IO (or I/O) is an abbreviation for input/output, most commonly referring to disk input/output.

learn more… | top users | synonyms

16
votes
4answers
8k views

Measuring 'total bytes written' under Linux

We're quite interested in exploring the possibility of using SSD drives in a server environment. However, one thing that we need to establish is expected drive longevity. According to this article ...
1
vote
2answers
49 views

What are front merges in I/O scheduling and how can I tune this parameter?

My Linux uses the Deadline algorithm for I/O scheduling. One of the parameters is the front_merges parameter under /sys/block/sda/queue/iosched/front_merges. By default it is set to 1, which means ...
3
votes
2answers
2k views

monitor IO to tmpfs partition?

How can I monitor the write speed to a tmpfs partition. It does not appear in the output of vmstat or iostat. I am running several python processes that are writing heavily to tmpfs and contributing ...
1
vote
1answer
1k views

Linux - KVM - very slow disk io

The I/O performance of my new server is pretty low. I Googled and tried everything I can imagine. First of all, here are the Hardware Components: AMD Opteron(tm) Processor 6344 4x Seagate ...
0
votes
1answer
18 views

Check If I/O causing high load average

I wants to understand how to measure if I/O is causing load average high and how to calculate optimal and critical I/O value. Because sometime there is a load spike on my server but other ...
1
vote
0answers
52 views

How I can reduce disk IO in MySQL 5.6.26?

I was using MySQL version 5.1.52 for my application but recently I have updated it to 5.6.26, but now I am facing very high disk IO. Following are system configuration: OS : Linux 2.6.39.4 RAM : ...
0
votes
0answers
23 views

How to find the bottleneck for slow rsync

I want to find the bottleneck for a slow rsync. I see these parts (on byte flow order): IO on source CPU on source Network CPU on destination IO on destination How can I debug this?
3
votes
2answers
76 views

Acceptable I/O speeds for 6 x 250GB SSDs in RAID 10

I'm running CentOS 7 (XFS filesystem) on a dell server with a PERC H700 raid controller. Inside this server I have 6 x Samsung 850 Evo 250GB SSDs (yes they are consumer drives however, this is a home ...
1
vote
0answers
51 views

KVM bad IO sync performance in Linux guest

I'm setting up virtualized Ubuntu 15.10 guest inside Ubuntu 15.04 server using libvirt and KVM. Storage in host system: # mount | grep ext4 /dev/sda1 on / type ext4 ...
3
votes
1answer
1k views

monitoring disk i/o via wmi

I'm using WMI to monitor Windows Server 2003 and Windows Server 2008 hosts. I got all the info I wanted but the disk I/O performance. I've tried quering the ...
0
votes
0answers
19 views

collectl vs strace - reported block io read/write size

I've got an xfs mount with standard settings (it's an AWS host): [root@host ~]# xfs_info /dev/xvda1 meta-data=/dev/xvda1 isize=256 agcount=4, agsize=524224 blks = ...
1
vote
0answers
14 views

Long Response Times for Reads via FCoE

We're getting some intriguing performance with our new FCoE environment, and I was hoping that people could let me know if what we're seeing is expected behaviour. Our switching environment consists ...
0
votes
0answers
45 views

How can I debug: iostat shows 100 util but there's 0 read or write in iotop

The server is an AWS EC2 instance. Ubuntu 14.04.2 LTS. I have an EBS (xvdf is the device name) mounted to the instance. And this is the problem drive. From iostat I see that drive is 100% utilized ...
1
vote
1answer
43 views

How to check what is causing performance issue

[Edit] This question is different than what is suggested by the moderator, I am trying to find out what could have caused the API to become slow because of the few lines of codes. I am not trying to ...
0
votes
1answer
40 views

How to ensure that I/O requests have returned to a normal rate?

On Amazon Web Services I am using a t2.small EC2 instance as a VPS serving a few websites on a LAMP (PHP) stack. I was just hit with a bill which almost triples my usual bill. I see that my I/O ...
2
votes
2answers
1k views

How can I monitor disk IO load on a Windows 2008 server?

We are running multiple processes on our servers, which are mostly CPU intensive, but also use the local HDDs for reading the data. I can trivially look at the CPU load and memory usage in TaskManager ...
0
votes
0answers
75 views

Starting PHP session sometimes take very long time

Sometime ago we have came upon interesting problem. Sometime (not everytime, lets pretend nearly each 100-200 hit) session_start() takes very long time. Up to 60 seconds. (longest one was 63, ...
1
vote
1answer
30 views

How many milliseconds of await is considered to be high? [closed]

How many milliseconds of await is considered to be high? i have 800ms and 600ms iostat -x avg-cpu: %user %nice %system %iowait %steal %idle 1.28 0.00 0.22 0.90 0.00 ...
0
votes
3answers
208 views

I/O and RAM limitations are important for Hadoop performance. But is disk speed related to I/O?

Hortonworks says this: "Most often performance of a Hadoop cluster will not be constrained by disk speed – I/O and RAM limitations will be more important." * How is disk speed not related to I/O ...
0
votes
1answer
15 views

Get NewRelic to respect ionice'd processes

On our web server, we perform an incremental backup of our files every 4 hours using rsnapshot. To perform the actual copying of files, I've configured it to use a custom script, cp-nice that has the ...
1
vote
2answers
51 views

Most side effect-free way to archive a large file while it is being modified

I am looking after an application that generates a large amount of data in a log file (about 5G a day) on a Red Hat server. This process runs for 24 hours during the week, so there is no point in the ...
1
vote
0answers
82 views

Redis parent process smashing disk despite appendfsync = no

We are seeing loads of IO from redis-server despite our save operations being set to occur once every 15 minutes only. The workload is a "full page cache"; we store blobs of compressed HTML. The HTML ...
3
votes
4answers
661 views

Azure IO performance

We have a number of Windows Server virtual machines that we use for .NET and Java development and QA. I find Azure attractive for the obvious reasons but mainly for the opportunity to reduce ...
0
votes
1answer
43 views

Ubuntu 12.04 high io by root process

Ubuntu server 12.04. Installed on hdd disk. There is postgresql database on server runing on other ssd disk. The problem is in high io by some root process on hdd disk. iotop shows 2 processes with ...
-1
votes
1answer
56 views

Ubuntu CPU I/O Rate Spike

Getting really crazy spikes today on a Ubuntu server for CPU / IO. CPU Chart is showing as much as 210% CPU usage - no idea how that is possible. IO has gone as high as 11912. (Usually well under ...
1
vote
1answer
35 views

Sustained io testing linux

I wish to hammer the io of some disks for an extended period of time and become aware whenever I can't read from a block (or some other symptom letting me know of an issue with backend storage). There ...
93
votes
7answers
78k views

Can anyone explain precisely what IOWait is?

As much as I have read about iowait, it is still mystery to me. I know it's the time spent by the CPU waiting for a IO operations to complete, but what kind of IO operations precisely? What I am also ...
0
votes
1answer
210 views

Finding correct IOPS to set limit with ESXi 5.5u2 and vSphere

We're running an ESXi 5.5u2 hypervisor that has a mirror of 2 15k SAS drives with a couple of VMs inside and we noticed some services become briefly unreachable if another VM is using all the IO. So ...
2
votes
0answers
132 views

__ticket_spinlock high cpu

We are having a strange problem on our Ubuntu 10.04 KVM infrastructure, where periodically, one of two vm webservers freaks out, with persistently high load, even if we restart the applications. (the ...
0
votes
1answer
1k views

Direct I/O on Linux

I'm trying to enable Direct I/O on /opt (/dev/sda6, ext4) on Linux Mint 13. What I'm trying is: mount -o dio,rw /dev/sda6 /opt as root. The system responds with: mount: wrong fs type, bad option, ...
2
votes
3answers
3k views

High disk I/O activity in CentOS server

I have about 16 websites in a CentOS dedicated, and I am having some problems on high traffic hours, it seems to be a high disk I/O activity causing a general slowdown. I've installed atop and this ...
5
votes
2answers
206 views

Windows Server 2012 with SSD local drives — Random or Sequential I/O?

How can I determine where my Windows Server 2012 is using Random or Sequential I/O operations when writing/reading the local SSD storage? I have been asked to provide details to our hardware vendor ...
0
votes
0answers
82 views

DRBD high iowait every 65 seconds

I have a peculiar problem: simple INSERT queries to MySQL slow down and appear in my slow q logs every 65 seconds exactly. My stack looks like: mysql56u (IUS) on CentOS over ext4 over drbd over ...
1
vote
2answers
349 views

No Space left on device after Jenkins installation

Is there any reason i would get a 'No space left on device" error on mkdir. I have confirmed that i have enough space left. around 68% is free. and also i have 1% iNodes consumed. This is CentOS 7 ...
0
votes
1answer
28 views

Is “'Light-Speed' Disk Access” really a thing? [closed]

I just saw an advert for Hyve hosting on You Tube. One statement made me curious, they said they offer "'Light-Speed' Disk Access": Is this just a fancy way of saying they have optical technology, ...
0
votes
2answers
192 views

Does Linux, Apache HTTPD or PHP cache frequently / recently accessed files?

Let's say we have a simple index.php file that goes: <?php inclde('file1.php'); inclde('file2.php'); inclde('file3.php'); Presumably, this will ultimately result in three additional ...
0
votes
1answer
74 views

High on %wa from top command, is there any way to constrain it?

Here's my last top info before it stucks: top - 18:26:10 up 238 days, 5:43, 3 users, load average: 1782.01, 1824.47, 1680.36 Tasks: 1938 total, 1 running, 1937 sleeping, 0 stopped, 0 zombie ...
13
votes
3answers
2k views

Virtual machines and I/O heavy workload, is it ever sane?

I have seen on numerous virtualization services (Azure) and products (vmware,kvm,hyperv) I/O and system stalls under heavy I/O workload. My questions are: Is it ever sane to use a Virtualized ...
0
votes
0answers
104 views

mdadm and LVM high load and IOwait

I've got a new CentOS 6.6 server with 2 HDD with mdadm & LVM. As I've used the CentOS install CD I assume everything should be aligned properly. I've just written a KVM image to a LVM LV using dd ...
4
votes
2answers
293 views

99% disk IO spikes with Percona

So we have a server that has seemingly random spikes in disk I/O, going up to 99.x% at random times and for no obvious reason, staying high for a while, and then going back down. This didn't use to be ...
6
votes
0answers
3k views

kworker consuming +90% IO and zero disk write

this is a standard apache web server on AWS Linux AMI + EBS. We are noticing high load average (+8) and iotop -a shows: Total DISK READ: 0.00 B/s | Total DISK WRITE: 2.37 M/s TID PRIO USER ...
1
vote
6answers
22k views

I/O Performance Benchmarking Linux

Just finished setting up a poor mans SAN with iSCSI and want to benchmark it. What are some good I/O performance benchmarks for Linux besides: hdparm -tT /dev/sda1 How do I get a IOPS measurement? ...
0
votes
1answer
111 views

What it means when Linux has no I/O scheduler

I have some virtual machines running Ubuntu cloud-based image 14.04-1 LTS version. I wanted to see the IO performance of different IO schedulers on the VM so I went to ...
0
votes
0answers
207 views

PHP-FPM Stuck & High IO

Actually on my mutual hosting server I'm using PHP 5.6.3 with one pool. Sometimes, my php-fpm process is stuck with 50% of WA and I can't kill it, I can't even restart my VM. I'm using 245MB/3968MB, ...
0
votes
1answer
68 views

ubuntu kvm disk io slowdown after some tyme

Host system: Ubuntu Server x64 12.04 mdadm raid 1 (/dev/sda /dev/sdb) no lvm dd bs=1M count=256 if=/dev/zero of=filename conv=fdatasync avarage ~ 40 MB/s NCQ on disks is disabled WriteCache is ...
0
votes
0answers
80 views

MySQL slow file I/O

I got a little issue with MySQL having slow file IO. When benchmarking 1k blocks (I did them on purpose that small for worst-case) I get an hdd speed of about 2MB/s. When looking at iotop while ...
0
votes
2answers
53 views

how to find the highest IO consumer on a disk? [closed]

Can some one help to find highest IO consumer on each individual disks? i.e Which process consumes the most IO on /dev/sda, the highest IO consumer on /dev/sdb etc.
1
vote
0answers
52 views

File IO being slow

I've rented this root server with a RAID1 mdadm software raid setup. Using dd to benchmark the file IO speed it achieves 230MB/s write (default blocksize). Certain tasks such as mysql are way slower, ...
0
votes
2answers
73 views

how to check if a process with heavy io usage is running properly

I am now managing a computer cluster for scientific computing. Some processes in the cluster need heavy io usage. Now I find such a process: Its state changes rapidly between DOWN and RUN and its ...
1
vote
1answer
63 views

What is the purpose of a ramdisk when fadvise exists?

My understanding is that fadvise will tell the system that the indicated files should be stored in the file system cache (RAM). What is the purpose of mounting a directory in a ramdisk when you can ...