mirror of https://github.com/schoebel/mars
arch-guide: add management summary
This commit is contained in:
Thomas Schoebel-Theuer
Thomas Schoebel-Theuer
parent
9d54207cb3
commit
55b691a5ca
|
|
@ -473,7 +473,206 @@ name "chap:Management-Summary"
|
|||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
TBD
|
||||
This guide is about
|
||||
\series bold
|
||||
investments and long-term follow-up cost
|
||||
\series default
|
||||
in the range of
|
||||
\series bold
|
||||
millions
|
||||
\series default
|
||||
of € or $.
|
||||
It tries to guide you through the jungle of storage solutions and their
|
||||
features, by focussing at
|
||||
\series bold
|
||||
fundamental principles
|
||||
\series default
|
||||
and high-level structures, called
|
||||
\series bold
|
||||
architecture
|
||||
\series default
|
||||
.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
For
|
||||
\series bold
|
||||
HA enterprise-critical data
|
||||
\series default
|
||||
in the range of
|
||||
\series bold
|
||||
petabytes
|
||||
\series default
|
||||
, different storage architectures are leading to very different properties
|
||||
in the
|
||||
\series bold
|
||||
cost and risk dimensions
|
||||
\series default
|
||||
.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
\begin_inset Flex Custom Color Box 3
|
||||
status open
|
||||
|
||||
\begin_layout Plain Layout
|
||||
\begin_inset Argument 1
|
||||
status open
|
||||
|
||||
\begin_layout Plain Layout
|
||||
|
||||
\series bold
|
||||
Provably best HA / Cloud Storage architecture
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
By intuitive explanations as well as mathematical arguments, this guide
|
||||
shows that
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
Permanent
|
||||
\series bold
|
||||
minimization of the distances
|
||||
\series default
|
||||
between storage and the compute nodes will both
|
||||
\series bold
|
||||
increase reliablity and reduce cost at the same time
|
||||
\series default
|
||||
.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
When applicable for a certain use case, the best architectural model is
|
||||
|
||||
\series bold
|
||||
sharding
|
||||
\series default
|
||||
on top of
|
||||
\series bold
|
||||
local storage
|
||||
\series default
|
||||
.
|
||||
It can easily save a cost factor of about 2, while increasing
|
||||
\series bold
|
||||
architectural reliability
|
||||
\series default
|
||||
at the same time.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
When the so-called
|
||||
\series bold
|
||||
FlexibleSharding
|
||||
\series default
|
||||
variant of the sharding model is combined with a novel load balancing method
|
||||
called
|
||||
\series bold
|
||||
Football
|
||||
\series default
|
||||
, it can deliver a very similar level of
|
||||
\series bold
|
||||
flexibility
|
||||
\series default
|
||||
than network-centric BigCluster architectures are promising.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
By both intuitive and mathematical explanations, and contrary to some contempora
|
||||
ry belief, you will learn
|
||||
\series bold
|
||||
\emph on
|
||||
why
|
||||
\emph default
|
||||
BigCluster architectures are generally worse
|
||||
\series default
|
||||
in practically any dimension.
|
||||
There exist certain use cases where BigCluster cannot be explicitly recommended.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
When built and dimensioned properly,
|
||||
\series bold
|
||||
cross-datacenter replication
|
||||
\series default
|
||||
and/or
|
||||
\series bold
|
||||
geo-redundancy
|
||||
\series default
|
||||
will
|
||||
\emph on
|
||||
not
|
||||
\emph default
|
||||
double TCO = Total Cost of Ownership, but can cost roughly about the same
|
||||
as local redundancy in the same datacenter.
|
||||
The key is a certain class of
|
||||
\series bold
|
||||
wide-area distribution of resources
|
||||
\series default
|
||||
|
||||
\emph on
|
||||
in place of
|
||||
\emph default
|
||||
local replication.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
When cross-datacenter replication and/or geo-redundancy is required, the
|
||||
so-called
|
||||
\series bold
|
||||
ability for butterfly
|
||||
\series default
|
||||
leads to further HA improvements.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
Object-based
|
||||
\series bold
|
||||
Cloud Storage
|
||||
\series default
|
||||
can also be built on top of a sharding model.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Itemize
|
||||
You will learn
|
||||
\series bold
|
||||
why OpenSource component-based storage systems
|
||||
\series default
|
||||
are much cheaper than commercial storage appliances (up to
|
||||
\emph on
|
||||
factors
|
||||
\emph default
|
||||
), at least when you need a few petabytes of storage.
|
||||
Alone by relinquishing Vendor-Lock-In and going to RAID-based Linux storage,
|
||||
invest will typically decrease by factors between 3 and 10.
|
||||
By going to a
|
||||
\family typewriter
|
||||
LocalSharding
|
||||
\family default
|
||||
or
|
||||
\family typewriter
|
||||
FlexibleSharding
|
||||
\family default
|
||||
model, where possible,
|
||||
\emph on
|
||||
another
|
||||
\emph default
|
||||
decrease factor of about 2 is typically possible.
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
\noindent
|
||||
In addition, this guide explains the ideas behind the OpenSource components
|
||||
Football on top of MARS.
|
||||
It can be used for replication over short to very long distances, as well
|
||||
as for load balancing via background data migration while your services
|
||||
are running.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Chapter
|
||||
|
|
|
|||
Loading…
Reference in New Issue