rbd-mirror ceph quincy Not able to find rbd_mirror_journal_max_fetch_bytes config in rbd mirror
12 Jan
2023
12 Jan
'23
11:18 a.m.
Hello All,
In the ceph quincy Not able to find rbd_mirror_journal_max_fetch_bytes
config
in rbd mirror
i configured the ceph cluster almost 400 tb and enable the rbd-mirror in the
starting stage i'm able to achive the almost 9 GB speed , but after the rebalane
completed of the all the images . rbd-mirror speed got automaticily reduce to between 4
to
5 mbps.
in my primary cluster we are continuelsy writing the 50 to 400 mbps data but
replication
speed only we get the 4 to 5 mbps. also we have the 10 Gbps replication network
bandwidth.
Note::- I also try to find the option rbd_mirror_journal_max_fetch_bytes but i'm not
able to find the this option in the configuration. also when i try to set from the
command
line it's showing error like
command:
ceph config set client.rbd rbd_mirror_journal_max_fetch_bytes 33554432
error:
Error EINVAL: unrecognized config option 'rbd_mirror_journal_max_fetch_bytes'
cluster version
ceph version 17.2.5 (98318ae89f1a893a6ded3a640405cdbb33e08757) quincy (stable)
Please suggest any alternative way to configurre this option or how i can improve the
replication n/w speed.
13 Jan
13 Jan
1:06 p.m.
Hi,
apparently this config option has been removed between N and O
releases. I found this revision [1] from 2019 and the pull request [2]
in favor of adjusting the journal fetch based on memory target. I
didn't read the whole conversation but to me it looks like the docs
are outdated and I'd recommend to create a tracker issue for that. I
also don't have an answer how to tune the journal fetch performance,
hopefully someone can chime in here. But if it's based on the
rbd_mirror memory target I'd try to play with some of these values
(maybe in a test environment first):
rbd_mirror_memory_target
rbd_mirror_memory_cache_min
If you have the resources, maybe increase the memory_target and see if
the speed increases.
Regards,
Eugen
[1]
https://tracker.ceph.com/projects/ceph/repository/revisions/1ef12ea0d29f955…
[2] https://github.com/ceph/ceph/pull/27670
Zitat von ankit raikwar <ankit199999raikwar(a)gmail.com>om>:
Hello All,
In the ceph quincy Not able to find
rbd_mirror_journal_max_fetch_bytes config
in rbd mirror
i configured the ceph cluster almost 400 tb and enable
the rbd-mirror in the
starting stage i'm able to achive the almost 9 GB speed , but after
the rebalane
completed of the all the images . rbd-mirror speed got automaticily
reduce to between 4 to
5 mbps.
in my primary cluster we are continuelsy writing the 50 to 400
mbps data but replication
speed only we get the 4 to 5 mbps. also we have the 10 Gbps
replication network
bandwidth.
Note::- I also try to find the option
rbd_mirror_journal_max_fetch_bytes but i'm not
able to find the this option in the configuration. also when i try
to set from the command
line it's showing error like
command:
ceph config set client.rbd rbd_mirror_journal_max_fetch_bytes 33554432
error:
Error EINVAL: unrecognized config option 'rbd_mirror_journal_max_fetch_bytes'
cluster version
ceph version 17.2.5 (98318ae89f1a893a6ded3a640405cdbb33e08757)
quincy (stable)
Please suggest any alternative way to configurre this option or how
i can improve the
replication n/w speed.
_______________________________________________
ceph-users mailing list -- ceph-users(a)ceph.io
To unsubscribe send an email to ceph-users-leave(a)ceph.io
15 Jan
15 Jan
6:30 p.m.
@Eugen Block
Thank for your response , i tryed both option but i don't see ant effect on the
replication speed . can you or any one suggest any other way because it's so slow we
are not able to continue with this slow speed . please help or suggest any configuration.
19 Jan
19 Jan
6:45 a.m.
Hello Everyone,
i tried to both of the values and try to increase max 20 gb but
i did't see any difference in the mirror speed can you please guide me or help me to
tune these value or any other way.
vlaues you i tried :
rbd_mirror_memory_target
rbd_mirror_memory_cache_min
23 Jan
23 Jan
5:16 p.m.
hello ,
i tryed all of the option it's not working , my replication network speed
still same , can you help me any other way we can do speed performance increase
30 Jan
30 Jan
9:08 a.m.
Hi,
it's not the best idea to create multiple threads for the same topic.
I don't really have an answer for you, but maybe you could try to add
more rbd-mirror daemons and see if the replication speed increases. I
haven't tried that myself yet, though.
Regards,
Eugen
Zitat von ankit raikwar <ankit199999raikwar(a)gmail.com>om>:
hello ,
i tryed all of the option it's not working , my
replication network speed still same , can you help me any other way
we can do speed performance increase
_______________________________________________
ceph-users mailing list -- ceph-users(a)ceph.io
To unsubscribe send an email to ceph-users-leave(a)ceph.io
461
days inactive
479
days old
5 comments
2 participants
participants (2)
-
ankit raikwar -
Eugen Block