mirror of
https://github.com/schoebel/mars
synced 2025-03-01 19:10:48 +00:00
doc: update #41,42,49
This commit is contained in:
Thomas Schoebel-Theuer
Thomas Schoebel-Theuer
parent
2197058f84
commit
479fc63a93
27
docu/images/handshake.fig
Normal file
27
docu/images/handshake.fig
Normal file
@ -0,0 +1,27 @@
|
||||
#FIG 3.2 Produced by xfig version 3.2.5c
|
||||
Landscape
|
||||
Center
|
||||
Metric
|
||||
A4
|
||||
100.00
|
||||
Single
|
||||
-2
|
||||
1200 2
|
||||
1 3 0 1 0 7 50 -1 -1 0.000 1 0.0000 900 225 186 186 900 225 1080 270
|
||||
1 3 0 1 0 7 50 -1 -1 0.000 1 0.0000 1350 1800 186 186 1350 1800 1530 1845
|
||||
1 3 0 1 0 7 50 -1 -1 0.000 1 0.0000 3150 225 186 186 3150 225 3330 270
|
||||
1 3 0 1 0 7 50 -1 -1 0.000 1 0.0000 3825 1800 186 186 3825 1800 4005 1845
|
||||
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 0 0 6
|
||||
450 900 900 900 900 450 3150 450 3150 900 4050 900
|
||||
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 0 0 6
|
||||
450 1575 1350 1575 1350 1125 3825 1125 3825 1575 4050 1575
|
||||
2 1 1 1 0 7 50 -1 -1 4.000 0 0 -1 1 0 2
|
||||
1 1 1.00 60.00 120.00
|
||||
450 2250 4050 2250
|
||||
4 1 0 50 -1 2 13 0.0000 0 150 105 900 315 1\001
|
||||
4 1 0 50 -1 2 13 0.0000 0 135 105 3150 315 3\001
|
||||
4 1 0 50 -1 2 13 0.0000 0 150 105 1350 1890 2\001
|
||||
4 0 0 50 -1 4 13 0.0000 0 195 1515 -900 1485 actual response\001
|
||||
4 0 0 50 -1 4 13 0.0000 0 150 1065 -900 810 todo switch\001
|
||||
4 0 0 50 -1 0 12 0.0000 4 135 360 2205 2205 time\001
|
||||
4 1 0 50 -1 2 13 0.0000 0 150 105 3825 1890 4\001
|
||||
@ -4609,6 +4609,220 @@ modprobe
|
||||
have to restore bulks of nodes in a short time.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Section
|
||||
The State of MARS
|
||||
\begin_inset CommandInset label
|
||||
LatexCommand label
|
||||
name "sec:The-State-of"
|
||||
|
||||
\end_inset
|
||||
|
||||
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
In general, MARS tries to
|
||||
\emph on
|
||||
hide
|
||||
\emph default
|
||||
any network failures from you as best as it can.
|
||||
After a network problem, any internal low-level socket connections are
|
||||
|
||||
\emph on
|
||||
transparently
|
||||
\emph default
|
||||
tried to re-open ASAP, without need for sysadmin intervention.
|
||||
In difference to DRBD, network failures will
|
||||
\emph on
|
||||
not
|
||||
\emph default
|
||||
automatically alter the state of MARS, such as switching to
|
||||
\family typewriter
|
||||
disconnected
|
||||
\family default
|
||||
after a
|
||||
\family typewriter
|
||||
ko_timeout
|
||||
\family default
|
||||
or similar.
|
||||
From a high-level sysadmin viewpoint, communication may just take a very
|
||||
long time to succeed.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
When the behaviour of MARS is different from DRBD, it is usually intended
|
||||
as a feature.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
MARS is not only an
|
||||
\series bold
|
||||
asynchronous
|
||||
\series default
|
||||
system at block IO level, but also
|
||||
\series bold
|
||||
at control level
|
||||
\series default
|
||||
.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
This is
|
||||
\emph on
|
||||
necessary
|
||||
\emph default
|
||||
because in a widely distributed long-distance system running on slow or
|
||||
even temporarily failing networks, actions may take a long time, and there
|
||||
may be many actions
|
||||
\series bold
|
||||
started in parallel
|
||||
\series default
|
||||
.
|
||||
Synchronous concepts are generally not sufficient for that.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
Although MARS tries to
|
||||
\emph on
|
||||
approximate
|
||||
\emph default
|
||||
/
|
||||
\emph on
|
||||
emulate
|
||||
\emph default
|
||||
the synchronous control behaviour of DRBD at the interface level (
|
||||
\family typewriter
|
||||
marsadm
|
||||
\family default
|
||||
) in many situations as best as it can, the
|
||||
\emph on
|
||||
internal
|
||||
\emph default
|
||||
control model is asynchronous.
|
||||
As an experiencend sysadmin, you will be curious how it works in principle.
|
||||
When you know something about it, you will no longer be surprised when
|
||||
some (detail) behaviour is different from DRBD.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
The general principle is an asynchronous 2-edge handshake protocol, which
|
||||
is used almost everywhere in MARS:
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
\noindent
|
||||
\align center
|
||||
\begin_inset Graphics
|
||||
filename images/handshake.fig
|
||||
width 80col%
|
||||
|
||||
\end_inset
|
||||
|
||||
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
We have a binary todo switch, which can be either in state
|
||||
\begin_inset Quotes eld
|
||||
\end_inset
|
||||
|
||||
on
|
||||
\begin_inset Quotes erd
|
||||
\end_inset
|
||||
|
||||
or
|
||||
\begin_inset Quotes eld
|
||||
\end_inset
|
||||
|
||||
off
|
||||
\begin_inset Quotes erd
|
||||
\end_inset
|
||||
|
||||
.
|
||||
In addition, we have an actual response indicator, which is similar to
|
||||
an LED indicating the actual status.
|
||||
In our example, we imagine that both are used for controlling a big ventilator,
|
||||
having a huge inert mass.
|
||||
Imagine a big machine from a power plant, which is as tall as a human.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
We start in a situation where the binary switch is off, and the ventilator
|
||||
is stopped.
|
||||
At point 1, we turn on the switch.
|
||||
At that moment, a big contactor will sound like
|
||||
\begin_inset Quotes eld
|
||||
\end_inset
|
||||
|
||||
zonggg
|
||||
\begin_inset Quotes erd
|
||||
\end_inset
|
||||
|
||||
, and a big motor will start to hum.
|
||||
At first you won't hear anything else.
|
||||
It will take a while, say 1 minute, until the big wheel will have reached
|
||||
its final operating RPM, due to the huge inert mass.
|
||||
During that spin-up, the lights in your room will become slightly darker.
|
||||
When having reached the full RPM at point 2, your workplace will then be
|
||||
noisier, but in exchange your room lights will be back at ordinary strength,
|
||||
and the actual response LED will start to lit in order to indicate that
|
||||
the big fan is now operational.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
Assume we want to turn the system off.
|
||||
When turning the todo switch to
|
||||
\begin_inset Quotes eld
|
||||
\end_inset
|
||||
|
||||
off
|
||||
\begin_inset Quotes erd
|
||||
\end_inset
|
||||
|
||||
at point 3, first nothing will seem to happen at all.
|
||||
The big wheel will keep spinning due to its heavy inert mass, and the RPM
|
||||
as well as the sound will go down only slowly.
|
||||
During spin-down, the actual response LED will stay illuminated, in order
|
||||
to warn you that you should not touch the wheel, otherwise you may get
|
||||
injuried
|
||||
\begin_inset Foot
|
||||
status open
|
||||
|
||||
\begin_layout Plain Layout
|
||||
Notice that it is only safe to access the wheel when
|
||||
\emph on
|
||||
both
|
||||
\emph default
|
||||
the switch and the LED are off.
|
||||
Conversely, if at least one of them is on, something is going on inside
|
||||
the machine.
|
||||
Transferred to MARS: always look at
|
||||
\emph on
|
||||
both
|
||||
\emph default
|
||||
the todo switch and the correponding actual indicator in order to not miss
|
||||
something.
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
.
|
||||
The LED will only go off after, say, 2 minutes, when the wheel has actually
|
||||
stopped at point 4.
|
||||
After that, the cycle may potentially start over again.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
As you can see, all four possible cartesian product combinations between
|
||||
two boolean values are occurring in the diagram.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Standard
|
||||
The same handshake protocol is used in MARS for communication between userspace
|
||||
and kernelspace, as well as for communication in the widely distributed
|
||||
system.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Section
|
||||
Inspecting the State of MARS
|
||||
\begin_inset CommandInset label
|
||||
@ -5333,6 +5547,14 @@ todo-{attach,sync,fetch,replay,primary}
|
||||
\family default
|
||||
Shows a boolean value (0 or 1) indicating the current state of the correspondin
|
||||
g todo switch (whether on or off).
|
||||
The meaning of todo switches is illustrated in section
|
||||
\begin_inset CommandInset ref
|
||||
LatexCommand ref
|
||||
reference "sec:The-State-of"
|
||||
|
||||
\end_inset
|
||||
|
||||
.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Labeling
|
||||
@ -5377,6 +5599,15 @@ is-*
|
||||
todo-*
|
||||
\family default
|
||||
values when something is not (yet) working.
|
||||
More explanations can be found in section
|
||||
\begin_inset CommandInset ref
|
||||
LatexCommand ref
|
||||
reference "sec:The-State-of"
|
||||
|
||||
\end_inset
|
||||
|
||||
.
|
||||
|
||||
\end_layout
|
||||
|
||||
\begin_layout Labeling
|
||||
@ -5950,7 +6181,7 @@ Misc Informational Status
|
||||
\family typewriter
|
||||
get-primary
|
||||
\family default
|
||||
Return the name of the current designated primary node.
|
||||
Return the name of the current designated primary node as locally known.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Labeling
|
||||
@ -5970,9 +6201,29 @@ appears
|
||||
guess
|
||||
\series default
|
||||
\emph default
|
||||
, because it is not generally unique in split brain situation! Don't rely
|
||||
on this.
|
||||
Try to a avoid it.
|
||||
, because it is not generally unique in split brain situations! Don't use
|
||||
this macro.
|
||||
Instead, use
|
||||
\family typewriter
|
||||
is-primary
|
||||
\family default
|
||||
on those nodes you are interested in.
|
||||
The explanations from section
|
||||
\begin_inset CommandInset ref
|
||||
LatexCommand ref
|
||||
reference "sec:The-State-of"
|
||||
|
||||
\end_inset
|
||||
|
||||
also apply to
|
||||
\family typewriter
|
||||
get-primary
|
||||
\family default
|
||||
versus
|
||||
\family typewriter
|
||||
actual-primary
|
||||
\family default
|
||||
analogously.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Labeling
|
||||
|
||||
Loading…
Reference in New Issue
Block a user