Date: Tue, 1 Nov 2016 14:29:13 -0700 From: Jason Harmening <jason.harmening@gmail.com> To: freebsd-stable@freebsd.org Subject: Re: huge nanosleep variance on 11-stable Message-ID: <6167392c-c37a-6e39-aa22-ca45435d6088@gmail.com> In-Reply-To: <c88341e2-4c52-ed3c-a469-6446da4415f4@gmail.com> References: <c88341e2-4c52-ed3c-a469-6446da4415f4@gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --HDJ66P9oeeKbWwFf87EVABbhlNgJwSWjQ Content-Type: multipart/mixed; boundary="CwVNp2n6VHORNLW5VDPT3ugoQViEouw1S"; protected-headers="v1" From: Jason Harmening <jason.harmening@gmail.com> To: freebsd-stable@freebsd.org Message-ID: <6167392c-c37a-6e39-aa22-ca45435d6088@gmail.com> Subject: Re: huge nanosleep variance on 11-stable References: <c88341e2-4c52-ed3c-a469-6446da4415f4@gmail.com> In-Reply-To: <c88341e2-4c52-ed3c-a469-6446da4415f4@gmail.com> --CwVNp2n6VHORNLW5VDPT3ugoQViEouw1S Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable repro code is at http://pastebin.com/B68N4AFY if anyone's interested. On 11/01/16 13:58, Jason Harmening wrote: > Hi everyone, >=20 > I recently upgraded my main amd64 server from 10.3-stable (r302011) to > 11.0-stable (r308099). It went smoothly except for one big issue: > certain applications (but not the system as a whole) respond very > sluggishly, and video playback of any kind is extremely choppy. >=20 > The system is under very light load, and I see no evidence of abnormal > interrupt latency or interrupt load. More interestingly, if I place th= e > system under full load (~0.0% idle) the problem *disappears* and > playback/responsiveness are smooth and quick. >=20 > Running ktrace on some of the affected apps points me at the problem: > huge variance in the amount of time spent in the nanosleep system call.= > A sleep of, say, 5ms might take anywhere from 5ms to ~500ms from entry > to return of the syscall. OTOH, anything CPU-bound or that waits on > condvars or I/O interrupts seems to work fine, so this doesn't seem to > be an issue with overall system latency. >=20 > I can repro this with a simple program that just does a 3ms usleep in a= > tight loop (i.e. roughly the amount of time a video player would sleep > between frames @ 30fps). At light load ktrace will show the huge > nanosleep variance; under heavy load every nanosleep will complete in > almost exactly 3ms. >=20 > FWIW, I don't see this on -current, although right now all my -current > images are VMs on different HW so that might not mean anything. I'm no= t > aware of any recent timer- or scheduler- specific changes, so I'm > wondering if perhaps the recent IPI or taskqueue changes might be > somehow to blame. >=20 > I'm not especially familiar w/ the relevant parts of the kernel, so any= > guidance on where I should focus my debugging efforts would be much > appreciated. >=20 > Thanks, > Jason >=20 --CwVNp2n6VHORNLW5VDPT3ugoQViEouw1S-- --HDJ66P9oeeKbWwFf87EVABbhlNgJwSWjQ Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- iQF8BAEBCgBmBQJYGQkpXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRENkY3MTQyREU0MTU4MTgyRkZDNUU2ODVC QjlGOEJGOTkyODQxRDFCAAoJELufi/mShB0bC1sH/3wywXoqkh+fmPZZL8D3TZlc L5jH7AOdQyy7AB+KDhEeJqxalA/yGulquLC9gqaDLDheKjEJf7SCCzgsZ/s9lzh0 cC705ux+kUkGOhHAtOG+r0OVMmw1PMPJrlkg67OC9qUVKs2sG45BVinl5fB0CJWG J7VfkI3471mnozkLUrwpox/R5g2mjPOI/f8XzXLxyiYz9Fuc+jFNREoqdCPv5aco VhHY7Pg2Wif11A77LrG+C/5l5EjUcATgBlKhhj1FLe47UPlUucy25k9Fk71zqrKJ SEx6aiSUX8xY7VjNi5mjv7YlYUTRJIxaFUGEMqRUYwFvmihdOOUpGCiDMQOis0M= =Y9p7 -----END PGP SIGNATURE----- --HDJ66P9oeeKbWwFf87EVABbhlNgJwSWjQ--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?6167392c-c37a-6e39-aa22-ca45435d6088>