why after increase the hash table partitions, TPMC decrease - Mailing list pgsql-hackers

From Xiaoyulei
Subject why after increase the hash table partitions, TPMC decrease
Date
Msg-id E8870A2F6A4B1045B1C292B77EAB207C5BA392E6@SZXEMA501-MBX.china.huawei.com
Whole thread Raw
Responses Re: why after increase the hash table partitions, TPMC decrease
Re: why after increase the hash table partitions, TPMC decrease
List pgsql-hackers
<div class="WordSection1"><p class="MsoNormal"><span lang="EN-US"> </span><p class="MsoNormal"><span lang="EN-US">We
usebenchmarksql to start tpcc test in postgresql 9.3.3.</span><p class="MsoNormal"><span lang="EN-US">Before test we
setbenchmarksql client number about 800. And we increase the hash partitions from 16 to 1024 , in order to reduce
the hashpartition locks competition.</span><p class="MsoNormal"><span lang="EN-US">We expect that after increase the
numberof partitions, reduces lock competition, TPMC should be increased. But the test results on the contrary, after
modifiedto 1024, TPMC did not increase, but decrease. </span><p class="MsoNormal"><span lang="EN-US">Why such
result?</span><pclass="MsoNormal"><span lang="EN-US"> </span><p class="MsoNormal"><span lang="EN-US">We modify the
followingmacro definition:</span><p class="MsoNormal"><span lang="EN-US">NUM_BUFFER_PARTITIONS 1024</span><p
class="MsoNormal"><spanlang="EN-US">LOG2_NUM_PREDICATELOCK_PARTITIONS 10</span><p class="MsoNormal"><span
lang="EN-US">LOG2_NUM_LOCK_PARTITIONS10</span><p class="MsoNormal"><span lang="EN-US"> </span></div> 

pgsql-hackers by date:

Previous
From: Kyotaro HORIGUCHI
Date:
Subject: Re: How about a proper TEMPORARY TABLESPACE?
Next
From: Fabien COELHO
Date:
Subject: Re: PL/PgSQL: RAISE and the number of parameters