Date: Sun, 16 Oct 2022 16:06:58 -0600 From: Warner Losh <imp@bsdimp.com> To: void <void@f-m.fm> Cc: freebsd-fs <freebsd-fs@freebsd.org> Subject: Re: zfs with operations like rm -rf takes a very long time recently Message-ID: <CANCZdfp%2BJYOJ4a4jrWvRSsO-vi-_JrK=iCh7eiC2f0hk7m3-AA@mail.gmail.com> In-Reply-To: <528a0bcc-6bcd-4d66-aeff-273542deb21d@app.fastmail.com> References: <f25d069a-2ee7-491a-a5ef-a14b973c12e2@app.fastmail.com> <CAOtMX2jW1s8n_FGez4-sCMBnbd-GDUoj9Sx83gaTBTEuW58HQw@mail.gmail.com> <1625dc7b-81c4-4350-8f86-1b65f5a860d9@app.fastmail.com> <CAOtMX2hjGnpLgs2vD1pTELK-nF9nBORhCj57zyYmkEmHAGohnQ@mail.gmail.com> <64a0af42-630d-4f42-8b8c-921b68b03078@app.fastmail.com> <CANCZdfq5bUWvc649Xi0gNBSe3y95B5zeLOJ29DjP=FG3CzCcjQ@mail.gmail.com> <528a0bcc-6bcd-4d66-aeff-273542deb21d@app.fastmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--00000000000088c32405eb2e1423 Content-Type: text/plain; charset="UTF-8" On Sun, Oct 16, 2022 at 3:53 PM void <void@f-m.fm> wrote: > On Sun, 16 Oct 2022, at 16:51, Warner Losh wrote: > > > The only thing that looks high here is the load cycle count and maybe > > the power off retract count. With > > 40k power on hours, that's a power off every 90 hours? That seems a > > little weird. And the load cycle > > is almost 20 times the power on hours, suggesting it's going on every > > few minutes. That's higher than > > I'd expect as well. The power cycle count is also high for the number > > of hours. Your disk is pushing 4 years > > old too, which may mean its past expected life. So this profile > > suggests possible signs of fatigue. > > Thanks for the explainer. The disk is a dedicated ruggedised external > disk. Before it was used in a stationary context with the pi, it'd be > lugged around with a netbook or > laptop, hence the large number of powercycles. > OK. That makes perfect sense then. For a server drive, that data is crazy and suggests a drive that's been abused by flakey hardware. For an external drive like that, it's not terribly out of the ordinary.... The disk is quite busy and performing decently well for the load... The quite busy part I see others are trying to explain and/or diagnose, so I'll leave them to it. Warner --00000000000088c32405eb2e1423 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr"><div dir=3D"ltr"><br></div><br><div class=3D"gmail_quote">= <div dir=3D"ltr" class=3D"gmail_attr">On Sun, Oct 16, 2022 at 3:53 PM void = <<a href=3D"mailto:void@f-m.fm">void@f-m.fm</a>> wrote:<br></div><blo= ckquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-left= :1px solid rgb(204,204,204);padding-left:1ex">On Sun, 16 Oct 2022, at 16:51= , Warner Losh wrote:<br> <br> > The only thing that looks high here is the load cycle count and maybe = <br> > the power off retract count. With<br> > 40k power on hours, that's a power off every 90 hours? That seems = a <br> > little weird. And the load cycle<br> > is almost 20 times the power on hours, suggesting it's going on ev= ery <br> > few minutes. That's higher than<br> > I'd expect as well. The power cycle count is also high for the num= ber <br> > of hours. Your disk is pushing 4 years<br> > old too, which may mean its past expected life. So this profile <br> > suggests possible signs of fatigue.<br> <br> Thanks for the explainer. The disk is a dedicated ruggedised external disk.= Before it was used in a stationary context with the pi, it'd be lugged= around with a netbook or<br> laptop, hence the large number of powercycles.<br></blockquote><div><br></d= iv><div>OK. That makes perfect sense then. For a server drive, that data is= crazy and suggests</div><div>a drive=C2=A0that's been abused by flakey= hardware. For an external drive like that, it's not</div><div>terribly= out of the ordinary....</div><div><br></div><div>The disk is quite busy an= d performing decently well for the load...=C2=A0 The quite busy</div><div>p= art I see others are trying to explain and/or diagnose, so I'll leave= =C2=A0them to it.</div><div><br></div><div>Warner</div></div></div> --00000000000088c32405eb2e1423--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CANCZdfp%2BJYOJ4a4jrWvRSsO-vi-_JrK=iCh7eiC2f0hk7m3-AA>