Search found 11 matches

by NickJ
Sat Mar 24, 2012 3:21 am
Forum: Latest News
Topic: [2012-02-27] FancyCache Beta 0.7.2 published
Replies: 24
Views: 56953

Re: [2012-02-27] FancyCache Beta 0.7.2 published

Due to Win7 background defragmentation that's not an issue. The last few times I've loaded up the defrag utility I've been at 0% fragmentation.
by NickJ
Tue Mar 20, 2012 6:57 am
Forum: Technical Support
Topic: Any word on Fancycache with persistant L2 cache
Replies: 11
Views: 10250

Re: Any word on Fancycache with persistant L2 cache

minhgi wrote:Patiently waiting and very eager =)
This is highest on my wish list too - as it's a step closer to a software SRT equivalent.
by NickJ
Tue Mar 20, 2012 6:55 am
Forum: Latest News
Topic: [2012-02-27] FancyCache Beta 0.7.2 published
Replies: 24
Views: 56953

Re: [2012-02-27] FancyCache Beta 0.7.2 published

Intel SRT's solution to the problem is to not cache large sequential operations which doesn't require file awareness. This would accomplish the same objective as not caching "large files" that are "read only sequentially".
by NickJ
Thu Feb 16, 2012 1:24 am
Forum: Bug Report and Suggestion
Topic: Strict FIFO writing
Replies: 4
Views: 4246

Re: Strict FIFO writing

Upon power loss and system failure only a battery on the controller and an UPS will save you with a lazy cache in use. In case that disk caching stability is a requirement, your sitting with a server that includes a proper I/O card to handle the caching. There is no way that you can archive the sam...
by NickJ
Mon Feb 13, 2012 11:16 pm
Forum: Bug Report and Suggestion
Topic: Strict FIFO writing
Replies: 4
Views: 4246

Re: Strict FIFO writing

Well, I don't think a Strict FIFO writing will do much help for power failure issue. The results is quite unexpected on power failure or crash/hang, when defer-write is enabled. So usually Defer-Write is enabled on unimportant data. Anyway I'd like to thank you for your ideas! From my perspective p...
by NickJ
Sat Feb 11, 2012 11:45 pm
Forum: Bug Report and Suggestion
Topic: High CPU usage issues
Replies: 2
Views: 3946

Re: High CPU usage issues

Suggested fix? I assume the issue is because all writes are forced through the cache even when it's full. Thus, if writes bypass the cache when the cache is full it should fix the issue. Thinking about this further, it seems like a short term naive band-aid solution that encourages data corruption....
by NickJ
Sat Feb 11, 2012 11:42 pm
Forum: Bug Report and Suggestion
Topic: Strict FIFO writing
Replies: 4
Views: 4246

Strict FIFO writing

For system stability purposes, if I'm using FancyCache on my system drive, I want it to be no worse than not using FancyCache on a system drive in case of a power failure. Currently if a power failure happens, I'm under the impression that the expected outcome may include corruption, since FancyCach...
by NickJ
Thu Feb 09, 2012 2:03 am
Forum: Technical Support
Topic: Readyboost and FancyCache
Replies: 1
Views: 4390

Re: Readyboost and FancyCache

Tested this - Enabling Readyboost and FancyCache on the same system does not cause any corruption or instability that I've seen. FancyCache can be compared to Superfetch, with Readyboost being Superfetch's L2 Cache.
by NickJ
Thu Feb 09, 2012 1:57 am
Forum: Technical Support
Topic: Consistent results? How to measure?
Replies: 5
Views: 5650

Re: Consistent results? How to measure?

The CDM read results seem to be all over the place due to the caching algorithm you're using. Try again with LRU instead of LFU-R, and you should see more consistent results. The entire cache isn't available for your test, unless you tell it to replace "everything" older, which is what LRU...
by NickJ
Thu Feb 09, 2012 1:03 am
Forum: Bug Report and Suggestion
Topic: High CPU usage issues
Replies: 2
Views: 3946

High CPU usage issues

When writing to a full cache with FancyCache, each thread uses significantly more CPU usage than a write to an empty cache, or a write with FancyCache disabled. This is causing a significant performance hit in high CPU usage multi threaded applications and benchmarks. To clearly reproduce: Enable Fa...