[
https://issues.apache.org/jira/browse/HBASE-29688?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18033324#comment-18033324
]
Charles Connell edited comment on HBASE-29688 at 10/27/25 8:43 PM:
-------------------------------------------------------------------
I've
[benchmarked|https://gist.github.com/charlesconnell/5a9d5a8692b90e37306bacbf744dc106]
the difference between the UnsafeComparer and my proposed replacement:
{noformat}
# Mac M1 Max
# JMH version: 1.37
# VM version: JDK 25, OpenJDK 64-Bit Server VM, 25+36-LTS
# VM options: -Dsun.misc.unsafe.memory.access=allow
ByteArrayCompareBenchmark.unsafeComparator 9 thrpt 5
679373509.181 ± 17561676.662 ops/s
ByteArrayCompareBenchmark.unsafeComparator 33 thrpt 5
412046005.567 ± 25551650.942 ops/s
ByteArrayCompareBenchmark.unsafeComparator 257 thrpt 5
169960886.832 ± 9793752.909 ops/s
ByteArrayCompareBenchmark.varHandleComparator 9 thrpt 5
487103012.003 ± 5842773.421 ops/s
ByteArrayCompareBenchmark.varHandleComparator 33 thrpt 5
312281408.502 ± 11319895.597 ops/s
ByteArrayCompareBenchmark.varHandleComparator 257 thrpt 5
133557753.922 ± 4077060.935 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 9 thrpt 5
474057917.767 ± 29268632.793 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 33 thrpt 5
312999998.024 ± 5646232.939 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 257 thrpt 5
132833531.369 ± 6260749.122 ops/s
# i7ie (Intel Xeon Platinum 8559C) (Emerald Rapids)
# JMH version: 1.37
# VM version: JDK 25, OpenJDK 64-Bit Server VM, 25+36-LTS
# VM options: -Dsun.misc.unsafe.memory.access=allow
ByteArrayCompareBenchmark.unsafeComparator 9 thrpt 5
318417708.508 ± 6072564.489 ops/s
ByteArrayCompareBenchmark.unsafeComparator 33 thrpt 5
175300534.835 ± 3409995.305 ops/s
ByteArrayCompareBenchmark.unsafeComparator 257 thrpt 5
82865593.629 ± 1073498.160 ops/s
ByteArrayCompareBenchmark.varHandleComparator 9 thrpt 5
255940141.048 ± 7105789.861 ops/s
ByteArrayCompareBenchmark.varHandleComparator 33 thrpt 5
134540416.892 ± 1854513.331 ops/s
ByteArrayCompareBenchmark.varHandleComparator 257 thrpt 5
54486457.058 ± 4494699.622 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 9 thrpt 5
255147221.627 ± 6375799.084 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 33 thrpt 5
132934229.619 ± 3607628.153 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 257 thrpt 5
54864065.799 ± 1420237.829 ops/s
{noformat}
There is definitely a penalty in switching to VarHandle. However, since Unsafe
is going away eventually, I don't think there is really any choice but to stop
using Unsafe.
was (Author: charlesconnell):
I've
[benchmarked|https://gist.github.com/charlesconnell/5a9d5a8692b90e37306bacbf744dc106]
the difference between the UnsafeComparer and my proposed replacement:
{code}
# Mac M1 Max
# JMH version: 1.37
# VM version: JDK 25, OpenJDK 64-Bit Server VM, 25+36-LTS
# VM options: -Dsun.misc.unsafe.memory.access=allow
ByteArrayCompareBenchmark.unsafeComparator 9 thrpt 5
679373509.181 ± 17561676.662 ops/s
ByteArrayCompareBenchmark.unsafeComparator 33 thrpt 5
412046005.567 ± 25551650.942 ops/s
ByteArrayCompareBenchmark.unsafeComparator 257 thrpt 5
169960886.832 ± 9793752.909 ops/s
ByteArrayCompareBenchmark.varHandleComparator 9 thrpt 5
487103012.003 ± 5842773.421 ops/s
ByteArrayCompareBenchmark.varHandleComparator 33 thrpt 5
312281408.502 ± 11319895.597 ops/s
ByteArrayCompareBenchmark.varHandleComparator 257 thrpt 5
133557753.922 ± 4077060.935 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 9 thrpt 5
474057917.767 ± 29268632.793 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 33 thrpt 5
312999998.024 ± 5646232.939 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 257 thrpt 5
132833531.369 ± 6260749.122 ops/s
# i7ie (Intel Xeon Platinum 8559C) (Emerald Rapids)
# JMH version: 1.37
# VM version: JDK 25, OpenJDK 64-Bit Server VM, 25+36-LTS
# VM options: -Dsun.misc.unsafe.memory.access=allow
ByteArrayCompareBenchmark.unsafeComparator 9 thrpt 5
318417708.508 ± 6072564.489 ops/s
ByteArrayCompareBenchmark.unsafeComparator 33 thrpt 5
175300534.835 ± 3409995.305 ops/s
ByteArrayCompareBenchmark.unsafeComparator 257 thrpt 5
82865593.629 ± 1073498.160 ops/s
ByteArrayCompareBenchmark.varHandleComparator 9 thrpt 5
255940141.048 ± 7105789.861 ops/s
ByteArrayCompareBenchmark.varHandleComparator 33 thrpt 5
134540416.892 ± 1854513.331 ops/s
ByteArrayCompareBenchmark.varHandleComparator 257 thrpt 5
54486457.058 ± 4494699.622 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 9 thrpt 5
255147221.627 ± 6375799.084 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 33 thrpt 5
132934229.619 ± 3607628.153 ops/s
ByteArrayCompareBenchmark.varHandleLittleEndianComparator 257 thrpt 5
54864065.799 ± 1420237.829 ops/s
{code}
There is definitely a penalty in switching to VarHandle. However, since Unsafe
is going away eventually, I don't think there is really any choice but to stop
using Unsafe.
> Use VarHandle instead of Unsafe where possible in 3.x
> -----------------------------------------------------
>
> Key: HBASE-29688
> URL: https://issues.apache.org/jira/browse/HBASE-29688
> Project: HBase
> Issue Type: Improvement
> Reporter: Charles Connell
> Assignee: Charles Connell
> Priority: Minor
> Labels: pull-request-available
>
> Java offers {{VarHandle}} to facilitate fast access to memory, in place of
> the {{Unsafe#get*}} and {{Unsafe#put*}} methods. It can be used as almost a
> drop-in replacement, and the performance is similar. {{VarHandle}} was
> introduced in Java 9. HBase 2.x supports Java 8, so we cannot use
> {{VarHandle}} in 2.x releases, but we can prepare to use it in 3.x releases,
> which target Java 17. This will eliminate most uses of {{Unsafe}} in HBase.
> Remaining uses of {{Unsafe}} are for copying memory regions. There is an
> alternative available for that, {{MemorySegment}}, that is available in Java
> 22 and higher, but we'll tackle that much later.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
