Re: Possible optimization to 51d in multithread

2019-10-24 Thread Илья Шипицин
[image: Find out More] <https://51degrees.com/emailsig.aspx> > > > > *From:* Илья Шипицин [mailto:chipits...@gmail.com] > *Sent:* 24 October 2019 08:04 > *To:* Ben Shillito > *Cc:* Willy Tarreau ; HAProxy > *Subject:* Re: Possible optimization to 51d in multit

RE: Possible optimization to 51d in multithread

2019-10-24 Thread Ben Shillito
..@1wt.eu>] Sent: 23 October 2019 07:04 To: Ben Shillito mailto:b...@51degrees.com>> Cc: HAProxy mailto:haproxy@formilux.org>> Subject: Possible optimization to 51d in multithread Hi Ben, after Brian reported the thread performance regression affecting the pattern matchings in hap

Re: Possible optimization to 51d in multithread

2019-10-24 Thread Илья Шипицин
omes to the > performance of HAProxy. > > Thanks, > > Ben Shillito > Developer > O: +44 1183 287152 > E: b...@51degrees.com > T: @51Degrees > > -Original Message- > From: Willy Tarreau [mailto:w...@1wt.eu] > Sent: 23 October 2019 07:04 > To:

Possible optimization to 51d in multithread

2019-10-23 Thread Willy Tarreau
Hi Ben, after Brian reported the thread performance regression affecting the pattern matchings in haproxy when relying on the LRU cache, I had a look at other users of the LRU cache and found that 51d.c is using it with a lock as well and may also suffer from a lack of linearity with threads.