Re: [patch] latency problem in md driver

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



/ 2006-12-22 16:40:17 +0100
\ Lars Ellenberg:
> the issue at hand is:
> because md does special case the barrier bit, it strips off everything
> else by re-assigning only the io direction and the barrier bit.
> 
>  ==> I'd like it to also pass at least the sync bit.

some additional info maybe regarding the motivation for this patch.
in drbd 0.7, we have some bitmap on some block device.
this can grow pretty large (128MB), and the code reading/writing it
does synchronous sector size io (which is stupid, and has been changed
already in current drbd svn). --- ok, too much detail ---

anyways, initializing 128MB using 512 Byte bios at a time
with BIO_RW_SYNC using current md raid1 code takes about 5 _minutes_.

with the patch posted earlier, it takes about 5 _seconds_.

this same performance loss will affect every users that are bound
by many small synchronous updates, unless they explicitly unplug
somewhere else.

-- 
: Lars Ellenberg                            Tel +43-1-8178292-55 :
: LINBIT Information Technologies GmbH      Fax +43-1-8178292-82 :
: Vivenotgasse 48, A-1120 Vienna/Europe    http://www.linbit.com :
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [Linux RAID Wiki]     [ATA RAID]     [Linux SCSI Target Infrastructure]     [Linux Block]     [Linux IDE]     [Linux SCSI]     [Linux Hams]     [Device Mapper]     [Device Mapper Cryptographics]     [Kernel]     [Linux Admin]     [Linux Net]     [GFS]     [RPM]     [git]     [Yosemite Forum]


  Powered by Linux