We’re using Ubuntu 14.04 on x86_64. We just added ‘osd mount options xfs = rw,noatime,inode64,allocsize=1m’ to the [osd] section of our ceph.conf so XFS allocates
1M blocks for new files. That only affected new files, so manual defragmentation was still necessary to clean up older data, but once that was done everything got better and stayed better.
You can use the xfs_db command to check fragmentation on an XFS volume and xfs_fsr to perform a defragmentation. The defragmentation can run on a mounted filesystem
too, so you don’t even have to rely on Ceph to avoid downtime. I probably wouldn’t run it everywhere at once though for performance reasons. A single OSD at a time would be ideal, but that’s a matter of preference.
From: ceph-users [mailto:ceph-users-bounces@xxxxxxxxxxxxxx]
On Behalf Of Thomas Bennett
Sent: Wednesday, November 30, 2016 5:58 AM
Cc: ceph-users@xxxxxxxxxxxxxx
Subject: Re: [ceph-users] Is there a setting on Ceph that we can use to fix the minimum read size?
Thanks for the replies. Always good to hear back from a community :)
I'm using Linux on x86_64 architecture and the block size is limited to the page size which is 4k. So it looks like I'm hitting hard limits in any changes. to increase the block size.
I found this out by running the following command:
$ mkfs.xfs -f -b size=8192 /dev/sda1
$ mount -v /dev/sda1 /tmp/disk/
mount: Function not implemented
#huh???
Checking out the man page:
... XFS on Linux currently only supports pagesize or smaller blocks.
I'm hesitant to implement btrfs as its still experimental and ext4 seems to have the same current limitation.
Our current approach is to exclude the hard drive that we're getting the poor read rates from our procurement process, but it would still be nice to find out how much control we have over how ceph-osd daemons read from the drives. I may
attempts a strace on an osd daemon as we read to see what the actual read request size is being asked to the kernel.
On Tue, Nov 29, 2016 at 11:53 PM, Steve Taylor <steve.taylor@xxxxxxxxxxxxxxxx> wrote:
We configured XFS on our OSDs to use 1M blocks (our use case is RBDs with 1M blocks) due to massive
fragmentation in our filestores a while back. We were having to defrag all the time and cluster performance was noticeably degraded. We also create and delete lots of RBD snapshots on a daily basis, so that likely contributed to the fragmentation as well.
It’s been MUCH better since we switched XFS to use 1M allocations. Virtually no fragmentation and performance is consistently good.
From: ceph-users [mailto:ceph-users-bounces@xxxxxxxxxxxxxx]
On Behalf Of Kate Ward
Sent: Tuesday, November 29, 2016 2:02 PM
To: Thomas Bennett <thomas@xxxxxxxxx>
Cc: ceph-users@xxxxxxxxxxxxxx
Subject: Re: [ceph-users] Is there a setting on Ceph that we can use to fix the minimum read size?
I have no experience with XFS, but wouldn't expect poor behaviour with it. I use ZFS myself and know that it would combine writes, but btrfs might be an option.
Do you know what block size was used to create the XFS filesystem? It looks like 4k is the default (reasonable) with a max of 64k. Perhaps a larger block size will give better performance
for your particular use case. (I use a 1M block size with ZFS.)
Hi Kate,
Thanks for your reply. We currently use xfs as created by ceph-deploy.
What would you recommend we try?
On Tue, Nov 29, 2016 at 11:14 AM, Kate Ward
<kate.ward@xxxxxxxxxxxxx> wrote:
What filesystem do you use on the OSD? Have you considered a different filesystem that is better at combining requests before they get to the drive?
Hi,
We have a use case where we are reading 128MB objects off spinning disks.
We've benchmarked a number of different hard drive and have noticed that for a particular hard drive, we're experiencing slow reads by comparison.
This occurs when we have multiple readers (even just 2) reading objects off the OSD.
We've recreated the effect using iozone and have noticed that once the record size drops to 4k, the hard drive miss behaves.
Is there a setting on Ceph that we can change to fix the minimum read size when the ceph-osd daemon reads the object of the hard drives, to see if we can overcome the overall slow
read rate.
|
If you are not the intended recipient of this message or received it erroneously, please notify the sender and delete it, together with any attachments, and be
advised that any dissemination or copying of this message is prohibited.
|
| If you are not the intended recipient of this message or received it erroneously, please notify the sender and delete it, together with any attachments, and be advised that any dissemination or copying of this
message is prohibited. |
|
