212878 2020-06-07 02:05:48 -0700 Lazily allocate HistoricUsageData 2021-12-19 13:11:52 -0800 1 1 1 Unclassified WebKit New Bugs WebKit Nightly Build Unspecified Unspecified RESOLVED FIXED https://bugs.webkit.org/show_bug.cgi?id=233476 InRadar P2 Normal --- 1 ysuzuki ysuzuki saam sam simon.fraser webkit-bug-importer oldest_to_newest 1660045 0 ysuzuki 2020-06-07 02:05:48 -0700 Lazily allocate HistoricUsageData 1660046 1 401289 ysuzuki 2020-06-07 02:06:23 -0700 Created attachment 401289 Patch 1660047 2 401290 ysuzuki 2020-06-07 02:07:32 -0700 Created attachment 401290 Patch 1660078 3 sam 2020-06-07 08:21:41 -0700 Hey Yusuke, just so I understand a little better, what is the benefit of removing this from the __DATA section? 1660322 4 saam 2020-06-08 12:58:10 -0700 (In reply to Sam Weinig from comment #3) > Hey Yusuke, just so I understand a little better, what is the benefit of > removing this from the __DATA section? I believe the goal is to reduce dirty memory usage 1660323 5 saam 2020-06-08 12:59:40 -0700 (In reply to Saam Barati from comment #4) > (In reply to Sam Weinig from comment #3) > > Hey Yusuke, just so I understand a little better, what is the benefit of > > removing this from the __DATA section? > > I believe the goal is to reduce dirty memory usage I guess to elaborate on how I model my understanding: This will take away space from other things in DATA that could’ve theoretically fit on one page and perhaps bumping it into two. 1660326 6 ysuzuki 2020-06-08 13:02:45 -0700 (In reply to Saam Barati from comment #5) > (In reply to Saam Barati from comment #4) > > (In reply to Sam Weinig from comment #3) > > > Hey Yusuke, just so I understand a little better, what is the benefit of > > > removing this from the __DATA section? > > > > I believe the goal is to reduce dirty memory usage > > I guess to elaborate on how I model my understanding: > This will take away space from other things in DATA that could’ve > theoretically fit on one page and perhaps bumping it into two. Yes, since __DATA is per page, it is possible that we construct a page like, [<---------------------------historicUsageData-------------><-small data->] In that case, if small data gets dirty, it taints entire page dirty even if historicUsageData part is not used at all. 1660346 7 sam 2020-06-08 13:18:28 -0700 (In reply to Yusuke Suzuki from comment #6) > (In reply to Saam Barati from comment #5) > > (In reply to Saam Barati from comment #4) > > > (In reply to Sam Weinig from comment #3) > > > > Hey Yusuke, just so I understand a little better, what is the benefit of > > > > removing this from the __DATA section? > > > > > > I believe the goal is to reduce dirty memory usage > > > > I guess to elaborate on how I model my understanding: > > This will take away space from other things in DATA that could’ve > > theoretically fit on one page and perhaps bumping it into two. > > Yes, since __DATA is per page, it is possible that we construct a page like, > > > [<---------------------------historicUsageData-------------><-small data->] > > In that case, if small data gets dirty, it taints entire page dirty even if > historicUsageData part is not used at all. Interesting. Would it ever make sense to annotate these rarely used large data portions with a specific section name to allow the linker to group rarely used data together? 1825429 8 ysuzuki 2021-12-19 01:35:44 -0800 (In reply to Sam Weinig from comment #7) > (In reply to Yusuke Suzuki from comment #6) > > (In reply to Saam Barati from comment #5) > > > (In reply to Saam Barati from comment #4) > > > > (In reply to Sam Weinig from comment #3) > > > > > Hey Yusuke, just so I understand a little better, what is the benefit of > > > > > removing this from the __DATA section? > > > > > > > > I believe the goal is to reduce dirty memory usage > > > > > > I guess to elaborate on how I model my understanding: > > > This will take away space from other things in DATA that could’ve > > > theoretically fit on one page and perhaps bumping it into two. > > > > Yes, since __DATA is per page, it is possible that we construct a page like, > > > > > > [<---------------------------historicUsageData-------------><-small data->] > > > > In that case, if small data gets dirty, it taints entire page dirty even if > > historicUsageData part is not used at all. > > Interesting. Would it ever make sense to annotate these rarely used large > data portions with a specific section name to allow the linker to group > rarely used data together? It is nice! So, if it is the data we need definitely, we should do that. But at the same time, by doing heap-allocation here, this patch reduces binary size :) 1825430 9 ysuzuki 2021-12-19 01:41:03 -0800 Committed r287238 (245398@trunk): <https://commits.webkit.org/245398@trunk> 1825431 10 webkit-bug-importer 2021-12-19 01:42:19 -0800 <rdar://problem/86680604> 1825446 11 simon.fraser 2021-12-19 09:31:31 -0800 Funny, I did this same thing but found that it didn't change binary size. The __DATA/_bss section is constructed at runtime (fresh pages mapped into memory). But if it has the side effect of shuffling around other things in __DATA then maybe it can affect binary size? 1825448 12 simon.fraser 2021-12-19 09:33:30 -0800 See bug 233476. 1825476 13 ysuzuki 2021-12-19 13:11:52 -0800 (In reply to Simon Fraser (smfr) from comment #11) > Funny, I did this same thing but found that it didn't change binary size. > > The __DATA/_bss section is constructed at runtime (fresh pages mapped into > memory). But if it has the side effect of shuffling around other things in > __DATA then maybe it can affect binary size? Ah! Yes. But anyway, the original intent of this patch is avoid having dirty __DATA memory by purging large rarely used data from __DATA (as described in https://bugs.webkit.org/show_bug.cgi?id=212878#c6), and it is still held :) 401289 2020-06-07 02:06:23 -0700 2020-06-07 02:07:31 -0700 Patch bug-212878-20200607020622.patch text/plain 1610 ysuzuki U3VidmVyc2lvbiBSZXZpc2lvbjogMjYyNjk0CmRpZmYgLS1naXQgYS9Tb3VyY2UvV2ViQ29yZS9D aGFuZ2VMb2cgYi9Tb3VyY2UvV2ViQ29yZS9DaGFuZ2VMb2cKaW5kZXggNjQxMjczMjAyMmI0N2Fh NGY2MTBhZWY2Y2I3M2U3NzM3MTFlOTc0NS4uZDQ3OWQ4NThhMjU5ZDRmODgxMTNkNjc2MDkwMmY5 ZTc5ZWNmMjY5NiAxMDA2NDQKLS0tIGEvU291cmNlL1dlYkNvcmUvQ2hhbmdlTG9nCisrKyBiL1Nv dXJjZS9XZWJDb3JlL0NoYW5nZUxvZwpAQCAtMSwzICsxLDE1IEBACisyMDIwLTA2LTA3ICBZdXN1 a2UgU3V6dWtpICA8eXN1enVraUBhcHBsZS5jb20+CisKKyAgICAgICAgTGF6aWx5IGFsbG9jYXRl IEhpc3RvcmljVXNhZ2VEYXRhCisgICAgICAgIGh0dHBzOi8vYnVncy53ZWJraXQub3JnL3Nob3df YnVnLmNnaT9pZD0yMTI4NzgKKworICAgICAgICBSZXZpZXdlZCBieSBOT0JPRFkgKE9PUFMhKS4K KworICAgICAgICBUaGlzIGlzIG9ubHkgdXNlZCB3aGVuIHJlc291cmNlLW92ZXJsYXkgaXMgZW5h YmxlZC4gV2Ugc2hvdWxkIGFsbG9jYXRlIGl0IGxhemlseSBpbnN0ZWFkIG9mIHB1dHRpbmcgdGhp cyBpbiBfX0RBVEEuCisKKyAgICAgICAgKiBwYWdlL2NvY29hL1Jlc291cmNlVXNhZ2VPdmVybGF5 Q29jb2EubW06CisgICAgICAgIChXZWJDb3JlOjpoaXN0b3JpY1VzYWdlRGF0YSk6CisKIDIwMjAt MDYtMDYgIFl1c3VrZSBTdXp1a2kgIDx5c3V6dWtpQGFwcGxlLmNvbT4KIAogICAgICAgICBDcmFz aCB3aGVuIHJ1bm5pbmcgd2ViLWFwaXMgZGF0YSBjb2xsZWN0aW9uCmRpZmYgLS1naXQgYS9Tb3Vy Y2UvV2ViQ29yZS9wYWdlL2NvY29hL1Jlc291cmNlVXNhZ2VPdmVybGF5Q29jb2EubW0gYi9Tb3Vy Y2UvV2ViQ29yZS9wYWdlL2NvY29hL1Jlc291cmNlVXNhZ2VPdmVybGF5Q29jb2EubW0KaW5kZXgg ZTI2MzkzNDZiYjY0YzZmNzk3NmFjOTc0Y2E4ZGZkOWZjMGNjNTAyYS4uNzMxNmQ5YTFhZDY4YWFl MmQxM2MzZDg5MWZkMjNjNDhlYmE3ODUzYSAxMDA2NDQKLS0tIGEvU291cmNlL1dlYkNvcmUvcGFn ZS9jb2NvYS9SZXNvdXJjZVVzYWdlT3ZlcmxheUNvY29hLm1tCisrKyBiL1NvdXJjZS9XZWJDb3Jl L3BhZ2UvY29jb2EvUmVzb3VyY2VVc2FnZU92ZXJsYXlDb2NvYS5tbQpAQCAtMTg0LDggKzE4NCwx MiBAQCBIaXN0b3JpY1Jlc291cmNlVXNhZ2VEYXRhOjpIaXN0b3JpY1Jlc291cmNlVXNhZ2VEYXRh KCkKIAogc3RhdGljIEhpc3RvcmljUmVzb3VyY2VVc2FnZURhdGEmIGhpc3RvcmljVXNhZ2VEYXRh KCkKIHsKLSAgICBzdGF0aWMgTmV2ZXJEZXN0cm95ZWQ8SGlzdG9yaWNSZXNvdXJjZVVzYWdlRGF0 YT4gZGF0YTsKLSAgICByZXR1cm4gZGF0YTsKKyAgICBzdGF0aWMgSGlzdG9yaWNSZXNvdXJjZVVz YWdlRGF0YSogZGF0YSB7IG51bGxwdHIgfTsKKyAgICBzdGF0aWMgc3RkOjpvbmNlX2ZsYWcgb25j ZUtleTsKKyAgICBzdGQ6OmNhbGxfb25jZShvbmNlS2V5LCBbJl0geworICAgICAgICBkYXRhID0g bmV3IEhpc3RvcmljUmVzb3VyY2VVc2FnZURhdGE7CisgICAgfSk7CisgICAgcmV0dXJuICpkYXRh OwogfQogCiBzdGF0aWMgdm9pZCBhcHBlbmREYXRhVG9IaXN0b3J5KGNvbnN0IFJlc291cmNlVXNh Z2VEYXRhJiBkYXRhKQo= 401290 2020-06-07 02:07:32 -0700 2020-06-08 12:58:25 -0700 Patch bug-212878-20200607020731.patch text/plain 1809 ysuzuki U3VidmVyc2lvbiBSZXZpc2lvbjogMjYyNjk0CmRpZmYgLS1naXQgYS9Tb3VyY2UvV2ViQ29yZS9D aGFuZ2VMb2cgYi9Tb3VyY2UvV2ViQ29yZS9DaGFuZ2VMb2cKaW5kZXggNjQxMjczMjAyMmI0N2Fh NGY2MTBhZWY2Y2I3M2U3NzM3MTFlOTc0NS4uZDQ3OWQ4NThhMjU5ZDRmODgxMTNkNjc2MDkwMmY5 ZTc5ZWNmMjY5NiAxMDA2NDQKLS0tIGEvU291cmNlL1dlYkNvcmUvQ2hhbmdlTG9nCisrKyBiL1Nv dXJjZS9XZWJDb3JlL0NoYW5nZUxvZwpAQCAtMSwzICsxLDE1IEBACisyMDIwLTA2LTA3ICBZdXN1 a2UgU3V6dWtpICA8eXN1enVraUBhcHBsZS5jb20+CisKKyAgICAgICAgTGF6aWx5IGFsbG9jYXRl IEhpc3RvcmljVXNhZ2VEYXRhCisgICAgICAgIGh0dHBzOi8vYnVncy53ZWJraXQub3JnL3Nob3df YnVnLmNnaT9pZD0yMTI4NzgKKworICAgICAgICBSZXZpZXdlZCBieSBOT0JPRFkgKE9PUFMhKS4K KworICAgICAgICBUaGlzIGlzIG9ubHkgdXNlZCB3aGVuIHJlc291cmNlLW92ZXJsYXkgaXMgZW5h YmxlZC4gV2Ugc2hvdWxkIGFsbG9jYXRlIGl0IGxhemlseSBpbnN0ZWFkIG9mIHB1dHRpbmcgdGhp cyBpbiBfX0RBVEEuCisKKyAgICAgICAgKiBwYWdlL2NvY29hL1Jlc291cmNlVXNhZ2VPdmVybGF5 Q29jb2EubW06CisgICAgICAgIChXZWJDb3JlOjpoaXN0b3JpY1VzYWdlRGF0YSk6CisKIDIwMjAt MDYtMDYgIFl1c3VrZSBTdXp1a2kgIDx5c3V6dWtpQGFwcGxlLmNvbT4KIAogICAgICAgICBDcmFz aCB3aGVuIHJ1bm5pbmcgd2ViLWFwaXMgZGF0YSBjb2xsZWN0aW9uCmRpZmYgLS1naXQgYS9Tb3Vy Y2UvV2ViQ29yZS9wYWdlL2NvY29hL1Jlc291cmNlVXNhZ2VPdmVybGF5Q29jb2EubW0gYi9Tb3Vy Y2UvV2ViQ29yZS9wYWdlL2NvY29hL1Jlc291cmNlVXNhZ2VPdmVybGF5Q29jb2EubW0KaW5kZXgg ZTI2MzkzNDZiYjY0YzZmNzk3NmFjOTc0Y2E4ZGZkOWZjMGNjNTAyYS4uNTQyZTU5ODhlNzFjNzI1 NTk5MzIxM2QwZjJjNWJlNTc2Yzk0YTg1OSAxMDA2NDQKLS0tIGEvU291cmNlL1dlYkNvcmUvcGFn ZS9jb2NvYS9SZXNvdXJjZVVzYWdlT3ZlcmxheUNvY29hLm1tCisrKyBiL1NvdXJjZS9XZWJDb3Jl L3BhZ2UvY29jb2EvUmVzb3VyY2VVc2FnZU92ZXJsYXlDb2NvYS5tbQpAQCAtMTQ2LDYgKzE0Niw3 IEBAIHN0cnVjdCBIaXN0b3JpY01lbW9yeUNhdGVnb3J5SW5mbyB7CiB9OwogCiBzdHJ1Y3QgSGlz dG9yaWNSZXNvdXJjZVVzYWdlRGF0YSB7CisgICAgV1RGX01BS0VfU1RSVUNUX0ZBU1RfQUxMT0NB VEVEOwogICAgIEhpc3RvcmljUmVzb3VyY2VVc2FnZURhdGEoKTsKIAogICAgIFJpbmdCdWZmZXI8 ZmxvYXQ+IGNwdTsKQEAgLTE4NCw4ICsxODUsMTIgQEAgSGlzdG9yaWNSZXNvdXJjZVVzYWdlRGF0 YTo6SGlzdG9yaWNSZXNvdXJjZVVzYWdlRGF0YSgpCiAKIHN0YXRpYyBIaXN0b3JpY1Jlc291cmNl VXNhZ2VEYXRhJiBoaXN0b3JpY1VzYWdlRGF0YSgpCiB7Ci0gICAgc3RhdGljIE5ldmVyRGVzdHJv eWVkPEhpc3RvcmljUmVzb3VyY2VVc2FnZURhdGE+IGRhdGE7Ci0gICAgcmV0dXJuIGRhdGE7Cisg ICAgc3RhdGljIEhpc3RvcmljUmVzb3VyY2VVc2FnZURhdGEqIGRhdGEgeyBudWxscHRyIH07Cisg ICAgc3RhdGljIHN0ZDo6b25jZV9mbGFnIG9uY2VLZXk7CisgICAgc3RkOjpjYWxsX29uY2Uob25j ZUtleSwgWyZdIHsKKyAgICAgICAgZGF0YSA9IG5ldyBIaXN0b3JpY1Jlc291cmNlVXNhZ2VEYXRh OworICAgIH0pOworICAgIHJldHVybiAqZGF0YTsKIH0KIAogc3RhdGljIHZvaWQgYXBwZW5kRGF0 YVRvSGlzdG9yeShjb25zdCBSZXNvdXJjZVVzYWdlRGF0YSYgZGF0YSkK