Well we may have missed something, because that dtrace will
only capture write(2) and pwrite(2) - whatever is generating the writes
may be using another interface (writev(2) for example).
What about taking it down a layer:
dtrace -n 'fsinfo:::write /args[0]->fi_fs == "zfs"/ {
@[execname,args[0]->fi_pathname] = count(); }'
On Jun 11, 2011, at 12:34 PM, Jim Klimov wrote:
> 2011-06-11 19:16, Jim Mauro пишет:
>> Does this reveal anything;
>>
>> dtrace -n 'syscall::*write:entry /fds[arg0].fi_fs == "zfs"/ {
>> @[execname,fds[arg0].fi_pathname]=count(); }'
>
> Alas, not much.
>
> # time dtrace -n 'syscall::*write:entry /fds[arg0].fi_fs == "zfs"/ {
> @[execname,fds[arg0].fi_pathname]=count(); }'
> dtrace: description 'syscall::*write:entry ' matched 2 probes
> ^C
>
> freeram-watchdog /var/log/freeram-watchdog.log.1307796483 57
>
> real 1m0.635s
> user 0m1.436s
> sys 0m0.361s
>
> So during a minute of running I had about 3 seconds of DTrace script init
> and appends to the log file every second (as well as TXG Syncs every
> second). Strangely, no other files showed up, though previous rwsnoop
> runs showed regular IOs (once a minute or more often) to a few other files.
>
> Thanks,
> //Jim
>
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
