►
From YouTube: RCE 62: Ceph Petabyte Scale Storage
Description
http://bestdreamhostcoupons.com
RCE 62: Ceph Petabyte Scale Storage Download the entire show and subscribe at: Brock Palen and Jeff Squyres speak with Sage Weil about Ceph, a next generation distributed storage and filesystem for Linux. Sage Weil designed Ceph as part of his PhD research in Storage Systems at the University of California, Santa Cruz. Since graduating, he has continued to refine the system with the goal of providing a stable next generation distributed storage and file system for Linux. Prior to his graduate work, Sage helped found New Dream Network, the company behind DreamHost.com, who now supports a small team of Ceph developers. RCE 62: Ceph Petabyte Scale Storage
A
A
You
can
find
our
old
shows
there
subscribe
by
rss,
itunes,
etc.
You
can
also
follow
me
on
twitter,
where
actually
I've
been
kind
of
active
recently
been
mentioning
some
things
and
we
have
a
lot
of
upcoming
events,
so
you
can
follow
me
on
twitter
at
brockpalin.
All
one
word
and
again
I
have
jeff
squires
from
cisco
systems
and
one
of
the
authors
of
openmpi
and
jeff.
You
just
got
back
from
another
mpi
forum
meeting,
so
I
assume
the
next
revision
of
mpi
is
cooking
along.
It's.
B
Coming
there's
there's
a
buff
at
super
computing
about
mpi
3.0,
we're
looking
to
be
done
with
npi
3.0
by
next
super
computing,
and
that
is
data's
tentative.
But
that's
that's
the
goal,
we're
shooting
for
and
there's
a
bunch
of
interesting
things
coming
in
there
and
the
biggest
fight
right
now
is
about
c
plus
plus,
which
is
really
interesting,
and
I
feel
responsible
for
because
I
created
the
c
plus
plus
bindings
back
in
1996..
C
B
The
inter
machinations
of
the
mpi
forum,
but
come
to
the
the
boss
at
super
competing
to
hear
all
about
that
and
speaking
of
boss,
I
have
my
own
boss
as
well
with
george
basilica,
from
the
university
of
tennessee,
about
the
state
of
the
union,
for
open,
mpi
and
and
thankfully
the
super
computing
organizers
did
not
put
us
opposite
the
the
mpich
buff
this
year
last
year.
They
did.
It
was
kind
of
disappointing
because
so
you
couldn't
go
to
both
and
I'd
like
to
hear
what
those
guys
have
to
say
too.
A
Yeah
I'll
also
be,
at
se
I'll,
be
floating
around,
I'm
not
doing
any
speaking
at
sc,
but
I'll
be
there
the
entire
week.
Also,
I
have
coming
up
at
my
home
institution
university
of
michigan
right
here
in
ann
arbor.
We
have
a
cyber
infrastructure
days
coming
up
just
a
couple
of
days.
The
29th,
through
the
first
november
and
december
and
I'll
actually
be
speaking
there
on
exceed,
which
is
the
follow-on
to
terror
grid
with
phil
blood
from
pittsburgh.
A
A
B
One
throwback
to
super
computing
too:
we
gotta
we
feel
like
we
need
to
mention
the
student
cluster
competition,
because
that
was
just
so
awesome
last
year
that
we
were
a
part
of
it
and
the
energy
and
the
excitement
around
that.
You
need
to
go
stop
by
and
see
all
the
things
that
I
think
they're
on
the
floor
this
year
or
right
adjacent,
I'm
not
sure
exactly
where
they
are
but
need
to
go,
see
him
and
talk
to
him,
because
it
was
really
really
very
cool.
Last
year.
A
Yeah,
I
know
that
was
that
was
a
great
thing
last
year
and
I
think
you
know
doug
and
those
guys
have
been
putting
a
lot
of
neat
stuff
together
with
teams
and
stuff
this
year.
So
I'm
excited
to
see
what
actually
I
need.
I
need
to
look
up
what
the
challenges
are
this
year,
what
the
applications
are.
I'm
curious.
B
All
right
I'll
throw
out
one
last
thing
too
also
my
blog
and
my
twitter
on
there
brock's
been
more
active
on
twitter
than
I
have
recently,
but
I've
been
answering
a
bunch
of
mpi
related
questions
on
my
blog
recently.
So
if
you
have
any
questions
about
how
mpi
works
or
why
we
do
the
things
the
way
we
do
or
anything
about
the
forum
or
the
standard,
please
feel
free
to,
let
me
know
either
an
email
or
twitter
and
I'll
write
up
a
blog
post
about
it.
B
A
Yes,
yes,
our
guest
today
comes
from
dreamhost.
His
name
is
sage
a
while
and
he's
actually
the
did.
I
believe
he
actually
started
the
ceph
distributed
file
system
project
so
sage.
Why
don't
you
take
a
moment
to
introduce
yourself.
C
Sure
yeah,
my
name
is
sage
weil.
I
did
my
graduate
work
at
the
university
of
california,
santa
cruz,
where
my
thesis
was
on
the
distributed
storage
and
out
of
that
grew
the
self-distributed
file
system
and,
since
finishing
I've,
sort
of
continued
working
on
that
project
to
make
it
a
viable,
open
source
solution
to
the
scalability
and
reliability
issues
that
people
have
for
hpc
type,
hpc
type,
storage
and
enterprise.
For
that
matter,.
A
C
It
it
grew
out
of
the
tri
labs
that
sandia
livermore
and
los
alamos
a
series
of
grants
they
made
to
santa
cruz
to
look
at
scalable,
pedoscale,
object-based
storage
system
and
so
there's
some
initial
research
there
dealing
with
low-level
object,
file
systems
and
placement
algorithms.
C
But
when
I
joined
the
project
I
was
focusing
on
distributed
metadata
and
sort
of
how
to
deal
with
that
issue.
At
the
time,
livermore
in
particular,
was
just
starting
to
use
luster
and
they
were
having
a
lot
of
pain
with
lack
of
scalability
in
the
metadata
server,
and
so
that
was
sort
of
the
key
motivation
for
that
work,
but
sort
of
out
of
that
whole.
B
C
I
think
traditional
systems
typically
talk
about
storage
in
terms
of
blocks,
so
you'd
have
like
either
on
a
single
disk.
It's
block
number
some
large
number
or
in
a
I
guess,
a
sam
file
system.
You
talk
about
block
offsets
within
a
line
or
something
like
that.
In
contrast,
the
idea
with
object-based
storage
is
that
you,
you
name
in
the
same
way
that
you
name
a
block
by
numbering
it.
You
would
name
the
object,
but
it
isn't
necessarily
a
number
and
it
doesn't
have
a
fixed
size.
C
So
the
object
can
be
small
or
large
and
can
have
some
metadata
associated
with
it
as
well,
and
it
essentially,
the
the
sort
of
the
key
idea
is
that,
while
traditionally
file
systems
are
have
to
pay
attention
to
data
layout
and
placement
and
block
allocation-
and
you
know
which
sectors
on
the
disk
are
storing
what
data
using
an
object-based
interface
lets,
you
push
all
of
that
complexity
into
the
lowest
levels
of
the
system,
where
it's
more
or
less
hidden
and
all
the
distributed
clustered.
Whatever
the
higher
levels
of
the
file
system.
A
C
Yeah,
so
normally
we
we
put
our
osd
as
we
call
them,
although
it
has
nothing
to
do
with
this,
because
the
t10
ost
that's
sort
of
a
poor
choice,
name
but
then,
basically,
the
set
storage
servers
that
manage
the
objects,
sit
on
top
of
normally
a
butterfest
file
system
and
then
batman
where
they
actually
show
up,
is
just
files,
and
so
the
sort
of
the
low-level
file
system
on
each
of
those
nodes
handles
all
those
details.
C
You
can
also
run
it
on
xbs
or
hd4
or
whatever
else,
but
that's
the
that's
the
basic
idea
and
then
step
itself
only
has
to
worry
about.
You
know,
what's
in
the
objects
and
where
in
the
cluster,
are
they
located
and
it
doesn't
have
to
care
about
rewriting
a
tree
implementation
to
track
free
space
or
whatever.
B
Now
you
threw
out
a
bunch
of
alphabet
soup
there.
Can
you
decrypt
some
of
those
things
there,
so
you
said
things
like
t10
and
and
whatnot
what
what
are
some
of
these
things
for
people
who
aren't
familiar
with
file
systems
and
whatnot.
C
Well,
I
hesitate
a
little
bit
to
talk
about
t10
because
it's
sort
of
a
red
herring,
but
essentially
there
is
a
there's-
a
push,
maybe
five
or
ten
years
ago
to
have
this
idea
of
an
object
disc.
That
basically
encapsulates
encapsulates
this
idea
of
pushing
the
details
of
block
allocation
into
the
device,
and
the
original
vision
was
that
you
would
actually
buy
a
hard
drive
that
you
would
store
objects
on
and
the
protocol.
You
wouldn't,
you
wouldn't
say,
store
this
block.
C
This
data
in
this
stick
size,
block,
we'd,
actually
name
the
objects
and
so
forth
that
there's
a
spec
that
came
out
of
that
and
it
never
really
took
off,
and
so
now,
when
people
talk
about
osds
or
object
disks,
usually
that's
what
they
think
about,
but
in
reality
they
don't
actually
exist
in
the
real
world.
For
the
most
part,
there
are
some
people
that
sort
of
approximate
that
specification
and
their
products,
but
nobody
actually
sells
devices.
C
So,
in
contrast
to
that,
seth
is
something
completely
different.
So
basically,
the
idea
is
that
you
just
take
the
basic
idea
of
pushing
the
details
of
block
allocation
into
the
storage
nodes
and
the
lowest
sort
of
layers
of
the
system
as
possible.
A
So
I
think
you
already
kind
of
answered
this
question
a
little
bit.
Let's
get
it
explicitly,
there's
already
a
couple
of
free
license:
parallel
file
systems
out
there
you
know
luster
pvfs2,
oh,
why
go
in
the
complete
direction
of
building
a
completely
new
implementation,
rather
than
just
putting
contributing
distributed
metadata
to
luster.
C
The
real,
I
think,
the
real
difference
is
that
those
systems
aren't
really
designed
with
fault
tolerance
in
mind,
whereas
sort
of
when
we
were
at
the
drawing
board
with
sef.
We
sort
of
realized
that,
in
order
to
build
something,
that's
going
to
scale
to
hundreds
or
thousands
of
nodes
or
more
that
you
really
have
to
design
for
failure
from
the
from
the
beginning
and
those
systems
tend
to
be
constructed.
On.