diff for duplicates of <20120207132745.GH5938@suse.de> diff --git a/a/1.txt b/N1/1.txt index 6eb2fb5..71c576b 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -7,8 +7,8 @@ On Tue, Feb 07, 2012 at 08:45:18PM +0800, Hillf Danton wrote: > > > > > > Patch 1 serialises access to min_free_kbytes. It's not strictly needed -> > by this series but as the series cares about watermarks in -> > general, it's a harmless fix. It could be merged independently. +> > by this series but as the series cares about watermarks in +> > general, it's a harmless fix. It could be merged independently. > > > > > Any light shed on tuning min_free_kbytes for every day work? @@ -18,28 +18,28 @@ For every day work, leave min_free_kbytes as the default. > > > Patch 2 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to -> > preserve access to pages allocated under low memory situations -> > to callers that are freeing memory. +> > preserve access to pages allocated under low memory situations +> > to callers that are freeing memory. > > > > Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC -> > reserves without setting PFMEMALLOC. +> > reserves without setting PFMEMALLOC. > > > > Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves -> > for later use by network packet processing. +> > for later use by network packet processing. > > > > Patch 5 ignores memory policies when ALLOC_NO_WATERMARKS is set. > > > > Patches 6-11 allows network processing to use PFMEMALLOC reserves when -> > the socket has been marked as being used by the VM to clean -> > pages. If packets are received and stored in pages that were -> > allocated under low-memory situations and are unrelated to -> > the VM, the packets are dropped. +> > the socket has been marked as being used by the VM to clean +> > pages. If packets are received and stored in pages that were +> > allocated under low-memory situations and are unrelated to +> > the VM, the packets are dropped. > > > > Patch 12 is a micro-optimisation to avoid a function call in the -> > common case. +> > common case. > > > > Patch 13 tags NBD sockets as being SOCK_MEMALLOC so they can use -> > PFMEMALLOC if necessary. +> > PFMEMALLOC if necessary. > > > > If it is feasible to bypass hang by tuning min_mem_kbytes, @@ -73,11 +73,11 @@ downsides are it would be equally if not more complex than this approach that it may still hang. > > Patch 14 notes that it is still possible for the PFMEMALLOC reserve -> > to be depleted. To prevent this, direct reclaimers get -> > throttled on a waitqueue if 50% of the PFMEMALLOC reserves are -> > depleted. It is expected that kswapd and the direct reclaimers -> > already running will clean enough pages for the low watermark -> > to be reached and the throttled processes are woken up. +> > to be depleted. To prevent this, direct reclaimers get +> > throttled on a waitqueue if 50% of the PFMEMALLOC reserves are +> > depleted. It is expected that kswapd and the direct reclaimers +> > already running will clean enough pages for the low watermark +> > to be reached and the throttled processes are woken up. > > > > Patch 15 adds a statistic to track how often processes get throttled > > @@ -105,10 +105,3 @@ but NBD may be more fragile. -- Mel Gorman SUSE Labs - --- -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/ . -Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ -Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a> diff --git a/a/content_digest b/N1/content_digest index 3f94709..5604aeb 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -22,8 +22,8 @@ "> >\n" "> >\n" "> > Patch 1 serialises access to min_free_kbytes. It's not strictly needed\n" - "> > by this series but as the series cares about watermarks in\n" - "> > general, it's a harmless fix. It could be merged independently.\n" + "> > \302\240 \302\240 \302\240 \302\240by this series but as the series cares about watermarks in\n" + "> > \302\240 \302\240 \302\240 \302\240general, it's a harmless fix. It could be merged independently.\n" "> >\n" "> >\n" "> Any light shed on tuning min_free_kbytes for every day work?\n" @@ -33,28 +33,28 @@ "\n" "> \n" "> > Patch 2 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to\n" - "> > preserve access to pages allocated under low memory situations\n" - "> > to callers that are freeing memory.\n" + "> > \302\240 \302\240 \302\240 \302\240preserve access to pages allocated under low memory situations\n" + "> > \302\240 \302\240 \302\240 \302\240to callers that are freeing memory.\n" "> >\n" "> > Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC\n" - "> > reserves without setting PFMEMALLOC.\n" + "> > \302\240 \302\240 \302\240 \302\240reserves without setting PFMEMALLOC.\n" "> >\n" "> > Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves\n" - "> > for later use by network packet processing.\n" + "> > \302\240 \302\240 \302\240 \302\240for later use by network packet processing.\n" "> >\n" "> > Patch 5 ignores memory policies when ALLOC_NO_WATERMARKS is set.\n" "> >\n" "> > Patches 6-11 allows network processing to use PFMEMALLOC reserves when\n" - "> > the socket has been marked as being used by the VM to clean\n" - "> > pages. If packets are received and stored in pages that were\n" - "> > allocated under low-memory situations and are unrelated to\n" - "> > the VM, the packets are dropped.\n" + "> > \302\240 \302\240 \302\240 \302\240the socket has been marked as being used by the VM to clean\n" + "> > \302\240 \302\240 \302\240 \302\240pages. If packets are received and stored in pages that were\n" + "> > \302\240 \302\240 \302\240 \302\240allocated under low-memory situations and are unrelated to\n" + "> > \302\240 \302\240 \302\240 \302\240the VM, the packets are dropped.\n" "> >\n" "> > Patch 12 is a micro-optimisation to avoid a function call in the\n" - "> > common case.\n" + "> > \302\240 \302\240 \302\240 \302\240common case.\n" "> >\n" "> > Patch 13 tags NBD sockets as being SOCK_MEMALLOC so they can use\n" - "> > PFMEMALLOC if necessary.\n" + "> > \302\240 \302\240 \302\240 \302\240PFMEMALLOC if necessary.\n" "> >\n" ">\n" "> If it is feasible to bypass hang by tuning min_mem_kbytes,\n" @@ -88,11 +88,11 @@ "that it may still hang.\n" "\n" "> > Patch 14 notes that it is still possible for the PFMEMALLOC reserve\n" - "> > to be depleted. To prevent this, direct reclaimers get\n" - "> > throttled on a waitqueue if 50% of the PFMEMALLOC reserves are\n" - "> > depleted. It is expected that kswapd and the direct reclaimers\n" - "> > already running will clean enough pages for the low watermark\n" - "> > to be reached and the throttled processes are woken up.\n" + "> > \302\240 \302\240 \302\240 \302\240to be depleted. To prevent this, direct reclaimers get\n" + "> > \302\240 \302\240 \302\240 \302\240throttled on a waitqueue if 50% of the PFMEMALLOC reserves are\n" + "> > \302\240 \302\240 \302\240 \302\240depleted. \302\240It is expected that kswapd and the direct reclaimers\n" + "> > \302\240 \302\240 \302\240 \302\240already running will clean enough pages for the low watermark\n" + "> > \302\240 \302\240 \302\240 \302\240to be reached and the throttled processes are woken up.\n" "> >\n" "> > Patch 15 adds a statistic to track how often processes get throttled\n" "> >\n" @@ -119,13 +119,6 @@ "\n" "-- \n" "Mel Gorman\n" - "SUSE Labs\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" - "Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/\n" - "Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>" + SUSE Labs -273c7ddc4932389a01da1b1eb41665619adc98067bdeeb8009c83ecc07acaa17 +02d58413753ac9102f59981ebd69451fd8473c4e52778a88581e2739dbcb8034
diff --git a/a/1.txt b/N2/1.txt index 6eb2fb5..a270fce 100644 --- a/a/1.txt +++ b/N2/1.txt @@ -7,8 +7,8 @@ On Tue, Feb 07, 2012 at 08:45:18PM +0800, Hillf Danton wrote: > > > > > > Patch 1 serialises access to min_free_kbytes. It's not strictly needed -> > by this series but as the series cares about watermarks in -> > general, it's a harmless fix. It could be merged independently. +> > by this series but as the series cares about watermarks in +> > general, it's a harmless fix. It could be merged independently. > > > > > Any light shed on tuning min_free_kbytes for every day work? @@ -18,28 +18,28 @@ For every day work, leave min_free_kbytes as the default. > > > Patch 2 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to -> > preserve access to pages allocated under low memory situations -> > to callers that are freeing memory. +> > preserve access to pages allocated under low memory situations +> > to callers that are freeing memory. > > > > Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC -> > reserves without setting PFMEMALLOC. +> > reserves without setting PFMEMALLOC. > > > > Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves -> > for later use by network packet processing. +> > for later use by network packet processing. > > > > Patch 5 ignores memory policies when ALLOC_NO_WATERMARKS is set. > > > > Patches 6-11 allows network processing to use PFMEMALLOC reserves when -> > the socket has been marked as being used by the VM to clean -> > pages. If packets are received and stored in pages that were -> > allocated under low-memory situations and are unrelated to -> > the VM, the packets are dropped. +> > the socket has been marked as being used by the VM to clean +> > pages. If packets are received and stored in pages that were +> > allocated under low-memory situations and are unrelated to +> > the VM, the packets are dropped. > > > > Patch 12 is a micro-optimisation to avoid a function call in the -> > common case. +> > common case. > > > > Patch 13 tags NBD sockets as being SOCK_MEMALLOC so they can use -> > PFMEMALLOC if necessary. +> > PFMEMALLOC if necessary. > > > > If it is feasible to bypass hang by tuning min_mem_kbytes, @@ -73,11 +73,11 @@ downsides are it would be equally if not more complex than this approach that it may still hang. > > Patch 14 notes that it is still possible for the PFMEMALLOC reserve -> > to be depleted. To prevent this, direct reclaimers get -> > throttled on a waitqueue if 50% of the PFMEMALLOC reserves are -> > depleted. It is expected that kswapd and the direct reclaimers -> > already running will clean enough pages for the low watermark -> > to be reached and the throttled processes are woken up. +> > to be depleted. To prevent this, direct reclaimers get +> > throttled on a waitqueue if 50% of the PFMEMALLOC reserves are +> > depleted. It is expected that kswapd and the direct reclaimers +> > already running will clean enough pages for the low watermark +> > to be reached and the throttled processes are woken up. > > > > Patch 15 adds a statistic to track how often processes get throttled > > diff --git a/a/content_digest b/N2/content_digest index 3f94709..a514ff6 100644 --- a/a/content_digest +++ b/N2/content_digest @@ -22,8 +22,8 @@ "> >\n" "> >\n" "> > Patch 1 serialises access to min_free_kbytes. It's not strictly needed\n" - "> > by this series but as the series cares about watermarks in\n" - "> > general, it's a harmless fix. It could be merged independently.\n" + "> > \302\240 \302\240 \302\240 \302\240by this series but as the series cares about watermarks in\n" + "> > \302\240 \302\240 \302\240 \302\240general, it's a harmless fix. It could be merged independently.\n" "> >\n" "> >\n" "> Any light shed on tuning min_free_kbytes for every day work?\n" @@ -33,28 +33,28 @@ "\n" "> \n" "> > Patch 2 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to\n" - "> > preserve access to pages allocated under low memory situations\n" - "> > to callers that are freeing memory.\n" + "> > \302\240 \302\240 \302\240 \302\240preserve access to pages allocated under low memory situations\n" + "> > \302\240 \302\240 \302\240 \302\240to callers that are freeing memory.\n" "> >\n" "> > Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC\n" - "> > reserves without setting PFMEMALLOC.\n" + "> > \302\240 \302\240 \302\240 \302\240reserves without setting PFMEMALLOC.\n" "> >\n" "> > Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves\n" - "> > for later use by network packet processing.\n" + "> > \302\240 \302\240 \302\240 \302\240for later use by network packet processing.\n" "> >\n" "> > Patch 5 ignores memory policies when ALLOC_NO_WATERMARKS is set.\n" "> >\n" "> > Patches 6-11 allows network processing to use PFMEMALLOC reserves when\n" - "> > the socket has been marked as being used by the VM to clean\n" - "> > pages. If packets are received and stored in pages that were\n" - "> > allocated under low-memory situations and are unrelated to\n" - "> > the VM, the packets are dropped.\n" + "> > \302\240 \302\240 \302\240 \302\240the socket has been marked as being used by the VM to clean\n" + "> > \302\240 \302\240 \302\240 \302\240pages. If packets are received and stored in pages that were\n" + "> > \302\240 \302\240 \302\240 \302\240allocated under low-memory situations and are unrelated to\n" + "> > \302\240 \302\240 \302\240 \302\240the VM, the packets are dropped.\n" "> >\n" "> > Patch 12 is a micro-optimisation to avoid a function call in the\n" - "> > common case.\n" + "> > \302\240 \302\240 \302\240 \302\240common case.\n" "> >\n" "> > Patch 13 tags NBD sockets as being SOCK_MEMALLOC so they can use\n" - "> > PFMEMALLOC if necessary.\n" + "> > \302\240 \302\240 \302\240 \302\240PFMEMALLOC if necessary.\n" "> >\n" ">\n" "> If it is feasible to bypass hang by tuning min_mem_kbytes,\n" @@ -88,11 +88,11 @@ "that it may still hang.\n" "\n" "> > Patch 14 notes that it is still possible for the PFMEMALLOC reserve\n" - "> > to be depleted. To prevent this, direct reclaimers get\n" - "> > throttled on a waitqueue if 50% of the PFMEMALLOC reserves are\n" - "> > depleted. It is expected that kswapd and the direct reclaimers\n" - "> > already running will clean enough pages for the low watermark\n" - "> > to be reached and the throttled processes are woken up.\n" + "> > \302\240 \302\240 \302\240 \302\240to be depleted. To prevent this, direct reclaimers get\n" + "> > \302\240 \302\240 \302\240 \302\240throttled on a waitqueue if 50% of the PFMEMALLOC reserves are\n" + "> > \302\240 \302\240 \302\240 \302\240depleted. \302\240It is expected that kswapd and the direct reclaimers\n" + "> > \302\240 \302\240 \302\240 \302\240already running will clean enough pages for the low watermark\n" + "> > \302\240 \302\240 \302\240 \302\240to be reached and the throttled processes are woken up.\n" "> >\n" "> > Patch 15 adds a statistic to track how often processes get throttled\n" "> >\n" @@ -128,4 +128,4 @@ "Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/\n" "Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>" -273c7ddc4932389a01da1b1eb41665619adc98067bdeeb8009c83ecc07acaa17 +ab64592404fbd72b5047b9bb83e665d3046d26eb5cb0fa46f2303e7240903390
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.