Try running your initial test in reverse. Copy or of fuse first and then the kennel driver. I think you'll find that you are dealing with more than 1 later of caching affecting this test. Caching on the OSD and kernel caching primarily.
On Sat, Apr 8, 2017, 8:04 PM Deepak Naidu <dnaidu@xxxxxxxxxx> wrote:
Hmm pretty odd. When I ran test on ceph kernel vs ceph fuse , FUSE has always been slower for both read and writes.
Try using tools like fio to run IO test with directIO(bypass system cache)
--DeepakPretty much says it all. 1GB test file copy to local:
$ time cp /mnt/ceph-kernel-driver-test/test.img .
real 2m50.063suser 0m0.000ssys 0m9.000s
$ time cp /mnt/ceph-fuse-test/test.img .
real 0m3.648suser 0m0.000ssys 0m1.872s
Yikes. The kernel driver averages ~5MB and the fuse driver averages ~150MBish? Something crazy is happening here. It's not caching, I ran both tests fresh.
Ubuntu 16.04.2, 4.4.0-72-generic, ceph-fuse 10.2.6-1xenial, ceph-fs-common 10.2.6-0ubuntu0.16.04.1 (I also tried the 16.04.2 one, same issue).
Anyone run into this? Did a lot of digging on the ML and didn't see anything. I'm was going to use FUSE for production, but it tends to lag more on a lot of small requests so I had to fall back the kernel driver._______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________
This email message is for the sole use of the intended recipient(s) and may contain confidential information. Any unauthorized review, use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message.
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
