[Gluster-users] Hot Tier

Dmitri Chebotarov 4dimach at gmail.com
Mon Jul 31 13:52:49 UTC 2017


Hi

At this point I already detached Hot Tier volume to run rebalance. Many
volume settings only take effect for the new data (or rebalance), so I
thought may this was the case with Hot Tier as well. Once rebalance
finishes, I'll re-attache hot tier.

cluster.write-freq-threshold and cluster.read-freq-threshold control number
of times data is read/write before it moved to hot tier. In my case both
are set to '2', I didn't think I needed to disable
performance.io-cache/quick-read as well. Will give it a try.

Here is the volume info (no hot tier at this time)

~]# gluster v info home

Volume Name: home
Type: Disperse
Volume ID: 4583a3cf-4deb-4707-bd0d-e7defcb1c39b
Status: Started
Snapshot Count: 0
Number of Bricks: 1 x (8 + 4) = 12
Transport-type: tcp
Bricks:
Brick1: MMR01:/rhgs/b0/data
Brick2: MMR02:/rhgs/b0/data
Brick3: MMR03:/rhgs/b0/data
Brick4: MMR04:/rhgs/b0/data
Brick5: MMR05:/rhgs/b0/data
Brick6: MMR06:/rhgs/b0/data
Brick7: MMR07:/rhgs/b0/data
Brick8: MMR08:/rhgs/b0/data
Brick9: MMR09:/rhgs/b0/data
Brick10: MMR10:/rhgs/b0/data
Brick11: MMR11:/rhgs/b0/data
Brick12: MMR12:/rhgs/b0/data
Options Reconfigured:
diagnostics.client-log-level: CRITICAL
cluster.write-freq-threshold: 2
cluster.read-freq-threshold: 2
features.record-counters: on
nfs.disable: on
performance.readdir-ahead: enable
transport.address-family: inet
client.event-threads: 4
server.event-threads: 4
cluster.lookup-optimize: on
cluster.readdir-optimize: on
cluster.locking-scheme: granular
cluster.shd-max-threads: 8
cluster.shd-wait-qlength: 10000
cluster.data-self-heal-algorithm: full
features.cache-invalidation: on
features.cache-invalidation-timeout: 600
performance.stat-prefetch: on
performance.cache-invalidation: on
performance.md-cache-timeout: 600
network.inode-lru-limit: 50000
performance.write-behind-window-size: 1MB
performance.client-io-threads: on
performance.read-ahead: disable
performance.cache-size: 256MB
performance.io-thread-count: 16
performance.strict-o-direct: on
network.ping-timeout: 30
network.remote-dio: disable
user.cifs: off
features.quota: on
features.inode-quota: on
features.quota-deem-statfs: on

~]# gluster v get home  performance.io-cache
performance.io-cache                    on

~]# gluster v get home  performance.quick-read
performance.quick-read                  on

Thank you.

On Mon, Jul 31, 2017 at 5:16 AM, Hari Gowtham <hgowtham at redhat.com> wrote:

> Hi,
>
> Before you try turning off the perf translators can you send us the
> following,
> So we will make sure that the other things haven't gone wrong.
>
> can you send us the log files for tier (would be better if you attach
> other logs too),
> the version of gluster you are using, the client, and the output for:
> gluster v info
> gluster v get v1 performance.io-cache
> gluster v get v1 performance.quick-read
>
> Do send us this and then we will let you know what should be done,
> as reads should also cause promotion
>
>
> On Mon, Jul 31, 2017 at 2:21 PM, Hari Gowtham <hgowtham at redhat.com> wrote:
> > For the tier daemon to migrate the files for read, few performance
> > translators have to be turned off.
> > By default the performance quick-read and io-cache are turned on. You
> > can turn them off so that
> > the files will be migrated for read.
> >
> > On Mon, Jul 31, 2017 at 11:34 AM, Hari Gowtham <hgowtham at redhat.com>
> wrote:
> >> Hi,
> >>
> >> If it was just reads then the tier daemon won't migrate the files to
> hot tier.
> >> If you create a file or write to a file that file will be made
> >> available on the hot tier.
> >>
> >>
> >> On Mon, Jul 31, 2017 at 11:06 AM, Nithya Balachandran
> >> <nbalacha at redhat.com> wrote:
> >>> Milind and Hari,
> >>>
> >>> Can you please take a look at this?
> >>>
> >>> Thanks,
> >>> Nithya
> >>>
> >>> On 31 July 2017 at 05:12, Dmitri Chebotarov <4dimach at gmail.com> wrote:
> >>>>
> >>>> Hi
> >>>>
> >>>> I'm looking for an advise on hot tier feature - how can I tell if the
> hot
> >>>> tier is working?
> >>>>
> >>>> I've attached replicated-distributed hot tier to an EC volume.
> >>>> Yet, I don't think it's working, at least I don't see any files
> directly
> >>>> on the bricks (only folder structure). 'Status' command has all 0s
> and 'In
> >>>> progress' for all servers.
> >>>>
> >>>> ~]# gluster volume tier home status
> >>>> Node                 Promoted files       Demoted files        Status
> >>>> ---------            ---------            ---------
> ---------
> >>>> localhost            0                    0                    in
> progress
> >>>> MMR11                0                    0                    in
> progress
> >>>> MMR08                0                    0                    in
> progress
> >>>> MMR03                0                    0                    in
> progress
> >>>> MMR02                0                    0                    in
> progress
> >>>> MMR07                0                    0                    in
> progress
> >>>> MMR06                0                    0                    in
> progress
> >>>> MMR09                0                    0                    in
> progress
> >>>> MMR12                0                    0                    in
> progress
> >>>> MMR10                0                    0                    in
> progress
> >>>> MMR05                0                    0                    in
> progress
> >>>> MMR04                0                    0                    in
> progress
> >>>> Tiering Migration Functionality: home: success
> >>>>
> >>>>
> >>>> I have a folder with .yml files (Ansible) on the gluster volume,
> which as
> >>>> I understand is 'cache friendly'.
> >>>> No matter how many times I read files, nothing is moved to the hot
> tier
> >>>> bricks.
> >>>>
> >>>> Thank you.
> >>>>
> >>>> _______________________________________________
> >>>> Gluster-users mailing list
> >>>> Gluster-users at gluster.org
> >>>> http://lists.gluster.org/mailman/listinfo/gluster-users
> >>>
> >>>
> >>>
> >>> _______________________________________________
> >>> Gluster-users mailing list
> >>> Gluster-users at gluster.org
> >>> http://lists.gluster.org/mailman/listinfo/gluster-users
> >>
> >>
> >>
> >> --
> >> Regards,
> >> Hari Gowtham.
> >
> >
> >
> > --
> > Regards,
> > Hari Gowtham.
>
>
>
> --
> Regards,
> Hari Gowtham.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20170731/112e3991/attachment.html>


More information about the Gluster-users mailing list