Date: Wed, 27 Aug 2025 19:26:50 +0200 From: =?UTF-8?Q?Olivier_Cochard=2DLabb=C3=A9?= <olivier@freebsd.org> To: freebsd-current@freebsd.org, src-committers@freebsd.org Cc: Gleb Smirnoff <glebius@freebsd.org> Subject: Re: August 2025 stabilization week Message-ID: <CA%2Bq%2BTco7sd1hSzyRTExBWm=agg8CCt2YhqfdoL6vzfkivqBRQA@mail.gmail.com> In-Reply-To: <aK3vurudrhdPf2Y-@cell.glebi.us> References: <aKwYB4d6l4ze-yXA@cell.glebi.us> <aK3vurudrhdPf2Y-@cell.glebi.us>
index | next in thread | previous in thread | raw e-mail
[-- Attachment #1 --] On Tue, Aug 26, 2025 at 7:32 PM Gleb Smirnoff <glebius@freebsd.org> wrote: > > The performance & stability A/B testing at Netflix just started and we > expect to have results tomorrow. > > I will be AFK for the rest of the week, and thus passing responsibility > for the stabweek on Olivier Cochard olivier@. He will update on the > A/B test results, collect any success/failure reports and close the > week. > > -- > Gleb Smirnoff > Wednesday update: - We noticed a 100% reproducible kernel panic while running the ZFS regression tests (cd /usr/tests; kyua test sys/cddl/zfs/tests/). This issue was reported here: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=289131 - Our daily A/B test (22-hour run on 32 CDN servers total) at Netflix didn't show any regression or stability issues (stabweek July vs August). I was expecting more visible differences due to the OpenSSL upgrade, but I will have to wait for our long AB/BA performance results to get valuable data about this. - I've noticed that some of our ARM EC2 instances attach their ephemeral disk with a delay and display this error message in dmesg: cam_periph_alloc: attempt to re-allocate valid device nda0 rejected flags 0x100 refcount 4 ndaasync: Unable to attach to new device due to status 0x6 I'm still waiting for our contributions about this stabweek before closing the week. Regards, Olivier [-- Attachment #2 --] <div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-family:"courier new",monospace"><br></div></div><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Tue, Aug 26, 2025 at 7:32 PM Gleb Smirnoff <<a href="mailto:glebius@freebsd.org">glebius@freebsd.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br> The performance & stability A/B testing at Netflix just started and we<br> expect to have results tomorrow.<br> <br> I will be AFK for the rest of the week, and thus passing responsibility<br> for the stabweek on Olivier Cochard olivier@. He will update on the<br> A/B test results, collect any success/failure reports and close the<br> week.<br> <br> -- <br> Gleb Smirnoff<br></blockquote><div><br></div><div class="gmail_default" style="">Wednesday update:<br><br>- We noticed a 100% reproducible kernel panic while running the ZFS regression tests (cd /usr/tests; kyua test sys/cddl/zfs/tests/). This issue was reported here: <a href="https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=289131">https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=289131</a><br><br>- Our daily A/B test (22-hour run on 32 CDN servers total) at Netflix didn't show any regression or stability issues (stabweek July vs August). I was expecting more visible differences due to the OpenSSL upgrade, but I will have to wait for our long AB/BA performance results to get valuable data about this.<br><br>- I've noticed that some of our ARM EC2 instances attach their ephemeral disk with a delay and display this error message in dmesg:<br>cam_periph_alloc: attempt to re-allocate valid device nda0 rejected flags 0x100 refcount 4<br>ndaasync: Unable to attach to new device due to status 0x6<br><br>I'm still waiting for our contributions about this stabweek before closing the week.<br><br>Regards,<br>Olivier<font face="courier new, monospace"></font></div></div></div>home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2Bq%2BTco7sd1hSzyRTExBWm=agg8CCt2YhqfdoL6vzfkivqBRQA>