Re: kernel work week of 3-Feb-2010 HEADS UP
--0003255579eac3ea3a047ebc0cd0
Content-Type: text/plain; charset=ISO-8859-1
2010/2/4 Matthew Dillon <dillon@apollo.backplane.com>
>
> :Awesome :)
> :
> :Would such a SSD cache also improve write performance of a HAMMER file
> :system?
> :To improve write performance we'd probably need to put the UNDO/REDO log
> :on a SSD...
>
> No, the first iteration is strictly a clean slaved throw-away copy.
>
> Writes run to the actual media and free any related underlying swap
> copy. A new swap copy may be made later when the cached VM page
> associated with the write cycles back out of main memory.
>
Understood. So this basically means that when I do a read-after-write I
don't
have to read from disk as it's either in memory, or if I wait too long, it's
moved
to swap-cache and I still can access it quickly.
> :And will the new system also cache mmap'ed data of a file?
> :
> :Regards,
> :
> : Michael
>
> Yes. Both read() and mmap()'d data are backed by VM pages and are
> applicable to the cache.
>
Great!
Regards,
Michael
--0003255579eac3ea3a047ebc0cd0
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
<br><br><div class=3D"gmail_quote">2010/2/4 Matthew Dillon <span dir=3D"ltr=
"><<a href=3D"mailto:dillon@apollo.backplane.com">dillon@apollo.backplan=
e.com</a>></span><br><blockquote class=3D"gmail_quote" style=3D"margin:0=
0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<br>
:Awesome :)<br>
<div class=3D"im">:<br>
:Would such a SSD cache also improve write performance of a HAMMER file<br>
:system?<br>
:To improve write performance we'd probably need to put the UNDO/REDO l=
og<br>
:on a SSD...<br>
<br>
</div> =A0 =A0No, the first iteration is strictly a clean slaved throw-away=
copy.<br>
<br>
=A0 =A0Writes run to the actual media and free any related underlying swap=
<br>
=A0 =A0copy. =A0A new swap copy may be made later when the cached VM page<=
br>
=A0 =A0associated with the write cycles back out of main memory.<br></bloc=
kquote><div><br></div><div>Understood. So this basically means that when I =
do a read-after-write I don't</div><div>have to read from disk as it=
9;s either in memory, or if I wait too long, it's moved<br>
</div><div>to swap-cache and I still can access it quickly.</div><div><br><=
/div><blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-le=
ft:1px #ccc solid;padding-left:1ex;"><br>
:And will the new system also cache mmap'ed data of a file?<br>
:<br>
:Regards,<br>
:<br>
: =A0Michael<br>
<br>
=A0 =A0Yes. =A0Both read() and mmap()'d data are backed by VM pages an=
d are<br>
=A0 =A0applicable to the cache.<br></blockquote><div><br></div><div>Great!=
=A0</div><div><br></div><div>Regards,</div><div><br></div><div>=A0=A0Michae=
l</div></div>
--0003255579eac3ea3a047ebc0cd0--
討論串 (同標題文章)
完整討論串 (本文為第 9 之 30 篇)：