|| ||Andrew Morton <email@example.com>|
|| ||lkml <firstname.lastname@example.org>,
|| ||Fri, 13 Sep 2002 21:06:27 -0700|
Some additional work has been performed on the new, faster
I have converted TCP/IPV4 over to use the faster wakeups. It would
be appreciated if the people who are interested in (and set up for
testing) high performance networking could test this out. Note
however that there is no benefit to select()/poll(). That's quite
a large change.
So please bear in mind that this code will only help if applications
are generally sleeping in accept(), connect(), etc. At this stage
I'd like to know whether this work is generally something which should be
pursued further - let's be careful that the measurements are not
swamped by select()/poll() wakeups.
The individual patches are:
These apply against 2.5.26 and possibly earlier, and testing against
earlier kernels would be valid. Thanks.
Changes have been made to /proc/stat which break top(1) and vmstat(1).
New versions are available at
and newer versions will appear at
Ben's AIO patch conflicted with the readv/writev patch. This is
Ben's patch reworked to fit on top of readv-writev.patch
Fix a bogon which broke reiserfs4
Hirokazu Takahashi's writev() speedup.
Use the auto waitqueues in the VM and block layers. Broken out of
the wake-speedup patch.
David Hansen's per-NUMA-node kswapd patch.
Matthew Dobson's topology API.
Add `kswapd_steal' and `pgrefill' to /proc/vmstat. The former indicates
that, on a quick test, 99% of page reclaim is being performed by kswapd.
Instrumentation to show how much time is spent in disk wait. (Doesn't
appear to come out in the new top(1) though?)
Use auto-waitqueues in TCP/IPV4
Fix block-highmem for scsi
Indexed directories for ext3
spinlock/rwlock checking infrastructure
Cleanup and fix the ramdisk driver (doesn't work right yet)
O_DIRECT support for readv/writev
Use a sync iocb for generic_file_read
Reduce scheduling latency across zap_page_range
Resurrect buffermem accounting
ia32 huge tlb pages
Fix reverse map accounting leak
Add /proc/meminfo:Mapped - tha amount of memory which is mapped into pagetables
u.ext3_sb -> generic_sbp
Run readpage before dropping the page refcount
Fix an OOM condition on big highmem machines
Clean up the tlb gather code
arch-neutral dump_stack() function
move mdavise implementation into mm/madvise.c
VMA splitting patch
mmap.c cleanup and lock ranking fixes
Move submit_bh() and ll_rw_block() into fs/buffer.c
Display total slab memory in /proc/meminfo
Cleanup and extension of the writeback paths
free_area_init() code cleanup
alloc_pages cleanup and optimisation
Remove the pagetable walk from /proc/stat
Speed up writev
Fix up the handling of PF_NOWARN
Spel Jermy's naim wright
Infrastructure for communicating request queue congestion to the VM
avoid ext2 inode prereads if the queue is congested
non-blocking writeback infrastructure, use it for pdflush
Non-blocking page reclaim
Faster wakeup code
Use the faster wakeups in the VM and block layers
Speed up sys_sync() against multiple spindles
Early and smarter shrinking of slabs
Fix the generic_file_write-from-same-mmapped-page deadlock
Add /proc/buddyinfo - stats on the free pages pool
Remove struct free_area_struct and free_area_t, use `struct free_area'
Per-node kswapd instance
NUMA topology API
radix tree gang lookup
Move the vm accounting out of /proc/stat
Add kswapd_steal to /proc/vmstat
I/O wait statistics
Use fast wakeups in TCP/IPV4
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to email@example.com
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/