Re: Ceph Performance very bad even in Memory?!

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

 



Hey,

SDS is not just about performance. You want something reliable for the next
> 10(?) years, the more data you have the more this is going to be an issue.
> For me it is important that organisations like CERN and NASA are using it.
> If you look at this incident with the 'bug of the year' then you see the
> importance of such organisations/large user base being involved.


Sadly, that does not mean too much for me. From my personal experience I
saw plenty of companies lacking behind by using state of the art technology
and accepting huge software bottlenecks just by using excuses over and over
again instead of deeply optimizing software/hardware components.
Same on installing security updates, using proper ci, ... Another example
is that a lot of companies are still using openvpn (~70k+ lines of
code,very bad performance with huge latency) vs wireguard (~4k lines of
code, blazing fast).
Nothing against CERN or NASA, they are great companies and are doing world
changing things. Maybe they don't need the strong consistency AND
performance I'm looking for though..

Make sure to post results here. I am curious if ceph is really that far
> behind in performance compared to other solutions.


Sure will do, are images/attachments here possible?

On Sun, Jan 30, 2022 at 9:07 PM Marc <Marc@xxxxxxxxxxxxxxxxx> wrote:

> > Most people just accept the way software works and take bad performance
> > for
> > granted. Most excuses went on "cheap hardware", which I just eliminated
> by
> > using ram disks.
>
> SDS is not just about performance. You want something reliable for the
> next 10(?) years, the more data you have the more this is going to be an
> issue. For me it is important that organisations like CERN and NASA are
> using it. If you look at this incident with the 'bug of the year' then you
> see the importance of such organisations/large user base being involved.
>
> > I really can't imagine that the software is currently behaving.. aren't
> > the
> > devs testing sometimes performance?
>
> I sometimes wonder that too, and not even performance just the bugs that
> people run into when they upgrade.
>
> > On the good side this means, just a few simple code tweaks
> > (threading,async
> > wait, queues) should bring a huge impact on performance.
>
> I hope you are right! Then we can all look forward to better performance
> soon ;)
>
> > Currently I'm compiling ceph with crimson (the compile process seems also
> > a
> > bit messy).
> > To check what the expected performance is with the new seastore backend.
> >
> > I will check Linstor as well, thanks!
> >
>
> Make sure to post results here. I am curious if ceph is really that far
> behind in performance compared to other solutions.
>
>
>
>
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx



[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