Date: Wed, 28 Apr 2004 16:53:18 -0500 (CDT) From: Mike Silbersack <silby@silby.com> To: Daniel Eischen <eischen@vigrid.com> Cc: cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/sys proc.h src/sys/kern kern_thread.c subr_sleepqueue.c Message-ID: <20040428165138.Q5009@odysseus.silby.com> In-Reply-To: <Pine.GSO.4.10.10404281719380.17691-100000@pcnet5.pcnet.com> References: <Pine.GSO.4.10.10404281719380.17691-100000@pcnet5.pcnet.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 28 Apr 2004, Daniel Eischen wrote: > > Interestingly enough, in addition to stumbling upon this problem with > > mysql, the benchmarking I'm doing for a class project also found a problem > > in the mysql client libraries. For some reasons, when selecting blobs, > > libmysql will get into a loop where it does 4 byte reads. Yes, it will > > read entire 100K objects 4 bytes at a time. I'll post about this to the > > relevant mailing lists next week... > > That sounds like a mysql bug. The threads libraries (except for > libc_r) don't do anything with read(). > > -- > Dan Eischen Apologies, I didn't mean to implicate the threading libraries in regards to this bug. The client program that's doing the dumb reads isn't threaded. I mentioned it in the same thread because I was thinking that if this client bug is slowing down MySQL's client libraries on all FreeBSD systems, then once it's fixed _and_ libpthread works well, MySQL will really fly! Mike "Silby" Silbersack
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040428165138.Q5009>