Re: optimize bluestore for random write i/o

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



I bet you'd see better memstore results with my vector based object
implementation instead of bufferlists.

Where can I find it?

Nick Fisk noticed the same
thing you did.  One interesting observation he made was that disabling
CPU C/P states helped bluestore immensely in the iodepth=1 case.

This is exactly what I've done by `cpupower idle-set -D 0`. It basically increases iops 2-3 times.

Pipelined writes were added in rocksdb 5.5.1 back in the summer of 2017. That wasn't available when bluestore was being written.

In fact ... it slightly confuses me because even now bluestore IS writing to rocksdb from multiple threads sometimes. It's when bluestore_sync_submit_transaction is on and the write doesn't require aio (= when it's a deferred write) and when it holds several other conditions. It calls db->submit_transaction from the tp_osd_tp thread then.
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com




[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux