Date: 16 Oct 2001 19:57:32 +0200 From: Dag-Erling Smorgrav <des@ofug.org> To: John Baldwin <jhb@FreeBSD.org> Cc: cvs-all@FreeBSD.ORG, cvs-committers@FreeBSD.ORG, Bruce Evans <bde@zeta.org.au>, Matthew Dillon <dillon@apollo.backplane.com> Subject: Re: cvs commit: src/sys/vm vnode_pager.c Message-ID: <xzpzo6rxyb7.fsf@flood.ping.uio.no> In-Reply-To: <XFMail.011016103432.jhb@FreeBSD.org> References: <XFMail.011016103432.jhb@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
John Baldwin <jhb@FreeBSD.org> writes:
> How about turning off INVARIANTS and WITNESS and seeing if it does
> better? Witness did become more expensive when I made it work for
> reader/writer locks on May 4 as it has to manage a list of lock
> instances instead of embedding the list inside the lock object
> itself.
May 4 is about a month and a half before I started seeing these
problems, and the profiling data show that witness code and assertions
account for less than 4% of CPU time. Here are some of the pertinent
excerpts from the call graph:
[2] 88.0 32.31 0.03 1168605 _mtx_unlock_spin_flags <cycle 1> [2]
0.03 0.00 1168605/1720935 _mtx_assert [86]
1168605 witness_unlock <cycle 1> [37]
[...]
1168605 _mtx_unlock_spin_flags <cycle 1> [2]
0.00 0.00 16/1046526 mtx_destroy [20]
0.00 0.00 56/1046526 _sx_xunlock [223]
0.00 0.00 139/1046526 _sx_sunlock [152]
14.59 0.02 465448/1046526 _mtx_unlock_flags [8]
[37] 0.6 0.20 0.00 1634264 witness_unlock <cycle 1> [37]
68406 witness_lock_list_free <cycle 1> [267]
[...]
0.01 0.00 465448/1720935 _mtx_unlock_flags [8]
0.03 0.00 1168605/1720935 _mtx_unlock_spin_flags <cycle 1> [2]
[86] 0.1 0.05 0.00 1720935 _mtx_assert [86]
Out of 32.31 seconds spent in _mtx_unlock_spin_flags() and its
descendents, only about 0.25 seconds were spent in witness and
assertion code.
DES
--
Dag-Erling Smorgrav - des@ofug.org
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?xzpzo6rxyb7.fsf>
