diff for duplicates of <1471679705.4036.2.camel@perches.com> diff --git a/a/1.txt b/N1/1.txt index 3372874..311334a 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -21,17 +21,17 @@ On Sat, 2016-08-20 at 09:29 +0200, Michal Hocko wrote: > > I think this isn't worth the expansion in object size (x86-64 defconfig) > > > > $ size fs/proc/meminfo.o* -> > text data bss dec hex filename -> > 2698 8 0 2706 a92 fs/proc/meminfo.o.new -> > 2142 8 0 2150 866 fs/proc/meminfo.o.old +> > text data bss dec hex filename +> > 2698 8 0 2706 a92 fs/proc/meminfo.o.new +> > 2142 8 0 2150 866 fs/proc/meminfo.o.old > > > > Creating a new static in task_mmu would be smaller and faster code. > Hmm, nasty... > add/remove: 0/0 grow/shrink: 2/1 up/down: 1081/-24 (1057) -> function old new delta -> meminfo_proc_show 1134 1745 +611 -> show_smap 560 1030 +470 -> show_val_kb 140 116 -24 +> function old new delta +> meminfo_proc_show 1134 1745 +611 +> show_smap 560 1030 +470 +> show_val_kb 140 116 -24 > Total: Before=91716, After=92773, chg +1.15% > > it seems to be calls to seq_write which blown up the size. So I've tried @@ -39,10 +39,10 @@ On Sat, 2016-08-20 at 09:29 +0200, Michal Hocko wrote: > macros and that reduced the size but not fully back to the original code > size. So it seems the value shifts consumed some portion of that as well. > I've ended up with the following incremental diff which leads to -> text data bss dec hex filename -> 100728 1443 400 102571 190ab fs/proc/built-in.o.next -> 101658 1443 400 103501 1944d fs/proc/built-in.o.patched -> 100951 1443 400 102794 1918a fs/proc/built-in.o.incremental +> text data bss dec hex filename +> 100728 1443 400 102571 190ab fs/proc/built-in.o.next +> 101658 1443 400 103501 1944d fs/proc/built-in.o.patched +> 100951 1443 400 102794 1918a fs/proc/built-in.o.incremental > > There is still some increase wrt. the baseline but I guess that can be > explained by single seq_printf -> many show_name_val_kb calls. @@ -57,9 +57,3 @@ will speed up /proc/<pid>/smaps a whole lot more. Please test it using your little test bench. cheers, Joe - --- -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 40b2e92..db0236d 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -35,17 +35,17 @@ "> > I think this isn't worth the expansion in object size (x86-64 defconfig)\n" "> > \n" "> > $ size fs/proc/meminfo.o*\n" - "> > text\t data\t bss\t dec\t hex\tfilename\n" - "> > 2698\t 8\t 0\t 2706\t a92\tfs/proc/meminfo.o.new\n" - "> > 2142\t 8\t 0\t 2150\t 866\tfs/proc/meminfo.o.old\n" + "> > \302\240\302\240\302\240text\t\302\240\302\240\302\240data\t\302\240\302\240\302\240\302\240bss\t\302\240\302\240\302\240\302\240dec\t\302\240\302\240\302\240\302\240hex\tfilename\n" + "> > \302\240\302\240\302\2402698\t\302\240\302\240\302\240\302\240\302\240\302\2408\t\302\240\302\240\302\240\302\240\302\240\302\2400\t\302\240\302\240\302\2402706\t\302\240\302\240\302\240\302\240a92\tfs/proc/meminfo.o.new\n" + "> > \302\240\302\240\302\2402142\t\302\240\302\240\302\240\302\240\302\240\302\2408\t\302\240\302\240\302\240\302\240\302\240\302\2400\t\302\240\302\240\302\2402150\t\302\240\302\240\302\240\302\240866\tfs/proc/meminfo.o.old\n" "> > \n" "> > Creating a new static in task_mmu would be smaller and faster code.\n" "> Hmm, nasty...\n" "> add/remove: 0/0 grow/shrink: 2/1 up/down: 1081/-24 (1057)\n" - "> function old new delta\n" - "> meminfo_proc_show 1134 1745 +611\n" - "> show_smap 560 1030 +470\n" - "> show_val_kb 140 116 -24\n" + "> function\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\240\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\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240old\302\240\302\240\302\240\302\240\302\240new\302\240\302\240\302\240delta\n" + "> meminfo_proc_show\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\240\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\240\302\2401134\302\240\302\240\302\240\302\2401745\302\240\302\240\302\240\302\240+611\n" + "> show_smap\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\240\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\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240560\302\240\302\240\302\240\302\2401030\302\240\302\240\302\240\302\240+470\n" + "> show_val_kb\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\240\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\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240140\302\240\302\240\302\240\302\240\302\240116\302\240\302\240\302\240\302\240\302\240-24\n" "> Total: Before=91716, After=92773, chg +1.15%\n" "> \n" "> it seems to be calls to seq_write which blown up the size. So I've tried\n" @@ -53,10 +53,10 @@ "> macros and that reduced the size but not fully back to the original code\n" "> size. So it seems the value shifts consumed some portion of that as well.\n" "> I've ended up with the following incremental diff which leads to\n" - "> text data bss dec hex filename\n" - "> 100728 1443 400 102571 190ab fs/proc/built-in.o.next\n" - "> 101658 1443 400 103501 1944d fs/proc/built-in.o.patched\n" - "> 100951 1443 400 102794 1918a fs/proc/built-in.o.incremental\n" + "> \302\240\302\240\302\240text\302\240\302\240\302\240\302\240data\302\240\302\240\302\240\302\240\302\240bss\302\240\302\240\302\240\302\240\302\240dec\302\240\302\240\302\240\302\240\302\240hex filename\n" + "> \302\240100728\302\240\302\240\302\240\302\2401443\302\240\302\240\302\240\302\240\302\240400\302\240\302\240102571\302\240\302\240\302\240190ab fs/proc/built-in.o.next\n" + "> \302\240101658\302\240\302\240\302\240\302\2401443\302\240\302\240\302\240\302\240\302\240400\302\240\302\240103501\302\240\302\240\302\2401944d fs/proc/built-in.o.patched\n" + "> \302\240100951\302\240\302\240\302\240\302\2401443\302\240\302\240\302\240\302\240\302\240400\302\240\302\240102794\302\240\302\240\302\2401918a fs/proc/built-in.o.incremental\n" "> \n" "> There is still some increase wrt. the baseline but I guess that can be\n" "> explained by single seq_printf -> many show_name_val_kb calls.\n" @@ -70,12 +70,6 @@ "\n" "Please test it using your little test bench.\n" "\n" - "cheers, Joe\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>" + cheers, Joe -37c34c9e63f365662b6fb0c1ea1708be6e19372c3248225c90c29c4e9b9a5bda +51bc015a82505a6d9932f723f74451b9fdddf0d2fb7ab4e07c3ae14e42650ab8
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.