> Op 23 augustus 2016 om 22:24 schreef Nick Fisk <nick@xxxxxxxxxx>: > > > > > > -----Original Message----- > > From: Wido den Hollander [mailto:wido@xxxxxxxx] > > Sent: 23 August 2016 19:45 > > To: Ilya Dryomov <idryomov@xxxxxxxxx>; Nick Fisk <nick@xxxxxxxxxx> > > Cc: ceph-users <ceph-users@xxxxxxxxxxxxxx> > > Subject: Re: udev rule to set readahead on Ceph RBD's > > > > > > > Op 23 augustus 2016 om 18:32 schreef Ilya Dryomov <idryomov@xxxxxxxxx>: > > > > > > > > > On Mon, Aug 22, 2016 at 9:22 PM, Nick Fisk <nick@xxxxxxxxxx> wrote: > > > >> -----Original Message----- > > > >> From: Wido den Hollander [mailto:wido@xxxxxxxx] > > > >> Sent: 22 August 2016 18:22 > > > >> To: ceph-users <ceph-users@xxxxxxxxxxxxxx>; nick@xxxxxxxxxx > > > >> Subject: Re: udev rule to set readahead on Ceph RBD's > > > >> > > > >> > > > >> > Op 22 augustus 2016 om 15:17 schreef Nick Fisk <nick@xxxxxxxxxx>: > > > >> > > > > >> > > > > >> > Hope it's useful to someone > > > >> > > > > >> > https://gist.github.com/fiskn/6c135ab218d35e8b53ec0148fca47bf6 > > > >> > > > > >> > > > >> Thanks for sharing. Might this be worth adding it to ceph-common? > > > > > > > > Maybe, Ilya kindly set the default for krbd to 4MB last year in the kernel, but maybe having this available would be handy if people > > ever want a different default. It could be set to 4MB as well, with a note somewhere to point people at its direction if they need to > > change it. > > > > > > I remember you running tests and us talking about it, but I didn't > > > actually do it - the default is still a standard kernel-wide 128k. > > > I hesitated because it's obviously a trade off and we didn't have a > > > clear winner. Whatever (sensible) default we pick, users with > > > demanding all sequential workloads would want to crank it up anyway. > > Yes sorry, I was getting mixed up with the default max_sectors_kb which is now 4MB. > > > > > > > I don't have an opinion on the udev file. > > > > > > > I would vote for adding it to ceph-common so that it's there and users can easily change it. > > > > We can still default it to 128k which makes it just a file change for users. > > Yep, this sounds like a good idea > Can you send a Pull Request on Github for this? Wido > > > > Wido > > > > > > > > > >> > > > >> And is 16MB something we should want by default or does this apply to your situation better? > > > > > > > > It sort of applies to me. With a 4MB readahead you will probably struggle to get much more than around 50-80MB/s sequential > > reads, as the read ahead will only ever hit 1 object at a time. If you want to get nearer 200MB/s then you need to set either 16 or > > 32MB readahead. I need it to stream to LTO6 tape. Depending on what you are doing this may or may not be required. > > > > > > Thanks, > > > > > > Ilya > _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com