X-Git-Url: https://git.decadent.org.uk/gitweb/?a=blobdiff_plain;ds=inline;f=index.html;h=8408414c64d72ac5361560866e94d506202cb244;hb=57639466c3f960b39b3f040ec12f26035b394210;hp=12c844c561d94da49c17153299ec0870902c0eb0;hpb=c8edb32ab191e7e9e3cab0174437a51c680de859;p=kernel-news-talk.git
diff --git a/index.html b/index.html
index 12c844c..8408414 100644
--- a/index.html
+++ b/index.html
@@ -155,7 +155,7 @@
unnamed temporary file on that filesystem
- As with tmpfile(), the file disppears on
+ As with tmpfile(), the file disappears on
last close()
@@ -170,27 +170,6 @@
-
-
Lustre filesystem [3.12]
-
- -
- A distributed filesystem, popular for cluster computing
- applications
-
- -
- Developed out-of-tree since 1999, but now added to Linux staging
- directory
-
- -
- Was included in squeeze but dropped from wheezy as it didn't
- support Linux 3.2
-
- -
- Userland is now missing from Debian
-
-
-
-
Network busy-polling [3.11] (1)
A conventional network request/response process looks like:
@@ -253,13 +232,37 @@
+
+
Lustre filesystem [3.12]
+
+ -
+ A distributed filesystem, popular for cluster computing
+ applications
+
+ -
+ Developed out-of-tree since 1999, but now added to Linux staging
+ directory
+
+ -
+ Was included in squeeze but dropped from wheezy as it didn't
+ support Linux 3.2
+
+ -
+ Userland is now missing from Debian
+
+
+
+
Btrfs offline dedupe [3.12]
-
- Btrfs generally does COW rather than updating in-place, allowing
- snapshots and file copies to defer the actual copying and save
- space
+ Btrfs generally copies and frees blocks, rather than updating
+ in-place
+
+ -
+ This allows snapshots and file copies to copy-by-reference,
+ deferring the real copying until changes are made
-
Filesystems may still end up with multiple copies of the same
@@ -284,12 +287,11 @@
and ebtables
-
- All require a specific kernel module for each type of match
- and each possible action
+ All limited to single protocol, and need a kernel module for
+ each match type and each action
-
- Userland could only use the four protocol-specific APIs,
- although the internal netfilter API is more flexible
+ Kernel's internal netfilter API is more flexible
-
nftables exposes more of this flexibility, allowing userland
@@ -299,7 +301,7 @@
nftables userland tool uses this API and is already packaged
-
- Eventually, the old APIs will be removed and the old userland
+ Eventually, old APIs will be removed and old userland
tools must be ported to use nftables
@@ -343,7 +345,7 @@
but didn't support kernel running little-endian
- Linux 3.13 added little-endian kernel suport, along with new
+ Linux 3.13 added little-endian kernel support, along with new
userland ELF ABI variant - we call it ppc64el
@@ -353,6 +355,59 @@
+
+
File-private locking [3.15]
+
+ -
+ POSIX says that closing a file descriptor removes
+ the process's locks on that file
+
+ -
+ What if process has multiple file descriptors for the same
+ file? It loses all locks obtained through any descriptor!
+
+ -
+ Multithreaded processes may require serialisation around
+ file open/close to ensure they open each file exactly once
+
+ -
+ Hard and symbolic links can hide that two files are really the
+ same
+
+ -
+ Linux now provides file-private locks, associated with a
+ specific open file and removed when last descriptor for the
+ open file is closed
+
+
+
+
+
+
Multiqueue block devices [3.16]
+
+ -
+ Each block device has a command queue (possibly shared with
+ other devices)
+
+ -
+ Queue may be partly implemented by hardware (NCQ) or only
+ in software
+
+ -
+ A single queue means initiation is serialised and completion
+ involves IPI - can be bottleneck for fast devices
+
+ -
+ High-end SSDs support multiple queues, but kernel needed changes
+ to use them
+
+ -
+ nvme and mtip32xx drivers now support
+ multiqueue, but SCSI drivers don't yet - may be backport-able?
+
+
+
+
Questions?