diff for duplicates of <20110930085539.GD30857@redhat.com> diff --git a/a/1.txt b/N1/1.txt index f51a11d..4af8383 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -1,25 +1,20 @@ On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote: > Hi Johannes! ->=20 -> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> = -wrote: +> +> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote: > > But there is a flaw in that we have a zoned page allocator which does > > not care about the global state but rather the state of individual -> > memory zones. =A0And right now there is nothing that prevents one zon= -e +> > memory zones. And right now there is nothing that prevents one zone > > from filling up with dirty pages while other zones are spared, which > > frequently leads to situations where kswapd, in order to restore the > > watermark of free pages, does indeed have to write pages from that -> > zone's LRU list. =A0This can interfere so badly with IO from the flus= -her +> > zone's LRU list. This can interfere so badly with IO from the flusher > > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write > > requests from reclaim already, taking away the VM's only possibility -> > to keep such a zone balanced, aside from hoping the flushers will soo= -n +> > to keep such a zone balanced, aside from hoping the flushers will soon > > clean pages from that zone. ->=20 -> The obvious question is: how did you test this? Can you share the resul= -ts? +> +> The obvious question is: how did you test this? Can you share the results? Meh, sorry about that, they were in the series introduction the last time and I forgot to copy them over. @@ -35,11 +30,10 @@ most pronounced with slow backing devices. Test results -15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory +15M DMA + 3246M DMA32 + 504M Normal = 3765M memory 40% dirty ratio, 10% background ratio 16G USB thumb drive -10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1= -5)) +10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15)) seconds nr_vmscan_write (stddev) min| median| max @@ -63,6 +57,5 @@ patched: 568.806(17.496) 0.000| 0.000| 0.000 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=3Dmailto:"dont@kvack.org"> email@kvack.org </a> +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 45316b3..b7f990e 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -27,26 +27,21 @@ "b\0" "On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote:\n" "> Hi Johannes!\n" - ">=20\n" - "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> =\n" - "wrote:\n" + "> \n" + "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote:\n" "> > But there is a flaw in that we have a zoned page allocator which does\n" "> > not care about the global state but rather the state of individual\n" - "> > memory zones. =A0And right now there is nothing that prevents one zon=\n" - "e\n" + "> > memory zones. \302\240And right now there is nothing that prevents one zone\n" "> > from filling up with dirty pages while other zones are spared, which\n" "> > frequently leads to situations where kswapd, in order to restore the\n" "> > watermark of free pages, does indeed have to write pages from that\n" - "> > zone's LRU list. =A0This can interfere so badly with IO from the flus=\n" - "her\n" + "> > zone's LRU list. \302\240This can interfere so badly with IO from the flusher\n" "> > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write\n" "> > requests from reclaim already, taking away the VM's only possibility\n" - "> > to keep such a zone balanced, aside from hoping the flushers will soo=\n" - "n\n" + "> > to keep such a zone balanced, aside from hoping the flushers will soon\n" "> > clean pages from that zone.\n" - ">=20\n" - "> The obvious question is: how did you test this? Can you share the resul=\n" - "ts?\n" + "> \n" + "> The obvious question is: how did you test this? Can you share the results?\n" "\n" "Meh, sorry about that, they were in the series introduction the last\n" "time and I forgot to copy them over.\n" @@ -62,11 +57,10 @@ "\n" "\t\t\tTest results\n" "\n" - "15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory\n" + "15M DMA + 3246M DMA32 + 504M Normal = 3765M memory\n" "40% dirty ratio, 10% background ratio\n" "16G USB thumb drive\n" - "10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1=\n" - "5))\n" + "10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15))\n" "\n" "\t\tseconds\t\t\tnr_vmscan_write\n" "\t\t (stddev)\t min| median| max\n" @@ -90,8 +84,7 @@ "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=\n" - ".ca/\n" - "Don't email: <a href=3Dmailto:\"dont@kvack.org\"> email@kvack.org </a>" + "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>" -a551660e9a72f15479a5d07d8e6f3be947df96178fa27a626218936f33f799d7 +88562bb0a433103b3cd93e78f939f796c35e838b558dc6c67a7db8d55766be29
diff --git a/a/1.txt b/N2/1.txt index f51a11d..92e4173 100644 --- a/a/1.txt +++ b/N2/1.txt @@ -1,25 +1,20 @@ On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote: > Hi Johannes! ->=20 -> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> = -wrote: +> +> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote: > > But there is a flaw in that we have a zoned page allocator which does > > not care about the global state but rather the state of individual -> > memory zones. =A0And right now there is nothing that prevents one zon= -e +> > memory zones. And right now there is nothing that prevents one zone > > from filling up with dirty pages while other zones are spared, which > > frequently leads to situations where kswapd, in order to restore the > > watermark of free pages, does indeed have to write pages from that -> > zone's LRU list. =A0This can interfere so badly with IO from the flus= -her +> > zone's LRU list. This can interfere so badly with IO from the flusher > > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write > > requests from reclaim already, taking away the VM's only possibility -> > to keep such a zone balanced, aside from hoping the flushers will soo= -n +> > to keep such a zone balanced, aside from hoping the flushers will soon > > clean pages from that zone. ->=20 -> The obvious question is: how did you test this? Can you share the resul= -ts? +> +> The obvious question is: how did you test this? Can you share the results? Meh, sorry about that, they were in the series introduction the last time and I forgot to copy them over. @@ -35,11 +30,10 @@ most pronounced with slow backing devices. Test results -15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory +15M DMA + 3246M DMA32 + 504M Normal = 3765M memory 40% dirty ratio, 10% background ratio 16G USB thumb drive -10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1= -5)) +10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15)) seconds nr_vmscan_write (stddev) min| median| max @@ -59,10 +53,7 @@ ext4 vanilla: 561.197(15.782) 0.000|2725438.000|4143837.000 patched: 568.806(17.496) 0.000| 0.000| 0.000 --- -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=3Dmailto:"dont@kvack.org"> email@kvack.org </a> +_______________________________________________ +xfs mailing list +xfs@oss.sgi.com +http://oss.sgi.com/mailman/listinfo/xfs diff --git a/a/content_digest b/N2/content_digest index 45316b3..ec5837e 100644 --- a/a/content_digest +++ b/N2/content_digest @@ -5,48 +5,42 @@ "Subject\0Re: [patch 3/5] mm: try to distribute dirty pages fairly across zones\0" "Date\0Fri, 30 Sep 2011 10:55:39 +0200\0" "To\0Pekka Enberg <penberg@cs.helsinki.fi>\0" - "Cc\0Andrew Morton <akpm@linux-foundation.org>" - Mel Gorman <mgorman@suse.de> - Christoph Hellwig <hch@infradead.org> - Dave Chinner <david@fromorbit.com> - Wu Fengguang <fengguang.wu@intel.com> + "Cc\0Rik van Riel <riel@redhat.com>" + linux-ext4@vger.kernel.org Jan Kara <jack@suse.cz> - Rik van Riel <riel@redhat.com> - Minchan Kim <minchan.kim@gmail.com> - Chris Mason <chris.mason@oracle.com> - Theodore Ts'o <tytso@mit.edu> - Andreas Dilger <adilger.kernel@dilger.ca> - Shaohua Li <shaohua.li@intel.com> - xfs@oss.sgi.com linux-btrfs@vger.kernel.org - linux-ext4@vger.kernel.org + linux-kernel@vger.kernel.org + xfs@oss.sgi.com + Christoph Hellwig <hch@infradead.org> linux-mm@kvack.org + Andreas Dilger <adilger.kernel@dilger.ca> + Mel Gorman <mgorman@suse.de> + Shaohua Li <shaohua.li@intel.com> linux-fsdevel@vger.kernel.org - " linux-kernel@vger.kernel.org\0" + Theodore Ts'o <tytso@mit.edu> + Andrew Morton <akpm@linux-foundation.org> + Wu Fengguang <fengguang.wu@intel.com> + Chris Mason <chris.mason@oracle.com> + " Minchan Kim <minchan.kim@gmail.com>\0" "\00:1\0" "b\0" "On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote:\n" "> Hi Johannes!\n" - ">=20\n" - "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> =\n" - "wrote:\n" + "> \n" + "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote:\n" "> > But there is a flaw in that we have a zoned page allocator which does\n" "> > not care about the global state but rather the state of individual\n" - "> > memory zones. =A0And right now there is nothing that prevents one zon=\n" - "e\n" + "> > memory zones. \302\240And right now there is nothing that prevents one zone\n" "> > from filling up with dirty pages while other zones are spared, which\n" "> > frequently leads to situations where kswapd, in order to restore the\n" "> > watermark of free pages, does indeed have to write pages from that\n" - "> > zone's LRU list. =A0This can interfere so badly with IO from the flus=\n" - "her\n" + "> > zone's LRU list. \302\240This can interfere so badly with IO from the flusher\n" "> > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write\n" "> > requests from reclaim already, taking away the VM's only possibility\n" - "> > to keep such a zone balanced, aside from hoping the flushers will soo=\n" - "n\n" + "> > to keep such a zone balanced, aside from hoping the flushers will soon\n" "> > clean pages from that zone.\n" - ">=20\n" - "> The obvious question is: how did you test this? Can you share the resul=\n" - "ts?\n" + "> \n" + "> The obvious question is: how did you test this? Can you share the results?\n" "\n" "Meh, sorry about that, they were in the series introduction the last\n" "time and I forgot to copy them over.\n" @@ -62,11 +56,10 @@ "\n" "\t\t\tTest results\n" "\n" - "15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory\n" + "15M DMA + 3246M DMA32 + 504M Normal = 3765M memory\n" "40% dirty ratio, 10% background ratio\n" "16G USB thumb drive\n" - "10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1=\n" - "5))\n" + "10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15))\n" "\n" "\t\tseconds\t\t\tnr_vmscan_write\n" "\t\t (stddev)\t min| median| max\n" @@ -86,12 +79,9 @@ "vanilla:\t 561.197(15.782)\t 0.000|2725438.000|4143837.000\n" "patched:\t 568.806(17.496)\t 0.000| 0.000| 0.000\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=\n" - ".ca/\n" - "Don't email: <a href=3Dmailto:\"dont@kvack.org\"> email@kvack.org </a>" + "_______________________________________________\n" + "xfs mailing list\n" + "xfs@oss.sgi.com\n" + http://oss.sgi.com/mailman/listinfo/xfs -a551660e9a72f15479a5d07d8e6f3be947df96178fa27a626218936f33f799d7 +df9218ef0ae1c91be7da1d5a5cc76c3f7bef8962d77859de14a55a2bf83d51b5
diff --git a/a/1.txt b/N3/1.txt index f51a11d..8720f38 100644 --- a/a/1.txt +++ b/N3/1.txt @@ -1,25 +1,20 @@ On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote: > Hi Johannes! ->=20 -> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> = -wrote: +> +> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote: > > But there is a flaw in that we have a zoned page allocator which does > > not care about the global state but rather the state of individual -> > memory zones. =A0And right now there is nothing that prevents one zon= -e +> > memory zones. And right now there is nothing that prevents one zone > > from filling up with dirty pages while other zones are spared, which > > frequently leads to situations where kswapd, in order to restore the > > watermark of free pages, does indeed have to write pages from that -> > zone's LRU list. =A0This can interfere so badly with IO from the flus= -her +> > zone's LRU list. This can interfere so badly with IO from the flusher > > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write > > requests from reclaim already, taking away the VM's only possibility -> > to keep such a zone balanced, aside from hoping the flushers will soo= -n +> > to keep such a zone balanced, aside from hoping the flushers will soon > > clean pages from that zone. ->=20 -> The obvious question is: how did you test this? Can you share the resul= -ts? +> +> The obvious question is: how did you test this? Can you share the results? Meh, sorry about that, they were in the series introduction the last time and I forgot to copy them over. @@ -35,11 +30,10 @@ most pronounced with slow backing devices. Test results -15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory +15M DMA + 3246M DMA32 + 504M Normal = 3765M memory 40% dirty ratio, 10% background ratio 16G USB thumb drive -10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1= -5)) +10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15)) seconds nr_vmscan_write (stddev) min| median| max @@ -58,11 +52,3 @@ patched: 563.365(11.368) 0.000| 0.000| 1362.000 ext4 vanilla: 561.197(15.782) 0.000|2725438.000|4143837.000 patched: 568.806(17.496) 0.000| 0.000| 0.000 - --- -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=3Dmailto:"dont@kvack.org"> email@kvack.org </a> diff --git a/a/content_digest b/N3/content_digest index 45316b3..9fcbbd5 100644 --- a/a/content_digest +++ b/N3/content_digest @@ -27,26 +27,21 @@ "b\0" "On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote:\n" "> Hi Johannes!\n" - ">=20\n" - "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> =\n" - "wrote:\n" + "> \n" + "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote:\n" "> > But there is a flaw in that we have a zoned page allocator which does\n" "> > not care about the global state but rather the state of individual\n" - "> > memory zones. =A0And right now there is nothing that prevents one zon=\n" - "e\n" + "> > memory zones. \302\240And right now there is nothing that prevents one zone\n" "> > from filling up with dirty pages while other zones are spared, which\n" "> > frequently leads to situations where kswapd, in order to restore the\n" "> > watermark of free pages, does indeed have to write pages from that\n" - "> > zone's LRU list. =A0This can interfere so badly with IO from the flus=\n" - "her\n" + "> > zone's LRU list. \302\240This can interfere so badly with IO from the flusher\n" "> > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write\n" "> > requests from reclaim already, taking away the VM's only possibility\n" - "> > to keep such a zone balanced, aside from hoping the flushers will soo=\n" - "n\n" + "> > to keep such a zone balanced, aside from hoping the flushers will soon\n" "> > clean pages from that zone.\n" - ">=20\n" - "> The obvious question is: how did you test this? Can you share the resul=\n" - "ts?\n" + "> \n" + "> The obvious question is: how did you test this? Can you share the results?\n" "\n" "Meh, sorry about that, they were in the series introduction the last\n" "time and I forgot to copy them over.\n" @@ -62,11 +57,10 @@ "\n" "\t\t\tTest results\n" "\n" - "15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory\n" + "15M DMA + 3246M DMA32 + 504M Normal = 3765M memory\n" "40% dirty ratio, 10% background ratio\n" "16G USB thumb drive\n" - "10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1=\n" - "5))\n" + "10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15))\n" "\n" "\t\tseconds\t\t\tnr_vmscan_write\n" "\t\t (stddev)\t min| median| max\n" @@ -84,14 +78,6 @@ "\n" "ext4\n" "vanilla:\t 561.197(15.782)\t 0.000|2725438.000|4143837.000\n" - "patched:\t 568.806(17.496)\t 0.000| 0.000| 0.000\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=\n" - ".ca/\n" - "Don't email: <a href=3Dmailto:\"dont@kvack.org\"> email@kvack.org </a>" + "patched:\t 568.806(17.496)\t 0.000| 0.000| 0.000" -a551660e9a72f15479a5d07d8e6f3be947df96178fa27a626218936f33f799d7 +b2b72c1cdcd5e493a68e1e0af1365511990220ee537af5d66d242d3a4e125391
diff --git a/a/1.txt b/N4/1.txt index f51a11d..e952e26 100644 --- a/a/1.txt +++ b/N4/1.txt @@ -1,25 +1,20 @@ On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote: > Hi Johannes! ->=20 -> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> = -wrote: +> +> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote: > > But there is a flaw in that we have a zoned page allocator which does > > not care about the global state but rather the state of individual -> > memory zones. =A0And right now there is nothing that prevents one zon= -e +> > memory zones. And right now there is nothing that prevents one zone > > from filling up with dirty pages while other zones are spared, which > > frequently leads to situations where kswapd, in order to restore the > > watermark of free pages, does indeed have to write pages from that -> > zone's LRU list. =A0This can interfere so badly with IO from the flus= -her +> > zone's LRU list. This can interfere so badly with IO from the flusher > > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write > > requests from reclaim already, taking away the VM's only possibility -> > to keep such a zone balanced, aside from hoping the flushers will soo= -n +> > to keep such a zone balanced, aside from hoping the flushers will soon > > clean pages from that zone. ->=20 -> The obvious question is: how did you test this? Can you share the resul= -ts? +> +> The obvious question is: how did you test this? Can you share the results? Meh, sorry about that, they were in the series introduction the last time and I forgot to copy them over. @@ -35,11 +30,10 @@ most pronounced with slow backing devices. Test results -15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory +15M DMA + 3246M DMA32 + 504M Normal = 3765M memory 40% dirty ratio, 10% background ratio 16G USB thumb drive -10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1= -5)) +10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15)) seconds nr_vmscan_write (stddev) min| median| max @@ -63,6 +57,5 @@ patched: 568.806(17.496) 0.000| 0.000| 0.000 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=3Dmailto:"dont@kvack.org"> email@kvack.org </a> +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/N4/content_digest index 45316b3..a048c64 100644 --- a/a/content_digest +++ b/N4/content_digest @@ -27,26 +27,21 @@ "b\0" "On Fri, Sep 30, 2011 at 10:35:25AM +0300, Pekka Enberg wrote:\n" "> Hi Johannes!\n" - ">=20\n" - "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> =\n" - "wrote:\n" + "> \n" + "> On Fri, Sep 30, 2011 at 10:17 AM, Johannes Weiner <jweiner@redhat.com> wrote:\n" "> > But there is a flaw in that we have a zoned page allocator which does\n" "> > not care about the global state but rather the state of individual\n" - "> > memory zones. =A0And right now there is nothing that prevents one zon=\n" - "e\n" + "> > memory zones. And right now there is nothing that prevents one zone\n" "> > from filling up with dirty pages while other zones are spared, which\n" "> > frequently leads to situations where kswapd, in order to restore the\n" "> > watermark of free pages, does indeed have to write pages from that\n" - "> > zone's LRU list. =A0This can interfere so badly with IO from the flus=\n" - "her\n" + "> > zone's LRU list. This can interfere so badly with IO from the flusher\n" "> > threads that major filesystems (btrfs, xfs, ext4) mostly ignore write\n" "> > requests from reclaim already, taking away the VM's only possibility\n" - "> > to keep such a zone balanced, aside from hoping the flushers will soo=\n" - "n\n" + "> > to keep such a zone balanced, aside from hoping the flushers will soon\n" "> > clean pages from that zone.\n" - ">=20\n" - "> The obvious question is: how did you test this? Can you share the resul=\n" - "ts?\n" + "> \n" + "> The obvious question is: how did you test this? Can you share the results?\n" "\n" "Meh, sorry about that, they were in the series introduction the last\n" "time and I forgot to copy them over.\n" @@ -62,11 +57,10 @@ "\n" "\t\t\tTest results\n" "\n" - "15M DMA + 3246M DMA32 + 504M Normal =3D 3765M memory\n" + "15M DMA + 3246M DMA32 + 504M Normal = 3765M memory\n" "40% dirty ratio, 10% background ratio\n" "16G USB thumb drive\n" - "10 runs of dd if=3D/dev/zero of=3Ddisk/zeroes bs=3D32k count=3D$((10 << 1=\n" - "5))\n" + "10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15))\n" "\n" "\t\tseconds\t\t\tnr_vmscan_write\n" "\t\t (stddev)\t min| median| max\n" @@ -90,8 +84,7 @@ "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=\n" - ".ca/\n" - "Don't email: <a href=3Dmailto:\"dont@kvack.org\"> email@kvack.org </a>" + "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>" -a551660e9a72f15479a5d07d8e6f3be947df96178fa27a626218936f33f799d7 +915b363c851525146f518794d737f23d975caf52caeda748cd1e5aa3b957cd25
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.