fail sanity check

[HelloWorldGitHubUser]

Hi, I would like to ask when I run the docker, n_req stops at 658000000 and the command lines show these: "req: 658361220, key: 2334 size inconsistent. Old size: 356 new size: 35 terminate called after throwing an instance of 'std::runtime_error' what(): fail sanity check" Would you please tell me the reason, I'm a green hand at this and sorry to bother you!

[HelloWorldGitHubUser]

I'm wondering if I lack some compiler packages or sth

[sunnyszy]

Hi,

This error happens in the trace sanity check phase. The simulator assumes each key maps to a consistent size, however, "req: 658361220, key: 2334 size inconsistent. Old size: 356 new size: 35" means for key 2334 there are two different sizes in the trace. You need to check your trace file and modify it.

[HelloWorldGitHubUser]

ohhhh thx! I think I've found the problem. But btw, what does the parameter 'n_early_stop' mean in the python code? It seems that I can't find the corresponding parameter in the paper, or maybe, did I just ignore some key information?

[sunnyszy]

Hi,

It means to stop the simulation at a given number of requests. For example, n_early_stop = 1000000 means stopping the simulation program at 1M requests instead of finish the whole trace.

On Sun, Aug 7, 2022 at 11:21 AM HelloWorldGitHubUser < @.***> wrote:

ohhhh thx! I think I've found the problem. But btw, what does the parameter 'n_early_stop' mean in the python code? It seems that I can't find the corresponding parameter in the paper, or maybe, did I just ignore some key information?

— Reply to this email directly, view it on GitHub https://github.com/sunnyszy/lrb/issues/15#issuecomment-1207430359, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACXQ673QR53NLLWM4PVBUK3VX7H73ANCNFSM55YMNOLQ . You are receiving this because you commented.Message ID: @.***>

-- Best,

Zhenyu

[HelloWorldGitHubUser]

Thanks a lot!! I just found your description on this in the readme document but I just carelessly left the information out before, so so sorry again for bothering you :(

[HelloWorldGitHubUser]

Hi, sorry to bother you again...😟 But I'm afraid that after reading the paper, I'm still not so sure about the meanings of 'in_cache_metas' and 'out_cache_metas' in the 'lrb.cpp' code--or that is to say, what do in_cache and out_cache mean specifically? What's more, what does 'real_time_segment_window' mean in the 'simulation.cpp' code? Is it related to 'segment_window'? Thanks again!!

[HelloWorldGitHubUser]

Oh...I think I've figured out the first question,does 'in_cache_meatas' mean the metadata of those in the cache and 'out_cache_metas' mean meatadata of those in the memory window but out of the cache? but I still have no idea about the second question😔

[sunnyszy]

does 'in_cache_meatas' mean the metadata of those in the cache and 'out_cache_metas' mean meatadata of those in the memory window but out of the cache? Yes.

what does 'real_time_segment_window' mean in the 'simulation.cpp' code? Is it related to 'segment_window'? These are measurements for cache hits/misses. The segment_window is for a fixed number of requests. real_time_segment_window is for a fixed number of seconds. I don't think we use real_time_segment_window in the paper.

On Fri, Aug 12, 2022 at 12:08 AM HelloWorldGitHubUser < @.***> wrote:

Oh...I think I've figured out the first question,does 'in_cache_meatas' mean the metadata of those in the cache and 'out_cache_metas' mean meatadata of those in the memory window but out of the cache? but I still have no idea about the second question😔

— Reply to this email directly, view it on GitHub https://github.com/sunnyszy/lrb/issues/15#issuecomment-1212709512, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACXQ6732CCALBI5OL6M6DM3VYXE3HANCNFSM55YMNOLQ . You are receiving this because you commented.Message ID: @.***>

-- Best,

Zhenyu

[HelloWorldGitHubUser]

Oh I see,thanks a lot for your patience and kindness!!