On 4/22/2017 11:51 PM, Andrei Borzenkov wrote:
As a real life example (not Linux/pacemaker) - panicking node flush
eddisk buffers, so it was not safe to access shared filesystem until
this was complete. This could take quite a lot of time, so without agent
on *surviving* node(s) that monitors an
On 23/04/17 12:51 AM, Andrei Borzenkov wrote:
> 22.04.2017 23:33, Dmitri Maziuk пишет:
>> On 4/22/2017 12:02 PM, Digimer wrote:
>>
>>> Having SBD properly configured is *massively* safer than no fencing at
>>> all. So for people where other fence methods are not available for
>>> whatever reason, S
22.04.2017 23:33, Dmitri Maziuk пишет:
> On 4/22/2017 12:02 PM, Digimer wrote:
>
>> Having SBD properly configured is *massively* safer than no fencing at
>> all. So for people where other fence methods are not available for
>> whatever reason, SBD is the way to go.
>
> Now you're talking. IMO in
On 4/22/2017 12:02 PM, Digimer wrote:
Having SBD properly configured is *massively* safer than no fencing at
all. So for people where other fence methods are not available for
whatever reason, SBD is the way to go.
Now you're talking. IMO in a 2-node cluster, a node that kills itself in
respo
On 22/04/17 04:39 AM, Andrei Borzenkov wrote:
> 22.04.2017 11:31, Klaus Wenninger пишет:
>
I wonder how SBD fits into this discussion. It is marketed as stonith
agent, but it is based on committing suicide so relies on well-behaving
nodes. Which we by definition cannot trust to b
22.04.2017 11:31, Klaus Wenninger пишет:
>>> I wonder how SBD fits into this discussion. It is marketed as stonith
>>> agent, but it is based on committing suicide so relies on well-behaving
>>> nodes. Which we by definition cannot trust to behave well, otherwise
>>> we'd not need stonith in t
On 04/22/2017 09:20 AM, Digimer wrote:
> On 22/04/17 03:05 AM, Andrei Borzenkov wrote:
>> 18.04.2017 10:47, Ulrich Windl пишет:
>> ...
Now let me come back to quorum vs. stonith;
Said simply; Quorum is a tool for when everything is working. Fencing is
a tool for when things go w
On 22/04/17 03:05 AM, Andrei Borzenkov wrote:
> 18.04.2017 10:47, Ulrich Windl пишет:
> ...
>>>
>>> Now let me come back to quorum vs. stonith;
>>>
>>> Said simply; Quorum is a tool for when everything is working. Fencing is
>>> a tool for when things go wrong.
>>
>> I'd say: Quorum is the tool to
18.04.2017 10:47, Ulrich Windl пишет:
...
>>
>> Now let me come back to quorum vs. stonith;
>>
>> Said simply; Quorum is a tool for when everything is working. Fencing is
>> a tool for when things go wrong.
>
> I'd say: Quorum is the tool to decide who'll be alive and who's going to die,
> and STO
On 18/04/17 08:50 PM, Dimitri Maziuk wrote:
> On 04/18/2017 07:05 PM, Digimer wrote:
>
>> Certainly, the people creating the software have to assume that a
>> split-brain is devastating. Same for people who teach others and people
>> who write documentation.
>
> split brain is devastating when y
On 04/18/2017 07:05 PM, Digimer wrote:
> Certainly, the people creating the software have to assume that a
> split-brain is devastating. Same for people who teach others and people
> who write documentation.
split brain is devastating when you're drbd. When you're a
mere floating ip, assume make
On 18/04/17 07:55 PM, Dimitri Maziuk wrote:
> On 04/18/2017 06:15 PM, Alex Bruneau wrote:
>
>> Therein lies the true value: what happens when something really
>> messes up? How much do you really want to drive to the DC at 3am?
>
> Yes, exactly: what happens when something really messes up? Will
On 04/18/2017 06:15 PM, Alex Bruneau wrote:
> Therein lies the true value: what happens when something really
> messes up? How much do you really want to drive to the DC at 3am?
Yes, exactly: what happens when something really messes up? Will you
lose a cool million bucks or will a few people get
If your 1 node cluster hits a split brain situation, you have got bigger
problems!
Unless you can guarantee that a cluster can not encounter a split brain (to the
same degree a 1 node cluster can!), any cluster solution worth installing
should have a robust fencing method. Preferably more than
On 04/18/2017 02:47 AM, Ulrich Windl wrote:
> IMHO: a valid cluster software works starting at 1 node, then per induction
> also for n+1 nodes.
I'm not sure what a valid fencing configuration would be in a one-node
cluster, and since -- all together now -- YOU HAVE TO HAVE FENCING!..
Perhaps you
On 18/04/17 15:02, Digimer wrote:
> On 18/04/17 10:00 AM, Digimer wrote:
>> On 18/04/17 03:47 AM, Ulrich Windl wrote:
>> Digimer schrieb am 16.04.2017 um 20:17 in Nachricht
>>> <12cde13f-8bad-a2f1-6834-960ff3afc...@alteeve.ca>:
On 16/04/17 01:53 PM, Eric Robinson wrote:
> I was readin
On 04/18/2017 02:47 AM, Ulrich Windl wrote:
Digimer schrieb am 16.04.2017 um 20:17 in Nachricht
> <12cde13f-8bad-a2f1-6834-960ff3afc...@alteeve.ca>:
>> On 16/04/17 01:53 PM, Eric Robinson wrote:
>>> I was reading in "Clusters from Scratch" where Beekhof states, "Some would
>
>> argue that tw
On 18/04/17 10:00 AM, Digimer wrote:
> On 18/04/17 03:47 AM, Ulrich Windl wrote:
> Digimer schrieb am 16.04.2017 um 20:17 in Nachricht
>> <12cde13f-8bad-a2f1-6834-960ff3afc...@alteeve.ca>:
>>> On 16/04/17 01:53 PM, Eric Robinson wrote:
I was reading in "Clusters from Scratch" where Beekho
On 18/04/17 03:47 AM, Ulrich Windl wrote:
Digimer schrieb am 16.04.2017 um 20:17 in Nachricht
> <12cde13f-8bad-a2f1-6834-960ff3afc...@alteeve.ca>:
>> On 16/04/17 01:53 PM, Eric Robinson wrote:
>>> I was reading in "Clusters from Scratch" where Beekhof states, "Some would
>
>> argue that two-
>>> Digimer schrieb am 16.04.2017 um 20:17 in Nachricht
<12cde13f-8bad-a2f1-6834-960ff3afc...@alteeve.ca>:
> On 16/04/17 01:53 PM, Eric Robinson wrote:
>> I was reading in "Clusters from Scratch" where Beekhof states, "Some would
> argue that two-node clusters are always pointless, but that is an
20 matches
Mail list logo