Update jemalloc to version 5.2.1

[fwyzard]

This release is primarily about Windows. A critical virtual memory leak is resolved on all Windows platforms.
The regression was present in all releases since 5.0.0.

Bug fixes:

• Fix a severe virtual memory leak on Windows. This regression was first released in 5.0.0.
• Fix size 0 handling in posix_memalign(). This regression was first released in 5.2.0.
• Fix the prof_log unit test which may observe unexpected backtraces from compiler optimizations. The test was first added in 5.2.0.
• Fix the declaration of the extent_avail tree. This regression was first released in 5.1.0.
• Fix an incorrect reference in jeprof. This functionality was first released in 3.0.0.
• Fix an assertion on the deallocation fast-path. This regression was first released in 5.2.0.
• Fix the TLS_MODEL attribute in headers. This regression was first released in 5.0.0.

Optimizations and refactors:

• Implement opt.retain on Windows and enable by default on 64-bit.
• Optimize away a branch on the operator delete path.
• Add format annotation to the format generator function.
• Refactor and improve the size class header generation.
• Remove best fit.
• Avoid blocking on background thread locks for stats.

[cmsbuild]

A new Pull Request was created by @fwyzard (Andrea Bocci) for branch IB/CMSSW_11_1_X/master.

@cmsbuild, @smuzaffar, @mrodozov, @tulamor can you please review it and eventually sign? Thanks.
cms-bot commands are listed here

[smuzaffar]

please test

[cmsbuild]

The tests are being triggered in jenkins.
https://cmssdt.cern.ch/jenkins/job/ib-run-pr-tests/6346/console Started: 2020/05/15 23:34

[cmsbuild]

+1
Tested at: 4c4c5f2
https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-471b0a/6346/summary.html
CMSSW: CMSSW_11_1_X_2020-05-15-1100
SCRAM_ARCH: slc7_amd64_gcc820

[cmsbuild]

Comparison job queued.

[cmsbuild]

Comparison is ready
https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-471b0a/6346/summary.html

Comparison Summary:

• No significant changes to the logs found
• Reco comparison results: 4 differences found in the comparisons
• DQMHistoTests: Total files compared: 35
• DQMHistoTests: Total histograms compared: 2702162
• DQMHistoTests: Total failures: 17
• DQMHistoTests: Total nulls: 0
• DQMHistoTests: Total successes: 2701826
• DQMHistoTests: Total skipped: 319
• DQMHistoTests: Total Missing objects: 0
• DQMHistoSizes: Histogram memory added: 0.0 KiB( 34 files compared)
• Checked 150 log files, 16 edm output root files, 35 DQM output files

[smuzaffar]

+externals

[cmsbuild]

This pull request is fully signed and it will be integrated in one of the next IB/CMSSW_11_1_X/master IBs (tests are also fine). This pull request will now be reviewed by the release team before it's merged. @silviodonato, @dpiparo (and backports should be raised in the release meeting by the corresponding L2)

[fwyzard]

FYI, here is a comparison of the full-node HLT performance using jemalloc 5.2.0 (current the version in CMSSW and standalone), jemalloc 5.2.1, and the latter with some additional options:

We might say that 5.2.1 is slightly better than 5.2.0, but it doesn't seem statistically significant.

Enabling "heap profiling" (even if we don't use it) has a slight hit.
My "peal memory" patches (jemalloc/jemalloc#1176, rebased on 5.2.1) don't seem to give any degradation in performance.