuff and updates a progress bar. If I call the method after the form is fully loaded (i.e.: by assigning it to a button on the form) everything works fine. The problem is that I need the method to start working as soon as the form loads, by itself, so I would place it in the Form_Load method. The problem is that even though I call Application.DoEvents() right before calling that method from within Form_Load, the form doesn't show up until the method has completed everything. As I said, if I let the form load first and call the method from another UI element for instance, everything works fine. Thanks in advance.

    Read the article

  • SQL Server IO handling mechanism can be severely affected by high CPU usage

    - by sqlworkshops
    Are you using SSD or SAN / NAS based storage solution and sporadically observe SQL Server experiencing high IO wait times or from time to time your DAS / HDD becomes very slow according to SQL Server statistics? Read on… I need your help to up vote my connect item – https://connect.microsoft.com/SQLServer/feedback/details/744650/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage. Instead of taking few seconds, queries could take minutes/hours to complete when CPU is busy.In SQL Server when a query / request needs to read data that is not in data cache or when the request has to write to disk, like transaction log records, the request / task will queue up the IO operation and wait for it to complete (task in suspended state, this wait time is the resource wait time). When the IO operation is complete, the task will be queued to run on the CPU. If the CPU is busy executing other tasks, this task will wait (task in runnable state) until other tasks in the queue either complete or get suspended due to waits or exhaust their quantum of 4ms (this is the signal wait time, which along with resource wait time will increase the overall wait time). When the CPU becomes free, the task will finally be run on the CPU (task in running state).The signal wait time can be up to 4ms per runnable task, this is by design. So if a CPU has 5 runnable tasks in the queue, then this query after the resource becomes available might wait up to a maximum of 5 X 4ms = 20ms in the runnable state (normally less as other tasks might not use the full quantum).In case the CPU usage is high, let’s say many CPU intensive queries are running on the instance, there is a possibility that the IO operations that are completed at the Hardware and Operating System level are not yet processed by SQL Server, keeping the task in the resource wait state for longer than necessary. In case of an SSD, the IO operation might even complete in less than a millisecond, but it might take SQL Server 100s of milliseconds, for instance, to process the completed IO operation. For example, let’s say you have a user inserting 500 rows in individual transactions. When the transaction log is on an SSD or battery backed up controller that has write cache enabled, all of these inserts will complete in 100 to 200ms. With a CPU intensive parallel query executing across all CPU cores, the same inserts might take minutes to complete. WRITELOG wait time will be very high in this case (both under sys.dm_io_virtual_file_stats and sys.dm_os_wait_stats). In addition you will notice a large number of WAITELOG waits since log records are written by LOG WRITER and hence very high signal_wait_time_ms leading to more query delays. However, Performance Monitor Counter, PhysicalDisk, Avg. Disk sec/Write will report very low latency times.Such delayed IO handling also occurs to read operations with artificially very high PAGEIOLATCH_SH wait time (with number of PAGEIOLATCH_SH waits remaining the same). This problem will manifest more and more as customers start using SSD based storage for SQL Server, since they drive the CPU usage to the limits with faster IOs. We have a few workarounds for specific scenarios, but we think Microsoft should resolve this issue at the product level. We have a connect item open – https://connect.microsoft.com/SQLServer/feedback/details/744650/sql-server-io-handling-mechanism-can-be-severely-affected-by-high-cpu-usage - (with example scripts) to reproduce this behavior, please up vote the item so the issue will be addressed by the SQL Server product team soon.Thanks for your help and best regards,Ramesh MeyyappanHome: www.sqlworkshops.comLinkedIn: http://at.linkedin.com/in/rmeyyappan

    Read the article

  • Determining cause of high NFS/IO utilization without iotop

    - by Matt
    I have a server that is doing an NFSv4 export for user's home directories. There are roughly 25 users (mostly developers/analysts) and about 40 servers mounting the home directory export. Performance is miserable, with users often seeing multi-second lags for simple commands (like ls, or writing a small text file). Sometimes the home directory mount completely hangs for minutes, with users getting "permission denied" errors. The hardware is a Dell R510 with dual E5620 CPUs and 8 GB RAM. There are eight 15k 2.5” 600 GB drives (Seagate ST3600057SS) configured in hardware RAID-6 with a single hot spare. RAID controller is a Dell PERC H700 w/512MB cache (Linux sees this as a LSI MegaSAS 9260). OS is CentOS 5.6, home directory partition is ext3, with options “rw,data=journal,usrquota”. I have the HW RAID configured to present two virtual disks to the OS: /dev/sda for the OS (boot, root and swap partitions), and /dev/sdb for the home directories. What I find curious, and suspicious, is that the sda device often has very high utilization, even though it only contains the OS. I would expect this virtual drive to be idle almost all the time. The system is not swapping, according to "free" and "vmstat". Why would there be major load on this device? Here is a 30-second snapshot from iostat: Time: 09:37:28 AM Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0.00 44.09 0.03 107.76 0.13 607.40 11.27 0.89 8.27 7.27 78.35 sda1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 sda2 0.00 44.09 0.03 107.76 0.13 607.40 11.27 0.89 8.27 7.27 78.35 sdb 0.00 2616.53 0.67 157.88 2.80 11098.83 140.04 8.57 54.08 4.21 66.68 sdb1 0.00 2616.53 0.67 157.88 2.80 11098.83 140.04 8.57 54.08 4.21 66.68 dm-0 0.00 0.00 0.03 151.82 0.13 607.26 8.00 1.25 8.23 5.16 78.35 dm-1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 dm-2 0.00 0.00 0.67 2774.84 2.80 11099.37 8.00 474.30 170.89 0.24 66.84 dm-3 0.00 0.00 0.67 2774.84 2.80 11099.37 8.00 474.30 170.89 0.24 66.84 Looks like iotop is the ideal tool to use to sniff out these kinds of issues. But I'm on CentOS 5.6, which doesn't have a new enough kernel to support that program. I looked at Determining which process is causing heavy disk I/O?, and besides iotop, one of the suggestions said to do a "echo 1 /proc/sys/vm/block_dump". I did that (after directing kernel messages to tempfs). In about 13 minutes I had about 700k reads or writes, roughly half from kjournald and the other half from nfsd: # egrep " kernel: .*(READ|WRITE)" messages | wc -l 768439 # egrep " kernel: kjournald.*(READ|WRITE)" messages | wc -l 403615 # egrep " kernel: nfsd.*(READ|WRITE)" messages | wc -l 314028 For what it's worth, for the last hour, utilization has constantly been over 90% for the home directory drive. My 30-second iostat keeps showing output like this: Time: 09:36:30 PM Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0.00 6.46 0.20 11.33 0.80 71.71 12.58 0.24 20.53 14.37 16.56 sda1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 sda2 0.00 6.46 0.20 11.33 0.80 71.71 12.58 0.24 20.53 14.37 16.56 sdb 137.29 7.00 549.92 3.80 22817.19 43.19 82.57 3.02 5.45 1.74 96.32 sdb1 137.29 7.00 549.92 3.80 22817.19 43.19 82.57 3.02 5.45 1.74 96.32 dm-0 0.00 0.00 0.20 17.76 0.80 71.04 8.00 0.38 21.21 9.22 16.57 dm-1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 dm-2 0.00 0.00 687.47 10.80 22817.19 43.19 65.48 4.62 6.61 1.43 99.81 dm-3 0.00 0.00 687.47 10.80 22817.19 43.19 65.48 4.62 6.61 1.43 99.82

    Read the article

  • High Load - Low IO - Low CPU usage

    - by devup
    I have a system whose load is rather high. As you can see from the top output below, CPU usage and I/O is negligible: top - 17:31:59 up 4 days, 2:34, 2 users, load average: 1.00, 0.99, 1.00 Tasks: 71 total, 1 running, 70 sleeping, 0 stopped, 0 zombie Cpu(s): 2.0%us, 2.0%sy, 0.0%ni, 95.9%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 960720k total, 707288k used, 253432k free, 67328k buffers Swap: 2811896k total, 2644k used, 2809252k free, 528928k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 15310 root 20 0 2512 1128 888 R 2.1 0.1 0:00.05 top I would appreciate any assistance with isolating the cause(s) of high load for when I/O and CPU are not factors.

    Read the article

  • RAID 5 heavy IO hard freezes Ubuntu: Why?

    - by Luke has no name
    I have a software RAID 5 partition on LVM in Ubuntu (desktop, actually, but I'm using it as a server). I have been rsyncing a ton of data to it, and the computer was hard freezing, as in I needed to press "Reset". So I thought it was rsync. But I decided I'd try a dd if=/dev/zero of=/path/to/raid5 and sure enough, the computer locked up. Did an identical dd to a JBOD partition on the same machine, and it didn't crash. Assuming a clean RAID5 partition, tri-core processor 2GB of ram, 6GB swap, what could be causing this?

    Read the article

< Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >