diff for duplicates of <1489613914.2733.96.camel@linux.intel.com> diff --git a/a/1.txt b/N1/1.txt index 6f4e739..dce70d7 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -24,13 +24,13 @@ On Wed, 2017-03-15 at 17:28 +0100, Michal Hocko wrote: >From Aaron's data, it seems like 4 is a reasonable value for max_active: -max_active:A A A time -1A A A A A A A A A A A A A 8.9sA A A A+-0.5% -2A A A A A A A A A A A A A 5.65sA A A+-5.5% -4A A A A A A A A A A A A A 4.84sA A A+-0.16% -8A A A A A A A A A A A A A 4.77sA A A+-0.97% -16A A A A A A A A A A A A 4.85sA A A+-0.77% -32A A A A A A A A A A A A 6.21sA A A+-0.46% +max_active: time +1 8.9s ±0.5% +2 5.65s ±5.5% +4 4.84s ±0.16% +8 4.77s ±0.97% +16 4.85s ±0.77% +32 6.21s ±0.46% > Moreover, and this is a more generic question, is this functionality @@ -42,7 +42,7 @@ should help start the next job sooner. > After all the amount of the work to > be done is the same we just risk more lock contentions, unexpected CPU > usage etc. Which workloads will benefit from having exit path faster? -> A +> > > > > > > > > if we offload the page freeing to the worker then the original context @@ -62,16 +62,10 @@ should help start the next job sooner. You do have a point that this page freeing activities should strive to affect other threads not in the same cgroup minimally. -On the other hand, we also don't do this throttling of kworkersA +On the other hand, we also don't do this throttling of kworkers today (e.g. pdflush) according to the cgroup it is doing work for. Thanks. Tim - --- -To unsubscribe, send a message with 'unsubscribe linux-mm' in -the body to majordomo@kvack.org. For more info on Linux MM, -see: http://www.linux-mm.org/ . -Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a> diff --git a/a/content_digest b/N1/content_digest index c83ef1c..a5c0f8d 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -41,13 +41,13 @@ "\n" ">From Aaron's data, it seems like 4 is a reasonable value for max_active:\n" "\n" - "max_active:A A A time\n" - "1A A A A A A A A A A A A A 8.9sA A A A+-0.5%\n" - "2A A A A A A A A A A A A A 5.65sA A A+-5.5%\n" - "4A A A A A A A A A A A A A 4.84sA A A+-0.16%\n" - "8A A A A A A A A A A A A A 4.77sA A A+-0.97%\n" - "16A A A A A A A A A A A A 4.85sA A A+-0.77%\n" - "32A A A A A A A A A A A A 6.21sA A A+-0.46%\n" + "max_active:\302\240\302\240\302\240time\n" + "1\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\2408.9s\302\240\302\240\302\240\302\2610.5%\n" + "2\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\2405.65s\302\240\302\240\302\2615.5%\n" + "4\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\2404.84s\302\240\302\240\302\2610.16%\n" + "8\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\2404.77s\302\240\302\240\302\2610.97%\n" + "16\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\2404.85s\302\240\302\240\302\2610.77%\n" + "32\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\2406.21s\302\240\302\240\302\2610.46%\n" "\n" "\n" "> Moreover, and this is a more generic question, is this functionality\n" @@ -59,7 +59,7 @@ "> After all the amount of the work to\n" "> be done is the same we just risk more lock contentions, unexpected CPU\n" "> usage etc. Which workloads will benefit from having exit path faster?\n" - "> A \n" + "> \302\240\n" "> > \n" "> > > \n" "> > > if we offload the page freeing to the worker then the original context\n" @@ -79,18 +79,12 @@ "You do have a point that this page freeing activities should strive to\n" "affect other threads not in the same cgroup minimally.\n" "\n" - "On the other hand, we also don't do this throttling of kworkersA \n" + "On the other hand, we also don't do this throttling of kworkers\302\240\n" "today (e.g. pdflush) according to the cgroup it is doing work for.\n" "\n" "\n" "Thanks.\n" "\n" - "Tim\n" - "\n" - "--\n" - "To unsubscribe, send a message with 'unsubscribe linux-mm' in\n" - "the body to majordomo@kvack.org. For more info on Linux MM,\n" - "see: http://www.linux-mm.org/ .\n" - "Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>" + Tim -8a6485abefdba63702a9bad49501741bf045c29b3fd8aff9f62749346142fe49 +0287a6cc46f98557e8877af919e2d8264cd53747933b7de66e4d0efb4e7d9b5f
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.