Date: Tue, 06 May 2025 08:44:46 -0700 From: Cy Schubert <Cy.Schubert@cschubert.com> To: Gleb Smirnoff <glebius@freebsd.org> Cc: Cy Schubert <Cy.Schubert@cschubert.com>, src-committers@freebsd.org, dev-commits-src-all@freebsd.org, dev-commits-src-main@freebsd.org Subject: Re: git: d15792780760 - main - unix: new implementation of unix/stream & unix/seqpacket Message-ID: <20250506154446.917B818D@slippy.cwsent.com> In-Reply-To: <aBopyxs3FAqD6K4P@cell.glebi.us> References: <202505051956.545JuOPR085707@gitrepo.freebsd.org> <20250506150654.DEAF8300@slippy.cwsent.com> <aBopyxs3FAqD6K4P@cell.glebi.us>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <aBopyxs3FAqD6K4P@cell.glebi.us>, Gleb Smirnoff writes: > On Tue, May 06, 2025 at 08:06:54AM -0700, Cy Schubert wrote: > C> Is anyone else experiencing rsync hangs with this? I'm noticing rsync hang > s > C> with large files, like those in /usr/obj or a poudriere package repo. > C> > C> I haven't reverted this locally yet, just guessing ATM. > > Does rsync use unix(4) socket? What is the kernel stack of the sleeping > process? procstat -k $pid > > -- > Gleb Smirnoff On the sending machine: bob# procstat -k 50742 PID TID COMM TDNAME KSTACK 50742 103321 rsync - mi_switch sleepq_switch sleepq_catch_signals sleepq_timedwait_sig _cv_timedwait_sig_sbt kern_select sys_select amd64_syscall fast_syscall_common bob# bob# procstat -k 50743 PID TID COMM TDNAME KSTACK 50743 100644 rsh - mi_switch sleepq_switch sleepq_catch_signals sleepq_wait_sig _cv_wait_sig kern_select sys_select amd64_syscall fast_syscall_common bob# On the receiving machine: cwsys# procstat -k 46918 PID TID COMM TDNAME KSTACK 46918 100848 rsync - mi_switch sleepq_catch_signals sleepq_timedwait_sig _cv_timedwait_sig_sbt seltdwait kern_select sys_select amd64_syscall fast_syscall_common cwsys# procstat -k 46919 PID TID COMM TDNAME KSTACK 46919 100999 rsync - mi_switch sleepq_catch_signals sleepq_timedwait_sig _cv_timedwait_sig_sbt seltdwait kern_select sys_select amd64_syscall fast_syscall_common cwsys# It's proceeding but exceptionally slowly. The hangs occur at 0% and at some points during the transfer. Noticed using rsync --progress. -- Cheers, Cy Schubert <Cy.Schubert@cschubert.com> FreeBSD UNIX: <cy@FreeBSD.org> Web: https://FreeBSD.org NTP: <cy@nwtime.org> Web: https://nwtime.org e^(i*pi)+1=0
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20250506154446.917B818D>