Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 28 Oct 2013 14:28:04 -0400
From:      Allan Jude <freebsd@allanjude.com>
To:        freebsd-current@freebsd.org
Subject:   Re: ZFS txg implementation flaw
Message-ID:  <526EACB4.9030906@allanjude.com>
In-Reply-To: <20131028181631.GV63359@zxy.spb.ru>
References:  <20131028092844.GA24997@zxy.spb.ru> <0F1D571E-2806-4392-A5EC-BE66A3C92BF7@gmail.com> <20131028181631.GV63359@zxy.spb.ru>

next in thread | previous in thread | raw e-mail | index | archive | help
On 2013-10-28 14:16, Slawa Olhovchenkov wrote:
> On Mon, Oct 28, 2013 at 10:45:02AM -0700, aurfalien wrote:
>
>> On Oct 28, 2013, at 2:28 AM, Slawa Olhovchenkov wrote:
>>
>>> I can be wrong.
>>> As I see ZFS cretate seperate thread for earch txg writing.
>>> Also for writing to L2ARC.
>>> As result -- up to several thousands threads created and destoyed per
>>> second. And hundreds thousands page allocations, zeroing, maping
>>> unmaping and freeing per seconds. Very high overhead.
>>>
>>> In systat -vmstat I see totfr up to 600000, prcfr up to 200000.
>>>
>>> Estimated overhead -- 30% of system time.
>>>
>>> Can anybody implement thread and page pool for txg?
>> Would lowering vfs.zfs.txg.timeout be a way to tame or mitigate this?
> vfs.zfs.txg.timeout: 5
>
> Only x5 lowering (less in real case with burst writing). And more fragmentation on writing and etc.
> _______________________________________________
> freebsd-current@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-current
> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org"
>From my understanding, increasing the timeout so you are doing fewer
transaction groups, would actually be the way to increase performance,
at the cost of 'bursty' writing and the associated uneven latency.

-- 
Allan Jude




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?526EACB4.9030906>