i/graphs/graph_1485_=
6.png" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_1485_6=
.png</a><br>
faustino: =A0<a href=3D"
http://tools.bitfolk.com/cacti/graphs/graph_1314_6.=
png" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_1314_6.p=
ng</a><br>
kahlua: =A0 =A0<a href=3D"
http://tools.bitfolk.com/cacti/graphs/graph_1192_=
6.png" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_1192_6=
.png</a><br>
kwak: =A0 =A0 =A0<a href=3D"
http://tools.bitfolk.com/cacti/graphs/graph_111=
3_6.png" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_1113=
_6.png</a><br>
obstler: =A0 <a href=3D"
http://tools.bitfolk.com/cacti/graphs/graph_1115_6.=
png" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_1115_6.p=
ng</a><br>
president: <a href=3D"
http://tools.bitfolk.com/cacti/graphs/graph_2639_4.pn=
g" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_2639_4.png=
</a><br>
urquell: =A0 <a href=3D"
http://tools.bitfolk.com/cacti/graphs/graph_2013_6.=
png" target=3D"_blank">
http://tools.bitfolk.com/cacti/graphs/graph_2013_6.p=
ng</a><br>
<br>
(Play at home quiz: which four of the above do you think have eight<br>
disks instead of four? Which one has four 10kRPM SAS disks? Answers<br>
at [4])<br>
<br>
In general we've found that keeping the IO latency below 10ms keeps<br>
people happy.<br>
<br>
There have been short periods where we've failed to keep it below<br>
10ms and I'm sure that many of you can remember times when you've<b=
r>
found your VPS sluggish. Conversely I suspect that not many<br>
customers can think of times when their VPSes have been the *cause*<br>
of high IO load, yet high IO load is in general only caused by<br>
customer VMs! So for every time you have experienced this, someone<br>
else was causing it![5]<br>
<br>
I think that, being in the business of providing virtual<br>
infrastructure at commodity prices, we can't really expect too many<br>
people to want or be able to take the time to profile their storage<br>
use and make a call on what needs to be backed by SATA or SSD.<br>
<br>
I think we first need to try to make it as good as possible for<br>
everyone, always. There may be a time in the future where it's<br>
commonplace for customers to evaluate storage in terms of IO<br>
operations per second instead of gigabytes, but I don't think we are<br=
>
there yet.<br>
<br>
As for the "low-end customers subsidise higher-end customers"<br>
argument, that's just how shared infrastructure works and is already<br=
>
the case in many existing metrics, so what's one more? While we<br>
continue to not have a good way to ration out IO capacity it is<br>
difficult to add it as a line item.<br>
<br>
So, at the moment I'm more drawn to the "both" option but wit=
h the<br>
main focus being on caching with a view to making it better for<br>
everyone, and hopefully overall reducing our costs. If we can sell<br>
some dedicated SSD storage to those who have determined that they<br>
need it then that would be a bonus.<br>
<br>
Thoughts? Don't say, "buy a big SAN!" :-)<br>
<br>
Cheers,<br>
Andy<br>
<br>
[1] You know, when we double the RAM or whatever but keep the price<br>
=A0 =A0to you the same.<br>
<br>
[2] Hot swap trays plus Linux md =3D online array grow. In theory.<br>
<br>
[3] "Nice virtual machine you have here. Would be a real shame if<br>
=A0 =A0 the storage latency were to go through the roof, yanno? We got<br>
=A0 =A0 some uh=85 extras=85 that can help you right out of that mess.<br>
=A0 =A0 Pauly will drop by tomorrow with an invoice."<br>
=A0 =A0 =A0 =97 Tony Soprano's Waste Management and Virtual Server Hos=
ting,
<br>%0A>%20<br>%0A>%20In%20general%20we've%20found%20that%20keeping%20the%20IO%20latency%20below%2010ms%20keeps<br>%0A>%20people%20happy.<br>%0A>%20<br>%0A>%20There%20have%20been%20short%20periods%20where%20we've%20failed%20to%20keep%20it%20below<br>%0A>%2010ms%20and%20I'm%20sure%20that%20many%20of%20you%20can%20remember%20times%20when%20you've<b=%0A>%20r>%0A>%20found%20your%20VPS%20sluggish.%20Conversely%20I%20suspect%20that%20not%20many<br>%0A>%20customers%20can%20think%20of%20times%20when%20their%20VPSes%20have%20been%20the%20*cause*<br>%0A>%20of%20high%20IO%20load,%20yet%20high%20IO%20load%20is%20in%20general%20only%20caused%20by<br>%0A>%20customer%20VMs!%20So%20for%20every%20time%20you%20have%20experienced%20this,%20someone<br>%0A>%20else%20was%20causing%20it!%5B5%5D<br>%0A>%20<br>%0A>%20I%20think%20that,%20being%20in%20the%20business%20of%20providing%20virtual<br>%0A>%20infrastructure%20at%20commodity%20prices,%20we%20can't%20really%20expect%20too%20many<br>%0A>%20people%20to%20want%20or%20be%20able%20to%20take%20the%20time%20to%20profile%20their%20storage<br>%0A>%20use%20and%20make%20a%20call%20on%20what%20needs%20to%20be%20backed%20by%20SATA%20or%20SSD.<br>%0A>%20<br>%0A>%20I%20think%20we%20first%20need%20to%20try%20to%20make%20it%20as%20good%20as%20possible%20for<br>%0A>%20everyone,%20always.%20There%20may%20be%20a%20time%20in%20the%20future%20where%20it's<br>%0A>%20commonplace%20for%20customers%20to%20evaluate%20storage%20in%20terms%20of%20IO<br>%0A>%20operations%20per%20second%20instead%20of%20gigabytes,%20but%20I%20don't%20think%20we%20are<br=%0A>%20>%0A>%20there%20yet.<br>%0A>%20<br>%0A>%20As%20for%20the%20"low-end%20customers%20subsidise%20higher-end%20customers"<br>%0A>%20argument,%20that's%20just%20how%20shared%20infrastructure%20works%20and%20is%20already<br=%0A>%20>%0A>%20the%20case%20in%20many%20existing%20metrics,%20so%20what's%20one%20more?%20While%20we<br>%0A>%20continue%20to%20not%20have%20a%20good%20way%20to%20ration%20out%20IO%20capacity%20it%20is<br>%0A>%20difficult%20to%20add%20it%20as%20a%20line%20item.<br>%0A>%20<br>%0A>%20So,%20at%20the%20moment%20I'm%20more%20drawn%20to%20the%20"both"%20option%20but%20wit=%0A>%20h%20the<br>%0A>%20main%20focus%20being%20on%20caching%20with%20a%20view%20to%20making%20it%20better%20for<br>%0A>%20everyone,%20and%20hopefully%20overall%20reducing%20our%20costs.%20If%20we%20can%20sell<br>%0A>%20some%20dedicated%20SSD%20storage%20to%20those%20who%20have%20determined%20that%20they<br>%0A>%20need%20it%20then%20that%20would%20be%20a%20bonus.<br>%0A>%20<br>%0A>%20Thoughts?%20Don't%20say,%20"buy%20a%20big%20SAN!"%20:-)<br>%0A>%20<br>%0A>%20Cheers,<br>%0A>%20Andy<br>%0A>%20<br>%0A>%20%5B1%5D%20You%20know,%20when%20we%20double%20the%20RAM%20or%20whatever%20but%20keep%20the%20price<br>%0A>%20%20=A0%20=A0to%20you%20the%20same.<br>%0A>%20<br>%0A>%20%5B2%5D%20Hot%20swap%20trays%20plus%20Linux%20md%20=3D%20online%20array%20grow.%20In%20theory.<br>%0A>%20<br>%0A>%20%5B3%5D%20"Nice%20virtual%20machine%20you%20have%20here.%20Would%20be%20a%20real%20shame%20if<br>%0A>%20%20=A0%20=A0%20the%20storage%20latency%20were%20to%20go%20through%20the%20roof,%20yanno?%20We%20got<br>%0A>%20%20=A0%20=A0%20some%20uh=85%20extras=85%20that%20can%20help%20you%20right%20out%20of%20that%20mess.<br>%0A>%20%20=A0%20=A0%20Pauly%20will%20drop%20by%20tomorrow%20with%20an%20invoice."<br>%0A>%20%20=A0%20=A0%20=A0%20=97%20Tony%20Soprano's%20Waste%20Management%20and%20Virtual%20Server%20Hos=%0A>%20ting, "Reply to this message")
