ZRE: Protect syscache from bloating with negative cache entries

From: "Tsunakawa, Takayuki" <tsunakawa(dot)takay(at)jp(dot)fujitsu(dot)com>
To: 'Tomas Vondra' <tomas(dot)vondra(at)2ndquadrant(dot)com>, 'Kyotaro HORIGUCHI' <horiguchi(dot)kyotaro(at)lab(dot)ntt(dot)co(dot)jp>
Cc: "alvherre(at)2ndquadrant(dot)com" <alvherre(at)2ndquadrant(dot)com>, "bruce(at)momjian(dot)us" <bruce(at)momjian(dot)us>, "andres(at)anarazel(dot)de" <andres(at)anarazel(dot)de>, "robertmhaas(at)gmail(dot)com" <robertmhaas(at)gmail(dot)com>, "tgl(at)sss(dot)pgh(dot)pa(dot)us" <tgl(at)sss(dot)pgh(dot)pa(dot)us>, "Ideriha, Takeshi" <ideriha(dot)takeshi(at)jp(dot)fujitsu(dot)com>, "pgsql-hackers(at)lists(dot)postgresql(dot)org" <pgsql-hackers(at)lists(dot)postgresql(dot)org>, "michael(dot)paquier(at)gmail(dot)com" <michael(dot)paquier(at)gmail(dot)com>, "david(at)pgmasters(dot)net" <david(at)pgmasters(dot)net>, "craig(at)2ndquadrant(dot)com" <craig(at)2ndquadrant(dot)com>
Subject: ZRE: Protect syscache from bloating with negative cache entries
Date: 2019-02-20 00:22:15
Message-ID: 0A3221C70F24FB45833433255569204D1FB9DE8A@G01JPEXMBYT05
Views: Raw Message | Whole Thread | Download mbox | Resend email
Lists: pgsql-hackers

From: Tomas Vondra [mailto:tomas(dot)vondra(at)2ndquadrant(dot)com]
> 0.7% may easily be just a noise, possibly due to differences in layout
> of the binary. How many runs? What was the variability of the results
> between runs? What hardware was this tested on?

3 runs, with the variability of about +-2%. Luckly, all those three runs (incidentally?) showed slight performance decrease with the patched version. The figures I wrote are the highest ones.

The hardware is, a very poor man's VM:
CPU: 4 core Intel(R) Xeon(R) CPU E7-4890 v2 @ 2.80GHz

> FWIW I doubt tests with such small small schema are proving anything -
> the cache/lists are likely tiny. That's why I tested with much larger
> number of relations.

Yeah, it requires many relations to test the repeated catcache eviction and new entry creation, which would show the need to increase catalog_cache_max_size for users. I tested with small number of relations to see the impact of additional processing while the catcache is not full -- memory accounting and catcache LRU chain maintenance.

Takayuki Tsunakawa

Browse pgsql-hackers by date

  From Date Subject
Next Message RSR999GMAILCOM 2019-02-20 00:27:02 Using old master as new replica after clean switchover
Previous Message Ideriha, Takeshi 2019-02-20 00:02:19 RE: Protect syscache from bloating with negative cache entries