0
votes
1answer
68 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
49 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 # ...
4
votes
1answer
153 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 ...
3
votes
1answer
63 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 ...
2
votes
1answer
82 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
196 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 ...
3
votes
1answer
57 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 ...
1
vote
0answers
100 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 ...
2
votes
2answers
92 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 ...
10
votes
1answer
193 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 ...
3
votes
1answer
155 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 ...
3
votes
1answer
323 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 ...
0
votes
1answer
87 views

HDD operations slow server down, hangs completely

When running a tar cvzf command or copying large folders on the production server, the CPU load goes up to 8.5 (running on 8 cores) and the whole system hangs, neither apache is responding to any ...
1
vote
1answer
79 views

low priority linux filesystem

Does anybody know of a some sort of (virtual) filesystem that will run as a low priority i.e. All other regular disk activity will take priority? The reason for this is an application I am developing ...
6
votes
3answers
333 views

How to keep subtree removal (`rm -rf`) from starving other processes for Disk I/O?

We have a very large (multi-GB) Nginx cache directory for a busy site, which we occasionally need to clear all at once. I've solved this in the past by moving the cache folder to a new path, making a ...
0
votes
0answers
335 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 ...
2
votes
1answer
672 views

High iowait for unknown reason

I'm having a hard time figure out the reason cause high iowait on my server. This is log of iostat -xm 5 5 Linux 2.6.32-358.6.1.el6.x86_64 (prod-1.localdomain) 09/28/2013 _x86_64_ (16 CPU) ...
3
votes
2answers
399 views

linux: how to simulate hard disk latency? I want to increase iowait value without using a cpu power

Is it possible to set an arbitrary delay for I/O operations? I would like to learn how do iowait and disk %util impact the performance. There are a lot of tools to stress the disk (bonnie++ etc.) but ...
1
vote
3answers
1k views

High await in sar

My database server has the following sar output for the data device: [postgres@dbsrv07 ~]$ LC_ALL=POSIX sar -d |egrep "await|dev253-2" 00:00:01 DEV tps rd_sec/s wr_sec/s avgrq-sz ...
3
votes
3answers
102 views

Running a process within a limited amount of resources, in Linux

Is there a way to run a process (e.g. ls, du, find .. etc) within a strictly limited amount of resources (i.e. cpu, memory, I/O) aside from using nice & ionice, as I didn't find them effective ...
-2
votes
2answers
268 views

whats the difference between 1lane and 2lane with SATA-3 speeds? [closed]

I read the beauty of PCIe is that a designer can combine two, four, eight or sixteen of PCIe lanes into a single data port. 2.5 Gb/s PCIe×1 5 Gb/s PCIe×2 I have two sata 3 drives that I want to ...
1
vote
1answer
202 views

iotop does not show writes

What could be writing on the disk that iotop does not show? # iotop -a Total DISK READ: 8.19 M/s | Total ****DISK WRITE: 3.34 M/s**** TID PRIO USER DISK READ DISK WRITE> SWAPIN IO ...
2
votes
3answers
90 views

Detect file update from modification time

Is there a way to see how often a file is being updated? I mean I need to see if the modification time of a file is updated in a dynamic way (same as tail shows if the file is updated in a dynamic ...
0
votes
0answers
50 views

High load cause? [duplicate]

Possible Duplicate: what is my server high load cause (4 cores and 8 thread cpu) What is my high load cause? CPU,RAM or IO? 4 Core, 8 thread cpu top - 22:27:07 up 149 days, 5:26, 1 ...
2
votes
1answer
281 views

Poor KVM guest IO performances

I've a DOM0 packed with two 3TB hard drives configured as a software RAID1, also sporting 16GB of memory. The DOM0's Linux distro is a CentOS 6.3 and the hypervisor is a libvirt-managed KVM. I'm ...
-3
votes
4answers
452 views

what is my server high load cause (4 cores and 8 thread cpu)

What should i do if I want to prevent this high load. My website becomes slow when load is higher than 8. Please see iotop result too. top - 20:23:10 up 127 days, 3:22, 1 user, load average: ...
-1
votes
0answers
54 views

Is there a way to find out why IO is so high? [duplicate]

Possible Duplicate: Detecting Disk Writes Linux Why my server has high load despite mere 1.5% CPU usage My server has high load despite low CPU usage. I did root@host [/var/log]# ...
2
votes
3answers
450 views

Disk write speed much slower than read speed

I have a VPS server (WiredTree), running CentOS. After experiencing some performance issues I created a simple benchmark for disk read/write speed using the following script: echo Write to disk dd ...
2
votes
1answer
163 views

Linux buffer memory always stays at zero

One of my hosted server is a Xen guest running Debian and linux kernel 2.6.32 then 2.6.38. It has been running fine for quite some time (more than a year) but I recently noticed something weird. For ...
1
vote
2answers
2k views

Determining cause of high NFS/IO utilization without iotop

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. ...
3
votes
0answers
298 views

Quantifying the effects of partition mis-alignment

I'm experiencing some significant performance issues on an NFS server. I've been reading up a bit on partition alignment, and I think I have my partitions mis-aligned. I can't find anything that ...
-1
votes
3answers
2k views

iostat shows 100% utilization - what can be done to improve performance?

I have dedicated web server with CentOS. Recently, I get very high server load, probably caused due to IO bottleneck. iostat -mx 3 shows: avg-cpu: %user %nice %system %iowait %steal %idle ...
0
votes
0answers
204 views

Weird Slowdown on I/O (4K blocks ?)

I have two identical servers, running Proxmox 2. 2x AMD 6 cores 2.3Ghz 64 Gigs of RAM DDR3 ECC (8*8) ASUS KCMA-D8 2x Seagate 2TB - (st2000dm001) One server is running perfectly fine. The other one ...
1
vote
2answers
846 views

How iostat figures out to take CPU idle time to consider as %idle or %iowait?

I was going through iostat man page. According to it, %iowait Show the percentage of time that the CPU or CPUs were idle during which the system had an outstanding disk I/O request. %idle ...
2
votes
2answers
401 views

Testing a production hard hard / debugging high I/O Load

I've been getting a lot of high load lately on this server more so then it should for what little is on this system. Seems like just the simplest stuff using the disk like a YUM update will spike the ...
3
votes
0answers
43 views

How can I measure disk cache churn on Linux? [duplicate]

Possible Duplicate: Is there a way to get Cache Hit/Miss ratios for block devices in Linux? I have a file server which serves out large (25GB-1TB+) files over the network from local ...
-6
votes
1answer
312 views

What buffer size should I use to maximize disk I/O bandwidth? (16Kb, 32Kb, 64Kb, etc.) [closed]

I am trying to write a file as fast as I can through a buffered FileChannel similar to a BufferedOutputStream. I am wondering what is the optimum chunk of data I should use per write call to maximize ...
1
vote
0answers
422 views

I/O error on non-existent device?

Getting the following in /var/log/messages: Sep 17 10:38:53 server1 kernel: end_request: I/O error, dev sde, sector 0 Sep 17 10:38:53 server1 kernel: end_request: I/O error, dev sde, sector 63 Sep 17 ...
4
votes
3answers
807 views

Linux utility to record IO statistics (random/sequential, block sizes, read/write ratio)

As part of provisioning our new server (see other SF) I'd like to find out the following: ratio of random to sequential reads & writes amount of data read & written at a time (pref in ...
2
votes
1answer
892 views

Debian: nginx using an extreme amount of disk I/O

We're currently haveing an issue with one of our nginx servers. It's using an extreme amount of disk I/O. It's the / (root - cciss/c0d0) partition that's being abused. See picture of iotop here: ...
2
votes
1answer
323 views

Limit linux buffer usage by process

We have a production server running different process which take advantage of existing linux buffers to improve their performance, such as a mysql server. This server has exhaustive IO load. On this ...
1
vote
1answer
65 views

Partitioning disk I/O on linux

I have a server that runs two different workloads: heavy, linear write (stores all network traffic as pcaps); and a transactional DB workload where IDS alerts are written to (frequent inserts) and ...
8
votes
6answers
892 views

Linux I/O bottleneck with data-movers

I have a 24 core machine with 94.6GiB RAM running Ubuntu server 10.04. The box is experiencing high %iowait, unlike another server we have (4 cores) running the same types and amounts of processes. ...
-4
votes
1answer
1k views

What are some options for acquiring a free realtime Linux distribution? [closed]

By realtime I mean something that can help with fast network I/O; Low-latency and high-throughput.
4
votes
2answers
2k views

Can I run iostat on a Synology?

I have a Synology RS812RP+ which I'm using for a little bit of departmental testing. I've stuffed a bunch of SSD disks in it, and I'm curious about monitoring the disk IO. iostat doesn't come ...
3
votes
1answer
721 views

KVM IO leads to high system load, WD Caviar Green (EACS)

I have Ubuntu 12.04 host running Linux 3.2.0-24-generic, libvirt 0.9.8-2ubuntu17, qemu-kvm 1.0+noroms-0ubuntu13. Host uses elevator=deadline, guests use elevator=noop. All KVM guests use virtio, no ...
1
vote
2answers
424 views

Multiple ip to single interface

i'm using openstack, but i think this is a more general problem. Actually i've a dedicated which comes with 1 ip address, i bought another one, and added using openstack's nova-manage cli. So now ...
0
votes
2answers
57 views

How can I decide up the nature of performed IO?

I am using Linux (3.2.12-3.2.4). I have few "syncer" processes which updates lots and lots SQLite db files in a loop. The database sizes vary from 1 MB to few GB. I have a "searcher" process which ...
0
votes
1answer
666 views

Should You Continue Polling Socket For Readiness After An EAGAIN or EWOULDBLOCK Error?

I am creating a web crawler with a multiplexed download manager using Linux epoll (Linux 2.6.30.x). I pick links from a database of over 40,000 domains (each domain having between 1 and 2000 urls), a ...
11
votes
10answers
5k views

What creates CPU I/O wait but no disk operations?

I have CPU I/O wait steady around 50%, but when I run iostat 1 it shows little to no disk activity. What causes wait without iops? NOTE: There no NFS or FUSE filesystems here, but it is using Xen ...