jbarrigafk

@kaitoan2000 if it is possible to stop all the writing and reading that you have in your cluster of lizardfs through the clients. After that, you should stop the URAFT...

trap -- '' SIGPROF ; trap -- '' SIGVTALRM; /usr/sbin/mfsmaster -c /etc/mfs/mfsmaster.cfg -d Good, back to this topic. I keep trying to make lizardfs Master / shadow work before continuing...

> > we decided to remove the uraft function and only work with master / shadow, even so, only one of the metadata servers is the one that starts correctly,...

In our productive environment we still can't connect shadow with the master. I'm still waiting, the messages that appear are the following: ``` Jul 22 13:05:21 mfsmaster2-sv mfsmaster[171208]: running in...

 @kaitoan2000 the cpu remains between 60 and 70% with master.fs.checksum.changing_not_recalculated_chunk process. I don't understand why it does an unloading filesystem if all the changelogs...

@pbeza I initially thought it was something with uraft, but since my cluster is in a productive environment I decided to remove uraft. Even without uraft, lizardfs still has the...

@19wolf all ur cluster on the same LAN NET? are u using raid on your chunkservers? using SSD Disks?

@19wolf try disabling pfsync from chunkservers config and increase number of threads ``` ## Number of threads which handle (in a round-robin manner) connections ## with clients; these threads are...

> I tried that, it's a slight bit better but not much > > ``` > $ dd if=/dev/zero of=/data/test3.img bs=10M count=1 oflag=dsync > 1+0 records in > 1+0 records...

@19wolf What are you trying to do? Do you still have slow writing? in which of your disks? you have 3xdisks at 99% capacity ... So u change xor3 goal...