Re: svn commit: r218596 - head/sys/dev/ahci
On 12 Feb, 2011, at 09:06 , Alexander Motin wrote: > Author: mav > Date: Sat Feb 12 07:06:40 2011 > New Revision: 218596 > URL: http://svn.freebsd.org/changeset/base/218596 > > Log: > Disable NCQ for multiport Marvell 88SX61XX SATA controllers. Simultaneous > active I/O to several disks (copying large file on ZFS) causes timeout after > just a few seconds of run. Single port 88SX6111 seems like not affected. > > Skip reading transferred bytes count for these controllers. It works for > 88SX6111, but 88SX6145 always returns zero there. Haven't tested others, > but better to be safe. > > Modified: > head/sys/dev/ahci/ahci.c > I was using Marvell 6121 for quite some time with OCZ Throttle eSATA 8G flash drive for zfs l2arc, but the timeouts were not there from the beginning. Maybe NCQ was not enabled in earlier drivers? Also there is no other drive/ssd attached to the controller, the OCZ drive reports that it supports 2 tag openings. atapci2@pci0:4:0:0: class=0x01018f card=0x612111ab chip=0x612111ab rev=0xb2 hdr=0x00 vendor = 'Marvell Semiconductor (Was: Galileo Technology Ltd)' device = '6121 SATA2 Controller' class = mass storage subclass = ATA bar [10] = type I/O Port, range 32, base 0xbf00, size 8, enabled bar [14] = type I/O Port, range 32, base 0xbe00, size 4, enabled bar [18] = type I/O Port, range 32, base 0xbd00, size 8, enabled bar [1c] = type I/O Port, range 32, base 0xbc00, size 4, enabled bar [20] = type I/O Port, range 32, base 0xbb00, size 16, enabled bar [24] = type Memory, range 32, base 0xfb9ff000, size 1024, enabled cap 01[48] = powerspec 2 supports D0 D1 D3 current D0 cap 05[50] = MSI supports 1 message cap 10[e0] = PCI-Express 1 legacy endpoint max data 128(128) link x1(x1) ecap 0001[100] = AER 1 0 fatal 0 non-fatal 1 corrected ___ svn-src-head@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/svn-src-head To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
Re: svn commit: r226402 - head/sys/netinet
On Oct 15, 2011, at 9:41 PM, Gleb Smirnoff wrote:
> Author: glebius
> Date: Sat Oct 15 18:41:25 2011
> New Revision: 226402
> URL: http://svn.freebsd.org/changeset/base/226402
>
> Log:
> Add support for IPv4 /31 prefixes, as described in RFC3021.
>
> To run a /31 network, participating hosts MUST drop support
> for directed broadcasts, and treat the first and last addresses
> on subnet as unicast. The broadcast address for the prefix
> should be the link local broadcast address, INADDR_BROADCAST.
>
> Modified:
> head/sys/netinet/in.c
> head/sys/netinet/in.h
>
> Modified: head/sys/netinet/in.c
> ==
> --- head/sys/netinet/in.c Sat Oct 15 16:28:06 2011(r226401)
> +++ head/sys/netinet/in.c Sat Oct 15 18:41:25 2011(r226402)
> @@ -897,8 +897,11 @@ in_ifinit(struct ifnet *ifp, struct in_i
>*/
> ia->ia_ifa.ifa_metric = ifp->if_metric;
> if (ifp->if_flags & IFF_BROADCAST) {
> - ia->ia_broadaddr.sin_addr.s_addr =
> - htonl(ia->ia_subnet | ~ia->ia_subnetmask);
> + if (ia->ia_subnetmask == IN_RFC3021_MASK)
> + ia->ia_broadaddr.sin_addr.s_addr = INADDR_BROADCAST;
> + else
> + ia->ia_broadaddr.sin_addr.s_addr =
> + htonl(ia->ia_subnet | ~ia->ia_subnetmask);
> } else if (ifp->if_flags & IFF_LOOPBACK) {
> ia->ia_dstaddr = ia->ia_addr;
> flags |= RTF_HOST;
> @@ -1230,9 +1233,11 @@ in_broadcast(struct in_addr in, struct i
> if (ifa->ifa_addr->sa_family == AF_INET &&
> (in.s_addr == ia->ia_broadaddr.sin_addr.s_addr ||
>/*
> - * Check for old-style (host 0) broadcast.
> + * Check for old-style (host 0) broadcast, but
> + * taking into account that RFC 3021 obsoletes it.
> */
> - t == ia->ia_subnet) &&
> + (ia->ia_subnetmask != IN_RFC3021_MASK &&
> + t == ia->ia_subnet)) &&
>/*
> * Check for an all one subnetmask. These
> * only exist when an interface gets a secondary
>
> Modified: head/sys/netinet/in.h
> ==
> --- head/sys/netinet/in.h Sat Oct 15 16:28:06 2011(r226401)
> +++ head/sys/netinet/in.h Sat Oct 15 18:41:25 2011(r226402)
> @@ -392,6 +392,8 @@ __END_DECLS
>
> #define IN_LOOPBACKNET 127 /* official! */
>
> +#define IN_RFC3021_MASK (u_int32_t)0xfffe
> +
> /*
> * Options for use with [gs]etsockopt at the IP level.
> * First word of comment is data type; bool is stored in int.
>
That's great! Thanks!
Any plans for MFC?
Regards,
Nikolay
___
svn-src-head@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/svn-src-head
To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
Re: svn commit: r226713 - head/sys/netinet
On Oct 25, 2011, at 7:06 AM, Qing Li wrote: > Author: qingli > Date: Tue Oct 25 04:06:29 2011 > New Revision: 226713 > URL: http://svn.freebsd.org/changeset/base/226713 > > Log: > Exclude host routes when checking for prefix coverage on multiple > interfaces. A host route has a NULL mask so check for that condition. > I have also been told by developers who customize the packet output > path with direct manipulation of the route entry (or the outgoing > interface to be specific). This patch checks for the route mask > explicitly to make sure custom code will not panic. > > PR: kern/161805 > MFC after: 3 days > > Modified: > head/sys/netinet/in.c > Without this patch my stable/8 routers were crashing just after a few minutes. A few hours after the commit I applied it manually and the machines are up since then, thanks! Regards, Nikolay ___ svn-src-head@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/svn-src-head To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
Re: svn commit: r237656 - in head: contrib/top usr.bin/top
On Jun 27, 2012, at 9:08 PM, John Baldwin wrote:
> Author: jhb
> Date: Wed Jun 27 18:08:48 2012
> New Revision: 237656
> URL: http://svn.freebsd.org/changeset/base/237656
>
> Log:
> Add a new line to top that provides a brief summary of the ZFS ARC memory
> usage on hosts using ZFS. The new line displays the total amount of RAM
> used by the ARC along with the size of MFU, MRU, anonymous (in flight),
> headers, and other (miscellaneous) sub-categories. The line is not
> displayed on systems that are not using ZFS.
>
> Reviewed by: avg, fs@
> MFC after: 3 days
>
> Modified:
> head/contrib/top/display.c
> head/contrib/top/layout.h
> head/contrib/top/machine.h
> head/contrib/top/top.c
> head/usr.bin/top/machine.c
> head/usr.bin/top/top.local.1
>
>
> Modified: head/usr.bin/top/machine.c
> ==
> --- head/usr.bin/top/machine.cWed Jun 27 17:51:09 2012
> (r237655)
> +++ head/usr.bin/top/machine.cWed Jun 27 18:08:48 2012
> (r237656)
> @@ -176,6 +176,12 @@ char *memorynames[] = {
> "K Free", NULL
> };
>
> +int arc_stats[7];
> +char *arcnames[] = {
> + "K Total, ", "K MRU, ", "K MFU, ", "K Anon, ", "K Header, ", "K Other",
> + NULL
> +};
> +
>
> + if (arc_enabled) {
> + GETSYSCTL("kstat.zfs.misc.arcstats.size", arc_stat);
> + arc_stats[0] = arc_stat >> 10;
> + GETSYSCTL("vfs.zfs.mfu_size", arc_stat);
> + arc_stats[1] = arc_stat >> 10;
> + GETSYSCTL("vfs.zfs.mru_size", arc_stat);
> + arc_stats[2] = arc_stat >> 10;
> + GETSYSCTL("vfs.zfs.anon_size", arc_stat);
> + arc_stats[3] = arc_stat >> 10;
> + GETSYSCTL("kstat.zfs.misc.arcstats.hdr_size", arc_stat);
> + GETSYSCTL("kstat.zfs.misc.arcstats.l2_hdr_size", arc_stat2);
> + arc_stats[4] = arc_stat + arc_stat2 >> 10;
> + GETSYSCTL("kstat.zfs.misc.arcstats.other_size", arc_stat);
> + arc_stats[5] = arc_stat >> 10;
> + si->arc = arc_stats;
> + }
> +
Hi,
It looks like MFU and MRU are swapped in top's display.
I'm using this to correct the output:
--- /usr/src/.zfs/snapshot/patches/usr.bin/top/machine.c2012-09-26
08:20:26.0 +0200
+++ usr.bin/top/machine.c 2012-10-17 17:00:14.988895167 +0200
@@ -515,9 +515,9 @@
if (arc_enabled) {
GETSYSCTL("kstat.zfs.misc.arcstats.size", arc_stat);
arc_stats[0] = arc_stat >> 10;
- GETSYSCTL("vfs.zfs.mfu_size", arc_stat);
- arc_stats[1] = arc_stat >> 10;
GETSYSCTL("vfs.zfs.mru_size", arc_stat);
+ arc_stats[1] = arc_stat >> 10;
+ GETSYSCTL("vfs.zfs.mfu_size", arc_stat);
arc_stats[2] = arc_stat >> 10;
GETSYSCTL("vfs.zfs.anon_size", arc_stat);
arc_stats[3] = arc_stat >> 10;
___
svn-src-head@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/svn-src-head
To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
Re: svn commit: r241773 - head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs
On Oct 20, 2012, at 1:02 PM, Andriy Gapon wrote: > Author: avg > Date: Sat Oct 20 10:02:18 2012 > New Revision: 241773 > URL: http://svn.freebsd.org/changeset/base/241773 > > Log: > zfs: wait in arc_lowmem only if curproc == pageproc > > ... otherwise the current thread might be holding ARC locks and thus run > into a deadlock. This happens, for example, when a thread does memory > allocation in the ARC code and runs into KVA shortage. > Also, it really makes the most sense to wait in pageproc, so that the > results of ARC reclamation are seen before the page cache is acted upon. > In other cases where vm_lowmem is invoked, e.g. on KVA space shortage, > the callers perform multiple attempts (up to 8) and wait for rather > long intervals between them (up to 4 seconds), so ARC reclaim results > should become visible even without explicit waiting on the ARC thread. > > Note that this is not a critical issue for typical ZFS usages where KVA > space should already be large enough. On amd64 systems setting KVA size > to twice the physical memory size is known to mitigate KVA fragmentation > issues in practice. > > Side note: perhaps vm_lowmem 'how' parameter should be used to > differentiate between causes of the event. > > Reported by: Nikolay Denev > MFC after: 19 days > > Modified: > head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/arc.c Thanks! ___ svn-src-head@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/svn-src-head To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
Re: svn commit: r206082 - in head: . share/man/man7 share/mk sys/conf
On 2 Apr, 2010, at 09:55 , Alexander Leidinger wrote: > Author: netchild > Date: Fri Apr 2 06:55:31 2010 > New Revision: 206082 > URL: http://svn.freebsd.org/changeset/base/206082 > > Log: > WITH_CTF can now be specified in src.conf (not recommended, there > are some problems with static executables), make.conf (would also > affect ports which do not use GNU make and do not override the > compile targets) or in the kernel config (via "makeoptions > WITH_CTF=yes"). > > Additional (related) changes: > - propagate WITH_CTF to module builds > - do not add -g to the linker flags, it's a noop there anyway > (at least according to the man page of ld) > - do not add -g to CFLAGS unconditionally > we need to have a look if it is really needed (IMO not) or if there > is a way to add it only when WITH_CTF is used > > Note: ctfconvert / ctfmerge lines will not appear in the build output, > to protect the innocent (those which do not build with WITH_CTF would > see the shell-test and may think WITH_CTF is used). > > Reviewed by: imp, jhb, scottl (earlier version) > Discussed on:arch@ > > Modified: > head/UPDATING > head/share/man/man7/build.7 > head/share/mk/bsd.lib.mk > head/share/mk/bsd.port.mk > head/share/mk/bsd.prog.mk > head/share/mk/sys.mk > head/sys/conf/kern.mk > head/sys/conf/kern.post.mk > head/sys/conf/kern.pre.mk > head/sys/conf/kmod.mk > Finally! Thanks for this. I got tired of rebuilding kernels after accidentally forgetting to put WITH_CTF on the make command line. :) I hope that this can also be MFC-ed to 8-STABLE at least. Regards, Niki___ svn-src-head@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/svn-src-head To unsubscribe, send any mail to "svn-src-head-unsubscr...@freebsd.org"
