diff for duplicates of <20160901162139.GA6687@linux.intel.com> diff --git a/a/1.txt b/N1/1.txt index f343e18..446dc1a 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -83,9 +83,7 @@ isn't comparable to my bare metal system, but it's interesting that the use of PMDs over tripled the performance in my VM. Hmm... We'll keep digging into this. Thanks again for the report. :) - --- -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> +_______________________________________________ +Linux-nvdimm mailing list +Linux-nvdimm@lists.01.org +https://lists.01.org/mailman/listinfo/linux-nvdimm diff --git a/a/content_digest b/N1/content_digest index 0e598e4..bd0090f 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -8,20 +8,18 @@ "Date\0Thu, 1 Sep 2016 10:21:39 -0600\0" "To\0Kani" " Toshimitsu <toshi.kani@hpe.com>\0" - "Cc\0ross.zwisler@linux.intel.com <ross.zwisler@linux.intel.com>" + "Cc\0tytso@mit.edu <tytso@mit.edu>" + akpm@linux-foundation.org <akpm@linux-foundation.org> + mawilcox@microsoft.com <mawilcox@microsoft.com> + linux-nvdimm@lists.01.org <linux-nvdimm@lists.01.org> + david@fromorbit.com <david@fromorbit.com> linux-kernel@vger.kernel.org <linux-kernel@vger.kernel.org> linux-mm@kvack.org <linux-mm@kvack.org> adilger.kernel@dilger.ca <adilger.kernel@dilger.ca> viro@zeniv.linux.org.uk <viro@zeniv.linux.org.uk> - dan.j.williams@intel.com <dan.j.williams@intel.com> - akpm@linux-foundation.org <akpm@linux-foundation.org> - mawilcox@microsoft.com <mawilcox@microsoft.com> - linux-nvdimm@lists.01.org <linux-nvdimm@lists.01.org> - linux-fsdevel@vger.kernel.org <linux-fsdevel@vger.kernel.org> jack@suse.com <jack@suse.com> - tytso@mit.edu <tytso@mit.edu> - linux-ext4@vger.kernel.org <linux-ext4@vger.kernel.org> - " david@fromorbit.com <david@fromorbit.com>\0" + linux-fsdevel@vger.kernel.org <linux-fsdevel@vger.kernel.org> + " linux-ext4@vger.kernel.org <linux-ext4@vger.kernel.org>\0" "\00:1\0" "b\0" "On Wed, Aug 31, 2016 at 10:08:59PM +0000, Kani, Toshimitsu wrote:\n" @@ -109,11 +107,9 @@ "PMDs over tripled the performance in my VM. Hmm...\n" "\n" "We'll keep digging into this. Thanks again for the report. :)\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>" + "_______________________________________________\n" + "Linux-nvdimm mailing list\n" + "Linux-nvdimm@lists.01.org\n" + https://lists.01.org/mailman/listinfo/linux-nvdimm -4890b686e1b6c18bab101fe692fbb42bafe732a33e4364393d6fed1ad24f3eab +6e971d93d2c8d540efd1004aa2a5e14107cc8e809d8f433e560bc799122b5057
diff --git a/a/1.txt b/N2/1.txt index f343e18..a0d8406 100644 --- a/a/1.txt +++ b/N2/1.txt @@ -5,22 +5,22 @@ On Wed, Aug 31, 2016 at 10:08:59PM +0000, Kani, Toshimitsu wrote: > > > On Tue, 2016-08-30 at 17:01 -0600, Ross Zwisler wrote: > > > > > > > > On Tue, Aug 23, 2016 at 04:04:10PM -0600, Ross Zwisler wrote: -> : +> �: > > > > -> > > > Ping on this series? Any objections or comments? +> > > > Ping on this series?��Any objections or comments? > > > > > > Hi Ross, > > > > > > I am seeing a major performance loss in fio mmap test with this -> > > patch-set applied. This happens with or without my patches [1] -> > > applied on top of yours. Without my patches, dax_pmd_fault() falls +> > > patch-set applied. �This happens with or without my patches [1] +> > > applied on top of yours. �Without my patches,�dax_pmd_fault() falls > > > back to the pte handler since an mmap'ed address is not 2MB- > > > aligned. > > > > > > I have attached three test results. -> > > o rc4.log - 4.8.0-rc4 (base) -> > > o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte) -> > > o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps) +> > > �o rc4.log - 4.8.0-rc4 (base) +> > > �o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte) +> > > �o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps) > > > > > > My test steps are as follows. > > > @@ -44,11 +44,11 @@ On Wed, Aug 31, 2016 at 10:08:59PM +0000, Kani, Toshimitsu wrote: > > > > Yep, thanks for the report. > -> I have some more observations. It seems this issue is related with pmd -> mappings after all. fio creates "randrw.0.0" file. In my setup, an -> initial test run creates pmd mappings and hits this issue. Subsequent +> I have some more observations. �It seems this issue is related with pmd +> mappings after all. �fio creates "randrw.0.0" file. �In my setup, an +> initial test run creates pmd mappings and hits this issue. �Subsequent > test runs (i.e. randrw.0.0 exists), without my patches, fall back to -> pte mappings and do not hit this issue. With my patches applied, +> pte mappings and do not hit this issue. �With my patches applied, > subsequent runs still create pmd mappings and hit this issue. I've been able to reproduce this on my test setup, and I agree that it appears diff --git a/a/content_digest b/N2/content_digest index 0e598e4..bb03b9b 100644 --- a/a/content_digest +++ b/N2/content_digest @@ -31,22 +31,22 @@ "> > > On Tue, 2016-08-30 at 17:01 -0600, Ross Zwisler wrote:\n" "> > > > \n" "> > > > On Tue, Aug 23, 2016 at 04:04:10PM -0600, Ross Zwisler wrote:\n" - "> \302\240:\n" + "> \303\257\302\277\302\275:\n" "> > > > \n" - "> > > > Ping on this series?\302\240\302\240Any objections or comments?\n" + "> > > > Ping on this series?\303\257\302\277\302\275\303\257\302\277\302\275Any objections or comments?\n" "> > > \n" "> > > Hi Ross,\n" "> > > \n" "> > > I am seeing a major performance loss in fio mmap test with this\n" - "> > > patch-set applied. \302\240This happens with or without my patches [1]\n" - "> > > applied on top of yours. \302\240Without my patches,\302\240dax_pmd_fault() falls\n" + "> > > patch-set applied. \303\257\302\277\302\275This happens with or without my patches [1]\n" + "> > > applied on top of yours. \303\257\302\277\302\275Without my patches,\303\257\302\277\302\275dax_pmd_fault() falls\n" "> > > back to the pte handler since an mmap'ed address is not 2MB-\n" "> > > aligned.\n" "> > > \n" "> > > I have attached three test results.\n" - "> > > \302\240o rc4.log - 4.8.0-rc4 (base)\n" - "> > > \302\240o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte)\n" - "> > > \302\240o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps)\n" + "> > > \303\257\302\277\302\275o rc4.log - 4.8.0-rc4 (base)\n" + "> > > \303\257\302\277\302\275o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte)\n" + "> > > \303\257\302\277\302\275o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps)\n" "> > > \n" "> > > My test steps are as follows.\n" "> > > \n" @@ -70,11 +70,11 @@ "> > \n" "> > Yep, thanks for the report.\n" "> \n" - "> I have some more observations. \302\240It seems this issue is related with pmd\n" - "> mappings after all. \302\240fio creates \"randrw.0.0\" file. \302\240In my setup, an\n" - "> initial test run creates pmd mappings and hits this issue. \302\240Subsequent\n" + "> I have some more observations. \303\257\302\277\302\275It seems this issue is related with pmd\n" + "> mappings after all. \303\257\302\277\302\275fio creates \"randrw.0.0\" file. \303\257\302\277\302\275In my setup, an\n" + "> initial test run creates pmd mappings and hits this issue. \303\257\302\277\302\275Subsequent\n" "> test runs (i.e. randrw.0.0 exists), without my patches, fall back to\n" - "> pte mappings and do not hit this issue. \302\240With my patches applied,\n" + "> pte mappings and do not hit this issue. \303\257\302\277\302\275With my patches applied,\n" "> subsequent runs still create pmd mappings and hit this issue.\n" "\n" "I've been able to reproduce this on my test setup, and I agree that it appears\n" @@ -116,4 +116,4 @@ "see: http://www.linux-mm.org/ .\n" "Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>" -4890b686e1b6c18bab101fe692fbb42bafe732a33e4364393d6fed1ad24f3eab +7013a96c3782c3752c4cac51e95d4f53a28a27ad27860a1b843e1d422dbb007c
diff --git a/a/1.txt b/N3/1.txt index f343e18..58213f7 100644 --- a/a/1.txt +++ b/N3/1.txt @@ -5,22 +5,22 @@ On Wed, Aug 31, 2016 at 10:08:59PM +0000, Kani, Toshimitsu wrote: > > > On Tue, 2016-08-30 at 17:01 -0600, Ross Zwisler wrote: > > > > > > > > On Tue, Aug 23, 2016 at 04:04:10PM -0600, Ross Zwisler wrote: -> : +> : > > > > -> > > > Ping on this series? Any objections or comments? +> > > > Ping on this series? Any objections or comments? > > > > > > Hi Ross, > > > > > > I am seeing a major performance loss in fio mmap test with this -> > > patch-set applied. This happens with or without my patches [1] -> > > applied on top of yours. Without my patches, dax_pmd_fault() falls +> > > patch-set applied. This happens with or without my patches [1] +> > > applied on top of yours. Without my patches, dax_pmd_fault() falls > > > back to the pte handler since an mmap'ed address is not 2MB- > > > aligned. > > > > > > I have attached three test results. -> > > o rc4.log - 4.8.0-rc4 (base) -> > > o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte) -> > > o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps) +> > > o rc4.log - 4.8.0-rc4 (base) +> > > o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte) +> > > o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps) > > > > > > My test steps are as follows. > > > @@ -44,11 +44,11 @@ On Wed, Aug 31, 2016 at 10:08:59PM +0000, Kani, Toshimitsu wrote: > > > > Yep, thanks for the report. > -> I have some more observations. It seems this issue is related with pmd -> mappings after all. fio creates "randrw.0.0" file. In my setup, an -> initial test run creates pmd mappings and hits this issue. Subsequent +> I have some more observations. It seems this issue is related with pmd +> mappings after all. fio creates "randrw.0.0" file. In my setup, an +> initial test run creates pmd mappings and hits this issue. Subsequent > test runs (i.e. randrw.0.0 exists), without my patches, fall back to -> pte mappings and do not hit this issue. With my patches applied, +> pte mappings and do not hit this issue. With my patches applied, > subsequent runs still create pmd mappings and hit this issue. I've been able to reproduce this on my test setup, and I agree that it appears diff --git a/a/content_digest b/N3/content_digest index 0e598e4..e3be195 100644 --- a/a/content_digest +++ b/N3/content_digest @@ -31,22 +31,22 @@ "> > > On Tue, 2016-08-30 at 17:01 -0600, Ross Zwisler wrote:\n" "> > > > \n" "> > > > On Tue, Aug 23, 2016 at 04:04:10PM -0600, Ross Zwisler wrote:\n" - "> \302\240:\n" + "> :\n" "> > > > \n" - "> > > > Ping on this series?\302\240\302\240Any objections or comments?\n" + "> > > > Ping on this series? Any objections or comments?\n" "> > > \n" "> > > Hi Ross,\n" "> > > \n" "> > > I am seeing a major performance loss in fio mmap test with this\n" - "> > > patch-set applied. \302\240This happens with or without my patches [1]\n" - "> > > applied on top of yours. \302\240Without my patches,\302\240dax_pmd_fault() falls\n" + "> > > patch-set applied. This happens with or without my patches [1]\n" + "> > > applied on top of yours. Without my patches, dax_pmd_fault() falls\n" "> > > back to the pte handler since an mmap'ed address is not 2MB-\n" "> > > aligned.\n" "> > > \n" "> > > I have attached three test results.\n" - "> > > \302\240o rc4.log - 4.8.0-rc4 (base)\n" - "> > > \302\240o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte)\n" - "> > > \302\240o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps)\n" + "> > > o rc4.log - 4.8.0-rc4 (base)\n" + "> > > o non-pmd.log - 4.8.0-rc4 + your patchset (fall back to pte)\n" + "> > > o pmd.log - 4.8.0-rc4 + your patchset + my patchset (use pmd maps)\n" "> > > \n" "> > > My test steps are as follows.\n" "> > > \n" @@ -70,11 +70,11 @@ "> > \n" "> > Yep, thanks for the report.\n" "> \n" - "> I have some more observations. \302\240It seems this issue is related with pmd\n" - "> mappings after all. \302\240fio creates \"randrw.0.0\" file. \302\240In my setup, an\n" - "> initial test run creates pmd mappings and hits this issue. \302\240Subsequent\n" + "> I have some more observations. It seems this issue is related with pmd\n" + "> mappings after all. fio creates \"randrw.0.0\" file. In my setup, an\n" + "> initial test run creates pmd mappings and hits this issue. Subsequent\n" "> test runs (i.e. randrw.0.0 exists), without my patches, fall back to\n" - "> pte mappings and do not hit this issue. \302\240With my patches applied,\n" + "> pte mappings and do not hit this issue. With my patches applied,\n" "> subsequent runs still create pmd mappings and hit this issue.\n" "\n" "I've been able to reproduce this on my test setup, and I agree that it appears\n" @@ -116,4 +116,4 @@ "see: http://www.linux-mm.org/ .\n" "Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>" -4890b686e1b6c18bab101fe692fbb42bafe732a33e4364393d6fed1ad24f3eab +f0569820c3a136e160ee9b46f135cb3bbf5a1e4d1db3c2e57baeae10ff0eee46
diff --git a/a/1.txt b/N4/1.txt index f343e18..75e614e 100644 --- a/a/1.txt +++ b/N4/1.txt @@ -83,9 +83,3 @@ isn't comparable to my bare metal system, but it's interesting that the use of PMDs over tripled the performance in my VM. Hmm... We'll keep digging into this. Thanks again for the report. :) - --- -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/N4/content_digest index 0e598e4..fc21c96 100644 --- a/a/content_digest +++ b/N4/content_digest @@ -16,7 +16,7 @@ dan.j.williams@intel.com <dan.j.williams@intel.com> akpm@linux-foundation.org <akpm@linux-foundation.org> mawilcox@microsoft.com <mawilcox@microsoft.com> - linux-nvdimm@lists.01.org <linux-nvdimm@lists.01.org> + linux-nvdimm@lists.01.org <linux-nvdimm@ml01.01.org> linux-fsdevel@vger.kernel.org <linux-fsdevel@vger.kernel.org> jack@suse.com <jack@suse.com> tytso@mit.edu <tytso@mit.edu> @@ -108,12 +108,6 @@ "isn't comparable to my bare metal system, but it's interesting that the use of\n" "PMDs over tripled the performance in my VM. Hmm...\n" "\n" - "We'll keep digging into this. Thanks again for the report. :)\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>" + We'll keep digging into this. Thanks again for the report. :) -4890b686e1b6c18bab101fe692fbb42bafe732a33e4364393d6fed1ad24f3eab +a00be0a47f4c15d4a5d103d3052428bc58443e26551deda92801d1ff31a94873
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.