Server Fault Stack Exchange
Server Fault Stack Exchange

Questions tagged [iops]

111 questions
5
votes
2 answers

Get an AWS EC2 ebs volume to perform over 20,000 IOPS

The company I work for is currently going through an AWS migration, and for 99% of services, their commodity hardware does the job just fine. Except for the production Database, we currently sit at 60,000 IOPS just to keep up with requests, and…
Ben Coughlan
  • 163
  • 5
5
votes
1 answer

What is the size of an IO Operation (IOP) in AWS EBS?

My research suggests that both the standard and the maximum (kernel limitations) block size for modern file systems (ext4, xfs) is 4KB. However, AWS allows IO operations as large as 256KB and says For 32 KB or smaller I/O operations, you should see…
user4258
  • 151
  • 1
  • 2
5
votes
1 answer

Will a SSD storage perform like a magnetic for small root volumes in AWS EC2?

I have a t1.micro instance with 8GB of magnetic EBS volume as it's root disk with a LAMP environment on it. I thought that I will upgrade it to t2.micro with 8GB of General Purpose SSD volume. However I read that the magnetic storage has ~100 IOPS,…
Gavriel
  • 229
  • 2
  • 10
5
votes
1 answer

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) avg-cpu: %user %nice %system %iowait %steal …
favadi
  • 537
  • 2
  • 7
  • 15
5
votes
7 answers

setup lowcost image storage server with 24x SSD array to get high IOPS?

I want to build let's name it a lowcost Ra*san which would host for our social site the images (many millions) we have 5 sizes of every photo with 3 KB, 7 KB, 15 KB, 25 KB and 80 KB per Image. My idea is to build a Server with 24x consumer 240 GB…
Nenad
  • 375
  • 1
  • 5
  • 14
5
votes
1 answer

Estimate IOPS for an Amazon EBS volume using Windows PerfMon

I'm evaluating moving our aging infrastructure to Amazon's AWS and am trying to estimate costs. I know our current disk space requirements, bandwidth, and most of the other variables that will affect cost. The one that's got me stumped is IOPS on…
Andorbal
  • 163
  • 6
4
votes
1 answer

VMWare ESXI extremely high write latency

I hope you can help.. this is more of a sanity check just to verify my line of thinking at the minute. We've got a VMWare cluster setup that is networked to a high performance SAN. Everything performs nicely, running fio write tests I can get IOPS…
Chris
  • 1,289
  • 2
  • 18
  • 34
4
votes
1 answer

Terrible (~1.4x vs expected ~2x) random read performance in new ZFS mirror (raid1)

I am testing a ZFS mirror using FIO (Flexible I/O tester) to understand the random read scalability of ZFS mirrors. The primary and secondary caches have been set to none as the application I use performs it's own caching. For testing purposes I am…
Greg
  • 1,657
  • 5
  • 27
  • 38
4
votes
1 answer

"Hot data" and erasure coding: how to know if it is efficiently handled?

It is well known that erasure coding adds extra complexity because of encoding and decoding operations. Due to this drawback, most of cloud services recommend to use data replication for hot data and erasure coding for cold data. For example, from…
denaitre
  • 88
  • 5
4
votes
1 answer

Does ZFS really stripe across every vdev, even in very large zpools?

I have read that ZFS stripes the data in a zpool across all top-level vdevs, assuming all vdevs are added at the beginning of the pool's life. Everything I have read seems to regard this as a good thing. But, it seems to me like for deployments with…
mbaynton
  • 163
  • 2
  • 7
4
votes
1 answer

ESXi 5x: Changing number of IOPS per path sees dramatic improvements

I'm a bit embarrassed that I've never seen or used the -iops parameter as part of the esxcli deviceconfig options. I stumbled upon an article and proceeded to benchmark before and after using various block sizes and read/write values and am seeing…
gravyface
  • 13,957
  • 19
  • 68
  • 100
4
votes
1 answer

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 + write) per volume (we use 4 EBS volumes combined),…
Nimrod Gutman
  • 143
  • 1
  • 5
3
votes
1 answer

Measuring Only Page Faults That Reach the Disk

I would like to measure "truly" hard page faults, i.e. page faults that result in a disk IO. It looks as if Memory\Page Reads/sec might do the trick, but as was explained in this answer, the page reads value includes reads that are satisfied from…
Helge Klein
  • 2,101
  • 1
  • 16
  • 22
3
votes
1 answer

Microsoft performance monitor counter - Disk activity & file

I'm looking for a way to quickly (via PowerShell Get-Counter) show me the I/O load (IOPS preferable to bytes) on a certain physical disk, along with the file access information - presumably the file path. Essentially what I want is the information…
maloitpro
  • 41
  • 4
3
votes
1 answer

Different IOPs measured on server and storage

I have this strange behavior that I can not explain to myself - hopyfully someone here can. We received some server (hardware) and mounted an NFS drive. We plan to use these servers as Splunk indexer but - since Splunk does not suggest NFS as…
pinas
  • 171
  • 1
  • 1
  • 5
1
2
3 4 5 6 7 8