The tag has no wiki summary.

learn more… | top users | synonyms

0
votes
0answers
30 views

Can poor Internet connection affect the IO read on my server?

I'm trying to spot the culprit causing too much IO read in my server. Issuing IOTOP -ao I have come accross many httpd processes among which one caught my attention: PRIO USER DISK READ ...
2
votes
1answer
18 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 ...
5
votes
1answer
41 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
1answer
26 views

gstat output on FreeBSD: does it show an average over time?

When you run the gstat command on FreeBSD to get information about i/o performance, you can pass the -I (interval) option to change the default interval from 1 sec to some other time frame. My ...
-1
votes
0answers
8 views

NFS writes to md-raid extremely slow with busy jbd2 [migrated]

As far as I can remember, this problem appeared after upgrade from Debian Squeeze to Wheezy. The symptom is extremely slow write performance on the server's dmraid exclusively if written via nfs ...
3
votes
1answer
24 views

How to save iotop's output for a specific period of time

I am trying to discern what processes are making huge Read/Writes on my server disk. I know I can use iotop -ao but is there a way I can save iotop's output for a specific period of time to study ...
1
vote
2answers
34 views

What is the difference between truss -D and truss -E?

I am currently analyzing a command on Solaris that reads from a file and has very low performance. The truss -D commands shows me read system calls taking up to 0.03 seconds, but when I use truss -E, ...
0
votes
3answers
51 views

Evaluating the CPU I/O wait on Linux

Doing a top to check the io wait, I get these figures: Cpu(s): 6.7%us, 1.4%sy, 1.2%ni, 85.5%id, 5.0%wa, 0.0%hi, 0.3%si, 0.0%st Looking at these figures (%us ~= %wa), do they mean that: ...
2
votes
0answers
33 views

VPS Unknown Read/Write

I had an lfd email alert - I have installed CSF - today revealing that my server (Centos 6.6) has been using a lot of server resources for 5 minutes. I checked my VPS graphs and noticed that my ...
0
votes
0answers
59 views

High load and io caused by apache on Debian 7 server?

lately my VPS (4 CPU, 4GB RAM, 50GB HardDisk with around 10 websites, all very low real visitors (max. 100 / day) but maybe plenty of bots) got shut down by the hosting company. Reason: excessive ...
0
votes
1answer
38 views

how to find cause of io spike

Everyday at around the same time, the IO usage on the server where our mysql slave goes up to 100%. I have setup a script that takes IO information every five minutes so I can find out why this ...
2
votes
0answers
47 views

“Nosy Neighbor” and the CFQ scheduler

I'm trying to understand how does using CFQ affects the "Nosy Neighbor" problem. I'll ask it a bit naively, can a "Nosy Neighbor" even exist when using CFQ? Isn't that CFQ should make sure all ...
0
votes
2answers
91 views

Beyond 1Gb upload on a single linux server

I have a high hit nginx web server on CentOS that provides static large content. when the number concurrent connection are low, server could easily provide up to 4Gb of traffic , but when the number ...
2
votes
1answer
106 views

Does changing /sys/block/sda/queue settings take effect immediately?

How long does it take for changes to the following settings to take effect: /sys/block/sda/queue/scheduler /sys/block/sda/queue/rotational /sys/block/sda/queue/read_ahead_kb Is it ...
-1
votes
1answer
125 views

Innodb performs IO Operation when idle

I am currently doing some stress testing where I am pushing inserts to the database as fast as I can. The simulation inserts 10000 records per second. After inserting around 200 million records I ...
7
votes
1answer
139 views

rrdgraph generation fails on high IO load

We have a 4 core CPU production system which does a lot of cronjobs , having constant proc queue and an usual load of ~1.5. During night time we do some IO intensive stuff with postgres. We generate ...
0
votes
0answers
250 views

BUG: soft lockup - CPU#0 stuck for 23s! on XEN PV debian related to high i/o load

i am currently experiencing some problems with my Debian Xen System. It runns on an old opteron System with two Dual Core AMD Opteron(tm) Processor 275 CPUs. I am using image files (block devices) ...
0
votes
2answers
122 views

Unreasonable performance expectations for RAID 0 performance?

This is my first time building a machine with a hardware RAID card. We bought a Dell T620 with the H710P RAID controller (1GB NV Cache), a 160GB Solid State Drive (SATA Read Intensive MLC 3Gbps), and ...
1
vote
4answers
333 views

Changing the I/O scheduler for a specific disk

I would like to change permanently the I/O scheduler for a specific disk on Fedora 20. According to what I have found, this can be achieved by executing the following shell line as root: echo ...
0
votes
1answer
456 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 ...
2
votes
1answer
292 views

Is it possible to configure the Linux kernel I/O scheduler for an NFS mount?

On a normal block device you can change the i/o scheduler like this: # cat /sys/block/hda/queue/scheduler noop anticipatory deadline [cfq] # echo anticipatory > /sys/block/hda/queue/scheduler # ...
0
votes
1answer
199 views

Mongodump on Gridfs is killing the host IOs

I'm trying to make a mongodump from our production mongodb while the production is running. We have three production instances, one regular mongodb, one with very few gb of data on gridfs, one with a ...
4
votes
1answer
354 views

Linux page cache slows down IO on dual cpu server with 64GB ram

I have a massive problem with the linux page cache which slows down the IO. For instance if I copy a lvm partition with dd, linux cache the data in the buffers or caches (free –m). That is not the ...
2
votes
2answers
340 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 ...
3
votes
1answer
120 views

How can I measure complex I/O activity to develop realistic benchmarking? [closed]

I need to retrieve a few metric from my service server to benchmark another stroage solution. There are various options are provied by benchmark program(I choosed ...
0
votes
0answers
64 views

freebsd: disk i/o utilization statistic by user

Whether there some utils for collect/view statistic about disk I/O utilization by user in FreeBSD? After googling that question i found only sa, but in its manpage is not any information about ...
1
vote
1answer
112 views

can Iowait cause significant RAM consumption increase

I have a node.js process running continuously on a linux EC2 instance, it extracts data and stores it in mysql. Some reads are also performed on the database. The process can run well during hours or ...
0
votes
1answer
789 views

htcacheclean doesn't seem to be cleaning the cache

I'm running mod_cache with apache 2 on a fairly high traffic'd site. I've set the htcacheclean to run in demon mode every 10 minutes to keep the cache at 4GB. It's currently at 15GB and doesn't seem ...
2
votes
1answer
286 views

Setting I/O scheduler for SSD based RAID array on EC2 instances

I created a RAID array using the 2 local SSD drives on a EC2 c3.4xlarge instance. # mdadm --create /dev/md127 --level=0 --raid-devices=2 /dev/xvdf /dev/xvdg # mkfs.ext4 /dev/md127 # mkdir /data # ...
1
vote
0answers
73 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 ...
-1
votes
1answer
297 views

What dose these units means in zabbix?

When i try to set some items for my disk read and write, I found it by vfs.dev.read and vfs.dev.writefor zabbix-agent. This item contain a parameter named type which some of them are unknown for me. ...
2
votes
1answer
92 views

server hangs randomly without log entries

My physical server hangs randomly and I do not get any log entries during that time. So I let a script run: while true; do date >>/tmp/dates; sleep 1; done & disown After some minutes the ...
0
votes
1answer
584 views

report per-process IO stats with pidstat or sar

I'm trying to track io usage of a few "suspect" processes over time. Ideally would like to make those stats available via munin, or push directly to graphite. However, as a starting point it would be ...
1
vote
2answers
203 views

IOMeter showing hardly any data

I ran IOmeter on a Windows Server 2008 R2 SP1 server for 18 hours and when I clicked on "Stop current Test and Save Results" it stopped the worker processes (I only had 1). When looking at the ...
3
votes
1answer
73 views

Does ESX 5.X cache guest IO?

I am trying to find out if guest can see successful disk flush operation, but the host doesn't actually flush it to disk? How does ESXi work with guest I/O? Are they cached by ESXi before being ...
0
votes
2answers
137 views

How to benchmark maxCache 3.0 with SSDs? [duplicate]

We're a software development company and previously outsourced the HW side of business but now we're looking into building our own private cloud. We recently purchased a few servers, one of which is ...
1
vote
0answers
351 views

Why are pgpgin/s and majflt/s inconsistent in sar -B?

In sar -B ouptut, I would naively expect pgpgin/s to equal majflt/s multiplied by the system page size. From man sar: pgpgin/s Total number of kilobytes the system paged in ...
0
votes
1answer
255 views

Finding root cause of 99.99% iowait with 0% SWAPON

Users and DBAs are complaining that "Oracle is slow" on our OEL servers. The only thing I have found from the OS standpoint is that there are some strange IOWAIT stats from iotop. Output from iotop: ...
0
votes
1answer
63 views

How can I see which devices are used by a process?

iotop and iostat are great tools to see how much I/O is happening. But I haven't found out how these (or other) tools can show me the I/O rate per device and per process. So I'm looking for a way to ...
1
vote
0answers
143 views

Visualizing IO other then seekwatcher

Is there any other programs that can generate visuals/graphs/diagrams (movie and pictures) to visualize IO across a full device other then seekwatcher? NOTE: seekwatcher generates visuals(pic/movie) ...
2
votes
2answers
135 views

Simulate database I/O behaviour [closed]

I'm investigating some performance issue and I need a tool that can mock the same I/O behavior that a typical RDBMS is usually creating. I don't want to install a full blown RDBMS and mess around with ...
2
votes
1answer
179 views

I/O priority per LVM volume (cgroups)

How can I prioritize LVM volumes I/O performance using cgroups? I know I can use ionice to make changes at the process level but I wish to be able to do this per LV and not per process.
10
votes
1answer
220 views

how to do I/O sniffing

For sizing purposes I need to understand what requirements an application has to the I/O subsystem. I would love to do what I call I/O sniffing and obtain a list of events from the block layer like ...
1
vote
2answers
273 views

High Disk I/O on server reboot

A CentOS 5.8 machine has high Disk I/O upon starting up. The processes taking up disk IO are kmirrord, kjournald and pdflush. I have done the performed the following: 1) Mounted the filesystem with ...
1
vote
1answer
95 views

Munin graph Disk IOs for /dev/sda k unit interpretation

From Munin diskstats plugin Disk IOs for /dev/sda graph shows Max IO/sec -read/+write 1.75k/920.92. What does the k unit in Disk IOs graph mean?
3
votes
1answer
202 views

IO related performance bottleneck on a LAMP server

I am administering a big LAMP server with some thousand users. About a week ago, things slowed down, and the only thing I see that the IO latency is increased dramatically. Users experience slow page ...
4
votes
1answer
364 views

How to calculate the required EBS PIOPS for our mongo server?

We want to use provisioned IOPS EBS volume on our mongo machines, I'm a bit confused on how to calculate the number of provisioned IOPS to use. Currently we're getting an average of 25 IOPS (read + ...
3
votes
1answer
901 views

How to monitor NFS load from userland?

Apologies if I'm not using the proper jargon (although I'm a longtime linux user, I'm not an admin) or if this is a FAQ (though searching SE got lots of hits, I didn't see anything quite like this ...
1
vote
0answers
206 views

Reason for high CPU time when executing fio

After weeks of troubleshooting some performance issues I have on my VPS running Ubuntu 12.04 LTS, I am getting closer to the conclusion that the problem is related to IO. When I have a considerable ...
0
votes
1answer
42 views

How to disable search body in dovecot?

We run mail server of 30k e-mail accounts (Maildir) with dovecot imap server. We suffer from high IO load, especially when a user starts to search large imap folders. Is any way of preventing search ...