Date: Wed, 18 Aug 2010 23:17:56 +0400 From: pluknet <pluknet@gmail.com> To: Kostik Belousov <kostikbel@gmail.com> Cc: FreeBSD Current <freebsd-current@freebsd.org> Subject: Re: LOR on nfs: vfs_vnops.c:301 kern_descrip.c:1580 Message-ID: <AANLkTikwiTsiZtp5Zej8yDsR2b4%2B=TSL1oD-M_uRFqBd@mail.gmail.com> In-Reply-To: <AANLkTi=V8bumpGKgi1aLXxhJkdKdpG1jfyrcXbMyc3Yw@mail.gmail.com> References: <AANLkTimJ=d06D2z24QyRQ98zEa1Pemk4=vkNGLNiX90N@mail.gmail.com> <AANLkTi=22WWy8Z5VWqri1p70iRzyocD9bWvNHwJavZ%2Bj@mail.gmail.com> <20100816185456.GU2396@deviant.kiev.zoral.com.ua> <AANLkTimfZ=UCiX9eo9XCwcROwViFCxJoB-rD1JxdAt2B@mail.gmail.com> <20100817160445.GO2396@deviant.kiev.zoral.com.ua> <AANLkTimyk0ZUnHpxxJuJtTya2U3npj_5Bm8brmwHfzr3@mail.gmail.com> <AANLkTimXxF0US60NsbOV_HvRrib7SJWmrLqpEpznPTxB@mail.gmail.com> <20100818134623.GU2396@deviant.kiev.zoral.com.ua> <AANLkTi=V8bumpGKgi1aLXxhJkdKdpG1jfyrcXbMyc3Yw@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 18 August 2010 23:11, pluknet <pluknet@gmail.com> wrote: > On 18 August 2010 17:46, Kostik Belousov <kostikbel@gmail.com> wrote: >> On Wed, Aug 18, 2010 at 02:43:19PM +0400, pluknet wrote: >>> On 18 August 2010 12:07, pluknet <pluknet@gmail.com> wrote: >>> > On 17 August 2010 20:04, Kostik Belousov <kostikbel@gmail.com> wrote: >>> > >>> >> >>> >> Also please take a note of the John' suggestion to use the taskqueue= . >>> > >>> > I decided to go this road. Thank you both. >>> > Now I do nfs buildkernel survive and prepare some benchmark results. >>> > >>> >>> So, I modified the patch to defer proc_create() with taskqueue(9). >>> Below is `time make -j5 buildkernel WITHOUT_MODULES=3Dyes` perf. evalua= tion. >>> Done on 4-way CPU on clean /usr/obj with /usr/src & /usr/obj both >>> nfs-mounted over 1Gbit LAN. >>> >>> clean old >>> 1137.985u 239.411s 7:42.15 298.0% =A0 =A0 =A0 6538+2133k 87+43388io 226= pf+0w >>> >>> clean new >>> 1134.755u 240.032s 7:41.25 298.0% =A0 =A0 =A0 6553+2133k 87+43367io 224= pf+0w >>> >>> Patch needs polishing, though it generally works. >>> Not sure if shep_chan (or whatever name it will get) needs locking. >> As I said yesterday, if several requests to create nfsiod coming one >> after another, you would loose all but the last. >> >> You should put the requests into the list, probably protected by >> nfs_iod_mtx. >> > > How about this patch? Still several things to ask. > 1) I used malloc instance w/ M_NOWAIT, since it's called with nfs_iod_mtx= held. > 2) Probably busy/done gymnastics is a wrong mess. Your help is appreciate= d. > 3) if (1) is fine, is it right to use fail: logic (i.e. set > NFSIOD_NOT_AVAILABLE) > on memory shortage? Not tested. > > There are debug printf() left intentionally to see how 3 contexts run und= er load > to each other. I attached these messages as well if that makes sense. > Ah, yes. Sorry, forgot about that. This is from last run: 1139.225u 239.873s 7:44.90 296.6% 6524+2130k 77+43153io 220pf+0w --=20 wbr, pluknet
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTikwiTsiZtp5Zej8yDsR2b4%2B=TSL1oD-M_uRFqBd>