IO degradation in 2.4.17-pre2 vs. 2.4.16
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 9 lines
Quoted 7 lines
Yes, throughtput-only tests will have their numbers degradated with the change applied on 2.4.16-pre2.
The whole thing is just about tradeoffs: Interactivity vs throughtput.
I'm not going to destroy interactivity for end users to get beatiful dbench numbers.
Latency is more of an issue for end user machines.
Time for CONFIG_OPTIMIZE_THROUGHPUT / CONFIG_OPTIMIZE_LATENCY ?
Dan
Quoted 11 lines · Dan Maas
Quoted 9 lines
Quoted 7 lines
Yes, throughtput-only tests will have their numbers degradated with the change applied on 2.4.16-pre2.
The whole thing is just about tradeoffs: Interactivity vs throughtput.
I'm not going to destroy interactivity for end users to get beatiful dbench numbers.
Latency is more of an issue for end user machines.
Time for
CONFIG_OPTIMIZE_THROUGHPUT/CONFIG_OPTIMIZE_LATENCY?
That would be the best thing to do, yes.
Quoted 2 lines
Quoted 1 line
Time for
CONFIG_OPTIMIZE_THROUGHPUT/CONFIG_OPTIMIZE_LATENCY?That would be the best thing to do, yes.
/proc/sys not CONFIG_..
Quoted 4 lines · Alan Cox
Quoted 2 lines
Quoted 1 line
Time for
CONFIG_OPTIMIZE_THROUGHPUT/CONFIG_OPTIMIZE_LATENCY?That would be the best thing to do, yes.
/proc/sysnotCONFIG_..
YES!
Much much preferable...
cu
jjs
Quoted 5 lines · Alan Cox
Quoted 3 lines
Quoted 2 lines
Time for
CONFIG_OPTIMIZE_THROUGHPUT/CONFIG_OPTIMIZE_LATENCY?That would be the best thing to do, yes.
/proc/sysnotCONFIG_..
/proc/sys/vm/bdflush, to be precise.
I thought we discussed all this?
-