171019 2017-04-19 16:02:17 -0700 Tune GC related JSC options for iOS 2017-04-19 16:49:58 -0700 1 1 1 Unclassified WebKit JavaScriptCore WebKit Nightly Build Unspecified Unspecified RESOLVED FIXED InRadar P2 Normal --- 1 msaboff msaboff buildbot fpizlo jfbastien keith_miller mark.lam saam oldest_to_newest 1298870 0 msaboff 2017-04-19 16:02:17 -0700 Empirical tests show that iOS devices perform better with the options values overridden for a smaller number of cores in Options.cpp:overrideDefaults(). These are the options in question: Options::maximumMutatorUtilization() = 0.6; Options::concurrentGCMaxHeadroom() = 1.4; Options::minimumGCPauseMS() = 1; Options::useStochasticMutatorScheduler() = false; <rdar://problem/31718721> 1298872 1 307517 msaboff 2017-04-19 16:05:29 -0700 Created attachment 307517 Patch 1298878 2 307517 mark.lam 2017-04-19 16:14:23 -0700 Comment on attachment 307517 Patch r=me 1298879 3 307517 jfbastien 2017-04-19 16:14:56 -0700 Comment on attachment 307517 Patch View in context: https://bugs.webkit.org/attachment.cgi?id=307517&action=review r=me > Source/JavaScriptCore/runtime/Options.cpp:335 > + { Would it be better to duplicate the block below for iOS and not iOS, or do we expect the tuning parameters to stay the same for both (only the condition above changes)? 1298883 4 msaboff 2017-04-19 16:20:04 -0700 (In reply to JF Bastien from comment #3) > Comment on attachment 307517 [details] > Patch > > View in context: > https://bugs.webkit.org/attachment.cgi?id=307517&action=review > > r=me > > > Source/JavaScriptCore/runtime/Options.cpp:335 > > + { > > Would it be better to duplicate the block below for iOS and not iOS, or do > we expect the tuning parameters to stay the same for both (only the > condition above changes)? I opted to do it this way since these are all GC related and don't expect them to change. 1298889 5 msaboff 2017-04-19 16:23:41 -0700 Committed r215539: <http://trac.webkit.org/changeset/215539> 1298913 6 307517 fpizlo 2017-04-19 16:49:58 -0700 Comment on attachment 307517 Patch R=me too 307517 2017-04-19 16:05:29 -0700 2017-04-19 16:14:23 -0700 Patch 171019.patch text/plain 1229 msaboff SW5kZXg6IFNvdXJjZS9KYXZhU2NyaXB0Q29yZS9DaGFuZ2VMb2cKPT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PQotLS0gU291 cmNlL0phdmFTY3JpcHRDb3JlL0NoYW5nZUxvZwkocmV2aXNpb24gMjE1NTM2KQorKysgU291cmNl L0phdmFTY3JpcHRDb3JlL0NoYW5nZUxvZwkod29ya2luZyBjb3B5KQpAQCAtMSwzICsxLDE1IEBA CisyMDE3LTA0LTE5ICBNaWNoYWVsIFNhYm9mZiAgPG1zYWJvZmZAYXBwbGUuY29tPgorCisgICAg ICAgIFR1bmUgR0MgcmVsYXRlZCBKU0Mgb3B0aW9ucyBmb3IgaU9TCisgICAgICAgIGh0dHBzOi8v YnVncy53ZWJraXQub3JnL3Nob3dfYnVnLmNnaT9pZD0xNzEwMTkKKworICAgICAgICBSZXZpZXdl ZCBieSBOT0JPRFkgKE9PUFMhKS4KKworICAgICAgICBBbHdheXMgc2V0IHRoZXNlIEdDIG9wdGlv bnMgb24gaU9TLgorCisgICAgICAgICogcnVudGltZS9PcHRpb25zLmNwcDoKKyAgICAgICAgKEpT Qzo6b3ZlcnJpZGVEZWZhdWx0cyk6CisKIDIwMTctMDQtMTkgIEpGIEJhc3RpZW4gIDxqZmJhc3Rp ZW5AYXBwbGUuY29tPgogCiAgICAgICAgIFdlYkFzc2VtYmx5OiBmYXN0IG1lbW9yeSBjbGVhbnVw cwpJbmRleDogU291cmNlL0phdmFTY3JpcHRDb3JlL3J1bnRpbWUvT3B0aW9ucy5jcHAKPT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09 PT09PQotLS0gU291cmNlL0phdmFTY3JpcHRDb3JlL3J1bnRpbWUvT3B0aW9ucy5jcHAJKHJldmlz aW9uIDIxNTQ3MSkKKysrIFNvdXJjZS9KYXZhU2NyaXB0Q29yZS9ydW50aW1lL09wdGlvbnMuY3Bw CSh3b3JraW5nIGNvcHkpCkBAIC0zMjksNyArMzI5LDEwIEBAIHN0YXRpYyB2b2lkIHNjYWxlSklU UG9saWN5KCkKIAogc3RhdGljIHZvaWQgb3ZlcnJpZGVEZWZhdWx0cygpCiB7Ci0gICAgaWYgKFdU Rjo6bnVtYmVyT2ZQcm9jZXNzb3JDb3JlcygpIDwgNCkgeworI2lmICFQTEFURk9STShJT1MpCisg ICAgaWYgKFdURjo6bnVtYmVyT2ZQcm9jZXNzb3JDb3JlcygpIDwgNCkKKyNlbmRpZgorICAgIHsK ICAgICAgICAgT3B0aW9uczo6bWF4aW11bU11dGF0b3JVdGlsaXphdGlvbigpID0gMC42OwogICAg ICAgICBPcHRpb25zOjpjb25jdXJyZW50R0NNYXhIZWFkcm9vbSgpID0gMS40OwogICAgICAgICBP cHRpb25zOjptaW5pbXVtR0NQYXVzZU1TKCkgPSAxOwo=